diff --git a/configure.ac b/configure.ac index d78c24da49..1360719bfc 100644 --- a/configure.ac +++ b/configure.ac @@ -1,1547 +1,1548 @@ dnl dnl autoconf for Pacemaker dnl dnl License: GNU General Public License (GPL) dnl =============================================== dnl Bootstrap dnl =============================================== AC_PREREQ(2.53) dnl Suggested structure: dnl information on the package dnl checks for programs dnl checks for libraries dnl checks for header files dnl checks for types dnl checks for structures dnl checks for compiler characteristics dnl checks for library functions dnl checks for system services AC_INIT(pacemaker, 1.1.1, pacemaker@oss.clusterlabs.org) CRM_DTD_VERSION="1.2" PKG_FEATURES="" HB_PKG=heartbeat AC_CONFIG_AUX_DIR(.) AC_CANONICAL_HOST dnl Where #defines go (e.g. `AC_CHECK_HEADERS' below) dnl dnl Internal header: include/config.h dnl - Contains ALL defines dnl - include/config.h.in is generated automatically by autoheader dnl - NOT to be included in any header files except lha_internal.h dnl (which is also not to be included in any other header files) dnl dnl External header: include/crm_config.h dnl - Contains a subset of defines checked here dnl - Manually edit include/crm_config.h.in to have configure include dnl new defines dnl - Should not include HAVE_* defines dnl - Safe to include anywhere AM_CONFIG_HEADER(include/config.h include/crm_config.h) ALL_LINGUAS="en fr" AC_ARG_WITH(version, [ --with-version=version Override package version (if you're a packager needing to pretend) ], [ PACKAGE_VERSION="$withval" ]) AC_ARG_WITH(pkg-name, [ --with-pkg-name=name Override package name (if you're a packager needing to pretend) ], [ PACKAGE_NAME="$withval" ]) AM_INIT_AUTOMAKE($PACKAGE_NAME, $PACKAGE_VERSION) AC_DEFINE_UNQUOTED(PACEMAKER_VERSION, "$PACKAGE_VERSION", Current pacemaker version) PACKAGE_SERIES=`echo $PACKAGE_VERSION | awk -F. '{ print $1"."$2 }'` AC_SUBST(PACKAGE_SERIES) dnl automake >= 1.11 offers --enable-silent-rules for suppressing the output from dnl normal compilation. When a failure occurs, it will then display the full dnl command line dnl Wrap in m4_ifdef to avoid breaking on older platforms m4_ifdef([AM_SILENT_RULES],[AM_SILENT_RULES]) CC_IN_CONFIGURE=yes export CC_IN_CONFIGURE LDD=ldd dnl ======================================================================== dnl Compiler characteristics dnl ======================================================================== AC_PROG_CC dnl Can force other with environment variable "CC". AM_PROG_CC_C_O AC_PROG_CC_STDC AC_LIBTOOL_DLOPEN dnl Enable dlopen support... AC_LIBLTDL_CONVENIENCE dnl make libltdl a convenience lib AC_PROG_LIBTOOL AC_C_STRINGIZE AC_TYPE_SIZE_T AC_CHECK_SIZEOF(char) AC_CHECK_SIZEOF(short) AC_CHECK_SIZEOF(int) AC_CHECK_SIZEOF(long) AC_CHECK_SIZEOF(long long) AC_STRUCT_TIMEZONE dnl =============================================== dnl Helpers dnl =============================================== cc_supports_flag() { local CFLAGS="$@" AC_MSG_CHECKING(whether $CC supports "$@") AC_COMPILE_IFELSE([int main(){return 0;}] ,[RC=0; AC_MSG_RESULT(yes)],[RC=1; AC_MSG_RESULT(no)]) return $RC } extract_header_define() { AC_MSG_CHECKING(for $2 in $1) Cfile=/tmp/extract_define.$2.${$} printf "#include \n" > ${Cfile}.c printf "#include <%s>\n" $1 >> ${Cfile}.c printf "int main(int argc, char **argv) { printf(\"%%s\", %s); return 0; }\n" $2 >> ${Cfile}.c $CC $CFLAGS ${Cfile}.c -o ${Cfile} value=`${Cfile}` AC_MSG_RESULT($value) printf $value rm -f ${Cfile}.c ${Cfile} } dnl =============================================== dnl Configure Options dnl =============================================== dnl Some systems, like Solaris require a custom package name AC_ARG_WITH(pkgname, [ --with-pkgname=name name for pkg (typically for Solaris) ], [ PKGNAME="$withval" ], [ PKGNAME="LXHAhb" ], ) AC_SUBST(PKGNAME) AC_ARG_ENABLE([ansi], [ --enable-ansi force GCC to compile to ANSI/ANSI standard for older compilers. [default=yes]]) AC_ARG_ENABLE([fatal-warnings], [ --enable-fatal-warnings very pedantic and fatal warnings for gcc [default=yes]]) AC_ARG_ENABLE([pretty], [ --enable-pretty Pretty-print compiler output unless there is an error [default=no]]) AC_ARG_ENABLE([quiet], [ --enable-quiet Supress make output unless there is an error [default=no]]) AC_ARG_ENABLE([thread-safe], [ --enable-thread-safe Enable some client libraries to be thread safe. [default=no]]) AC_ARG_ENABLE([bundled-ltdl], [ --enable-bundled-ltdl Configure, build and install the standalone ltdl library bundled with ${PACKAGE} [default=no]]) LTDL_LIBS="" AC_ARG_WITH(ais, [ --with-ais Support the OpenAIS messaging and membership layer ], [ SUPPORT_AIS=$withval ], [ SUPPORT_AIS=try ], ) AC_ARG_WITH(heartbeat, [ --with-heartbeat Support the Heartbeat messaging and membership layer ], [ SUPPORT_HEARTBEAT=$withval ], [ SUPPORT_HEARTBEAT=try ], ) AC_ARG_WITH(snmp, [ --with-snmp Support the SNMP protocol ], [ SUPPORT_SNMP=$withval ], [ SUPPORT_SNMP=try ], ) AC_ARG_WITH(esmtp, [ --with-esmtp Support the sending mail notifications with the esmtp library ], [ SUPPORT_ESMTP=$withval ], [ SUPPORT_ESMTP=try ], ) AISPREFIX="" AC_ARG_WITH(ais-prefix, [ --with-ais-prefix=DIR Prefix used when OpenAIS was installed [$prefix]], [ AISPREFIX=$withval ], [ AISPREFIX=$prefix ]) LCRSODIR="" AC_ARG_WITH(lcrso-dir, [ --with-lcrso-dir=DIR OpenAIS lcrso files. ], [ LCRSODIR="$withval" ]) INITDIR="" AC_ARG_WITH(initdir, [ --with-initdir=DIR directory for init (rc) scripts [${INITDIR}]], [ INITDIR="$withval" ]) PUBLICAN_BRAND="common" AC_ARG_WITH(brand, [ --with-brand=brand Brand to use for generated documentation [$PUBLICAN_BRAND]], [ PUBLICAN_BRAND="$withval" ]) AC_SUBST(PUBLICAN_BRAND) dnl =============================================== dnl General Processing dnl =============================================== AC_SUBST(HB_PKG) INIT_EXT="" echo Our Host OS: $host_os/$host AC_MSG_NOTICE(Sanitizing prefix: ${prefix}) case $prefix in NONE) prefix=/usr;; esac AC_MSG_NOTICE(Sanitizing exec_prefix: ${exec_prefix}) case $exec_prefix in dnl For consistency with Heartbeat, map NONE->$prefix NONE) exec_prefix=$prefix;; prefix) exec_prefix=$prefix;; esac AC_MSG_NOTICE(Sanitizing ais_prefix: ${AISPREFIX}) case $AISPREFIX in dnl For consistency with Heartbeat, map NONE->$prefix NONE) AISPREFIX=$prefix;; prefix) AISPREFIX=$prefix;; esac AC_MSG_NOTICE(Sanitizing INITDIR: ${INITDIR}) case $INITDIR in prefix) INITDIR=$prefix;; "") AC_MSG_CHECKING(which init (rc) directory to use) for initdir in /etc/init.d /etc/rc.d/init.d /sbin/init.d \ /usr/local/etc/rc.d /etc/rc.d do if test -d $initdir then INITDIR=$initdir break fi done AC_MSG_RESULT($INITDIR);; esac AC_SUBST(INITDIR) AC_MSG_NOTICE(Sanitizing libdir: ${libdir}) case $libdir in dnl For consistency with Heartbeat, map NONE->$prefix *prefix*|NONE) AC_MSG_CHECKING(which lib directory to use) for aDir in lib64 lib do trydir="${exec_prefix}/${aDir}" if test -d ${trydir} then libdir=${trydir} break fi done AC_MSG_RESULT($libdir); ;; esac dnl Expand autoconf variables so that we dont end up with '${prefix}' dnl in #defines and python scripts dnl NOTE: Autoconf deliberately leaves them unexpanded to allow dnl make exec_prefix=/foo install dnl No longer being able to do this seems like no great loss to me... eval prefix="`eval echo ${prefix}`" eval exec_prefix="`eval echo ${exec_prefix}`" eval bindir="`eval echo ${bindir}`" eval sbindir="`eval echo ${sbindir}`" eval libexecdir="`eval echo ${libexecdir}`" eval datadir="`eval echo ${datadir}`" eval sysconfdir="`eval echo ${sysconfdir}`" eval sharedstatedir="`eval echo ${sharedstatedir}`" eval localstatedir="`eval echo ${localstatedir}`" eval libdir="`eval echo ${libdir}`" eval includedir="`eval echo ${includedir}`" eval oldincludedir="`eval echo ${oldincludedir}`" eval infodir="`eval echo ${infodir}`" eval mandir="`eval echo ${mandir}`" dnl Home-grown variables eval INITDIR="${INITDIR}" eval docdir="`eval echo ${docdir}`" if test x"${docdir}" = x""; then docdir=${datadir}/doc/${PACKAGE}-${VERSION} #docdir=${datadir}/doc/packages/${PACKAGE} fi AC_SUBST(docdir) for j in prefix exec_prefix bindir sbindir libexecdir datadir sysconfdir \ sharedstatedir localstatedir libdir includedir oldincludedir infodir \ mandir INITDIR docdir do dirname=`eval echo '${'${j}'}'` if test ! -d "$dirname" then AC_MSG_WARN([$j directory ($dirname) does not exist!]) fi done dnl This OS-based decision-making is poor autotools practice; dnl feature-based mechanisms are strongly preferred. dnl dnl So keep this section to a bare minimum; regard as a "necessary evil". case "$host_os" in *bsd*) LIBS="-L/usr/local/lib" CPPFLAGS="$CPPFLAGS -I/usr/local/include" INIT_EXT=".sh" ;; *solaris*) ;; *linux*) AC_DEFINE_UNQUOTED(ON_LINUX, 1, Compiling for Linux platform) CFLAGS="$CFLAGS -I${prefix}/include" ;; darwin*) AC_DEFINE_UNQUOTED(ON_DARWIN, 1, Compiling for Darwin platform) LIBS="$LIBS -L${prefix}/lib" CFLAGS="$CFLAGS -I${prefix}/include" ;; esac dnl Eventually remove this CFLAGS="$CFLAGS -I${prefix}/include/heartbeat" AC_SUBST(INIT_EXT) AC_DEFINE_UNQUOTED(HA_LOG_FACILITY, LOG_DAEMON, Default logging facility) AC_MSG_NOTICE(Host CPU: $host_cpu) case "$host_cpu" in ppc64|powerpc64) case $CFLAGS in *powerpc64*) ;; *) if test "$GCC" = yes; then CFLAGS="$CFLAGS -m64" fi ;; esac esac AC_MSG_CHECKING(which format is needed to print uint64_t) ac_save_CFLAGS=$CFLAGS CFLAGS="-Wall -Werror" AC_COMPILE_IFELSE( [AC_LANG_PROGRAM( [ #include #include #include ], [ int max = 512; uint64_t bignum = 42; char *buffer = malloc(max); const char *random = "random"; snprintf(buffer, max-1, "", bignum, random); fprintf(stderr, "Result: %s\n", buffer); ] )], [U64T="%lu"], [U64T="%llu"] ) CFLAGS=$ac_save_CFLAGS AC_MSG_RESULT($U64T) AC_DEFINE_UNQUOTED(U64T, "$U64T", Correct printf format for logging uint64_t) AC_CHECK_HEADERS(hb_config.h) AC_CHECK_HEADERS(glue_config.h) GLUE_HEADER=none if test "$ac_cv_header_glue_config_h" = "yes"; then GLUE_HEADER=glue_config.h elif test "$ac_cv_header_hb_config_h" = "yes"; then GLUE_HEADER=hb_config.h else AC_MSG_FAILURE(Core development headers were not found) fi dnl Variables needed for substitution CRM_DTD_DIRECTORY="${datadir}/pacemaker" AC_DEFINE_UNQUOTED(CRM_DTD_DIRECTORY,"$CRM_DTD_DIRECTORY", Location for the Pacemaker Relax-NG Schema) AC_SUBST(CRM_DTD_DIRECTORY) AC_DEFINE_UNQUOTED(CRM_DTD_VERSION,"$CRM_DTD_VERSION", Current version of the Pacemaker Relax-NG Schema) AC_SUBST(CRM_DTD_VERSION) CRM_DAEMON_USER=`extract_header_define $GLUE_HEADER HA_CCMUSER` AC_DEFINE_UNQUOTED(CRM_DAEMON_USER,"$CRM_DAEMON_USER", User to run Pacemaker daemons as) AC_SUBST(CRM_DAEMON_USER) CRM_DAEMON_GROUP=`extract_header_define $GLUE_HEADER HA_APIGROUP` AC_DEFINE_UNQUOTED(CRM_DAEMON_GROUP,"$CRM_DAEMON_GROUP", Group to run Pacemaker daemons as) AC_SUBST(CRM_DAEMON_GROUP) CRM_STATE_DIR=${localstatedir}/run/crm AC_DEFINE_UNQUOTED(CRM_STATE_DIR,"$CRM_STATE_DIR", Where to keep state files and sockets) AC_SUBST(CRM_STATE_DIR) PE_STATE_DIR="${localstatedir}/lib/pengine" AC_DEFINE_UNQUOTED(PE_STATE_DIR,"$PE_STATE_DIR", Where to keep PEngine outputs) AC_SUBST(PE_STATE_DIR) dnl Eventually move out of the heartbeat dir tree and create compatability code CRM_CONFIG_DIR="${localstatedir}/lib/heartbeat/crm" AC_DEFINE_UNQUOTED(CRM_CONFIG_DIR,"$CRM_CONFIG_DIR", Where to keep CIB configuration files) AC_SUBST(CRM_CONFIG_DIR) dnl Eventually move out of the heartbeat dir tree and create compatability code dnl CRM_DAEMON_DIR=$libdir/pacemaker CRM_DAEMON_DIR=`extract_header_define $GLUE_HEADER HA_LIBHBDIR` AC_DEFINE_UNQUOTED(CRM_DAEMON_DIR,"$CRM_DAEMON_DIR", Location for Pacemaker daemons) AC_SUBST(CRM_DAEMON_DIR) dnl Create symlinks to here from CRM_DAEMON_DIR when needed HB_DAEMON_DIR=`extract_header_define $GLUE_HEADER HA_LIBHBDIR` AC_DEFINE_UNQUOTED(HB_DAEMON_DIR,"$HB_DAEMON_DIR", Location for Heartbeat expects Pacemaker daemons to be in) AC_SUBST(HB_DAEMON_DIR) dnl Needed so that the AIS plugin can clear out the directory as Heartbeat does HA_STATE_DIR=`extract_header_define $GLUE_HEADER HA_VARRUNDIR` AC_DEFINE_UNQUOTED(HA_STATE_DIR,"$HA_STATE_DIR", Where Heartbeat keeps state files and sockets) AC_SUBST(HA_STATE_DIR) CRM_RSCTMP_DIR=`extract_header_define $GLUE_HEADER HA_RSCTMPDIR` if test x$CRM_RSCTMP_DIR = x; then CRM_RSCTMP_DIR="$HA_STATE_DIR/heartbeat/rsctmp" fi AC_DEFINE_UNQUOTED(CRM_RSCTMP_DIR,"$CRM_RSCTMP_DIR", Where resource agents should keep state files) AC_SUBST(CRM_RSCTMP_DIR) dnl Needed for the location of hostcache in CTS.py HA_VARLIBHBDIR=`extract_header_define $GLUE_HEADER HA_VARLIBHBDIR` AC_SUBST(HA_VARLIBHBDIR) AC_DEFINE_UNQUOTED(UUID_FILE,"$localstatedir/lib/heartbeat/hb_uuid", Location of Heartbeat's UUID file) OCF_ROOT_DIR=`extract_header_define $GLUE_HEADER OCF_ROOT_DIR` if test "X$OCF_ROOT_DIR" = X; then AC_MSG_ERROR(Could not locate OCF directory) fi AC_SUBST(OCF_ROOT_DIR) OCF_RA_DIR=`extract_header_define $GLUE_HEADER OCF_RA_DIR` AC_DEFINE_UNQUOTED(OCF_RA_DIR,"$OCF_RA_DIR", Location for OCF RAs) AC_SUBST(OCF_RA_DIR) dnl Extract this value from glue_config.h once we no longer support anything else STONITH_PLUGIN_DIR="$libdir/stonith/plugins/stonith/" AC_DEFINE_UNQUOTED(STONITH_PLUGIN_DIR,"$STONITH_PLUGIN_DIR", Location for Stonith plugins) AC_SUBST(STONITH_PLUGIN_DIR) RH_STONITH_DIR="$sbindir" AC_DEFINE_UNQUOTED(RH_STONITH_DIR,"$RH_STONITH_DIR", Location for Red Hat Stonith agents) RH_STONITH_PREFIX="fence_" AC_DEFINE_UNQUOTED(RH_STONITH_PREFIX,"$RH_STONITH_PREFIX", Prefix for Red Hat Stonith agents) AC_PATH_PROGS(HG, hg false) AC_MSG_CHECKING(build version) BUILD_VERSION=unknown if test -f $srcdir/.hg_archival.txt; then BUILD_VERSION=`cat $srcdir/.hg_archival.txt | awk '/node:/ { print $2 }'` elif test -x $HG -a -d .hg; then BUILD_VERSION=`$HG id -itb` if test $? != 0; then BUILD_VERSION=unknown fi fi AC_DEFINE_UNQUOTED(BUILD_VERSION, "$BUILD_VERSION", Build version) AC_MSG_RESULT($BUILD_VERSION) AC_SUBST(BUILD_VERSION) dnl =============================================== dnl Program Paths dnl =============================================== PATH="$PATH:/sbin:/usr/sbin:/usr/local/sbin:/usr/local/bin" export PATH dnl Replacing AC_PROG_LIBTOOL with AC_CHECK_PROG because LIBTOOL dnl was NOT being expanded all the time thus causing things to fail. AC_CHECK_PROGS(LIBTOOL, glibtool libtool libtool15 libtool13) AM_PATH_PYTHON AC_CHECK_PROGS(MAKE, gmake make) AC_PATH_PROGS(HTML2TXT, lynx w3m) AC_PATH_PROGS(HELP2MAN, help2man) AC_PATH_PROGS(POD2MAN, pod2man, pod2man) AC_PATH_PROGS(ASCIIDOC, asciidoc) AC_PATH_PROGS(PUBLICAN, publican) AC_PATH_PROGS(XSLTPROC, xsltproc) AC_PATH_PROGS(FOP, fop) AC_PATH_PROGS(SSH, ssh, /usr/bin/ssh) AC_PATH_PROGS(SCP, scp, /usr/bin/scp) AC_PATH_PROGS(HG, hg, /bin/false) AC_PATH_PROGS(TAR, tar) AC_PATH_PROGS(MD5, md5) AC_PATH_PROGS(TEST, test) AC_PATH_PROGS(PKGCONFIG, pkg-config) AC_PATH_PROGS(XML2CONFIG, xml2-config) AC_PATH_PROGS(VALGRIND_BIN, valgrind, /usr/bin/valgrind) AC_DEFINE_UNQUOTED(VALGRIND_BIN, "$VALGRIND_BIN", Valgrind command) if test x"${LIBTOOL}" = x""; then AC_MSG_ERROR(You need (g)libtool installed in order to build ${PACKAGE}) fi if test x"${MAKE}" = x""; then AC_MSG_ERROR(You need (g)make installed in order to build ${PACKAGE}) fi AM_CONDITIONAL(BUILD_HELP, test x"${HELP2MAN}" != x"") if test x"${HELP2MAN}" != x""; then PKG_FEATURES="$PKG_FEATURES manpages" fi MANPAGE_XSLT="" if test x"${XSLTPROC}" != x""; then AC_MSG_CHECKING(docbook to manpage transform) XSLT=`find ${datadir} -name docbook.xsl` for xsl in $XSLT; do dname=`dirname $xsl` bname=`basename $dname` if test "$bname" = "manpages"; then MANPAGE_XSLT="$xsl" break fi done fi AC_MSG_RESULT($MANPAGE_XSLT) AC_SUBST(MANPAGE_XSLT) AM_CONDITIONAL(BUILD_XML_HELP, test x"${MANPAGE_XSLT}" != x"") if test x"${MANPAGE_XSLT}" != x""; then PKG_FEATURES="$PKG_FEATURES docbook-manpages" fi AM_CONDITIONAL(BUILD_ASCIIDOC, test x"${ASCIIDOC}" != x"") if test x"${ASCIIDOC}" != x""; then PKG_FEATURES="$PKG_FEATURES asciidoc" fi AM_CONDITIONAL(BUILD_DOCBOOK, test ${PUBLICAN} != x"") if test ${PUBLICAN} != x""; then PKG_FEATURES="$PKG_FEATURES publican" fi dnl =============================================== dnl Libraries dnl =============================================== AC_CHECK_LIB(socket, socket) dnl -lsocket AC_CHECK_LIB(c, dlopen) dnl if dlopen is in libc... AC_CHECK_LIB(dl, dlopen) dnl -ldl (for Linux) AC_CHECK_LIB(rt, sched_getscheduler) dnl -lrt (for Tru64) AC_CHECK_LIB(gnugetopt, getopt_long) dnl -lgnugetopt ( if available ) AC_CHECK_LIB(pam, pam_start) dnl -lpam (if available) AC_CHECK_LIB(uuid, uuid_parse) dnl e2fsprogs AC_CHECK_LIB(uuid, uuid_create) dnl ossp if test x"${PKGCONFIG}" = x""; then AC_MSG_ERROR(You need pkgconfig installed in order to build ${PACKAGE}) fi dnl dnl On many systems libcrypto is needed when linking against libsnmp. dnl Check to see if it exists, and if so use it. dnl AC_CHECK_LIB(crypto, CRYPTO_free, CRYPTOLIB="-lcrypto",) AC_SUBST(CRYPTOLIB) if test "x${enable_thread_safe}" = "xyes"; then GPKGNAME="gthread-2.0" else GPKGNAME="glib-2.0" fi if $PKGCONFIG --exists $GPKGNAME then GLIBCONFIG="$PKGCONFIG $GPKGNAME" else set -x echo PKG_CONFIG_PATH=$PKG_CONFIG_PATH $PKGCONFIG --exists $GPKGNAME; echo $? $PKGCONFIG --cflags $GPKGNAME; echo $? $PKGCONFIG $GPKGNAME; echo $? set +x AC_MSG_ERROR(You need glib2-devel installed in order to build ${PACKAGE}) fi AC_MSG_RESULT(using $GLIBCONFIG) # # Where is dlopen? # if test "$ac_cv_lib_c_dlopen" = yes; then LIBADD_DL="" elif test "$ac_cv_lib_dl_dlopen" = yes; then LIBADD_DL=-ldl else LIBADD_DL=${lt_cv_dlopen_libs} fi dnl dnl Check for location of gettext dnl dnl On at least Solaris 2.x, where it is in libc, specifying lintl causes dnl grief. Ensure minimal result, not the sum of all possibilities. dnl And do libc first. dnl Known examples: dnl c: Linux, Solaris 2.6+ dnl intl: BSD, AIX AC_CHECK_LIB(c, gettext) if test x$ac_cv_lib_c_gettext != xyes; then AC_CHECK_LIB(intl, gettext) fi if test x$ac_cv_lib_c_gettext != xyes -a x$ac_cv_lib_intl_gettext != xyes; then AC_MSG_ERROR(You need gettext installed in order to build ${PACKAGE}) fi if test "X$GLIBCONFIG" != X; then AC_MSG_CHECKING(for special glib includes: ) GLIBHEAD=`$GLIBCONFIG --cflags` AC_MSG_RESULT($GLIBHEAD) CPPFLAGS="$CPPFLAGS $GLIBHEAD" AC_MSG_CHECKING(for glib library flags) GLIBLIB=`$GLIBCONFIG --libs` AC_MSG_RESULT($GLIBLIB) LIBS="$LIBS $GLIBLIB" fi dnl ======================================================================== dnl Headers dnl ======================================================================== AC_HEADER_STDC AC_CHECK_HEADERS(arpa/inet.h) AC_CHECK_HEADERS(asm/types.h) AC_CHECK_HEADERS(assert.h) AC_CHECK_HEADERS(auth-client.h) AC_CHECK_HEADERS(ctype.h) AC_CHECK_HEADERS(dirent.h) AC_CHECK_HEADERS(errno.h) AC_CHECK_HEADERS(fcntl.h) AC_CHECK_HEADERS(getopt.h) AC_CHECK_HEADERS(glib.h) AC_CHECK_HEADERS(grp.h) AC_CHECK_HEADERS(limits.h) AC_CHECK_HEADERS(linux/errqueue.h) AC_CHECK_HEADERS(malloc.h) AC_CHECK_HEADERS(netdb.h) AC_CHECK_HEADERS(netinet/in.h) AC_CHECK_HEADERS(netinet/ip.h) AC_CHECK_HEADERS(pam/pam_appl.h) AC_CHECK_HEADERS(pthread.h) AC_CHECK_HEADERS(pwd.h) AC_CHECK_HEADERS(security/pam_appl.h) AC_CHECK_HEADERS(sgtty.h) AC_CHECK_HEADERS(signal.h) AC_CHECK_HEADERS(stdarg.h) AC_CHECK_HEADERS(stddef.h) AC_CHECK_HEADERS(stdio.h) AC_CHECK_HEADERS(stdlib.h) AC_CHECK_HEADERS(string.h) AC_CHECK_HEADERS(strings.h) AC_CHECK_HEADERS(sys/dir.h) AC_CHECK_HEADERS(sys/ioctl.h) AC_CHECK_HEADERS(sys/param.h) AC_CHECK_HEADERS(sys/poll.h) AC_CHECK_HEADERS(sys/resource.h) AC_CHECK_HEADERS(sys/select.h) AC_CHECK_HEADERS(sys/socket.h) AC_CHECK_HEADERS(sys/sockio.h) AC_CHECK_HEADERS(sys/stat.h) AC_CHECK_HEADERS(sys/time.h) AC_CHECK_HEADERS(sys/timeb.h) AC_CHECK_HEADERS(sys/types.h) AC_CHECK_HEADERS(sys/uio.h) AC_CHECK_HEADERS(sys/un.h) AC_CHECK_HEADERS(sys/utsname.h) AC_CHECK_HEADERS(sys/wait.h) AC_CHECK_HEADERS(time.h) AC_CHECK_HEADERS(unistd.h) AC_CHECK_HEADERS(winsock.h) dnl These headers need prerequisits before the tests will pass dnl AC_CHECK_HEADERS(net/if.h) dnl AC_CHECK_HEADERS(netinet/icmp6.h) dnl AC_CHECK_HEADERS(netinet/ip6.h) dnl AC_CHECK_HEADERS(netinet/ip_icmp.h) AC_MSG_CHECKING(for special libxml2 includes) if test "x$XML2CONFIG" = "x"; then AC_MSG_ERROR(libxml2 config not found) else XML2HEAD="`$XML2CONFIG --cflags`" AC_MSG_RESULT($XML2HEAD) AC_CHECK_LIB(xml2, xmlReadMemory) AC_CHECK_LIB(xslt, xsltApplyStylesheet) fi CPPFLAGS="$CPPFLAGS $XML2HEAD" AC_CHECK_HEADERS(libxml/xpath.h) AC_CHECK_HEADERS(libxslt/xslt.h) if test "$ac_cv_header_libxml_xpath_h" != "yes"; then AC_MSG_ERROR(The libxml developement headers were not found) fi if test "$ac_cv_header_libxslt_xslt_h" != "yes"; then AC_MSG_ERROR(The libxslt developement headers were not found) fi dnl ======================================================================== dnl Structures dnl ======================================================================== AC_CHECK_MEMBERS([struct tm.tm_gmtoff],,,[[#include ]]) dnl ======================================================================== dnl Functions dnl ======================================================================== AC_CHECK_FUNCS(g_log_set_default_handler) AC_CHECK_FUNCS(getopt, AC_DEFINE(HAVE_DECL_GETOPT, 1, [Have getopt function])) dnl ======================================================================== dnl ltdl dnl ======================================================================== AC_CHECK_LIB(ltdl, lt_dlopen, [LTDL_foo=1]) if test "x${enable_bundled_ltdl}" = "xyes"; then if test $ac_cv_lib_ltdl_lt_dlopen = yes; then AC_MSG_NOTICE([Disabling usage of installed ltdl]) fi ac_cv_lib_ltdl_lt_dlopen=no fi LIBLTDL_DIR="" if test $ac_cv_lib_ltdl_lt_dlopen != yes ; then AC_MSG_NOTICE([Installing local ltdl]) LIBLTDL_DIR=libltdl ( cd $srcdir ; $TAR -xvf libltdl.tar ) if test "$?" -ne 0; then AC_MSG_ERROR([$TAR of libltdl.tar in $srcdir failed]) fi AC_CONFIG_SUBDIRS(libltdl) else LIBS="$LIBS -lltdl" AC_MSG_NOTICE([Using installed ltdl]) INCLTDL="" LIBLTDL="" fi AC_SUBST(INCLTDL) AC_SUBST(LIBLTDL) AC_SUBST(LIBLTDL_DIR) dnl ======================================================================== dnl bzip2 dnl ======================================================================== AC_CHECK_HEADERS(bzlib.h) AC_CHECK_LIB(bz2, BZ2_bzBuffToBuffCompress) if test x$ac_cv_lib_bz2_BZ2_bzBuffToBuffCompress != xyes ; then AC_MSG_ERROR(BZ2 libraries not found) fi if test x$ac_cv_header_bzlib_h != xyes; then AC_MSG_ERROR(BZ2 Development headers not found) fi dnl ======================================================================== dnl ncurses dnl ======================================================================== dnl dnl A few OSes (e.g. Linux) deliver a default "ncurses" alongside "curses". dnl Many non-Linux deliver "curses"; sites may add "ncurses". dnl dnl However, the source-code recommendation for both is to #include "curses.h" dnl (i.e. "ncurses" still wants the include to be simple, no-'n', "curses.h"). dnl dnl ncurse takes precedence. dnl AC_CHECK_HEADERS(curses.h) AC_CHECK_HEADERS(curses/curses.h) AC_CHECK_HEADERS(ncurses.h) AC_CHECK_HEADERS(ncurses/ncurses.h) dnl Although n-library is preferred, only look for it if the n-header was found. CURSESLIBS='' if test "$ac_cv_header_ncurses_h" = "yes"; then AC_CHECK_LIB(ncurses, printw, [CURSESLIBS='-lncurses'; AC_DEFINE(HAVE_LIBNCURSES,1, have ncurses library)] ) fi if test "$ac_cv_header_ncurses_ncurses_h" = "yes"; then AC_CHECK_LIB(ncurses, printw, [CURSESLIBS='-lncurses'; AC_DEFINE(HAVE_LIBNCURSES,1, have ncurses library)] ) fi dnl Only look for non-n-library if there was no n-library. if test X"$CURSESLIBS" = X"" -a "$ac_cv_header_curses_h" = "yes"; then AC_CHECK_LIB(curses, printw, [CURSESLIBS='-lcurses'; AC_DEFINE(HAVE_LIBCURSES,1, have curses library)] ) fi dnl Only look for non-n-library if there was no n-library. if test X"$CURSESLIBS" = X"" -a "$ac_cv_header_curses_curses_h" = "yes"; then AC_CHECK_LIB(curses, printw, [CURSESLIBS='-lcurses'; AC_DEFINE(HAVE_LIBCURSES,1, have curses library)] ) fi if test "x$CURSESLIBS" != "x"; then PKG_FEATURES="$PKG_FEATURES ncurses" fi dnl Check for printw() prototype compatibility if test X"$CURSESLIBS" != X"" && cc_supports_flag -Wcast-qual && cc_supports_flag -Werror; then AC_MSG_CHECKING(whether printw() requires argument of "const char *") ac_save_LIBS=$LIBS LIBS="$CURSESLIBS $LIBS" ac_save_CFLAGS=$CFLAGS CFLAGS="-Wcast-qual -Werror" AC_LINK_IFELSE( [AC_LANG_PROGRAM( [ #if defined(HAVE_CURSES_H) # include #elif defined(HAVE_NCURSES_H) # include #endif ], [printw((const char *)"Test");] )], [ac_cv_compatible_printw=yes], [ac_cv_compatible_printw=no] ) LIBS=$ac_save_LIBS CFLAGS=$ac_save_CFLAGS AC_MSG_RESULT([$ac_cv_compatible_printw]) if test "$ac_cv_compatible_printw" = no; then AC_MSG_WARN([The printw() function of your ncurses or curses library is old, we will disable usage of the library. If you want to use this library anyway, please update to newer version of the library, ncurses 5.4 or later is recommended. You can get the library from http://www.gnu.org/software/ncurses/.]) AC_MSG_NOTICE([Disabling curses]) AC_DEFINE(HAVE_INCOMPATIBLE_PRINTW, 1, [Do we have incompatible printw() in curses library?]) fi fi AC_SUBST(CURSESLIBS) dnl ======================================================================== dnl Cluster infrastructure - Heartbeat dnl ======================================================================== dnl On Debian, AC_CHECK_LIBS fail if a library has any unresolved symbols dnl So check for all the depenancies (so they're added to LIBS) before checking for -lplumb AC_CHECK_LIB(pils, PILLoadPlugin) AC_CHECK_LIB(plumb, G_main_add_IPC_Channel) if test x"$ac_cv_lib_plumb_G_main_add_IPC_Channel" != x"yes"; then AC_MSG_FAILURE(Core Heartbeat utility libraries not found: $ac_cv_lib_plumb_G_main_add_IPC_Channel) fi dnl Compatability checks AC_CHECK_FUNCS(msgfromIPC_timeout) AC_CHECK_MEMBERS([struct lrm_ops.fail_rsc],,,[[#include ]]) dnl ======================================================================== dnl Cluster stack - Heartbeat dnl ======================================================================== case $SUPPORT_HEARTBEAT in 1|yes|true) AC_CHECK_LIB(hbclient, ll_cluster_new, [SUPPORT_HEARTBEAT=1], [AC_MSG_FAILURE(Unable to support Heartbeat: client libraries not found)]);; try) AC_CHECK_LIB(hbclient, ll_cluster_new, [SUPPORT_HEARTBEAT=1], [SUPPORT_HEARTBEAT=0]);; *) SUPPORT_HEARTBEAT=0;; esac AM_CONDITIONAL(BUILD_HEARTBEAT_SUPPORT, test $SUPPORT_HEARTBEAT = 1) AC_DEFINE_UNQUOTED(SUPPORT_HEARTBEAT, $SUPPORT_HEARTBEAT, Support the Heartbeat messaging and membership layer) dnl ======================================================================== dnl Cluster stack - OpenAIS dnl ======================================================================== AISLIB="" dnl Normalize the values case $SUPPORT_AIS in 1|yes|true) missingisfatal=1;; try) missingisfatal=0;; *) SUPPORT_AIS=no;; esac AC_MSG_CHECKING(for native AIS) AISMSGLIB="" AIS_VERSION="none" COROSYNC_PKG="$PKGCONFIG libcoroipcc" if test $SUPPORT_AIS = no; then AC_MSG_RESULT(no... not requested.) else AC_MSG_RESULT($SUPPORT_AIS, with '$AISPREFIX') AC_CHECK_HEADERS(openais/saAis.h) AC_CHECK_HEADERS(corosync/coroipcc.h) $COROSYNC_PKG --exists if test $? = 0; then AIS_VERSION="corosync" elif test "$ac_cv_header_openais_saAis_h" = "yes"; then AIS_VERSION="whitetank" else aisreason="Whitetank headers not found" fi fi if test $AIS_VERSION != "none"; then AC_MSG_CHECKING(for OpenAIS branch) AC_MSG_RESULT($AIS_VERSION) fi if test $AIS_VERSION = "corosync"; then if test "$ac_cv_header_corosync_coroipcc_h" != "yes"; then AIS_VERSION="none" aisreason="Corosync headers not found" fi saveLIBS="$LIBS" LIBS="$LIBS `$COROSYNC_PKG --libs-only-L`" AC_CHECK_LIB(coroipcc, coroipcc_msg_send_reply_receive, []) LIBS="$saveLIBS" if test $ac_cv_lib_coroipcc_coroipcc_msg_send_reply_receive != yes; then AC_MSG_RESULT(Cannot locate AIS messaging library) aisreason="requred Corosync libraries not found" AIS_VERSION="none" fi fi dnl continue? if test $AIS_VERSION = "whitetank"; then dnl Find it in lib, lib64, or wherever it wants to live... AC_MSG_CHECKING(location of OpenAIS libraries) dnl CoroSync location alib=`ls ${AISPREFIX}/*/libcpg.so | head -n 1` if test -z "$alib"; then dnl Whitetank location alib=`ls ${AISPREFIX}/*/*/libcpg.so | head -n 1` fi AISLIB=`dirname $alib` AC_MSG_RESULT($AISLIB) if test "x$AISLIB" = "x"; then AC_MSG_WARN(Use --with-ais-prefix to specify the prefix OpenAIS was installed with) aisreason="library directory not found" AIS_VERSION="none" elif test ! -d "$AISLIB"; then AC_MSG_WARN(Use --with-ais-prefix to specify the prefix OpenAIS was installed with) aisreason="specified library directory does not exist" AIS_VERSION="none" fi fi dnl continue? if test $AIS_VERSION = "whitetank"; then AC_MSG_CHECKING(location of OpenAIS plugins) if test -z "$LCRSODIR"; then LCRSODIR="$libexecdir/lcrso" alib=`ls ${AISPREFIX}/*/lcrso/objdb.lcrso | head -n 1` LCRSODIR=`dirname $alib` fi AC_MSG_RESULT($LCRSODIR) if test "x$LCRSODIR" = "x"; then AC_MSG_RESULT(Invalid. Please specify the correct location with --with-lcrso-dir) aisreason="plugin directory not found" AIS_VERSION="none" elif test ! -d "$LCRSODIR"; then AC_MSG_RESULT(Invalid. Please specify the correct location with --with-lcrso-dir) aisreason="specified plugin directory does not exist" AIS_VERSION="none" fi fi dnl continue? if test $AIS_VERSION = "whitetank"; then dnl Don't add the messaging library to LIBS since most daemons don't need/use it saveLIBS="$LIBS" LIBS="$LIBS -L${AISLIB} -R${AISLIB}" AC_CHECK_LIB(SaMsg, saSendReceiveReply, []) AC_CHECK_LIB(SaMsg, openais_msg_send_reply_receive, []) if test $ac_cv_lib_SaMsg_openais_msg_send_reply_receive = yes; then : OpenAIS elif test $ac_cv_lib_SaMsg_saSendReceiveReply = yes; then : OpenAIS AC_DEFINE_UNQUOTED(TRADITIONAL_AIS_IPC, 1, "Use the 'old' AIS IPC interface") else AC_MSG_RESULT(Cannot locate AIS messaging library) aisreason="requred libraries not found" AIS_VERSION="none" fi LIBS="$saveLIBS" fi SUPPORT_AIS=1 case $AIS_VERSION in corosync) AC_DEFINE_UNQUOTED(AIS_COROSYNC, 1, "AIS target is the corosync series") LCRSODIR=`$PKGCONFIG corosync --variable=lcrsodir` CFLAGS="$CFLAGS `$COROSYNC_PKG --cflags`" AISMSGLIB=`$COROSYNC_PKG --libs` ;; whitetank) AC_DEFINE_UNQUOTED(AIS_WHITETANK, 1, "AIS target is the whitetank series") CFLAGS="$CFLAGS -I$AISPREFIX/include/openais" AISMSGLIB="-L${AISLIB} -R${AISLIB} -lSaMsg" ;; none) SUPPORT_AIS=0 if test "x$aisreason" != x; then if test $missingisfatal = 0; then AC_MSG_WARN(Unable to support OpenAIS: $aisreason) else AC_MSG_FAILURE(Unable to support OpenAIS: $aisreason) fi fi ;; *) AC_MSG_FAILURE(Unknown OpenAIS branch: $AIS_VERSION);; esac AC_DEFINE_UNQUOTED(SUPPORT_AIS, $SUPPORT_AIS, Support the OpenAIS messaging and membership layer) AM_CONDITIONAL(BUILD_AIS_SUPPORT, test $SUPPORT_AIS = 1) dnl dnl Cluster stack - Sanity dnl STACKS="" CLUSTERLIBS="" if test $SUPPORT_HEARTBEAT = 1; then STACKS="$STACKS heartbeat" CLUSTERLIBS="$CLUSTERLIBS -lhbclient -lccmclient" fi if test $SUPPORT_AIS = 1; then STACKS="$STACKS $AIS_VERSION" CLUSTERLIBS="$CLUSTERLIBS ${AISMSGLIB}" else AISPREFIX="" LCRSODIR="$libdir" fi PKG_FEATURES="$PKG_FEATURES$STACKS" AC_MSG_CHECKING(for supported stacks) if test x"$STACKS" = x; then AC_MSG_FAILURE(You must choose at least one cluster stack to support) fi AC_MSG_RESULT($STACKS) AC_SUBST(CLUSTERLIBS) AC_SUBST(LCRSODIR) dnl ======================================================================== dnl SNMP dnl ======================================================================== case $SUPPORT_SNMP in 1|yes|true) missingisfatal=1;; try) missingisfatal=0;; *) SUPPORT_SNMP=no;; esac SNMPLIBS="" AC_MSG_CHECKING(for snmp support) if test $SUPPORT_SNMP = no; then AC_MSG_RESULT(no... not requested.) SUPPORT_SNMP=0 else SNMPCONFIG="" AC_MSG_RESULT($SUPPORT_SNMP) AC_CHECK_HEADERS(net-snmp/net-snmp-config.h) if test "x${ac_cv_header_net_snmp_net_snmp_config_h}" != "xyes"; then SUPPORT_SNMP="no" fi if test $SUPPORT_SNMP != no; then AC_PATH_PROGS(SNMPCONFIG, net-snmp-config) if test "X${SNMPCONFIG}" = "X"; then AC_MSG_RESULT(You need the net_snmp development package to continue.) SUPPORT_SNMP=no fi fi if test $SUPPORT_SNMP != no; then AC_MSG_CHECKING(for special snmp libraries) SNMPLIBS=`$SNMPCONFIG --agent-libs` AC_MSG_RESULT($SNMPLIBS) fi if test $SUPPORT_SNMP != no; then savedLibs=$LIBS LIBS="$LIBS $SNMPLIBS" AC_CHECK_FUNCS(netsnmp_transport_open_client) if test $ac_cv_func_netsnmp_transport_open_client != yes; then AC_CHECK_FUNCS(netsnmp_tdomain_transport) if test $ac_cv_func_netsnmp_tdomain_transport != yes; then SUPPORT_SNMP=no else AC_DEFINE_UNQUOTED(NETSNMPV53, 1, [Use the older 5.3 version of the net-snmp API]) fi fi LIBS=$savedLibs fi if test $SUPPORT_SNMP = no; then SNMPLIBS="" SUPPORT_SNMP=0 if test $missingisfatal = 0; then AC_MSG_WARN(Unable to support SNMP) else AC_MSG_FAILURE(Unable to support SNMP) fi else SUPPORT_SNMP=1 fi fi if test $SUPPORT_SNMP = 1; then PKG_FEATURES="$PKG_FEATURES snmp" fi AC_SUBST(SNMPLIBS) AM_CONDITIONAL(ENABLE_SNMP, test "$SUPPORT_SNMP" = "1") AC_DEFINE_UNQUOTED(ENABLE_SNMP, $SUPPORT_SNMP, Build in support for sending SNMP traps) dnl ======================================================================== dnl ESMTP dnl ======================================================================== case $SUPPORT_ESMTP in 1|yes|true) missingisfatal=1;; try) missingisfatal=0;; *) SUPPORT_ESMTP=no;; esac ESMTPLIB="" AC_MSG_CHECKING(for esmtp support) if test $SUPPORT_ESMTP = no; then AC_MSG_RESULT(no... not requested.) SUPPORT_ESMTP=0 else ESMTPCONFIG="" AC_MSG_RESULT($SUPPORT_ESMTP) AC_CHECK_HEADERS(libesmtp.h) if test "x${ac_cv_header_libesmtp_h}" != "xyes"; then ENABLE_ESMTP="no" fi if test $SUPPORT_ESMTP != no; then AC_PATH_PROGS(ESMTPCONFIG, libesmtp-config) if test "X${ESMTPCONFIG}" = "X"; then AC_MSG_RESULT(You need the libesmtp development package to continue.) SUPPORT_ESMTP=no fi fi if test $SUPPORT_ESMTP != no; then AC_MSG_CHECKING(for special esmtp libraries) ESMTPLIBS=`$ESMTPCONFIG --libs | tr '\n' ' '` AC_MSG_RESULT($ESMTPLIBS) fi if test $SUPPORT_ESMTP = no; then SUPPORT_ESMTP=0 if test $missingisfatal = 0; then AC_MSG_WARN(Unable to support ESMTP) else AC_MSG_FAILURE(Unable to support ESMTP) fi else SUPPORT_ESMTP=1 fi fi if test $SUPPORT_ESMTP = 1; then PKG_FEATURES="$PKG_FEATURES libesmtp" fi AC_SUBST(ESMTPLIBS) AM_CONDITIONAL(ENABLE_ESMTP, test "$SUPPORT_ESMTP" = "1") AC_DEFINE_UNQUOTED(ENABLE_ESMTP, $SUPPORT_ESMTP, Build in support for sending mail notifications with ESMTP) dnl ======================================================================== dnl GnuTLS dnl ======================================================================== AC_CHECK_HEADERS(gnutls/gnutls.h) AC_CHECK_HEADERS(security/pam_appl.h pam/pam_appl.h) dnl GNUTLS library: Attempt to determine by 'libgnutls-config' program. dnl If no 'libgnutls-config', try traditional autoconf means. AC_PATH_PROGS(LIBGNUTLS_CONFIG, libgnutls-config) if test -n "$LIBGNUTLS_CONFIG"; then AC_MSG_CHECKING(for gnutls header flags) GNUTLSHEAD="`$LIBGNUTLS_CONFIG --cflags`"; AC_MSG_RESULT($GNUTLSHEAD) AC_MSG_CHECKING(for gnutls library flags) GNUTLSLIBS="`$LIBGNUTLS_CONFIG --libs`"; AC_MSG_RESULT($GNUTLSLIBS) else AC_CHECK_LIB(gnutls, gnutls_init) fi AC_SUBST(GNUTLSHEAD) AC_SUBST(GNUTLSLIBS) dnl ======================================================================== dnl System Health dnl ======================================================================== dnl Check if servicelog development package is installed SERVICELOG=servicelog-1 SERVICELOG_EXISTS="no" AC_MSG_CHECKING(for $SERVICELOG packages) if $PKGCONFIG --exists $SERVICELOG then SERVICELOG_EXISTS="yes" fi AC_MSG_RESULT($SERVICELOG_EXISTS) AM_CONDITIONAL(BUILD_SERVICELOG, test "$SERVICELOG_EXISTS" = "yes") dnl Check if OpenIMPI packages and servicelog are installed OPENIPMI="OpenIPMI OpenIPMIposix" OPENIPMI_SERVICELOG_EXISTS="no" AC_MSG_CHECKING(for $SERVICELOG $OPENIPMI packages) if $PKGCONFIG --exists $OPENIPMI $SERVICELOG then OPENIPMI_SERVICELOG_EXISTS="yes" fi AC_MSG_RESULT($OPENIPMI_SERVICELOG_EXISTS) AM_CONDITIONAL(BUILD_OPENIPMI_SERVICELOG, test "$OPENIPMI_SERVICELOG_EXISTS" = "yes") dnl ======================================================================== dnl checks for library functions to replace them dnl dnl NoSuchFunctionName: dnl is a dummy function which no system supplies. It is here to make dnl the system compile semi-correctly on OpenBSD which doesn't know dnl how to create an empty archive dnl dnl scandir: Only on BSD. dnl System-V systems may have it, but hidden and/or deprecated. dnl A replacement function is supplied for it. dnl dnl setenv: is some bsdish function that should also be avoided (use dnl putenv instead) dnl On the other hand, putenv doesn't provide the right API for the dnl code and has memory leaks designed in (sigh...) Fortunately this dnl A replacement function is supplied for it. dnl dnl strerror: returns a string that corresponds to an errno. dnl A replacement function is supplied for it. dnl dnl unsetenv: is some bsdish function that should also be avoided (No dnl replacement) dnl A replacement function is supplied for it. dnl dnl strnlen: is a gnu function similar to strlen, but safer. dnl We wrote a tolearably-fast replacement function for it. dnl dnl strndup: is a gnu function similar to strdup, but safer. dnl We wrote a tolearably-fast replacement function for it. dnl dnl daemon: is a GNU function. The daemon() function is for programs wishing to dnl detach themselves from the controlling terminal and run in the dnl background as system daemon dnl A replacement function is supplied for it. AC_REPLACE_FUNCS(alphasort inet_pton NoSuchFunctionName scandir setenv strerror unsetenv strnlen strndup daemon strlcpy strlcat) dnl ======================================================================== dnl Compiler flags dnl ======================================================================== dnl Make sure that CFLAGS is not exported. If the user did dnl not have CFLAGS in their environment then this should have dnl no effect. However if CFLAGS was exported from the user's dnl environment, then the new CFLAGS will also be exported dnl to sub processes. CC_ERRORS="" CC_EXTRAS="" if export | fgrep " CFLAGS=" > /dev/null; then export -n CFLAGS || true # We don't want to bomb out if this fails fi if test "$GCC" != yes; then CFLAGS="$CFLAGS -g" enable_fatal_warnings=no else CFLAGS="$CFLAGS -ggdb3 -O0" # We had to eliminate -Wnested-externs because of libtool changes EXTRA_FLAGS="-fgnu89-inline -fstack-protector-all -Wall -Waggregate-return -Wbad-function-cast -Wcast-qual -Wcast-align -Wdeclaration-after-statement -Wendif-labels -Wfloat-equal -Wformat=2 -Wformat-security -Wformat-nonliteral -Winline -Wmissing-prototypes -Wmissing-declarations -Wnested-externs -Wno-long-long -Wno-strict-aliasing -Wpointer-arith -Wstrict-prototypes -Wunsigned-char -Wwrite-strings" # Additional warnings it might be nice to enable one day # -Wshadow # -Wunreachable-code for j in $EXTRA_FLAGS do if cc_supports_flag $j then CC_EXTRAS="$CC_EXTRAS $j" fi done dnl In lib/ais/Makefile.am there's a gcc option available as of v4.x GCC_MAJOR=`gcc -v 2>&1 | awk 'END{print $3}' | sed 's/[.].*//'` AM_CONDITIONAL(GCC_4, test "${GCC_MAJOR}" = 4) dnl System specific options case "$host_os" in *linux*|*bsd*) if test "${enable_fatal_warnings}" = "unknown"; then enable_fatal_warnings=yes fi ;; esac if test "x${enable_fatal_warnings}" != xno && cc_supports_flag -Werror ; then enable_fatal_warnings=yes else enable_fatal_warnings=no fi if test "x${enable_ansi}" != xno && cc_supports_flag -std=iso9899:199409 ; then AC_MSG_NOTICE(Enabling ANSI Compatibility) CC_EXTRAS="$CC_EXTRAS -ansi -D_GNU_SOURCE -DANSI_ONLY" fi AC_MSG_NOTICE(Activated additional gcc flags: ${CC_EXTRAS}) fi CFLAGS="$CFLAGS $CC_EXTRAS" NON_FATAL_CFLAGS="$CFLAGS" AC_SUBST(NON_FATAL_CFLAGS) dnl dnl We reset CFLAGS to include our warnings *after* all function dnl checking goes on, so that our warning flags don't keep the dnl AC_*FUNCS() calls above from working. In particular, -Werror will dnl *always* cause us troubles if we set it before here. dnl dnl if test "x${enable_fatal_warnings}" = xyes ; then AC_MSG_NOTICE(Enabling Fatal Warnings) CFLAGS="$CFLAGS -Werror" fi AC_SUBST(CFLAGS) dnl This is useful for use in Makefiles that need to remove one specific flag CFLAGS_COPY="$CFLAGS" AC_SUBST(CFLAGS_COPY) AC_SUBST(LIBADD_DL) dnl extra flags for dynamic linking libraries AC_SUBST(LIBADD_INTL) dnl extra flags for GNU gettext stuff... AC_SUBST(LOCALE) dnl Options for cleaning up the compiler output QUIET_LIBTOOL_OPTS="" QUIET_MAKE_OPTS="" if test "x${enable_quiet}" = "xyes"; then QUIET_LIBTOOL_OPTS="--quiet" QUIET_MAKE_OPTS="--quiet" fi AC_MSG_RESULT(Supress make details: ${enable_quiet}) dnl Put the above variables to use LIBTOOL="${LIBTOOL} --tag=CC \$(QUIET_LIBTOOL_OPTS)" MAKE="${MAKE} \$(QUIET_MAKE_OPTS)" AC_SUBST(CC) AC_SUBST(MAKE) AC_SUBST(LIBTOOL) AC_SUBST(QUIET_MAKE_OPTS) AC_SUBST(QUIET_LIBTOOL_OPTS) AC_DEFINE_UNQUOTED(CRM_FEATURES, "$PKG_FEATURES", Set of enabled features) dnl The Makefiles and shell scripts we output AC_CONFIG_FILES(Makefile \ cts/Makefile \ cts/CTSvars.py \ cts/LSBDummy \ cts/benchmark/Makefile \ cts/benchmark/clubench \ cib/Makefile \ crmd/Makefile \ pengine/Makefile \ pengine/regression.core.sh \ doc/Makefile \ doc/cibadmin.8 \ doc/crm_resource.8 \ doc/Pacemaker_Explained/publican.cfg \ + doc/Clusters_from_Scratch/publican.cfg \ include/Makefile \ include/crm/Makefile \ include/crm/common/Makefile \ include/crm/pengine/Makefile \ replace/Makefile \ lib/Makefile \ lib/ais/Makefile \ lib/common/Makefile \ lib/cib/Makefile \ lib/pengine/Makefile \ lib/transition/Makefile \ lib/fencing/Makefile \ lib/plugins/Makefile \ lib/plugins/lrm/Makefile \ fencing/Makefile \ extra/Makefile \ extra/resources/Makefile \ tools/Makefile \ tools/crm_report \ tools/hb2openais.sh \ tools/crm_primitive.py \ shell/Makefile \ shell/templates/Makefile \ shell/regression/Makefile \ shell/regression/testcases/Makefile \ shell/modules/Makefile \ shell/modules/ui.py \ shell/modules/ra.py \ shell/modules/vars.py \ shell/modules/help.py \ xml/Makefile \ ) dnl Now process the entire list of files added by previous dnl calls to AC_CONFIG_FILES() AC_OUTPUT() dnl ***************** dnl Configure summary dnl ***************** AC_MSG_RESULT([]) AC_MSG_RESULT([$PACKAGE configuration:]) AC_MSG_RESULT([ Version = ${VERSION} (Build: $BUILD_VERSION)]) AC_MSG_RESULT([ Features =${PKG_FEATURES}]) AC_MSG_RESULT([]) AC_MSG_RESULT([ Prefix = ${prefix}]) AC_MSG_RESULT([ Executables = ${sbindir}]) AC_MSG_RESULT([ Man pages = ${mandir}]) AC_MSG_RESULT([ Libraries = ${libdir}]) AC_MSG_RESULT([ Header files = ${includedir}]) AC_MSG_RESULT([ Arch-independent files = ${datadir}]) AC_MSG_RESULT([ State information = ${localstatedir}]) AC_MSG_RESULT([ System configuration = ${sysconfdir}]) AC_MSG_RESULT([ AIS Plugins = ${LCRSODIR}]) AC_MSG_RESULT([]) AC_MSG_RESULT([ Use system LTDL = ${ac_cv_lib_ltdl_lt_dlopen}]) AC_MSG_RESULT([]) AC_MSG_RESULT([ HA group name = ${CRM_DAEMON_GROUP}]) AC_MSG_RESULT([ HA user name = ${CRM_DAEMON_USER}]) AC_MSG_RESULT([]) AC_MSG_RESULT([ CFLAGS = ${CFLAGS}]) AC_MSG_RESULT([ Libraries = ${LIBS}]) AC_MSG_RESULT([ Stack Libraries = ${CLUSTERLIBS}]) diff --git a/doc/Clusters_from_Scratch/en-US/Ap-Configuration.xml b/doc/Clusters_from_Scratch/en-US/Ap-Configuration.xml new file mode 100644 index 0000000000..9b135ea684 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ap-Configuration.xml @@ -0,0 +1,274 @@ + + +%BOOK_ENTITIES; +]> + + Configuration Recap +
+ Final Cluster Configuration + + +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive WebData ocf:linbit:drbd \ +        params drbd_resource="wwwdata" \ +        op monitor interval="60s" +primitive WebFS ocf:heartbeat:Filesystem \ +        params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2” +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip=”192.168.122.101” cidr_netmask=”32” clusterip_hash=”sourceip” \ +        op monitor interval="30s" +primitive dlm ocf:pacemaker:controld \ +        op monitor interval="120s" +primitive gfs-control ocf:pacemaker:controld \ +   params daemon=”gfs_controld.pcmk” args=”-g 0” \ +        op monitor interval="120s" +primitive rsa-fencing stonith::external/ibmrsa \ +        params hostname=”pcmk-1 pcmk-2" ipaddr=192.168.122.31 userid=mgmt passwd=abc123 type=ibm \ +        op monitor interval="60s" +ms WebDataClone WebData \ +        meta master-max="2" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" +clone Fencing rsa-fencing +clone WebFSClone WebFS +clone WebIP ClusterIP  \ +        meta globally-unique=”true” clone-max=”2” clone-node-max=”2” +clone WebSiteClone WebSite +clone dlm-clone dlm \ +        meta interleave="true" +clone gfs-clone gfs-control \ +        meta interleave="true" +colocation WebFS-with-gfs-control inf: WebFSClone gfs-clone +colocation WebSite-with-WebFS inf: WebSiteClone WebFSClone +colocation fs_on_drbd inf: WebFSClone WebDataClone:Master +colocation gfs-with-dlm inf: gfs-clone dlm-clone +colocation website-with-ip inf: WebSiteClone WebIP +order WebFS-after-WebData inf: WebDataClone:promote WebFSClone:start +order WebSite-after-WebFS inf: WebFSClone WebSiteClone +order apache-after-ip inf: WebIP WebSiteClone +order start-WebFS-after-gfs-control inf: gfs-clone WebFSClone +order start-gfs-after-dlm inf: dlm-clone gfs-clone +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled=”true” \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” + +
+ +
+ Node List + + The list of cluster nodes is automatically populated by the cluster. + + + +node pcmk-1 +node pcmk-2 + +
+ +
+ Cluster Options + + This is where the cluster automatically stores some information about the cluster + + + + + dc-version - the version (including upstream source-code hash) of Pacemaker used on the DC + + + + + cluster-infrastructure - the cluster infrastructure being used (heartbeat or openais) + + + + + expected-quorum-votes - the maximum number of nodes expected to be part of the cluster + + + + + and where the admin can set options that control the way the cluster operates + + + + + stonith-enabled=true - Make use of STONITH + + + + + no-quorum-policy=ignore - Ignore loss of quorum and continue to host resources. + + + + + +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled=”true” \ +        no-quorum-policy="ignore" + +
+ +
+ Resources +
+ Default Options + + Here we configure cluster options that apply to every resource. + + + + + resource-stickiness - Specify the aversion to moving resources to other machines + + + + + +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” + +
+ +
+ Fencing + + + + TODO: Add text here + + + + + +primitive rsa-fencing stonith::external/ibmrsa \ +        params hostname=”pcmk-1 pcmk-2" ipaddr=192.168.122.31 userid=mgmt passwd=abc123 type=ibm \ +        op monitor interval="60s" +clone Fencing rsa-fencing + +
+ +
+ Service Address + + Users of the services provided by the cluster require an unchanging address with which to access it. Additionally, we cloned the address so it will be active on both nodes. An iptables rule (created as part of the resource agent) is used to ensure that each request only processed by one of the two clone instances. The additional meta options tell the cluster that we want two instances of the clone (one “request bucket” for each node) and that if one node fails, then the remaining node should hold both. + + + +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip=”192.168.122.101” cidr_netmask=”32” clusterip_hash=”sourceip” \ +        op monitor interval="30s" +clone WebIP ClusterIP   +        meta globally-unique=”true” clone-max=”2” clone-node-max=”2” + + + + TODO: The RA should check for globally-unique=true when cloned + + +
+ +
+ Distributed lock manager + + Cluster filesystems like GFS2 require a lock manager. This service starts the daemon that provides user-space applications (such as the GFS2 daemon) with access to the in-kernel lock manager. Since we need it to be available on all nodes in the cluster, we have it cloned. + + + +primitive dlm ocf:pacemaker:controld \ +        op monitor interval="120s" +clone dlm-clone dlm \ +        meta interleave="true + + + + TODO: Confirm interleave is no longer needed + + +
+ +
+ GFS control daemon + + GFS2 also needs a user-space/kernel bridge that runs on every node. So here we have another clone, however this time we must also specify that it can only run on machines that are also running the DLM (colocation constraint) and that it can only be started after the DLM is running (order constraint). Additionally, the gfs-control clone should only care about the DLM instances it is paired with, so we need to set the interleave option. + + + +primitive gfs-control ocf:pacemaker:controld \ +   params daemon=”gfs_controld.pcmk” args=”-g 0” \ +        op monitor interval="120s" +clone gfs-clone gfs-control \ +        meta interleave="true" +colocation gfs-with-dlm inf: gfs-clone dlm-clone +order start-gfs-after-dlm inf: dlm-clone gfs-clone + +
+ +
+ DRBD - Shared Storage + + Here we define the DRBD service and specify which DRBD resource (from drbd.conf) it should manage. We make it a master/slave resource and, in order to have an active/active setup, allow both instances to be promoted by specifying master-max=2. We also set the notify option so that the cluster will tell DRBD agent when it’s peer changes state. + + + +primitive WebData ocf:linbit:drbd \ +        params drbd_resource="wwwdata" \ +        op monitor interval="60s" +ms WebDataClone WebData \ +        meta master-max="2" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" + +
+ +
+ Cluster Filesystem + + The cluster filesystem ensures that files are read and written correctly. We need to specify the block device (provided by DRBD), where we want it mounted and that we are using GFS2. Again it is a clone because it is intended to be active on both nodes. The additional constraints ensure that it can only be started on nodes with active gfs-control and drbd instances. + + + +primitive WebFS ocf:heartbeat:Filesystem \ +        params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2” +clone WebFSClone WebFS +colocation WebFS-with-gfs-control inf: WebFSClone gfs-clone +colocation fs_on_drbd inf: WebFSClone WebDataClone:Master +order WebFS-after-WebData inf: WebDataClone:promote WebFSClone:start +order start-WebFS-after-gfs-control inf: gfs-clone WebFSClone + +
+ +
+ Apache + + Lastly we have the actual service, Apache. We need only tell the cluster where to find it’s main configuration file and restrict it to running on nodes that have the required filesystem mounted and the IP address active. + + + +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +clone WebSiteClone WebSite +colocation WebSite-with-WebFS inf: WebSiteClone WebFSClone +colocation website-with-ip inf: WebSiteClone WebIP +order apache-after-ip inf: WebIP WebSiteClone +order WebSite-after-WebFS inf: WebFSClone WebSiteClone + +
+ +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Ap-Corosync-Conf.xml b/doc/Clusters_from_Scratch/en-US/Ap-Corosync-Conf.xml new file mode 100644 index 0000000000..655046ccc8 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ap-Corosync-Conf.xml @@ -0,0 +1,88 @@ + + +%BOOK_ENTITIES; +]> + + Sample Corosync.conf + + +# Please read the Corosync.conf.5 manual page +compatibility: whitetank + +aisexec { +        # Run as root - this is necessary to be able to manage resources with Pacemaker +        user:        root +        group:        root +} + +service { +        # Load the Pacemaker Cluster Resource Manager +        ver:       0 +        name:      pacemaker +        use_mgmtd: no +        use_logd:  no +} + +totem { +        version: 2 + +        # How long before declaring a token lost (ms) +        token:          5000 + +        # How many token retransmits before forming a new configuration +        token_retransmits_before_loss_const: 10 + +        # How long to wait for join messages in the membership protocol (ms) +        join:           1000 + +        # How long to wait for consensus to be achieved before starting a new +        # round of membership configuration (ms) +        consensus:      2500 + +        # Turn off the virtual synchrony filter +        vsftype:        none + +        # Number of messages that may be sent by one processor on receipt of the token +        max_messages:   20 + +        # Stagger sending the node join messages by 1..send_join ms +        send_join: 45 + +        # Limit generated nodeids to 31-bits (positive signed integers) +        clear_node_high_bit: yes + +        # Disable encryption +        secauth:        off + +        # How many threads to use for encryption/decryption +        threads:           0 + +        # Optionally assign a fixed node id (integer) +        # nodeid:         1234 + +        interface { +                ringnumber: 0 + +                # The following values need to be set based on your environment +                bindnetaddr: 192.168.122.0 +                mcastaddr: 226.94.1.1 +                mcastport: 4000 +        } +} + +logging { +        debug: off +        fileline: off +        to_syslog: yes +        to_stderr: off +        syslog_facility: daemon +        timestamp: on +} + +amf { +        mode: disabled +} + + + diff --git a/doc/Clusters_from_Scratch/en-US/Ap-Reading.xml b/doc/Clusters_from_Scratch/en-US/Ap-Reading.xml new file mode 100644 index 0000000000..bcbc60e849 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ap-Reading.xml @@ -0,0 +1,30 @@ + + +%BOOK_ENTITIES; +]> + + Further Reading + + Project Website + + + http://www.clusterlabs.org + + + Cluster Commands + + + A comprehensive guide to cluster commands has been written by Novell and can be found at: + + + http://www.novell.com/documentation/sles11/book_sleha/index.html?page=/documentation/sles11/book_sleha/data/book_sleha.html + + + Corosync + + + http://www.corosync.org + + + diff --git a/doc/Clusters_from_Scratch/en-US/Author_Group.xml b/doc/Clusters_from_Scratch/en-US/Author_Group.xml new file mode 100644 index 0000000000..ed2f0918d4 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Author_Group.xml @@ -0,0 +1,17 @@ + + +%BOOK_ENTITIES; +]> + + + Dude + McPants + + Somewhere + Someone + + Dude.McPants@example.com + + + diff --git a/doc/Clusters_from_Scratch/en-US/Book_Info.xml b/doc/Clusters_from_Scratch/en-US/Book_Info.xml new file mode 100644 index 0000000000..22c0519e7e --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Book_Info.xml @@ -0,0 +1,66 @@ + + +%BOOK_ENTITIES; +]> + + Clusters from Scratch + Creating Active/Passive and Active/Active Clusters on Fedora + Pacemaker + 1.1 + 3 + 0 + + + The purpose of this document is to provide a start-to-finish guide to building an example active/passive cluster with Pacemaker and show how it can be converted to an active/active one. + + + The example cluster will use: + + + + Fedora 12 as the host operating system + + + + + Corosync to provide messaging and membership services, + + + + + Pacemaker to perform resource management, + + + + + DRBD as a cost-effective alternative to shared storage, + + + + + GFS2 as the cluster filesystem (in active/active mode) + + + + + The crm shell for displaying the configuration and making changes + + + + + + Given the graphical nature of the Fedora install process, a number of screenshots are included. However the guide is primarily composed of commands, the reasons for executing them and their expected outputs. + + + + + + + + + + + + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Active-Active.xml b/doc/Clusters_from_Scratch/en-US/Ch-Active-Active.xml new file mode 100644 index 0000000000..db6c122c22 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-Active-Active.xml @@ -0,0 +1,225 @@ + + +%BOOK_ENTITIES; +]> + + Reconfigure Pacemaker for Active/Active + + Almost everything is in place. Recent versions of DRBD are capable of operating in Primary/Primary mode and the filesystem we’re using is cluster aware. All we need to do now is reconfigure the cluster to take advantage of this. + + + This will involve a number of changes, so we’ll again use interactive mode. + + + +crm +cib new active + + + There’s no point making the services active on both locations if we can’t reach them, so lets first clone the IP address. Cloned IPaddr2 resources use an iptables rule to ensure that each request only processed by one of the two clone instances. The additional meta options tell the cluster how many instances of the clone we want (one “request bucket” for each node) and that if all other nodes fail, then the remaining node should hold all of them. Otherwise the requests would be simply discarded. + + + +configure clone WebIP ClusterIP  \ +        meta globally-unique=”true” clone-max=”2” clone-node-max=”2” + + + Now we must tell the ClusterIP how to decide which requests are processed by which hosts. To do this we must specify the clusterip_hash parameter. + + + Open the ClusterIP resource + + +configure edit  ClusterIP + + + And add the following to the params line + + +clusterip_hash="sourceip" + + + So that the complete definition looks like: + + + +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" clusterip_hash="sourceip" \ +        op monitor interval="30s" + + + Here is the full transcript + + + +[root@pcmk-1 ~]# crm +crm(live)# cib new active +INFO: active shadow CIB created +crm(active)# configure clone WebIP ClusterIP  \ +        meta globally-unique=”true” clone-max=”2” clone-node-max=”2” +crm(active)# configure show +node pcmk-1 +node pcmk-2 +primitive WebData ocf:linbit:drbd \ +        params drbd_resource="wwwdata" \ +        op monitor interval="60s" +primitive WebFS ocf:heartbeat:Filesystem \ +        params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2” +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip=”192.168.122.101” cidr_netmask=”32” clusterip_hash=”sourceip” \ +        op monitor interval="30s" +primitive dlm ocf:pacemaker:controld \ +        op monitor interval="120s" +primitive gfs-control ocf:pacemaker:controld \ +   params daemon=”gfs_controld.pcmk” args=”-g 0” \ +        op monitor interval="120s" +ms WebDataClone WebData \ +        meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" +clone WebIP ClusterIP \ + meta globally-unique=”true” clone-max=”2” clone-node-max=”2” +clone dlm-clone dlm \ +        meta interleave="true" +clone gfs-clone gfs-control \ +        meta interleave="true" +colocation WebFS-with-gfs-control inf: WebFS gfs-clone +colocation WebSite-with-WebFS inf: WebSite WebFS +colocation fs_on_drbd inf: WebFS WebDataClone:Master +colocation gfs-with-dlm inf: gfs-clone dlm-clone +colocation website-with-ip inf: WebSite WebIP +order WebFS-after-WebData inf: WebDataClone:promote WebFS:start +order WebSite-after-WebFS inf: WebFS WebSite +order apache-after-ip inf: WebIP WebSite +order start-WebFS-after-gfs-control inf: gfs-clone WebFS +order start-gfs-after-dlm inf: dlm-clone gfs-clone +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” + + + Notice how any constraints that referenced ClusterIP have been updated to use WebIP instead. This is an additional benefit of using the crm shell. + + + Next we need to convert the filesystem and Apache resources into clones. Again, the shell will automatically update any relevant constraints. + + + +configure clone WebFSClone WebFS +configure clone WebSiteClone WebSite + + + The last step is to tell the cluster that it is now allowed to promote both instances to be Primary (aka. Master). + + + +configure edit WebDataClone + + + Change master-max to 2 + + + +node pcmk-1 +node pcmk-2 +primitive WebData ocf:linbit:drbd \ +        params drbd_resource="wwwdata" \ +        op monitor interval="60s" +primitive WebFS ocf:heartbeat:Filesystem \ +        params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2” +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip=”192.168.122.101” cidr_netmask=”32” clusterip_hash=”sourceip” \ +        op monitor interval="30s" +primitive dlm ocf:pacemaker:controld \ +        op monitor interval="120s" +primitive gfs-control ocf:pacemaker:controld \ +   params daemon=”gfs_controld.pcmk” args=”-g 0” \ +        op monitor interval="120s" +ms WebDataClone WebData \ +        meta master-max="2" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" +clone WebFSClone WebFS +clone WebIP ClusterIP  \ +        meta globally-unique=”true” clone-max=”2” clone-node-max=”2” +clone WebSiteClone WebSite +clone dlm-clone dlm \ +        meta interleave="true" +clone gfs-clone gfs-control \ +        meta interleave="true" +colocation WebFS-with-gfs-control inf: WebFSClone gfs-clone +colocation WebSite-with-WebFS inf: WebSiteClone WebFSClone +colocation fs_on_drbd inf: WebFSClone WebDataClone:Master +colocation gfs-with-dlm inf: gfs-clone dlm-clone +colocation website-with-ip inf: WebSiteClone WebIP +order WebFS-after-WebData inf: WebDataClone:promote WebFSClone:start +order WebSite-after-WebFS inf: WebFSClone WebSiteClone +order apache-after-ip inf: WebIP WebSiteClone +order start-WebFS-after-gfs-control inf: gfs-clone WebFSClone +order start-gfs-after-dlm inf: dlm-clone gfs-clone +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” + + + Review the configuration before uploading it to the cluster, quitting the shell and watching the cluster’s response + + + +crm(active)# cib commit active +INFO: commited 'active' shadow CIB to the cluster +crm(active)# quit +bye +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Thu Sep  3 21:37:27 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +6 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +Master/Slave Set: WebDataClone +        Masters: [ pcmk-1 pcmk-2 ] +Clone Set: dlm-clone +        Started: [ pcmk-2 pcmk-1 ] +Clone Set: gfs-clone +        Started: [ pcmk-2 pcmk-1 ] +Clone Set: WebIP + Started: [ pcmk-1 pcmk-2 ] +Clone Set: WebFSClone + Started: [ pcmk-1 pcmk-2 ] +Clone Set: WebSiteClone + Started: [ pcmk-1 pcmk-2 ] + +
+ Recovery + + + TODO: Put one node into standby to demonstrate failover + + +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.xml b/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.xml new file mode 100644 index 0000000000..61a0eb353a --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-Active-Passive.xml @@ -0,0 +1,391 @@ + + +%BOOK_ENTITIES; +]> + + Creating an Active/Passive Cluster +
+ Exploring the Existing Configuration + + When Pacemaker starts up, it automatically records the number and details of the nodes in the cluster as well as which stack is being used and the version of Pacemaker being used. + + + This is what the base configuration should look like. + + + +[root@pcmk-2 ~]# crm configure show +node pcmk-1 +node pcmk-2 +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" + + + For those that are not of afraid of XML, you can see the raw configuration by appending “xml” to the previous command. + + + +[root@pcmk-2 ~]# crm configure show xml +<?xml version="1.0" ?> +<cib admin_epoch="0" crm_feature_set="3.0.1" dc-uuid="pcmk-1" epoch="13" have-quorum="1" num_updates="7" validate-with="pacemaker-1.0"> +  <configuration> +    <crm_config> +      <cluster_property_set id="cib-bootstrap-options"> +        <nvpair id="cib-bootstrap-options-dc-version" name="dc-version" value="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7"/> +        <nvpair id="cib-bootstrap-options-cluster-infrastructure" name="cluster-infrastructure" value="openais"/> +        <nvpair id="cib-bootstrap-options-expected-quorum-votes" name="expected-quorum-votes" value="2"/> +      </cluster_property_set> +    </crm_config> +    <rsc_defaults/> +    <op_defaults/> +    <nodes> +      <node id="pcmk-1" type="normal" uname="pcmk-1"/> +      <node id="pcmk-2" type="normal" uname="pcmk-2"/> +    </nodes> +    <resources/> +    <constraints/> +  </configuration> +</cib> + + + The last XML you’ll see in this document + + + Before we make any changes, its a good idea to check the validity of the configuration. + + + +[root@pcmk-1 ~]# crm_verify -L +crm_verify[2195]: 2009/08/27_16:57:12 ERROR: unpack_resources: Resource start-up disabled since no STONITH resources have been defined +crm_verify[2195]: 2009/08/27_16:57:12 ERROR: unpack_resources: Either configure some or disable STONITH with the stonith-enabled option +crm_verify[2195]: 2009/08/27_16:57:12 ERROR: unpack_resources: NOTE: Clusters with shared data need STONITH to ensure data integrity +Errors found during check: config not valid +  -V may provide more details +[root@pcmk-1 ~]# + + + As you can see, the tool has found some errors. + + + In order to guarantee the safety of your data + + If the data is corrupt, there is little point in continuing to make it available + + , Pacemaker ships with STONITH + + A common node fencing mechanism. Used to ensure data integrity by powering off “bad” nodes. + + enabled. However it also knows when no STONITH configuration has been supplied and reports this as a problem (since the cluster would not be able to make progress if a situation requiring node fencing arose). + + + For now, we will disable this feature and configure it later in the Configuring STONITH section. It is important to note that the use of STONITH is highly encouraged, turning it off tells the cluster to simply pretend that failed nodes are safely powered off. Some vendors will even refuse to support clusters that have it disabled. + + + To disable STONITH, we set the stonith-enabled cluster option to false. + +
+ + crm configure property stonith-enabled=false + + + crm_verify -L + +
+ + With the new cluster option set, the configuration is now valid. + +
+ +
+ Adding a Resource + + The first thing we should do is configure an IP address. Regardless of where the cluster service(s) are running, we need a consistent address to contact them on. Here I will choose and add 192.168.122.101 as the floating address, give it the imaginative name ClusterIP and tell the cluster to check that its running every 30 seconds. + + + + The chosen address must not be one already associated with a physical node + + + + +crm configure primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip=192.168.122.101 cidr_netmask=32 \ +        op monitor interval=30s + + + The other important piece of information here is ocf:heartbeat:IPaddr2. This tells Pacemaker three things about the resource you want to add. The first field, ocf, is the standard to which the resource script conforms to and where to find it. The second field is specific to OCF resources and tells the cluster which namespace to find the resource script in, in this case heartbeat. The last field indicates the name of the resource script. + + + To obtain a list of the available resource classes, run + + + +[root@pcmk-1 ~]# crm ra classes +heartbeat +lsb +ocf / heartbeat pacemaker +stonith + + + To then find all the OCF resource agents provided by Pacemaker and Heartbeat, run + + + +[root@pcmk-1 ~]# crm ra list ocf pacemaker +ClusterMon     Dummy          Stateful       SysInfo        SystemHealth   controld +ping           pingd           +[root@pcmk-1 ~]# crm ra list ocf heartbeat +AoEtarget              AudibleAlarm           ClusterMon             Delay +Dummy                  EvmsSCC                Evmsd                  Filesystem +ICP                    IPaddr                 IPaddr2                IPsrcaddr +LVM                    LinuxSCSI              MailTo                 ManageRAID +ManageVE               Pure-FTPd              Raid1                  Route +SAPDatabase            SAPInstance            SendArp                ServeRAID +SphinxSearchDaemon     Squid                  Stateful               SysInfo +VIPArip                VirtualDomain          WAS                    WAS6 +WinPopup               Xen                    Xinetd                 anything +apache                 db2                    drbd                   eDir88 +iSCSILogicalUnit       iSCSITarget            ids                    iscsi +ldirectord             mysql                  mysql-proxy            nfsserver +oracle                 oralsnr                pgsql                  pingd +portblock              rsyncd                 scsi2reservation       sfex +tomcat                 vmware                 +[root@pcmk-1 ~]# + + + Now verify that the IP resource has been added and display the cluster’s status to see that it is now active. + + + +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive ClusterIP ocf:heartbeat:IPaddr2 \ + params ip="192.168.122.101" cidr_netmask="32" \ + op monitor interval="30s" +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" \ +        stonith-enabled="false" \ +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Fri Aug 28 15:23:48 2009 +Stack: openais +Current DC: pcmk-1 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +1 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] +ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-1 + +
+ +
+ Perform a Failover + + Being a high-availability cluster, we should test failover of our new resource before moving on. + + + First, find the node on which the IP address is running. + + + +[root@pcmk-1 ~]# crm resource status ClusterIP +resource ClusterIP is running on: pcmk-1 +[root@pcmk-1 ~]# + + + Shut down Corosync on that machine. + + + +[root@pcmk-1 ~]# ssh pcmk-1 -- /etc/init.d/corosync stop +Stopping Corosync Cluster Engine (corosync): [ OK ] +Waiting for services to unload: [ OK ] +[root@pcmk-1 ~]# + + + Once Corosync is no longer running, go to the other node and check the cluster status with crm_mon. + + + +[root@pcmk-2 ~]# crm_mon +============ +Last updated: Fri Aug 28 15:27:35 2009 +Stack: openais +Current DC: pcmk-2 - partition WITHOUT quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +1 Resources configured. +============ + +Online: [ pcmk-2 ] +OFFLINE: [ pcmk-1 ] + + + There are three things to notice about the cluster’s current state. The first is that, as expected, pcmk-1 is now offline. However we can also see that ClusterIP isn’t running anywhere! + +
+ Quorum and Two-Node Clusters + + This is because the cluster no longer has quorum, as can be seen by the text “partition WITHOUT quorum” (emphasised green) in the output above. In order to reduce the possibility of data corruption, Pacemaker’s default behavior is to stop all resources if the cluster does not have quorum. + + + A cluster is said to have quorum when more than half the known or expected nodes are online, or for the mathematically inclined, whenever the following equation is true: + + + total_nodes - 1 < 2 * active_nodes + + + Therefore a two-node cluster only has quorum when both nodes are running, which is no longer the case for our cluster. This would normally make the creation of a two-node cluster pointless + + Actually some would argue that two-node clusters are always pointless, but that is an argument for another time. + + , however it is possible to control how Pacemaker behaves when quorum is lost. In particular, we can tell the cluster to simply ignore quorum altogether. + + + +[root@pcmk-1 ~]# crm configure property no-quorum-policy=ignore +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" + + + After a few moments, the cluster will start the IP address on the remaining node. Note that the cluster still does not have quorum. + + + +[root@pcmk-2 ~]# crm_mon +============ +Last updated: Fri Aug 28 15:30:18 2009 +Stack: openais +Current DC: pcmk-2 - partition WITHOUT quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +1 Resources configured. +============ +Online: [ pcmk-2 ] +OFFLINE: [ pcmk-1 ] + +ClusterIP (ocf::heartbeat:IPaddr): Started pcmk-2 + + + Now simulate node recovery by restarting the cluster stack on pcmk-1 and check the cluster’s status. + + + +[root@pcmk-1 ~]# /etc/init.d/corosync start +Starting Corosync Cluster Engine (corosync): [ OK ] +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Fri Aug 28 15:32:13 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +1 Resources configured. +============ +Online: [ pcmk-1 pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-1 + + + Here we see something that some may consider surprising, the IP is back running at its original location! + +
+ +
+ Prevent Resources from Moving after Recovery + + In some circumstances it is highly desirable to prevent healthy resources from being moved around the cluster. Move resources almost always requires a period of downtime and for complex services like Oracle databases, this period can be quite long. + + + To address this, Pacemaker has the concept of resource stickiness which controls how much a service prefers to stay running where it is. You may like to think of it as the “cost” of any downtime. By default, Pacemaker assumes there is zero cost associated with moving resources and will do so to achieve “optimal + + It should be noted that Pacemaker’s definition of optimal may not always agree with that of a human’s. The order in which Pacemaker processes lists of resources and nodes create implicit preferences (required in order to create a stabile solution) in situations where the administrator had not explicitly specified some. + + ” resource placement. We can specify a different stickiness for every resource, but it is often sufficient to change the default. + + + +crm configure rsc_defaults resource-stickiness=100 +[root@pcmk-2 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ + resource-stickiness="100" + + + If we now retry the failover test, we see that as expected ClusterIP still moves to pcmk-2 when pcmk-1 is taken offline. + + + +[root@pcmk-1 ~]# ssh pcmk-1 -- /etc/init.d/corosync stop +Stopping Corosync Cluster Engine (corosync):               [  OK  ] +Waiting for services to unload:                            [  OK  ] +[root@pcmk-1 ~]# ssh pcmk-2 -- crm_mon -1 +============ +Last updated: Fri Aug 28 15:39:38 2009 +Stack: openais +Current DC: pcmk-2 - partition WITHOUT quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +1 Resources configured. +============ + +Online: [ pcmk-2 ] +OFFLINE: [ pcmk-1 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 + + + However when we bring pcmk-1 back online, ClusterIP now remains running on pcmk-2. + + + +[root@pcmk-1 ~]# /etc/init.d/corosync start +Starting Corosync Cluster Engine (corosync): [ OK ] +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Fri Aug 28 15:41:23 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +1 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 + +
+ +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Apache.xml b/doc/Clusters_from_Scratch/en-US/Ch-Apache.xml new file mode 100644 index 0000000000..829e8388de --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-Apache.xml @@ -0,0 +1,456 @@ + + +%BOOK_ENTITIES; +]> + + Apache - Adding More Services + + + Now that we have a basic but functional active/passive two-node cluster, we’re ready to add some real services. We’re going to start with Apache because its a feature of many clusters and relatively simple to configure. + + +
+ Installation + + Before continuing, we need to make sure Apache is installed on both hosts. + + + +[root@ppcmk-1 ~]# yum install -y httpd +Setting up Install Process +Resolving Dependencies +--> Running transaction check +---> Package httpd.x86_64 0:2.2.13-2.fc12 set to be updated +--> Processing Dependency: httpd-tools = 2.2.13-2.fc12 for package: httpd-2.2.13-2.fc12.x86_64 +--> Processing Dependency: apr-util-ldap for package: httpd-2.2.13-2.fc12.x86_64 +--> Processing Dependency: /etc/mime.types for package: httpd-2.2.13-2.fc12.x86_64 +--> Processing Dependency: libaprutil-1.so.0()(64bit) for package: httpd-2.2.13-2.fc12.x86_64 +--> Processing Dependency: libapr-1.so.0()(64bit) for package: httpd-2.2.13-2.fc12.x86_64 +--> Running transaction check +---> Package apr.x86_64 0:1.3.9-2.fc12 set to be updated +---> Package apr-util.x86_64 0:1.3.9-2.fc12 set to be updated +---> Package apr-util-ldap.x86_64 0:1.3.9-2.fc12 set to be updated +---> Package httpd-tools.x86_64 0:2.2.13-2.fc12 set to be updated +---> Package mailcap.noarch 0:2.1.30-1.fc12 set to be updated +--> Finished Dependency Resolution + +Dependencies Resolved + +======================================================================================= + Package               Arch             Version                Repository         Size +======================================================================================= +Installing: + httpd               x86_64           2.2.13-2.fc12            rawhide           735 k +Installing for dependencies: + apr                 x86_64           1.3.9-2.fc12             rawhide           117 k + apr-util            x86_64           1.3.9-2.fc12             rawhide            84 k + apr-util-ldap       x86_64           1.3.9-2.fc12             rawhide            15 k + httpd-tools         x86_64           2.2.13-2.fc12            rawhide            63 k + mailcap             noarch           2.1.30-1.fc12            rawhide            25 k + +Transaction Summary +======================================================================================= +Install       6 Package(s) +Upgrade       0 Package(s) + +Total download size: 1.0 M +Downloading Packages: +(1/6): apr-1.3.9-2.fc12.x86_64.rpm                                   | 117 kB     00:00     +(2/6): apr-util-1.3.9-2.fc12.x86_64.rpm                             |  84 kB     00:00     +(3/6): apr-util-ldap-1.3.9-2.fc12.x86_64.rpm                         |  15 kB     00:00     +(4/6): httpd-2.2.13-2.fc12.x86_64.rpm                               | 735 kB     00:00     +(5/6): httpd-tools-2.2.13-2.fc12.x86_64.rpm                         |  63 kB     00:00     +(6/6): mailcap-2.1.30-1.fc12.noarch.rpm                             |  25 kB     00:00     +---------------------------------------------------------------------------------------- +Total                                                       875 kB/s | 1.0 MB     00:01     +Running rpm_check_debug +Running Transaction Test +Finished Transaction Test +Transaction Test Succeeded +Running Transaction +  Installing     : apr-1.3.9-2.fc12.x86_64                                         1/6 +  Installing     : apr-util-1.3.9-2.fc12.x86_64                                     2/6 +  Installing     : apr-util-ldap-1.3.9-2.fc12.x86_64                               3/6 +  Installing     : httpd-tools-2.2.13-2.fc12.x86_64                                 4/6 +  Installing     : mailcap-2.1.30-1.fc12.noarch                                     5/6 +  Installing     : httpd-2.2.13-2.fc12.x86_64                                       6/6 + +Installed: +  httpd.x86_64 0:2.2.13-2.fc12                                                         + +Dependency Installed: +  apr.x86_64 0:1.3.9-2.fc12            apr-util.x86_64 0:1.3.9-2.fc12 +  apr-util-ldap.x86_64 0:1.3.9-2.fc12  httpd-tools.x86_64 0:2.2.13-2.fc12 +  mailcap.noarch 0:2.1.30-1.fc12   + +Complete! +[root@pcmk-1 ~]# + + + Also, we need the wget tool in order for the cluster to be able to check the status of the Apache server. + + + +[root@pcmk-1 ~]# yum install -y wget +Setting up Install Process +Resolving Dependencies +--> Running transaction check +---> Package wget.x86_64 0:1.11.4-5.fc12 set to be updated +--> Finished Dependency Resolution + +Dependencies Resolved + +=========================================================================================== + Package        Arch             Version                      Repository               Size +=========================================================================================== +Installing: + wget         x86_64          1.11.4-5.fc12                   rawhide                393 k + +Transaction Summary +=========================================================================================== +Install       1 Package(s) +Upgrade       0 Package(s) + +Total download size: 393 k +Downloading Packages: +wget-1.11.4-5.fc12.x86_64.rpm                                            | 393 kB     00:00     +Running rpm_check_debug +Running Transaction Test +Finished Transaction Test +Transaction Test Succeeded +Running Transaction +  Installing     : wget-1.11.4-5.fc12.x86_64                                            1/1 + +Installed: +  wget.x86_64 0:1.11.4-5.fc12 + +Complete! +[root@pcmk-1 ~]# + +
+ +
+ Preparation + + First we need to create a page for Apache to serve up. On Fedora the default Apache docroot is /var/www/html, so we’ll create an index file there. + + + +[root@pcmk-1 ~]# cat <<-END >/var/www/html/index.html + <html> + <body>My Test Site - pcmk-1</body> + </html> + END +[root@pcmk-1 ~]# + + + For the moment, we will simplify things by serving up only a static site and manually sync the data between the two nodes. So run the command again on pcmk-2. + + + +[root@pcmk-2 ~]# cat <<-END >/var/www/html/index.html + <html> + <body>My Test Site - pcmk-2</body> + </html> + END +[root@pcmk-2 ~]# + +
+ +
+ Update the Configuration + + At this point, Apache is ready to go, all that needs to be done is to add it to the cluster. Lets call the resource WebSite. We need to use an OCF script called apache in the heartbeat namespace + + Compare the key used here ocf:heartbeat:apache with the one we used earlier for the IP address: ocf:heartbeat:IPaddr2 + + , the only required parameter is the path to the main Apache configuration file and we’ll tell the cluster to check once a minute that apache is still running. + + + +[root@pcmk-1 ~]# crm configure primitive WebSite ocf:heartbeat:apache params configfile=/etc/httpd/conf/httpd.conf op monitor interval=1min +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive WebSite ocf:heartbeat:apache \ + params configfile="/etc/httpd/conf/httpd.conf" \ + op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness="100" + + + After a short delay, we should see the cluster start apache + + + +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Fri Aug 28 16:12:49 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +2 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 +WebSite        (ocf::heartbeat:apache):        Started pcmk-1 + + + Wait a moment, the WebSite resource isn’t running on the same host as our IP address! + +
+ +
+ Ensuring Resources Run on the Same Host + + To reduce the load on any one machine, Pacemaker will generally try to spread the configured resources across the cluster nodes. However we can tell the cluster that two resources are related and need to run on the same host (or not at all). Here we instruct the cluster that WebSite can only run on the host that ClusterIP is active on. If ClusterIP is not active anywhere, WebSite will not be permitted to run anywhere. + + + +[root@pcmk-1 ~]# crm configure colocation website-with-ip INFINITY: WebSite ClusterIP +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +colocation website-with-ip inf: WebSite ClusterIP +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness="100" +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Fri Aug 28 16:14:34 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +2 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 +WebSite        (ocf::heartbeat:apache):        Started pcmk-2 + +
+ +
+ Controlling Resource Start/Stop Ordering + + When Apache starts, it binds to the available IP addresses. It doesn’t know about any addresses we add afterwards, so not only do they need to run on the same node, but we need to make sure ClusterIP is already active before we start WebSite. We do this by adding an ordering constraint. We need to give it a name (chose something descriptive like apache-after-ip), indicate that its mandatory (so that any recovery for ClusterIP will also trigger recovery of WebSite) and list the two resources in the order we need them to start. + + + +[root@pcmk-1 ~]# crm configure order apache-after-ip mandatory: ClusterIP WebSite +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +colocation website-with-ip inf: WebSite ClusterIP +order apache-after-ip inf: ClusterIP WebSite +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness="100" + +
+ +
+ Specifying a Preferred Location + + Pacemaker does not rely on any sort of hardware symmetry between nodes, so it may well be that one machine is more powerful than the other. In such cases it makes sense to host the resources there if it is available. To do this we create a location constraint. Again we give it a descriptive name (prefer-pcmk-1), specify the resource we want to run there (WebSite), how badly we’d like it to run there (we’ll use 50 for now, but in a two-node situation almost any value above 0 will do) and the host’s name. + + + +[root@pcmk-1 ~]# crm configure location prefer-pcmk-1 WebSite 50: pcmk-1 +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +location prefer-pcmk-1 WebSite 50: pcmk-1 +colocation website-with-ip inf: WebSite ClusterIP +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness="100" +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Fri Aug 28 16:17:35 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +2 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 +WebSite        (ocf::heartbeat:apache):        Started pcmk-2 + + + Wait a minute, the resources are still on pcmk-2! + + + Even though we now prefer pcmk-1 over pcmk-2, that preference is (intentionally) less than the resource stickiness (how much we preferred not to have unnecessary downtime). + + + To see the current placement scores, you can use a tool called ptest + + + ptest -sL + + + Include output + + + + + There is a way to force them to move though... + +
+ +
+ Manually Moving Resources Around the Cluster + + There are always times when an administrator needs to override the cluster and force resources to move to a specific location. Underneath we use location constraints like the one we created above, happily you don’t need to care. Just provide the name of the resource and the intended location, we’ll do the rest. + + + +[root@pcmk-1 ~]# crm resource move WebSite pcmk-1 +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Fri Aug 28 16:19:24 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +2 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-1 +WebSite        (ocf::heartbeat:apache):        Started pcmk-1 +Notice how the colocation rule we created has ensured that ClusterIP was also moved to pcmk-1. +For the curious, we can see the effect of this command by examining the configuration +crm configure show +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +location cli-prefer-WebSite WebSite \ + rule $id="cli-prefer-rule-WebSite" inf: #uname eq pcmk-1 +location prefer-pcmk-1 WebSite 50: pcmk-1 +colocation website-with-ip inf: WebSite ClusterIP +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness="100" + + + Highlighted is the automated constraint used to move the resources to pcmk-1 + +
+ Giving Control Back to the Cluster + + Once we’ve finished whatever activity that required us to move the resources to pcmk-1, in our case nothing, we can then allow the cluster to resume normal operation with the unmove command. Since we previously configured a default stickiness, the resources will remain on pcmk-1. + + + +[root@pcmk-1 ~]# crm resource unmove WebSite +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +location prefer-pcmk-1 WebSite 50: pcmk-1 +colocation website-with-ip inf: WebSite ClusterIP +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes="2" \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness="100" + + + Note that the automated constraint is now gone. If we check the cluster status, we can also see that as expected the resources are still active on pcmk-1. + + + +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Fri Aug 28 16:20:53 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +2 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + + ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-1 + WebSite        (ocf::heartbeat:apache):        Started pcmk-1 + +
+ +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-ClusterFS.xml b/doc/Clusters_from_Scratch/en-US/Ch-ClusterFS.xml new file mode 100644 index 0000000000..765359d23e --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-ClusterFS.xml @@ -0,0 +1,489 @@ + + +%BOOK_ENTITIES; +]> + + Cluster Filesystems - GFS2 +
+ Install a Cluster Filesystem - GFS2 + + The first thing to do is install gfs2-utils on each machine. + + + +[root@pcmk-1 ~]# yum install -y gfs2-utils gfs-pcmk +Setting up Install Process +Resolving Dependencies +--> Running transaction check +---> Package gfs-pcmk.x86_64 0:3.0.5-2.fc12 set to be updated +--> Processing Dependency: libSaCkpt.so.3(OPENAIS_CKPT_B.01.01)(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64 +--> Processing Dependency: dlm-pcmk for package: gfs-pcmk-3.0.5-2.fc12.x86_64 +--> Processing Dependency: libccs.so.3()(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64 +--> Processing Dependency: libdlmcontrol.so.3()(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64 +--> Processing Dependency: liblogthread.so.3()(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64 +--> Processing Dependency: libSaCkpt.so.3()(64bit) for package: gfs-pcmk-3.0.5-2.fc12.x86_64 +---> Package gfs2-utils.x86_64 0:3.0.5-2.fc12 set to be updated +--> Running transaction check +---> Package clusterlib.x86_64 0:3.0.5-2.fc12 set to be updated +---> Package dlm-pcmk.x86_64 0:3.0.5-2.fc12 set to be updated +---> Package openaislib.x86_64 0:1.1.0-1.fc12 set to be updated +--> Finished Dependency Resolution + +Dependencies Resolved + +=========================================================================================== + Package                Arch               Version                   Repository        Size +=========================================================================================== +Installing: + gfs-pcmk               x86_64             3.0.5-2.fc12              custom           101 k + gfs2-utils             x86_64             3.0.5-2.fc12              custom           208 k +Installing for dependencies: + clusterlib             x86_64             3.0.5-2.fc12              custom            65 k + dlm-pcmk               x86_64             3.0.5-2.fc12              custom            93 k + openaislib             x86_64             1.1.0-1.fc12              fedora            76 k + +Transaction Summary +=========================================================================================== +Install       5 Package(s) +Upgrade       0 Package(s) + +Total download size: 541 k +Downloading Packages: +(1/5): clusterlib-3.0.5-2.fc12.x86_64.rpm                                |  65 kB     00:00 +(2/5): dlm-pcmk-3.0.5-2.fc12.x86_64.rpm                                  |  93 kB     00:00 +(3/5): gfs-pcmk-3.0.5-2.fc12.x86_64.rpm                                  | 101 kB     00:00 +(4/5): gfs2-utils-3.0.5-2.fc12.x86_64.rpm                                | 208 kB     00:00 +(5/5): openaislib-1.1.0-1.fc12.x86_64.rpm                                |  76 kB     00:00 +------------------------------------------------------------------------------------------- +Total                                                           992 kB/s | 541 kB     00:00 +Running rpm_check_debug +Running Transaction Test +Finished Transaction Test +Transaction Test Succeeded +Running Transaction +  Installing     : clusterlib-3.0.5-2.fc12.x86_64                                       1/5 +  Installing     : openaislib-1.1.0-1.fc12.x86_64                                       2/5 +  Installing     : dlm-pcmk-3.0.5-2.fc12.x86_64                                         3/5 +  Installing     : gfs-pcmk-3.0.5-2.fc12.x86_64                                         4/5 +  Installing     : gfs2-utils-3.0.5-2.fc12.x86_64                                       5/5 + +Installed: +  gfs-pcmk.x86_64 0:3.0.5-2.fc12                    gfs2-utils.x86_64 0:3.0.5-2.fc12 + +Dependency Installed: +  clusterlib.x86_64 0:3.0.5-2.fc12   dlm-pcmk.x86_64 0:3.0.5-2.fc12 +  openaislib.x86_64 0:1.1.0-1.fc12   + +Complete! +[root@pcmk-1 x86_64]# + +
+ +
+ Setup Pacemaker-GFS2 Integration + + GFS2 needs two services to be running, the first is the user-space interface to the kernel’s distributed lock manager (DLM). The DLM is used to co-ordinate which node(s) can access a given file (and when) and integrates with Pacemaker to obtain node membership + + The list of nodes the cluster considers to be available + + information and fencing capabilities. + + + The second service is GFS2’s own control daemon which also integrates with Pacemaker to obtain node membership data. + +
+ Add the DLM service + + The DLM control daemon needs to run on all active cluster nodes, so we will use the shells interactive mode to create a cloned resource. + + + +[root@pcmk-1 ~]# crm +crm(live)# cib new stack-glue +INFO: stack-glue shadow CIB created +crm(stack-glue)# configure primitive dlm ocf:pacemaker:controld op monitor interval=120s +crm(stack-glue)# configure clone dlm-clone dlm meta interleave=true +crm(stack-glue)# configure show xml +crm(stack-glue)# configure show +node pcmk-1 +node pcmk-2 +primitive WebData ocf:linbit:drbd \ +        params drbd_resource="wwwdata" \ +        op monitor interval="60s" +primitive WebFS ocf:heartbeat:Filesystem \ +        params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype="ext4" +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +primitive dlm ocf:pacemaker:controld \ + op monitor interval="120s" +ms WebDataClone WebData \ +        meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" +clone dlm-clone dlm \ + meta interleave="true" +location prefer-pcmk-1 WebSite 50: pcmk-1 +colocation WebSite-with-WebFS inf: WebSite WebFS +colocation fs_on_drbd inf: WebFS WebDataClone:Master +colocation website-with-ip inf: WebSite ClusterIP +order WebFS-after-WebData inf: WebDataClone:promote WebFS:start +order WebSite-after-WebFS inf: WebFS WebSite +order apache-after-ip inf: ClusterIP WebSite +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” + + + + TODO: Explain the meaning of the interleave option + + + + Review the configuration before uploading it to the cluster, quitting the shell and watching the cluster’s response + + + +crm(stack-glue)# cib commit stack-glue +INFO: commited 'stack-glue' shadow CIB to the cluster +crm(stack-glue)# quit +bye +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Thu Sep  3 20:49:54 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +5 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +WebSite (ocf::heartbeat:apache):        Started pcmk-2 +Master/Slave Set: WebDataClone +        Masters: [ pcmk-1 ] +        Slaves: [ pcmk-2 ] +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 +Clone Set: dlm-clone + Started: [ pcmk-2 pcmk-1 ] +WebFS   (ocf::heartbeat:Filesystem):    Started pcmk-2 + +
+ +
+ Add the GFS2 service + + Once the DLM is active, we can add the GFS2 control daemon. + + + Use the crm shell to create the gfs-control cluster resource: + + + +[root@pcmk-1 ~]# crm +crm(live)# cib new gfs-glue --force +INFO: gfs-glue shadow CIB created +crm(gfs-glue)# configure primitive gfs-control ocf:pacemaker:controld params daemon=gfs_controld.pcmk args="-g 0" op monitor interval=120s +crm(gfs-glue)# configure clone gfs-clone gfs-control meta interleave=true + + + Now ensure Pacemaker only starts the gfs-control service on nodes that also have a copy of the dlm service (created above) already running + + + +crm(gfs-glue)# configure colocation gfs-with-dlm INFINITY: gfs-clone dlm-clone +crm(gfs-glue)# configure order start-gfs-after-dlm mandatory: dlm-clone gfs-clone + + + Review the configuration before uploading it to the cluster, quitting the shell and watching the cluster’s response + + + +crm(gfs-glue)# configure show +node pcmk-1 +node pcmk-2 +primitive WebData ocf:linbit:drbd \ +        params drbd_resource="wwwdata" \ +        op monitor interval="60s" +primitive WebFS ocf:heartbeat:Filesystem \ +        params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype="ext4" +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +primitive dlm ocf:pacemaker:controld \ +        op monitor interval="120s" +primitive gfs-control ocf:pacemaker:controld \ + params daemon=”gfs_controld.pcmk” args=”-g 0” \ + op monitor interval="120s" +ms WebDataClone WebData \ +        meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" +clone dlm-clone dlm \ +        meta interleave="true" +clone gfs-clone gfs-control \ + meta interleave="true" +location prefer-pcmk-1 WebSite 50: pcmk-1 +colocation WebSite-with-WebFS inf: WebSite WebFS +colocation fs_on_drbd inf: WebFS WebDataClone:Master +colocation gfs-with-dlm inf: gfs-clone dlm-clone +colocation website-with-ip inf: WebSite ClusterIP +order WebFS-after-WebData inf: WebDataClone:promote WebFS:start +order WebSite-after-WebFS inf: WebFS WebSite +order apache-after-ip inf: ClusterIP WebSite +order start-gfs-after-dlm inf: dlm-clone gfs-clone +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” +crm(gfs-glue)# cib commit gfs-glue +INFO: commited 'gfs-glue' shadow CIB to the cluster +crm(gfs-glue)# quit +bye +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Thu Sep  3 20:49:54 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +6 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +WebSite (ocf::heartbeat:apache):        Started pcmk-2 +Master/Slave Set: WebDataClone +        Masters: [ pcmk-1 ] +        Slaves: [ pcmk-2 ] +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 +Clone Set: dlm-clone +        Started: [ pcmk-2 pcmk-1 ] +Clone Set: gfs-clone + Started: [ pcmk-2 pcmk-1 ] +WebFS   (ocf::heartbeat:Filesystem):    Started pcmk-1 + +
+ +
+ +
+ Create a GFS2 Filesystem +
+ Preparation + + Before we do anything to the existing partition, we need to make sure it is unmounted. We do this by tell the cluster to stop the WebFS resource. This will ensure that other resources (in our case, Apache) using WebFS are not only stopped, but stopped in the correct order. + + + +[root@pcmk-1 ~]# crm_resource --resource WebFS --set-parameter target-role --meta --parameter-value Stopped +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Thu Sep  3 15:18:06 2009 +Stack: openais +Current DC: pcmk-1 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +6 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +Master/Slave Set: WebDataClone +        Masters: [ pcmk-1 ] +        Slaves: [ pcmk-2 ] +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-1 +Clone Set: dlm-clone +        Started: [ pcmk-2 pcmk-1 ] +Clone Set: gfs-clone +        Started: [ pcmk-2 pcmk-1 ] + + + + Note that both Apache and WebFS have been stopped. + + +
+ +
+ Create and Populate an GFS2 Partition + + Now that the cluster stack and integration pieces are running smoothly, we can create an GFS2 partition. + + + + This will erase all previous content stored on the DRBD device. Ensure you have a copy of any important data. + + + + We need to specify a number of additional parameters when creating a GFS2 partition. + + + First we must use the -p option to specify that we want to use the the Kernel’s DLM. Next we use -j to indicate that it should reserve enough space for two journals (one per node accessing the filesystem). + + + Lastly, we use -t to specify the lock table name. The format for this field is clustername:fsname. For the fsname, we just need to pick something unique and descriptive and since we haven’t specified a clustername yet, we will use the default (pcmk). + + + To specify an alternate name for the cluster, locate the service section containing “name: pacemaker” in corosync.conf and insert the following line anywhere inside the block: + + + clustername: myname + + + Do this on each node in the cluster and be sure to restart them before continuing. + + + +mkfs.gfs2 -p lock_dlm -j 2 -t pcmk:web /dev/drbd1 +[root@pcmk-1 ~]# mkfs.gfs2 -t pcmk:web -p lock_dlm -j 2 /dev/vdb +This will destroy any data on /dev/vdb. +It appears to contain: data + +Are you sure you want to proceed? [y/n] y + +Device:                    /dev/vdb +Blocksize:                 4096 +Device Size                1.00 GB (131072 blocks) +Filesystem Size:           1.00 GB (131070 blocks) +Journals:                  2 +Resource Groups:           2 +Locking Protocol:          "lock_dlm" +Lock Table:                "pcmk:web" +UUID:                      6B776F46-177B-BAF8-2C2B-292C0E078613 + +[root@pcmk-1 ~]# + + + Then (re)populate the new filesystem with data (web pages). For now we’ll create another variation on our home page. + + + +[root@pcmk-1 ~]# mount /dev/drbd1 /mnt/ +[root@pcmk-1 ~]# cat <<-END >/mnt/index.html +<html> +<body>My Test Site - GFS2</body> +</html> +END +[root@pcmk-1 ~]# umount /dev/drbd1 +[root@pcmk-1 ~]# drbdadm verify wwwdata +[root@pcmk-1 ~]# + +
+ +
+ +
+ Reconfigure the Cluster for GFS2 + + +[root@pcmk-1 ~]# crm +crm(live)# cib new GFS2 +INFO: GFS2 shadow CIB created +crm(GFS2)# configure delete WebFS +crm(GFS2)# configure primitive WebFS ocf:heartbeat:Filesystem params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2” + + + Now that we’ve recreated the resource, we also need to recreate all the constraints that used it. This is because the shell will automatically remove any constraints that referenced WebFS. + + + +crm(GFS2)# configure colocation WebSite-with-WebFS inf: WebSite WebFS +crm(GFS2)# configure colocation fs_on_drbd inf: WebFS WebDataClone:Master +crm(GFS2)# configure order WebFS-after-WebData inf: WebDataClone:promote WebFS:start +crm(GFS2)# configure order WebSite-after-WebFS inf: WebFS WebSite +crm(GFS2)# configure colocation WebFS-with-gfs-control INFINITY: WebFS gfs-clone +crm(GFS2)# configure order start-WebFS-after-gfs-control mandatory: gfs-clone WebFS +crm(GFS2)# configure show +node pcmk-1 +node pcmk-2 +primitive WebData ocf:linbit:drbd \ +        params drbd_resource="wwwdata" \ +        op monitor interval="60s" +primitive WebFS ocf:heartbeat:Filesystem \ + params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2” +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +primitive dlm ocf:pacemaker:controld \ +        op monitor interval="120s" +primitive gfs-control ocf:pacemaker:controld \ +   params daemon=”gfs_controld.pcmk” args=”-g 0” \ +        op monitor interval="120s" +ms WebDataClone WebData \ +        meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" +clone dlm-clone dlm \ +        meta interleave="true" +clone gfs-clone gfs-control \ +        meta interleave="true" +colocation WebFS-with-gfs-control inf: WebFS gfs-clone +colocation WebSite-with-WebFS inf: WebSite WebFS +colocation fs_on_drbd inf: WebFS WebDataClone:Master +colocation gfs-with-dlm inf: gfs-clone dlm-clone +colocation website-with-ip inf: WebSite ClusterIP +order WebFS-after-WebData inf: WebDataClone:promote WebFS:start +order WebSite-after-WebFS inf: WebFS WebSite +order apache-after-ip inf: ClusterIP WebSite +order start-WebFS-after-gfs-control inf: gfs-clone WebFS +order start-gfs-after-dlm inf: dlm-clone gfs-clone +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” + + + Review the configuration before uploading it to the cluster, quitting the shell and watching the cluster’s response + + + +crm(GFS2)# cib commit GFS2 +INFO: commited 'GFS2' shadow CIB to the cluster +crm(GFS2)# quit +bye +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Thu Sep  3 20:49:54 2009 +Stack: openais +Current DC: pcmk-2 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +6 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +WebSite (ocf::heartbeat:apache):        Started pcmk-2 +Master/Slave Set: WebDataClone +        Masters: [ pcmk-1 ] +        Slaves: [ pcmk-2 ] +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 +Clone Set: dlm-clone +        Started: [ pcmk-2 pcmk-1 ] +Clone Set: gfs-clone +        Started: [ pcmk-2 pcmk-1 ] +WebFS (ocf::heartbeat:Filesystem): Started pcmk-1 + +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Installation.xml b/doc/Clusters_from_Scratch/en-US/Ch-Installation.xml new file mode 100644 index 0000000000..ba0d75ea0e --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-Installation.xml @@ -0,0 +1,674 @@ + + +%BOOK_ENTITIES; +]> + + Installation +
+ OS Installation + + Detailed instructions for installing Fedora are available at http://docs.fedoraproject.org/install-guide/f12/ in a number of languages. The abbreviated version is as follows... + + + Point your browser to http://fedoraproject.org/en/get-fedora-all, locate the Install Media section and download the install DVD that matches your hardware. + + + Burn the disk image to a DVD + + http://docs.fedoraproject.org/readme-burning-isos/en-US.html + + and boot from it. Or use the image to boot a virtual machine as I have done here. After clicking through the welcome screen, select your language and keyboard layout + + http://docs.fedoraproject.org/install-guide/f12/en-US/html/s1-langselection-x86.html + + + + + + + Insert graphic here + + + + + Assign your machine a host name. + + http://docs.fedoraproject.org/install-guide/f12/en-US/html/sn-networkconfig-fedora.html + + I happen to control the clusterlabs.org domain name, so I will use that here. + + + + + Insert graphic here + + + + + You will then be prompted to indicate the machine’s physical location and to supply a root password. + + http://docs.fedoraproject.org/install-guide/f12/en-US/html/sn-account_configuration.html + + + + + Now select where you want Fedora installed. + + http://docs.fedoraproject.org/install-guide/f12/en-US/html/s1-diskpartsetup-x86.html + + As I don’t care about any existing data, I will accept the default and allow Fedora to use the complete drive. + + + IMPORTANT: If you plan on following the DRBD or GFS2 portions of this guide, you should reserve at least 1Gb of space on each machine from which to create a shared volume. + + + + + Insert graphic here + + + + + The next step is to configure networking. Do not accept the default. Cluster machines should never obtain an ip address via DHCP. Here I will use the internal addresses for the clusterlab.org network. + + + + + Insert graphic here + + + + + Next choose which software should be installed. Deselect the default “Office and Productivity” as its not appropriate for a cluster node. You will want to select the “Updates” channel though. We’ll install any needed software later. After you click next, Fedora will begin installing. + + + + + Insert graphic here + + + + + Insert graphic here + + + + + Once the node reboots, follow the on screen instructions + + http://docs.fedoraproject.org/install-guide/f12/en-US/html/ch-firstboot.html + + to create a system user and configure the time. It is highly recommended to enable NTP on your cluster nodes. Doing so ensures all nodes agree on the current time and makes reading log files significantly easier. + + + + + Insert graphic here + + + Click through the next screens until you reach the login window. Click on the user you created and supply the password you indicated earlier. + +
+ +
+ Cluster Software Installation + + + Installing the cluster in future versions of Fedora will be significantly easier now that the entire stack has been accepted into the distribution. However for now there are still some hoops to jump through. + + + + Start a terminal by going to Applications -> System Tools -> Terminal + + + + + Insert graphic here + + + That was the last screenshot by the way, from here on in we’re going to be working from the terminal. + + + Switch to the super user (aka. "root") account. You will need to supply the password you entered earlier during the installation process. + + + su - + + + [beekhof@pcmk-1 ~]$ su - + + + Password: + + + [root@pcmk-1 ~]# + + + Note that the username (the text before the @ symbol) now indicates we’re running as the super user “root”. + +
+ Install the Cluster Software + + Since version 12, Fedora comes with recent versions of everything you need, so simply fire up the shell and run: + + + +[root@pcmk-1 ~]# yum install -y pacemaker +Setting up Install Process +Resolving Dependencies +--> Running transaction check +---> Package pacemaker.x86_64 0:1.1.0-1.fc12 set to be updated +--> Processing Dependency: heartbeat >= 3.0.0 for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: resource-agents for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: corosync for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libgnutls.so.26(GNUTLS_1_4)(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: cluster-glue for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libcrmcluster.so.1()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libcib.so.1()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libltdl.so.7()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libccmclient.so.1()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libesmtp.so.5()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libxslt.so.1()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libpils.so.2()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libpengine.so.3()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: liblrm.so.2()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libtransitioner.so.1()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libstonithd.so.1()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libcrmcommon.so.2()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libplumb.so.2()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libnetsnmp.so.15()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libnetsnmpagent.so.15()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libnetsnmpmibs.so.15()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libpe_status.so.2()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libsensors.so.4()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libnetsnmphelpers.so.15()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libstonith.so.1()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libcoroipcc.so.4()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libpe_rules.so.2()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libgnutls.so.26()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Processing Dependency: libhbclient.so.1()(64bit) for package: pacemaker-1.1.0-1.fc12.x86_64 +--> Running transaction check +---> Package cluster-glue.x86_64 0:1.0-0.11.b79635605337.hg.fc12 set to be updated +--> Processing Dependency: perl-TimeDate for package: cluster-glue-1.0-0.11.b79635605337.hg.fc12.x86_64 +--> Processing Dependency: libOpenIPMIutils.so.0()(64bit) for package: cluster-glue-1.0-0.11.b79635605337.hg.fc12.x86_64 +--> Processing Dependency: libOpenIPMIposix.so.0()(64bit) for package: cluster-glue-1.0-0.11.b79635605337.hg.fc12.x86_64 +--> Processing Dependency: libopenhpi.so.2()(64bit) for package: cluster-glue-1.0-0.11.b79635605337.hg.fc12.x86_64 +--> Processing Dependency: libOpenIPMI.so.0()(64bit) for package: cluster-glue-1.0-0.11.b79635605337.hg.fc12.x86_64 +---> Package cluster-glue-libs.x86_64 0:1.0-0.11.b79635605337.hg.fc12 set to be updated +---> Package corosync.x86_64 0:1.1.2-1.fc12 set to be updated +---> Package corosynclib.x86_64 0:1.1.2-1.fc12 set to be updated +--> Processing Dependency: librdmacm.so.1(RDMACM_1.0)(64bit) for package: corosynclib-1.1.2-1.fc12.x86_64 +--> Processing Dependency: libibverbs.so.1(IBVERBS_1.0)(64bit) for package: corosynclib-1.1.2-1.fc12.x86_64 +--> Processing Dependency: libibverbs.so.1(IBVERBS_1.1)(64bit) for package: corosynclib-1.1.2-1.fc12.x86_64 +--> Processing Dependency: libibverbs.so.1()(64bit) for package: corosynclib-1.1.2-1.fc12.x86_64 +--> Processing Dependency: librdmacm.so.1()(64bit) for package: corosynclib-1.1.2-1.fc12.x86_64 +---> Package gnutls.x86_64 0:2.8.5-1.fc12 set to be updated +--> Processing Dependency: libtasn1.so.3(LIBTASN1_0_3)(64bit) for package: gnutls-2.8.5-1.fc12.x86_64 +--> Processing Dependency: libtasn1.so.3()(64bit) for package: gnutls-2.8.5-1.fc12.x86_64 +---> Package heartbeat.x86_64 0:3.0.0-0.5.0daab7da36a8.hg.fc12 set to be updated +--> Processing Dependency: PyXML for package: heartbeat-3.0.0-0.5.0daab7da36a8.hg.fc12.x86_64 +---> Package heartbeat-libs.x86_64 0:3.0.0-0.5.0daab7da36a8.hg.fc12 set to be updated +---> Package libesmtp.x86_64 0:1.0.4-12.fc12 set to be updated +---> Package libtool-ltdl.x86_64 0:2.2.6-15.fc12 set to be updated +---> Package libxslt.x86_64 0:1.1.26-1.fc12 set to be updated +---> Package lm_sensors-libs.x86_64 0:3.1.1-4.fc12 set to be updated +---> Package net-snmp-libs.x86_64 1:5.4.2.1-18.fc12 set to be updated +---> Package pacemaker-libs.x86_64 0:1.1.0-1.fc12 set to be updated +---> Package resource-agents.x86_64 0:3.0.5-1.fc12 set to be updated +--> Running transaction check +---> Package OpenIPMI-libs.x86_64 0:2.0.16-4.fc12 set to be updated +---> Package PyXML.x86_64 0:0.8.4-15 set to be updated +---> Package libibverbs.x86_64 0:1.1.3-3.fc12 set to be updated +--> Processing Dependency: libibverbs-driver for package: libibverbs-1.1.3-3.fc12.x86_64 +---> Package librdmacm.x86_64 0:1.0.10-1.fc12 set to be updated +---> Package libtasn1.x86_64 0:2.3-1.fc12 set to be updated +---> Package openhpi-libs.x86_64 0:2.14.0-5.fc12 set to be updated +---> Package perl-TimeDate.noarch 1:1.16-11.fc12 set to be updated +--> Running transaction check +---> Package libmlx4.x86_64 0:1.0.1-3.fc12 set to be updated +--> Finished Dependency Resolution + +Dependencies Resolved + +======================================================================================= + Package Arch Version Repository Size +======================================================================================= +Installing: + pacemaker x86_64 1.1.0-1.fc12 custom 545 k +Installing for dependencies: + OpenIPMI-libs x86_64 2.0.16-4.fc12 fedora 434 k + PyXML x86_64 0.8.4-15 fedora 808 k + cluster-glue x86_64 1.0-0.11.b79635605337.hg.fc12 fedora 222 k + cluster-glue-libs x86_64 1.0-0.11.b79635605337.hg.fc12 fedora 114 k + corosync x86_64 1.1.2-1.fc12 fedora 144 k + corosynclib x86_64 1.1.2-1.fc12 fedora 138 k + gnutls x86_64 2.8.5-1.fc12 fedora 350 k + heartbeat x86_64 3.0.0-0.5.0daab7da36a8.hg.fc12 fedora 172 k + heartbeat-libs x86_64 3.0.0-0.5.0daab7da36a8.hg.fc12 fedora 265 k + libesmtp x86_64 1.0.4-12.fc12 fedora 54 k + libibverbs x86_64 1.1.3-3.fc12 updates 42 k + libmlx4 x86_64 1.0.1-3.fc12 updates 26 k + librdmacm x86_64 1.0.10-1.fc12 updates 22 k + libtasn1 x86_64 2.3-1.fc12 fedora 232 k + libtool-ltdl x86_64 2.2.6-15.fc12 fedora 44 k + libxslt x86_64 1.1.26-1.fc12 fedora 397 k + lm_sensors-libs x86_64 3.1.1-4.fc12 updates 36 k + net-snmp-libs x86_64 1:5.4.2.1-18.fc12 fedora 1.3 M + openhpi-libs x86_64 2.14.0-5.fc12 fedora 128 k + pacemaker-libs x86_64 1.1.0-1.fc12 custom 250 k + perl-TimeDate noarch 1:1.16-11.fc12 fedora 33 k + resource-agents x86_64 3.0.5-1.fc12 updates 251 k + +Transaction Summary +======================================================================================= +Install 23 Package(s) +Upgrade 0 Package(s) + +Total download size: 5.9 M +Downloading Packages: +(1/23): OpenIPMI-libs-2.0.16-4.fc12.x86_64.rpm | 434 kB 00:00 +(2/23): PyXML-0.8.4-15.x86_64.rpm | 808 kB 00:00 +(3/23): cluster-glue-1.0-0.11.b79635605337.hg.fc12.x86_64.rpm | 222 kB 00:00 +(4/23): cluster-glue-libs-1.0-0.11.b79635605337.hg.fc12.x86_64. | 114 kB 00:00 +(5/23): corosync-1.1.2-1.fc12.x86_64.rpm | 144 kB 00:00 +(6/23): corosynclib-1.1.2-1.fc12.x86_64.rpm | 138 kB 00:00 +(7/23): gnutls-2.8.5-1.fc12.x86_64.rpm | 350 kB 00:00 +(8/23): heartbeat-3.0.0-0.5.0daab7da36a8.hg.fc12.x86_64.rpm | 172 kB 00:00 +(9/23): heartbeat-libs-3.0.0-0.5.0daab7da36a8.hg.fc12.x86_64.rp | 265 kB 00:00 +(10/23): libesmtp-1.0.4-12.fc12.x86_64.rpm | 54 kB 00:00 +(11/23): libibverbs-1.1.3-3.fc12.x86_64.rpm | 42 kB 00:00 +(12/23): libmlx4-1.0.1-3.fc12.x86_64.rpm | 26 kB 00:00 +(13/23): librdmacm-1.0.10-1.fc12.x86_64.rpm | 22 kB 00:00 +(14/23): libtasn1-2.3-1.fc12.x86_64.rpm | 232 kB 00:00 +(15/23): libtool-ltdl-2.2.6-15.fc12.x86_64.rpm | 44 kB 00:00 +(16/23): libxslt-1.1.26-1.fc12.x86_64.rpm | 397 kB 00:00 +(17/23): lm_sensors-libs-3.1.1-4.fc12.x86_64.rpm | 36 kB 00:00 +(18/23): net-snmp-libs-5.4.2.1-18.fc12.x86_64.rpm | 1.3 MB 00:00 +(19/23): openhpi-libs-2.14.0-5.fc12.x86_64.rpm | 128 kB 00:00 +(20/23): pacemaker-1.1.0-1.fc12.x86_64.rpm | 545 kB 00:00 +(21/23): pacemaker-libs-1.1.0-1.fc12.x86_64.rpm | 250 kB 00:00 +(22/23): perl-TimeDate-1.16-11.fc12.noarch.rpm | 33 kB 00:00 +(23/23): resource-agents-3.0.5-1.fc12.x86_64.rpm | 251 kB 00:00 +--------------------------------------------------------------------------------------- +Total 894 kB/s | 5.9 MB 00:06 + + + +Running rpm_check_debug +Running Transaction Test +Finished Transaction Test +Transaction Test Succeeded +Running Transaction + Installing : libtool-ltdl-2.2.6-15.fc12.x86_64 1/23 + Installing : lm_sensors-libs-3.1.1-4.fc12.x86_64 2/23 + Installing : 1:net-snmp-libs-5.4.2.1-18.fc12.x86_64 3/23 + Installing : libxslt-1.1.26-1.fc12.x86_64 4/23 + Installing : openhpi-libs-2.14.0-5.fc12.x86_64 5/23 + Installing : PyXML-0.8.4-15.x86_64 6/23 + Installing : libesmtp-1.0.4-12.fc12.x86_64 7/23 + Installing : OpenIPMI-libs-2.0.16-4.fc12.x86_64 8/23 + Installing : libtasn1-2.3-1.fc12.x86_64 9/23 + Installing : gnutls-2.8.5-1.fc12.x86_64 10/23 + Installing : 1:perl-TimeDate-1.16-11.fc12.noarch 11/23 + Installing : cluster-glue-libs-1.0-0.11.b79635605337.hg.fc12.x86_64 12/23 + Installing : cluster-glue-1.0-0.11.b79635605337.hg.fc12.x86_64 13/23 + Installing : libibverbs-1.1.3-3.fc12.x86_64 14/23 + Installing : resource-agents-3.0.5-1.fc12.x86_64 15/23 + Installing : librdmacm-1.0.10-1.fc12.x86_64 16/23 + Installing : corosynclib-1.1.2-1.fc12.x86_64 17/23 + Installing : corosync-1.1.2-1.fc12.x86_64 18/23 + Installing : libmlx4-1.0.1-3.fc12.x86_64 19/23 + Installing : heartbeat-libs-3.0.0-0.5.0daab7da36a8.hg.fc12.x86_64 20/23 + Installing : heartbeat-3.0.0-0.5.0daab7da36a8.hg.fc12.x86_64 21/23 + Installing : pacemaker-1.1.0-1.fc12.x86_64 22/23 + Installing : pacemaker-libs-1.1.0-1.fc12.x86_64 23/23 + +Installed: + pacemaker.x86_64 0:1.1.0-1.fc12 + +Dependency Installed: + OpenIPMI-libs.x86_64 0:2.0.16-4.fc12 + PyXML.x86_64 0:0.8.4-15 + cluster-glue.x86_64 0:1.0-0.11.b79635605337.hg.fc12 + cluster-glue-libs.x86_64 0:1.0-0.11.b79635605337.hg.fc12 + corosync.x86_64 0:1.1.2-1.fc12 + corosynclib.x86_64 0:1.1.2-1.fc12 + gnutls.x86_64 0:2.8.5-1.fc12 + heartbeat.x86_64 0:3.0.0-0.5.0daab7da36a8.hg.fc12 + heartbeat-libs.x86_64 0:3.0.0-0.5.0daab7da36a8.hg.fc12 + libesmtp.x86_64 0:1.0.4-12.fc12 + libibverbs.x86_64 0:1.1.3-3.fc12 + libmlx4.x86_64 0:1.0.1-3.fc12 + librdmacm.x86_64 0:1.0.10-1.fc12 + libtasn1.x86_64 0:2.3-1.fc12 + libtool-ltdl.x86_64 0:2.2.6-15.fc12 + libxslt.x86_64 0:1.1.26-1.fc12 + lm_sensors-libs.x86_64 0:3.1.1-4.fc12 + net-snmp-libs.x86_64 1:5.4.2.1-18.fc12 + openhpi-libs.x86_64 0:2.14.0-5.fc12 + pacemaker-libs.x86_64 0:1.1.0-1.fc12 + perl-TimeDate.noarch 1:1.16-11.fc12 + resource-agents.x86_64 0:3.0.5-1.fc12 + +Complete! +[root@pcmk-1 ~]# + +
+ +
+ Security Shortcuts + + To simplify this guide and focus on the aspects directly connected to clustering, we will now disable the machine’s firewall and SELinux installation. Both of these actions create significant security issues and should not be performed on machines that will be exposed to the outside world. + + + Create an Appendix that deals with (at least) re-enabling the firewall. + + + + + +sed -i.bak "s/SELINUX=enforcing/SELINUX=permissive/g" /etc/selinux/config +/sbin/chkconfig --del iptables + + + + + Now reboot all nodes so the new security settings take effect. + + + +
+ +
+ +
+ Before You Continue + + Repeat the Installation steps so that you have 2 Fedora nodes with the cluster software installed. + + + For the purposes of this document, the additional node is called pcmk-2 with address 192.168.122.42. + +
+ +
+ Setup +
+ Finalize Networking + + Confirm that you can communicate with the two new nodes: + +
+ Verify Connectivity by IP address + + + ping -c 3 192.168.122.102 +[root@pcmk-1 ~]# ping -c 3 192.168.122.102 +PING 192.168.122.102 (192.168.122.102) 56(84) bytes of data. +64 bytes from 192.168.122.102: icmp_seq=1 ttl=64 time=0.343 ms +64 bytes from 192.168.122.102: icmp_seq=2 ttl=64 time=0.402 ms +64 bytes from 192.168.122.102: icmp_seq=3 ttl=64 time=0.558 ms + +--- 192.168.122.102 ping statistics --- +3 packets transmitted, 3 received, 0% packet loss, time 2000ms +rtt min/avg/max/mdev = 0.343/0.434/0.558/0.092 ms + +
+ + Now we need to make sure we can communicate with the machines by their name. If you have a DNS server, add additional entries for the three machines. Otherwise, you’ll need to add the machines to /etc/hosts . Below are the entries for my cluster nodes: + +
+ Set up /etc/hosts entries + + + grep pcmk /etc/hosts +[root@pcmk-1 ~]# grep pcmk /etc/hosts +192.168.122.101 pcmk-1.clusterlabs.org pcmk-1 +192.168.122.102 pcmk-2.clusterlabs.org pcmk-2 + +
+ + We can now verify the setup by again using ping: + +
+ Verify Connectivity by Hostname + + + ping -c 3 pcmk-2 +[root@pcmk-1 ~]# ping -c 3 pcmk-2 +PING pcmk-2.clusterlabs.org (192.168.122.101) 56(84) bytes of data. +64 bytes from pcmk-1.clusterlabs.org (192.168.122.101): icmp_seq=1 ttl=64 time=0.164 ms +64 bytes from pcmk-1.clusterlabs.org (192.168.122.101): icmp_seq=2 ttl=64 time=0.475 ms +64 bytes from pcmk-1.clusterlabs.org (192.168.122.101): icmp_seq=3 ttl=64 time=0.186 ms + +--- pcmk-2.clusterlabs.org ping statistics --- +3 packets transmitted, 3 received, 0% packet loss, time 2001ms +rtt min/avg/max/mdev = 0.164/0.275/0.475/0.141 ms + +
+
+ +
+ Configure SSH + + SSH is a convenient and secure way to copy files and perform commands remotely. For the purposes of this guide, we will create a key without a password (using the -N “” option) so that we can perform remote actions without being prompted. + + + + NOTE: Unprotected SSH keys, those without a password, are not recommended for servers exposed to the outside world. + + + + Create a new key and allow anyone with that key to log in: + +
+ Creating and Activating a new SSH Key + + +[root@pcmk-1 ~]# ssh-keygen -t dsa -f ~/.ssh/id_dsa -N "" +Generating public/private dsa key pair. +Your identification has been saved in /root/.ssh/id_dsa. +Your public key has been saved in /root/.ssh/id_dsa.pub. +The key fingerprint is: +91:09:5c:82:5a:6a:50:08:4e:b2:0c:62:de:cc:74:44 root@pcmk-1.clusterlabs.org + +The key's randomart image is: ++--[ DSA 1024]----+ +|==.ooEo.. | +|X O + .o o | +| * A + | +| + . | +| . S | +| | +| | +| | +| | ++-----------------+ +[root@pcmk-1 ~]# cp .ssh/id_dsa.pub .ssh/authorized_keys +[root@pcmk-1 ~]# + +
+ + Install the key on the other nodes and test that you can now run commands remotely, without being prompted + +
+ Installing the SSH Key on Another Host + + +[root@pcmk-1 ~]# scp -r .ssh pcmk-2: +The authenticity of host 'pcmk-2 (192.168.122.102)' can't be established. +RSA key fingerprint is b1:2b:55:93:f1:d9:52:2b:0f:f2:8a:4e:ae:c6:7c:9a. +Are you sure you want to continue connecting (yes/no)? yes +Warning: Permanently added 'pcmk-2,192.168.122.102' (RSA) to the list of known hosts. +root@pcmk-2's password: +id_dsa.pub 100% 616 0.6KB/s 00:00 +id_dsa 100% 672 0.7KB/s 00:00 +known_hosts 100% 400 0.4KB/s 00:00 +authorized_keys 100% 616 0.6KB/s 00:00 +[root@pcmk-1 ~]# ssh pcmk-2 -- uname -n +pcmk-2 +[root@pcmk-1 ~]# + +
+
+ +
+ Short Node Names + + During installation, we filled in the machine’s fully qualifier domain name (FQDN) which can be rather long when it appears in cluster logs and status output. See for yourself how the machine identifies itself: + + + +[root@pcmk-1 ~]# uname -n +pcmk-1.clusterlabs.org +[root@pcmk-1 ~]# dnsdomainname +clusterlabs.org + + + The output from the second command is fine, but we really don’t need the domain name included in the basic host details. To address this, we need to update /etc/sysconfig/network. This is what it should look like before we start. + + + +cat /etc/sysconfig/network +NETWORKING=yes +HOSTNAME=pcmk-1.clusterlabs.org +GATEWAY=192.168.122.1 + + + All we need to do now is strip off the domain name portion, which is stored elsewhere anyway. + + +sed -i.bak 's/\.[a-z].*//g' /etc/sysconfig/network + + + Now confirm the change was successful. The revised file contents should look something like this. + + + +[root@pcmk-1 ~]# cat /etc/sysconfig/network +NETWORKING=yes +HOSTNAME=pcmk-1 +GATEWAY=192.168.122.1 + + + However we’re not finished. The machine wont normally see the shortened host name until about it reboots, but we can force it to update + + + +[root@pcmk-1 ~]# source /etc/sysconfig/network +[root@pcmk-1 ~]# hostname $HOSTNAME + + + Now check the machine is using the correct names + + + +[root@pcmk-1 ~]# uname -n +pcmk-1 +[root@pcmk-1 ~]# dnsdomainname +clusterlabs.org + + + Now repeat on pcmk-2. + +
+ +
+ Configuring Corosync + + Choose a port number and multi-cast + + http://en.wikipedia.org/wiki/Multicast + + address. + + http://en.wikipedia.org/wiki/Multicast_address + + + + + Be sure that the values you chose do not conflict with any existing clusters you might have. For advice on choosing a multi-cast address, see http://www.29west.com/docs/THPM/multicast-address-assignment.html + + + For this document, I have chosen port 4000 and used 226.94.1.1 as the multi-cast address. + + + +export ais_port=4000 +export ais_mcast=226.94.1.1 + + + Next we automatically determine the hosts address. By not using the full address, we make the configuration suitable to be copied to other nodes. + + +export ais_addr=`ip addr | grep "inet " | tail -n 1 | awk '{print $4}' | sed s/255/0/` + + + Display and verify the configuration options + + + +[root@pcmk-1 ~]# env | grep ais_ +ais_mcast=226.94.1.1 +ais_port=4000 +ais_addr=192.168.122.0 + + + Once you’re happy with the chosen values, update the Corosync configuration + + + +cp /etc/corosync/corosync.conf.example /etc/corosync/corosync.conf +sed -i.bak "s/.*mcastaddr:.*/mcastaddr:\ $ais_mcast/g" /etc/corosync/corosync.conf +sed -i.bak "s/.*mcastport:.*/mcastport:\ $ais_port/g" /etc/corosync/corosync.conf +sed -i.bak "s/.*bindnetaddr:.*/bindnetaddr:\ $ais_addr/g" /etc/corosync/corosync.conf + + + Tell Corosync to run as the root user + + + +cat <<-END >>/etc/corosync/corosync.conf +aisexec { + user: root + group: root +} +END + + + Finally, tell Corosync to start Pacemaker + + + +cat <<-END >>/etc/corosync/corosync.conf +service { + # Load the Pacemaker Cluster Resource Manager + name: pacemaker + ver: 0 +} +END + + + The final configuration should look something like the sample in the appendix. + +
+ +
+ Propagate the Configuration + + Now we need to copy the changes so far to the other node: + + + +[root@pcmk-1 ~]# for f in /etc/corosync/corosync.conf /etc/hosts; do scp $f pcmk-2:$f ; done +corosync.conf 100% 1528 1.5KB/s 00:00 +hosts 100% 281 0.3KB/s 00:00 +[root@pcmk-1 ~]# + +
+ +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Intro.xml b/doc/Clusters_from_Scratch/en-US/Ch-Intro.xml new file mode 100644 index 0000000000..84454a092c --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-Intro.xml @@ -0,0 +1,253 @@ + + +%BOOK_ENTITIES; +]> + + Read-Me-First +
+ The Scope of this Document + + The purpose of this document is to definitively explain the concepts used to configure Pacemaker. To achieve this best, it will focus exclusively on the XML syntax used to configure the CIB. + + + For those that are allergic to XML, Pacemaker comes with a cluster shell and a Python based GUI exists, however these tools will not be covered at all in this document + + It is hoped however, that having understood the concepts explained here, that the functionality of these tools will also be more readily understood. + + , precisely because they hide the XML. + + + Additionally, this document is NOT a step-by-step how-to guide for configuring a specific clustering scenario. Although such guides exist, the purpose of this document is to provide an understanding of the building blocks that can be used to construct any type of Pacemaker cluster. + +
+ +
+ What Is Pacemaker? + + Pacemaker is a cluster resource manager. It achieves maximum availability for your cluster services (aka. resources) by detecting and recovering from node and resource-level failures by making use of the messaging and membership capabilities provided by your preferred cluster infrastructure (either OpenAIS or Heartbeat). + + + Pacemaker's key features include: + + + + + Detection and recovery of node and service-level failures + + + + + Storage agnostic, no requirement for shared storage + + + + + Resource agnostic, anything that can be scripted can be clustered + + + + + Supports STONITH for ensuring data integrity + + + + + Supports large and small clusters + + + + + Supports both quorate and resource driven clusters + + + + + Supports practically any redundancy configuration + + + + + Automatically replicated configuration that can be updated from any node + + + + + Ability to specify cluster-wide service ordering, colocation and anti-colocation + + + + + Support for advanced services type + + + + Clones: for services which need to be active on multiple nodes + + + + + Multi-state: for services with multiple modes (eg. master/slave, primary/secondary) + + + + + + + + Unified, scriptable, cluster shell + + + +
+ +
+ Types of Pacemaker Clusters + + Pacemaker makes no assumptions about your environment, this allows it to support practically any redundancy configuration including Active/Active, Active/Passive, N+1, N+M, N-to-1 and N-to-N. + + +
+ Active/Passive Redundancy + + + + + Two-node Active/Passive clusters using Pacemaker and DRBD are a cost-effective solution for many High Availability situations. + +
+ + +
+ N plus 1 Redundancy + + + + + By supporting many nodes, Pacemaker can dramatically reduce hardware costs by allowing several active/passive clusters to be combined and share a common backup node + +
+ + +
+ N to N Redundancy + + + + + When shared storage is available, every node can potentially be used for failover. Pacemaker can even run multiple copies of services to spread out the workload. + +
+ +
+ +
+ Pacemaker Architecture + + At the highest level, the cluster is made up of three pieces: + + + + + Core cluster infrastructure providing messaging and membership functionality (illustrated in red) + + + + + Non-cluster aware components (illustrated in blue). In a Pacemaker cluster, these pieces include not only the scripts that knows how to start, stop and monitor resources, but also a local daemon that masks the differences between the different standards these scripts implement. + + + + + A brain (illustrated in green) that processes and reacts to events from the cluster (nodes leaving or joining) and resources (eg. monitor failures) as well as configuration changes from the administrator. In response to all of these events, Pacemaker will compute the ideal state of the cluster and plot a path to achieve it. This may include moving resources, stopping nodes and even forcing them offline with remote power switches. + + + + +
+ Conceptual Stack Overview + + + + + Conceptual overview of the cluster stack + +
+ + + When combined with OpenAIS, Pacemaker also supports popular open source cluster filesystems + + Even though Pacemaker also supports Heartbeat, the filesystems need to use the stack for messaging and membership and OpenAIS seems to be what they're standardizing on. Technically it would be possible for them to support Heartbeat as well, however there seems little interest in this. + + Due to recent standardization within the cluster filesystem community, they make use of a common distributed lock manager which makes use of OpenAIS for its messaging capabilities and Pacemaker for its membership (which nodes are up/down) and fencing services. + + +
+ The Pacemaker Stack + + + + + The Pacemaker stack when running on OpenAIS + +
+ +
+ Internal Components + + Pacemaker itself is composed of four key components (illustrated below in the same color scheme as the previous diagram): + + + + + CIB (aka. Cluster Information Base) + + + + + CRMd (aka. Cluster Resource Management daemon) + + + + + PEngine (aka. PE or Policy Engine) + + + + + STONITHd + + + + +
+ Internal Components + + + + + Subsystems of a Pacemaker cluster running on OpenAIS + +
+ + + The CIB uses XML to represent both the cluster's configuration and current state of all resources in the cluster. The contents of the CIB are automatically kept in sync across the entire cluster and are used by the PEngine to compute the ideal state of the cluster and how it should be achieved. + + + This list of instructions is then fed to the DC (Designated Co-ordinator). Pacemaker centralizes all cluster decision making by electing one of the CRMd instances to act as a master. Should the elected CRMd process, or the node it is on, fail... a new one is quickly established. + + + The DC carries out the PEngine's instructions in the required order by passing them to either the LRMd (Local Resource Management daemon) or CRMd peers on other nodes via the cluster messaging infrastructure (which in turn passes them on to their LRMd process). + + + The peer nodes all report the results of their operations back to the DC and based on the expected and actual results, will either execute any actions that needed to wait for the previous one to complete, or abort processing and ask the PEngine to recalculate the ideal cluster state based on the unexpected results. + + + In some cases, it may be necessary to power off nodes in order to protect shared data or complete resource recovery. For this Pacemaker comes with STONITHd. STONITH is an acronym for Shoot-The-Other-Node-In-The-Head and is usually implemented with a remote power switch. In Pacemaker, STONITH devices are modeled as resources (and configured in the CIB) to enable them to be easily monitored for failure, however STONITHd takes care of understanding the STONITH topology such that its clients simply request a node be fenced and it does the rest. + +
+ +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Shared-Storage.xml b/doc/Clusters_from_Scratch/en-US/Ch-Shared-Storage.xml new file mode 100644 index 0000000000..cc15d5dbe9 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-Shared-Storage.xml @@ -0,0 +1,1038 @@ + + +%BOOK_ENTITIES; +]> + + Shared Storage with DRBD + + Even if you’re serving up static websites, having to manually synchronize the contents of that website to all the machines in the cluster is not ideal. For dynamic websites, such as a wiki, its not even an option. Not everyone care afford network-attached storage but somehow the data needs to be kept in sync. Enter DRBD which can be thought of as network based RAID-1. See http://www.drbd.org/ for more details. + + + +
+ Install Pre-requisites + + DRBD does not currently ship with Fedora 12 and since there is a kernel component, can be sensitive to system updates which may change the kernel’s APIs and ABIs. For this reason we’ll simply build our own DRBD packages - to be sure they are a perfect match for the machine. + + + First we need to install a few packages that DRBD needs: + + + +[root@pcmk-1 ~]# yum install -y flex gcc glibc-devel kernel-headers kernel-devel rpm-build +Setting up Install Process +Resolving Dependencies +--> Running transaction check +---> Package flex.x86_64 0:2.5.35-7.fc12 set to be updated +---> Package gcc.x86_64 0:4.4.2-7.fc12 set to be updated +--> Processing Dependency: libgomp = 4.4.2-7.fc12 for package: gcc-4.4.2-7.fc12.x86_64 +--> Processing Dependency: cpp = 4.4.2-7.fc12 for package: gcc-4.4.2-7.fc12.x86_64 +--> Processing Dependency: cloog-ppl >= 0.15 for package: gcc-4.4.2-7.fc12.x86_64 +--> Processing Dependency: libgomp.so.1()(64bit) for package: gcc-4.4.2-7.fc12.x86_64 +---> Package glibc-devel.x86_64 0:2.11-2 set to be updated +--> Processing Dependency: glibc-headers = 2.11-2 for package: glibc-devel-2.11-2.x86_64 +--> Processing Dependency: glibc-headers for package: glibc-devel-2.11-2.x86_64 +---> Package kernel-devel.x86_64 0:2.6.31.6-162.fc12 set to be installed +---> Package kernel-headers.x86_64 0:2.6.31.6-162.fc12 set to be updated +---> Package rpm-build.x86_64 0:4.7.1-6.fc12 set to be updated +--> Processing Dependency: patch >= 2.5 for package: rpm-build-4.7.1-6.fc12.x86_64 +--> Processing Dependency: elfutils >= 0.128 for package: rpm-build-4.7.1-6.fc12.x86_64 +--> Processing Dependency: pkgconfig for package: rpm-build-4.7.1-6.fc12.x86_64 +--> Processing Dependency: unzip for package: rpm-build-4.7.1-6.fc12.x86_64 +--> Running transaction check +---> Package cloog-ppl.x86_64 0:0.15.7-1.fc12 set to be updated +--> Processing Dependency: libppl.so.7()(64bit) for package: cloog-ppl-0.15.7-1.fc12.x86_64 +--> Processing Dependency: libgmpxx.so.4()(64bit) for package: cloog-ppl-0.15.7-1.fc12.x86_64 +--> Processing Dependency: libppl_c.so.2()(64bit) for package: cloog-ppl-0.15.7-1.fc12.x86_64 +--> Processing Dependency: libgmp.so.3()(64bit) for package: cloog-ppl-0.15.7-1.fc12.x86_64 +---> Package cpp.x86_64 0:4.4.2-7.fc12 set to be updated +--> Processing Dependency: libmpfr.so.1()(64bit) for package: cpp-4.4.2-7.fc12.x86_64 +---> Package elfutils.x86_64 0:0.143-1.fc12 set to be updated +--> Processing Dependency: elfutils-libs-x86_64 = 0.143-1.fc12 for package: elfutils-0.143-1.fc12.x86_64 +--> Processing Dependency: libdw.so.1(ELFUTILS_0.127)(64bit) for package: elfutils-0.143-1.fc12.x86_64 +--> Processing Dependency: libasm.so.1(ELFUTILS_1.0)(64bit) for package: elfutils-0.143-1.fc12.x86_64 +--> Processing Dependency: libdw.so.1(ELFUTILS_0.126)(64bit) for package: elfutils-0.143-1.fc12.x86_64 +--> Processing Dependency: libdw.so.1(ELFUTILS_0.138)(64bit) for package: elfutils-0.143-1.fc12.x86_64 +--> Processing Dependency: libdw.so.1(ELFUTILS_0.122)(64bit) for package: elfutils-0.143-1.fc12.x86_64 +--> Processing Dependency: libdw.so.1()(64bit) for package: elfutils-0.143-1.fc12.x86_64 +--> Processing Dependency: libasm.so.1()(64bit) for package: elfutils-0.143-1.fc12.x86_64 +---> Package glibc-headers.x86_64 0:2.11-2 set to be updated +---> Package libgomp.x86_64 0:4.4.2-7.fc12 set to be updated +---> Package patch.x86_64 0:2.6-1.fc12 set to be updated +---> Package pkgconfig.x86_64 1:0.23-9.fc12 set to be updated +---> Package unzip.x86_64 0:5.52-11.fc12 set to be updated +--> Running transaction check +---> Package elfutils-libs.x86_64 0:0.143-1.fc12 set to be updated +---> Package gmp.x86_64 0:4.3.1-5.fc12 set to be updated +---> Package mpfr.x86_64 0:2.4.1-3.fc12 set to be updated +---> Package ppl.x86_64 0:0.10.2-10.fc12 set to be updated +--> Finished Dependency Resolution + +Dependencies Resolved + +========================================================================================== + Package                 Arch            Version                     Repository       Size +========================================================================================== +Installing: + flex                   x86_64          2.5.35-7.fc12              fedora          274 k + gcc                    x86_64          4.4.2-7.fc12                fedora           10 M + glibc-devel             x86_64          2.11-2                      fedora          951 k + kernel-devel           x86_64          2.6.31.6-162.fc12          updates         6.0 M + kernel-headers         x86_64          2.6.31.6-162.fc12          updates         743 k + rpm-build               x86_64          4.7.1-6.fc12                fedora          112 k +Installing for dependencies: + cloog-ppl               x86_64          0.15.7-1.fc12               fedora           82 k + cpp                     x86_64          4.4.2-7.fc12               fedora          3.7 M + elfutils               x86_64          0.143-1.fc12               fedora          177 k + elfutils-libs           x86_64          0.143-1.fc12               fedora          162 k + glibc-headers           x86_64          2.11-2                     fedora          580 k + gmp                     x86_64          4.3.1-5.fc12               fedora          198 k + libgomp                 x86_64          4.4.2-7.fc12               fedora           90 k + mpfr                   x86_64          2.4.1-3.fc12               fedora          149 k + patch                   x86_64          2.6-1.fc12                 updates          79 k + pkgconfig               x86_64          1:0.23-9.fc12               fedora           68 k + ppl                     x86_64          0.10.2-10.fc12              fedora          1.1 M + unzip                   x86_64          5.52-11.fc12                fedora          125 k + +Transaction Summary +========================================================================================== +Install      18 Package(s) +Upgrade       0 Package(s) + +Total download size: 24 M +Downloading Packages: +(1/18): cloog-ppl-0.15.7-1.fc12.x86_64.rpm                             |  82 kB     00:00 +(2/18): cpp-4.4.2-7.fc12.x86_64.rpm                                    | 3.7 MB     00:02 +(3/18): elfutils-0.143-1.fc12.x86_64.rpm                               | 177 kB     00:00 +(4/18): elfutils-libs-0.143-1.fc12.x86_64.rpm                          | 162 kB     00:00 +(5/18): flex-2.5.35-7.fc12.x86_64.rpm                                  | 274 kB     00:00 +(6/18): gcc-4.4.2-7.fc12.x86_64.rpm                                    |  10 MB     00:06 +(7/18): glibc-devel-2.11-2.x86_64.rpm                                  | 951 kB     00:00 +(8/18): glibc-headers-2.11-2.x86_64.rpm                                | 580 kB     00:00 +(9/18): gmp-4.3.1-5.fc12.x86_64.rpm                                    | 198 kB     00:00 +(10/18): kernel-devel-2.6.31.6-162.fc12.x86_64.rpm                     | 6.0 MB     00:22 +(11/18): kernel-headers-2.6.31.6-162.fc12.x86_64.rpm                   | 743 kB     00:01 +(12/18): libgomp-4.4.2-7.fc12.x86_64.rpm                               |  90 kB     00:00 +(13/18): mpfr-2.4.1-3.fc12.x86_64.rpm                                  | 149 kB     00:00 +(14/18): patch-2.6-1.fc12.x86_64.rpm                                   |  79 kB     00:00 +(15/18): pkgconfig-0.23-9.fc12.x86_64.rpm                              |  68 kB     00:00 +(16/18): ppl-0.10.2-10.fc12.x86_64.rpm                                 | 1.1 MB     00:00 +(17/18): rpm-build-4.7.1-6.fc12.x86_64.rpm                             | 112 kB     00:00 +(18/18): unzip-5.52-11.fc12.x86_64.rpm                                 | 125 kB     00:00 +------------------------------------------------------------------------------------------ +Total                                                         662 kB/s |  24 MB     00:37 +Running rpm_check_debug +Running Transaction Test +Finished Transaction Test +Transaction Test Succeeded +Running Transaction +  Installing     : gmp-4.3.1-5.fc12.x86_64                                           1/18 +  Installing     : mpfr-2.4.1-3.fc12.x86_64                                          2/18 +  Installing     : cpp-4.4.2-7.fc12.x86_64                                           3/18 +  Installing     : ppl-0.10.2-10.fc12.x86_64                                         4/18 +  Installing     : cloog-ppl-0.15.7-1.fc12.x86_64                                    5/18 +  Installing     : 1:pkgconfig-0.23-9.fc12.x86_64                                    6/18 +  Installing     : libgomp-4.4.2-7.fc12.x86_64                                       7/18 +  Installing     : elfutils-libs-0.143-1.fc12.x86_64                                 8/18 +  Installing     : elfutils-0.143-1.fc12.x86_64                                      9/18 +  Installing     : patch-2.6-1.fc12.x86_64                                          10/18 +  Installing     : unzip-5.52-11.fc12.x86_64                                        11/18 +  Installing     : kernel-headers-2.6.31.6-162.fc12.x86_64                          12/18 +  Installing     : rpm-build-4.7.1-6.fc12.x86_64                                    13/18 +  Installing     : flex-2.5.35-7.fc12.x86_64                                        14/18 +  Installing     : glibc-headers-2.11-2.x86_64                                      15/18 +  Installing     : glibc-devel-2.11-2.x86_64                                        16/18 +  Installing     : gcc-4.4.2-7.fc12.x86_64                                          17/18 +  Installing     : kernel-devel-2.6.31.6-162.fc12.x86_64                            18/18 + +Installed: +  flex.x86_64 0:2.5.35-7.fc12                     gcc.x86_64 0:4.4.2-7.fc12 +  glibc-devel.x86_64 0:2.11-2                     kernel-devel.x86_64 0:2.6.31.6-162.fc12 +  kernel-headers.x86_64 0:2.6.31.6-162.fc12       rpm-build.x86_64 0:4.7.1-6.fc12 + +Dependency Installed: +  cloog-ppl.x86_64 0:0.15.7-1.fc12      cpp.x86_64 0:4.4.2-7.fc12     +  elfutils.x86_64 0:0.143-1.fc12        elfutils-libs.x86_64 0:0.143-1.fc12 +  glibc-headers.x86_64 0:2.11-2         gmp.x86_64 0:4.3.1-5.fc12 +  libgomp.x86_64 0:4.4.2-7.fc12         mpfr.x86_64 0:2.4.1-3.fc12     +  patch.x86_64 0:2.6-1.fc12             pkgconfig.x86_64 1:0.23-9.fc12       +  ppl.x86_64 0:0.10.2-10.fc12           unzip.x86_64 0:5.52-11.fc12 + +Complete! +[root@pcmk-1 ~]# + +
+ +
+ Build DRBD Packages + + Once the development packages are installed, we can begin building DRBD. + + At the time of writing, the latest version was 8.3.6. If a later version is now available it would be advisable to try that first. + + + + + +[root@pcmk-1 ~]# wget http://oss.linbit.com/drbd/8.3/drbd-8.3.6.tar.gz +--2009-12-08 11:04:36--  http://oss.linbit.com/drbd/8.3/drbd-8.3.6.tar.gz +Resolving oss.linbit.com... 212.69.161.111 +Connecting to oss.linbit.com|212.69.161.111|:80... connected. +HTTP request sent, awaiting response... 200 OK +Length: 457469 (447K) [application/x-gzip] +Saving to: “drbd-8.3.6.tar.gz” + +100%[==============================================================>] 457,469     1.12M/s   in 0.4s     + +2009-12-08 11:04:37 (1.12 MB/s) - “drbd-8.3.6.tar.gz” saved [457469/457469] + +[root@pcmk-1 ~]# tar zxf drbd-8.3.6.tar.gz +[root@pcmk-1 ~]# cd drbd-8.3.6 +[root@pcmk-1 drbd-8.3.6]# make rpm +make: *** No rule to make target `rpm'.  Stop. +[root@pcmk-1 drbd-8.3.6]# ./configure --with-km --enable-spec +checking for gcc... gcc +checking for C compiler default output file name... a.out +checking whether the C compiler works... yes +checking whether we are cross compiling... no +checking for suffix of executables... +checking for suffix of object files... o +checking whether we are using the GNU C compiler... yes +checking whether gcc accepts -g... yes +checking for gcc option to accept ISO C89... none needed +checking whether ln -s works... yes +checking for sed... /bin/sed +checking for grep... /bin/grep +checking for flex... /usr/bin/flex +checking for rpmbuild... /usr/bin/rpmbuild +checking for xsltproc... /usr/bin/xsltproc +checking for tar... /bin/tar +checking for git... no +checking for dpkg-buildpackage... no +checking for udevadm... /sbin/udevadm +checking for udevinfo... /usr/bin/udevinfo +configure: WARNING: No dpkg-buildpackage found, building Debian packages is disabled. +configure: WARNING: Cannot update buildtag without git. You may safely ignore this warning when building from a tarball. +checking for /Makefile... no +configure: WARNING: Unable to find a kernel Makefile in . You will have to set KDIR correctly when invoking make. +checking for /etc/gentoo-release... no +checking for /etc/redhat-release... yes +checking for /etc/slackware-version... no +checking for /etc/debian_version... no +checking for /etc/SuSErelease... no +configure: configured for Red Hat (includes Fedora, RHEL, CentOS). +configure: creating ./config.status +config.status: creating drbd.spec +config.status: creating drbd-km.spec + + + The following build log is quite long and is only included for reference in case it does not work on your machine. Most people can skip to the end. + + + +[root@pcmk-1 drbd-8.3.6]# rpmbuild -ba --define "_sourcedir `pwd`/.." drbd-km.spec +Executing(%prep): /bin/sh -e /var/tmp/rpm-tmp.Q7iVhB ++ umask 022 ++ cd /root/rpmbuild/BUILD ++ cd /root/rpmbuild/BUILD ++ rm -rf drbd-8.3.6 ++ /usr/bin/gzip -dc /root/drbd-8.3.6.tar.gz ++ /bin/tar -xf - ++ STATUS=0 ++ '[' 0 -ne 0 ']' ++ cd drbd-8.3.6 ++ /bin/chmod -Rf a+rX,u+w,g-w,o-w . ++ test -d /lib/modules/2.6.31.6-162.fc12.x86_64/build/. +++ KDIR=/lib/modules/2.6.31.6-162.fc12.x86_64/build +++ scripts/get_uts_release.sh ++ test 2.6.31.6-162.fc12.x86_64 = 2.6.31.6-162.fc12.x86_64 ++ exit 0 +Executing(%build): /bin/sh -e /var/tmp/rpm-tmp.08bAH0 ++ umask 022 ++ cd /root/rpmbuild/BUILD ++ cd drbd-8.3.6 ++ CFLAGS='-O2 -g' ++ export CFLAGS ++ CXXFLAGS='-O2 -g' ++ export CXXFLAGS ++ FFLAGS='-O2 -g' ++ export FFLAGS ++ ./configure --host=x86_64-unknown-linux-gnu --build=x86_64-unknown-linux-gnu \ + --target=x86_64-redhat-linux --program-prefix= --prefix=/usr --exec-prefix=/usr \ + --bindir=/usr/bin --sbindir=/usr/sbin --sysconfdir=/etc --datadir=/usr/share \ + --includedir=/usr/include --libdir=/usr/lib64 --libexecdir=/usr/libexec \ + --localstatedir=/var --sharedstatedir=/var/lib --mandir=/usr/share/man \ + --infodir=/usr/share/info --without-utils --with-km --without-udev --without-xen \ + --without-pacemaker --without-heartbeat --without-rgmanager --without-bashcompletion +checking for x86_64-unknown-linux-gnu-gcc... no +checking for gcc... gcc +checking for C compiler default output file name... a.out +checking whether the C compiler works... yes +checking whether we are cross compiling... no +checking for suffix of executables... +checking for suffix of object files... o +checking whether we are using the GNU C compiler... yes +checking whether gcc accepts -g... yes +checking for gcc option to accept ISO C89... none needed +checking whether ln -s works... yes +checking for sed... /bin/sed +checking for grep... /bin/grep +checking for flex... /usr/bin/flex +checking for rpmbuild... /usr/bin/rpmbuild +checking for xsltproc... /usr/bin/xsltproc +checking for tar... /bin/tar +checking for git... no +checking for dpkg-buildpackage... no +checking for udevadm... /sbin/udevadm +checking for udevinfo... /usr/bin/udevinfo +configure: WARNING: No dpkg-buildpackage found, building Debian packages is disabled. +configure: WARNING: Cannot update buildtag without git. You may safely ignore this warning when building from a tarball. +checking for /Makefile... no +configure: WARNING: Unable to find a kernel Makefile in . You will have to set KDIR correctly when invoking make. +checking for /etc/gentoo-release... no +checking for /etc/redhat-release... yes +checking for /etc/slackware-version... no +checking for /etc/debian_version... no +checking for /etc/SuSErelease... no +configure: configured for Red Hat (includes Fedora, RHEL, CentOS). +configure: creating ./config.status +config.status: creating Makefile +config.status: creating user/Makefile +config.status: creating scripts/Makefile +config.status: creating documentation/Makefile ++ echo kernelversion=2.6.31.6-162.fc12.x86_64 +kernelversion=2.6.31.6-162.fc12.x86_64 ++ echo 'kversion=%{kversion}' +kversion=%{kversion} ++ echo krelver=2.6.31.6_162.fc12.x86_64 +krelver=2.6.31.6_162.fc12.x86_64 ++ make module KDIR=/lib/modules/2.6.31.6-162.fc12.x86_64/build +make[1]: Entering directory `/root/rpmbuild/BUILD/drbd-8.3.6/drbd' + +    Calling toplevel makefile of kernel source tree, which I believe is in +    KDIR=/lib/modules/2.6.31.6-162.fc12.x86_64/build + +test -f ../scripts/adjust_drbd_config_h.sh && \ +        KDIR=/lib/modules/2.6.31.6-162.fc12.x86_64/build O= /bin/bash ../scripts/adjust_drbd_config_h.sh +/lib/modules/2.6.31.6-162.fc12.x86_64/build ~/rpmbuild/BUILD/drbd-8.3.6/drbd +~/rpmbuild/BUILD/drbd-8.3.6/drbd + +  Using unmodified drbd_config.h + + + +make -C /lib/modules/2.6.31.6-162.fc12.x86_64/build   SUBDIRS=/root/rpmbuild/BUILD/drbd-8.3.6/drbd  modules +make[2]: Entering directory `/usr/src/kernels/2.6.31.6-162.fc12.x86_64' +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_buildtag.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_bitmap.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_proc.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_worker.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_receiver.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_req.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_actlog.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/lru_cache.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_main.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_strings.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_nl.o +  CC [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_tracing.o +  LD [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd.o +  LD [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_trace.o +  Building modules, stage 2. +  MODPOST 2 modules +  CC      /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd.mod.o +  LD [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd.ko +  CC      /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_trace.mod.o +  LD [M]  /root/rpmbuild/BUILD/drbd-8.3.6/drbd/drbd_trace.ko +make[2]: Leaving directory `/usr/src/kernels/2.6.31.6-162.fc12.x86_64' +mv .drbd_kernelrelease.new .drbd_kernelrelease +Memorizing module configuration ... done. +make[1]: Leaving directory `/root/rpmbuild/BUILD/drbd-8.3.6/drbd' + +        Module build was successful. ++ exit 0 +Executing(%install): /bin/sh -e /var/tmp/rpm-tmp.sAoLRi ++ umask 022 ++ cd /root/rpmbuild/BUILD ++ cd drbd-8.3.6 ++ rm -rf /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64 ++ make install DESTDIR=/root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64 +make[1]: Entering directory `/root/rpmbuild/BUILD/drbd-8.3.6/user' +make[1]: Nothing to be done for `install'. +make[1]: Leaving directory `/root/rpmbuild/BUILD/drbd-8.3.6/user' +make[1]: Entering directory `/root/rpmbuild/BUILD/drbd-8.3.6/scripts' +make[1]: Nothing to be done for `install'. +make[1]: Leaving directory `/root/rpmbuild/BUILD/drbd-8.3.6/scripts' +make[1]: Entering directory `/root/rpmbuild/BUILD/drbd-8.3.6/documentation' +set -e; for f in  ; do \ +                s=${f##*.}; \ +                install -v -D -m 644 $f /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64/usr/share/man/man$s/$f ; \ +        done +make[1]: Leaving directory `/root/rpmbuild/BUILD/drbd-8.3.6/documentation' +make -C drbd install +make[1]: Entering directory `/root/rpmbuild/BUILD/drbd-8.3.6/drbd' +install -d /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64/lib/modules/2.6.31.6-162.fc12.x86_64/kernel/drivers/block +install -m 644 drbd.ko /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64/lib/modules/2.6.31.6-162.fc12.x86_64/kernel/drivers/block +make[1]: Leaving directory `/root/rpmbuild/BUILD/drbd-8.3.6/drbd' ++ cd drbd ++ mv .kernel.config.gz k-config-2.6.31.6-162.fc12.x86_64.gz ++ /usr/lib/rpm/brp-compress ++ /usr/lib/rpm/brp-strip ++ /usr/lib/rpm/brp-strip-static-archive ++ /usr/lib/rpm/brp-strip-comment-note +Processing files: drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64 +Executing(%doc): /bin/sh -e /var/tmp/rpm-tmp.ixFNFB ++ umask 022 ++ cd /root/rpmbuild/BUILD ++ cd drbd-8.3.6 ++ DOCDIR=/root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64/usr/share/doc/drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6 ++ export DOCDIR ++ rm -rf /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64/usr/share/doc/drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6 ++ /bin/mkdir -p /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64/usr/share/doc/drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6 ++ cp -pr COPYING /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64/usr/share/doc/drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6 ++ cp -pr ChangeLog /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64/usr/share/doc/drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6 ++ cp -pr drbd/k-config-2.6.31.6-162.fc12.x86_64.gz /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64/usr/share/doc/drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6 ++ exit 0 +Requires(interp): /bin/sh /bin/sh /bin/sh +Requires(rpmlib): rpmlib(CompressedFileNames) <= 3.0.4-1 rpmlib(PayloadFilesHavePrefix) <= 4.0-1 +Requires(post): /bin/sh +Requires(preun): /bin/sh +Requires(postun): /bin/sh +Conflicts: drbd-kmod <= 8.3.6_3 +Checking for unpackaged file(s): /usr/lib/rpm/check-files /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64 +Wrote: /root/rpmbuild/SRPMS/drbd-km-8.3.6-12.fc12.src.rpm +Wrote: /root/rpmbuild/RPMS/x86_64/drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64.rpm +Executing(%clean): /bin/sh -e /var/tmp/rpm-tmp.MB9N8D ++ umask 022 ++ cd /root/rpmbuild/BUILD ++ cd drbd-8.3.6 ++ rm -rf /root/rpmbuild/BUILDROOT/drbd-km-8.3.6-12.fc12.x86_64 ++ exit 0 + + + + + +
+ Install the DRBD Packages + + The completed build process will store the result in the ~/RPMS/x86_64/ directory and all that is required now is to install the ones we need with YUM. + + + yum install -y drbd-utils drbd-pacemaker + + + Now install the kernel module we built + + + +cd /root/rpmbuild/RPMS/`uname -m` +[root@pcmk-1 x86_64]# yum localinstall -y --nogpgcheck drbd-utils-8.3.6-*.rpm drbd-pacemaker-8.3.6-*.rpm drbd-km-*-8.3.6-*.rpm +Setting up Local Package Process +Examining drbd-utils-8.3.6-1.fc12.x86_64.rpm: drbd-utils-8.3.6-1.fc12.x86_64 +Marking drbd-utils-8.3.6-1.fc12.x86_64.rpm to be installed +custom                                                                           | 1.2 kB     00:00 +Examining drbd-pacemaker-8.3.6-1.fc12.x86_64.rpm: drbd-pacemaker-8.3.6-1.fc12.x86_64 +Marking drbd-pacemaker-8.3.6-1.fc12.x86_64.rpm to be installed +Examining drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64.rpm: drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64 +Marking drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64.rpm to be installed +Resolving Dependencies +--> Running transaction check +---> Package drbd-km-2.6.31.6_162.fc12.x86_64.x86_64 0:8.3.6-12.fc12 set to be updated +---> Package drbd-pacemaker.x86_64 0:8.3.6-1.fc12 set to be updated +---> Package drbd-utils.x86_64 0:8.3.6-1.fc12 set to be updated +--> Finished Dependency Resolution + +Dependencies Resolved + +========================================================================================== + Package         Arch    Version          Repository                                 Size +========================================================================================== +Installing: + drbd-km-2.6.31.6_162.fc12.x86_64 +                x86_64 8.3.6-12.fc12  /drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64 +                                                                                     4.2 M + drbd-pacemaker  x86_64  8.3.6-1.fc12     /drbd-pacemaker-8.3.6-1.fc12.x86_64         40 k + drbd-utils      x86_64  8.3.6-1.fc12     /drbd-utils-8.3.6-1.fc12.x86_64            580 k + +Transaction Summary +========================================================================================== +Install       3 Package(s) +Upgrade       0 Package(s) + +Total size: 4.8 M +Downloading Packages: +Running rpm_check_debug +Running Transaction Test +Finished Transaction Test +Transaction Test Succeeded +Running Transaction +  Installing     : drbd-utils-8.3.6-1.fc12.x86_64                                     1/3 +  Installing     : drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64              2/3 +  Installing     : drbd-pacemaker-8.3.6-1.fc12.x86_64                                 3/3 + +Installed: +  drbd-km-2.6.31.6_162.fc12.x86_64.x86_64 0:8.3.6-12.fc12     +  drbd-pacemaker.x86_64 0:8.3.6-1.fc12     +  drbd-utils.x86_64 0:8.3.6-1.fc12                             + +Complete! +[root@pcmk-1 x86_64]# + + + By default DRBD configures itself to start when the machine is powered on, however since we want the cluster to manage it, we will need to disable this behavior: + + + chkconfig --del drbd + + + + + We could rebuild the drbd package on pcmk-2, however if they share the same architecture (x86_64 in this case) we can reuse the ones we built for pcmk-1. Assuming this is the case for you, copy them to pcmk-2 and install: + + + +[root@pcmk-1 ~]# cd /root/rpmbuild/RPMS/`uname -m` +[root@pcmk-1 x86_64]# scp drbd-*.rpm pcmk-2: +drbd-8.3.6-1.fc12.x86_64.rpm                               100%   21KB  20.7KB/s   00:00 +drbd-bash-completion-8.3.6-1.fc12.x86_64.rpm               100% 5260     5.1KB/s   00:00 +drbd-heartbeat-8.3.6-1.fc12.x86_64.rpm                     100% 6716     6.6KB/s   00:00 +drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64.rpm  100% 1271KB   1.2MB/s   00:00 +drbd-pacemaker-8.3.6-1.fc12.x86_64.rpm                     100%   18KB  17.7KB/s   00:00 +drbd-udev-8.3.6-1.fc12.x86_64.rpm                          100% 4103     4.0KB/s   00:00 +drbd-utils-8.3.6-1.fc12.x86_64.rpm                         100%  265KB 264.8KB/s   00:00 +drbd-xen-8.3.6-1.fc12.x86_64.rpm                           100% 6690     6.5KB/s   00:00 +[root@pcmk-1 x86_64]# ssh pcmk-2 -- yum localinstall -y --nogpgcheck drbd-utils-8.3.6-*.rpm drbd-pacemaker-8.3.6-*.rpm drbd-km-*-8.3.6-*.rpm +Setting up Local Package Process +Examining drbd-utils-8.3.6-1.fc12.x86_64.rpm: drbd-utils-8.3.6-1.fc12.x86_64 +Marking drbd-utils-8.3.6-1.fc12.x86_64.rpm to be installed +Examining drbd-pacemaker-8.3.6-1.fc12.x86_64.rpm: drbd-pacemaker-8.3.6-1.fc12.x86_64 +Marking drbd-pacemaker-8.3.6-1.fc12.x86_64.rpm to be installed +Examining drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64.rpm: drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64 +Marking drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64.rpm to be installed +Resolving Dependencies +--> Running transaction check +---> Package drbd-km-2.6.31.6_162.fc12.x86_64.x86_64 0:8.3.6-12.fc12 set to be updated +---> Package drbd-pacemaker.x86_64 0:8.3.6-1.fc12 set to be updated +---> Package drbd-utils.x86_64 0:8.3.6-1.fc12 set to be updated +--> Finished Dependency Resolution + +Dependencies Resolved + +================================================================================ + Package        Arch   Version        Repository                           Size +================================================================================ +Installing: + drbd-km-2.6.31.6_162.fc12.x86_64 +                x86_64 8.3.6-12.fc12  /drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64 +                                                                          4.2 M + drbd-pacemaker x86_64 8.3.6-1.fc12   /drbd-pacemaker-8.3.6-1.fc12.x86_64  40 k + drbd-utils     x86_64 8.3.6-1.fc12   /drbd-utils-8.3.6-1.fc12.x86_64     580 k + +Transaction Summary +================================================================================ +Install       3 Package(s) +Upgrade       0 Package(s) + +Total size: 4.8 M +Downloading Packages: +Running rpm_check_debug +Running Transaction Test +Finished Transaction Test +Transaction Test Succeeded +Running Transaction +  Installing     : drbd-utils-8.3.6-1.fc12.x86_64                           1/3 +  Installing     : drbd-km-2.6.31.6_162.fc12.x86_64-8.3.6-12.fc12.x86_64    2/3 +  Installing     : drbd-pacemaker-8.3.6-1.fc12.x86_64                       3/3 + +Installed: +  drbd-km-2.6.31.6_162.fc12.x86_64.x86_64 0:8.3.6-12.fc12                       +  drbd-pacemaker.x86_64 0:8.3.6-1.fc12                                           +  drbd-utils.x86_64 0:8.3.6-1.fc12                                               + +Complete! +[root@pcmk-1 x86_64]# ssh pcmk-2 -- chkconfig --del drbd +[root@pcmk-1 x86_64]# + +
+ +
+ +
+ Configure DRBD + + Before we configure DRBD, we need to set aside some disk for it to use. + +
+ Create A Partition for DRBD + + If you have more than 1Gb free, feel free to use it. For this guide however, 1Gb is plenty of space for a single html file and sufficient for later holding the GFS2 metadata. + + + +[root@pcmk-1 drbd-8.3.6]# lvcreate -n drbd-demo -L 1G VolGroup +  Logical volume "drbd-demo" created +[root@pcmk-1 drbd-8.3.6]# lvs +  LV        VG       Attr   LSize   Origin Snap%  Move Log Copy%  Convert +  drbd-demo VolGroup -wi-a- 1.00G                                       +  lv_root   VolGroup -wi-ao   7.30G                                       +  lv_swap   VolGroup -wi-ao 500.00M + + + Repeat this on the second node, be sure to use the same size partition. + + + +[root@pcmk-2 ~]# lvs +  LV      VG       Attr   LSize   Origin Snap%  Move Log Copy%  Convert +  lv_root VolGroup -wi-ao   7.30G                                       +  lv_swap VolGroup -wi-ao 500.00M                                       +[root@pcmk-2 ~]# lvcreate -n drbd-demo -L 1G VolGroup +  Logical volume "drbd-demo" created +[root@pcmk-2 ~]# lvs +  LV        VG       Attr   LSize   Origin Snap%  Move Log Copy%  Convert +  drbd-demo VolGroup -wi-a- 1.00G                                       +  lv_root   VolGroup -wi-ao   7.30G                                       +  lv_swap   VolGroup -wi-ao 500.00M + +
+ +
+ Write the DRBD Config + + There is no series of commands for build a DRBD configuration, so simply copy the configuration below to /etc/drbd.conf + + + Detailed information on the directives used in this configuration (and other alternatives) is available from http://www.drbd.org/users-guide/ch-configure.html + + + + Be sure to use the names and addresses of your nodes if they differ from the ones used in this guide. + + + + +global { +  usage-count yes; +} +common { +  protocol C; +} +resource wwwdata { +  meta-disk internal; +  device    /dev/drbd1; +  syncer { +    verify-alg sha1; +  } +  net { +    allow-two-primaries; +  } +  on pcmk-1 { +    disk      /dev/mapper/VolGroup-drbd--demo; +    address   192.168.122.101:7789; +  } +  on +pcmk-2 { +    disk      /dev/mapper/VolGroup-drbd--demo; +    address   192.168.122.102:7789; +  } +} + + + + TODO: Explain the reason for the allow-two-primaries option + + +
+ +
+ Initialize and Load DRBD + + With the configuration in place, we can now perform the DRBD initialization + + + +[root@pcmk-1 drbd-8.3.6]# drbdadm create-md wwwdata +md_offset 12578816 +al_offset 12546048 +bm_offset 12541952 + +Found some data + ==> This might destroy existing data! <== + +Do you want to proceed? +[need to type 'yes' to confirm] yes + +Writing meta data... +initializing activity log +NOT initialized bitmap +New drbd meta data block successfully created. +success + + + Now load the DRBD kernel module and confirm that everything is sane + + + +[root@pcmk-1 drbd-8.3.6]# modprobe drbd +[root@pcmk-1 drbd-8.3.6]# drbdadm up wwwdata +[root@pcmk-1 drbd-8.3.6]# cat /proc/drbd +version: 8.3.6 (api:88/proto:86-90) +GIT-hash: f3606c47cc6fcf6b3f086e425cb34af8b7a81bbf build by root@pcmk-1, 2009-12-08 11:22:57 + + 1: cs:WFConnection ro:Secondary/Unknown ds:Inconsistent/DUnknown C r---- +    ns:0 nr:0 dw:0 dr:0 al:0 bm:0 lo:0 pe:0 ua:0 ap:0 ep:1 wo:b oos:12248 +[root@pcmk-1 drbd-8.3.6]# + +Repeat on the second node +drbdadm --force create-md wwwdata +modprobe drbd +drbdadm up wwwdata +cat /proc/drbd +[root@pcmk-2 ~]# drbdadm --force create-md wwwdata +Writing meta data... +initializing activity log +NOT initialized bitmap +New drbd meta data block successfully created. +success +[root@pcmk-2 ~]# modprobe drbd +WARNING: Deprecated config file /etc/modprobe.conf, all config files belong into /etc/modprobe.d/. +[root@pcmk-2 ~]# drbdadm up wwwdata +[root@pcmk-2 ~]# cat /proc/drbd +version: 8.3.6 (api:88/proto:86-90) +GIT-hash: f3606c47cc6fcf6b3f086e425cb34af8b7a81bbf build by root@pcmk-1, 2009-12-08 11:22:57 + + 1: cs:Connected ro:Secondary/Secondary ds:Inconsistent/Inconsistent C r---- +    ns:0 nr:0 dw:0 dr:0 al:0 bm:0 lo:0 pe:0 ua:0 ap:0 ep:1 wo:b oos:12248 + + + Now we need to tell DRBD which set of data to use. Since both sides contain garbage, we can run the following on pcmk-1: + + + +[root@pcmk-1 ~]# drbdadm -- --overwrite-data-of-peer primary wwwdata +[root@pcmk-1 ~]# cat /proc/drbd +version: 8.3.6 (api:88/proto:86-90) +GIT-hash: f3606c47cc6fcf6b3f086e425cb34af8b7a81bbf build by root@pcmk-1, 2009-12-08 11:22:57 + 1: cs:SyncSource ro:Primary/Secondary ds:UpToDate/Inconsistent C r---- +    ns:2184 nr:0 dw:0 dr:2472 al:0 bm:0 lo:0 pe:0 ua:0 ap:0 ep:1 wo:b oos:10064 +        [=====>..............] sync'ed: 33.4% (10064/12248)K +        finish: 0:00:37 speed: 240 (240) K/sec +[root@pcmk-1 ~]# cat /proc/drbd +version: 8.3.6 (api:88/proto:86-90) +GIT-hash: f3606c47cc6fcf6b3f086e425cb34af8b7a81bbf build by root@pcmk-1, 2009-12-08 11:22:57 + 1: cs:Connected ro:Primary/Secondary ds:UpToDate/UpToDate C r---- +    ns:12248 nr:0 dw:0 dr:12536 al:0 bm:1 lo:0 pe:0 ua:0 ap:0 ep:1 wo:b oos:0 + + + pcmk-1 is now in the Primary state which allows it to be written to. Which means its a good point at which to create a filesystem and populate it with some data to serve up via our WebSite resource. + +
+ +
+ Populate DRBD with Data + + +[root@pcmk-1 ~]# mkfs.ext4 /dev/drbd1 +mke2fs 1.41.4 (27-Jan-2009) +Filesystem label= +OS type: Linux +Block size=1024 (log=0) +Fragment size=1024 (log=0) +3072 inodes, 12248 blocks +612 blocks (5.00%) reserved for the super user +First data block=1 +Maximum filesystem blocks=12582912 +2 block groups +8192 blocks per group, 8192 fragments per group +1536 inodes per group +Superblock backups stored on blocks: +        8193 + +Writing inode tables: done                             +Creating journal (1024 blocks): done +Writing superblocks and filesystem accounting information: done + +This filesystem will be automatically checked every 26 mounts or +180 days, whichever comes first.  Use tune2fs -c or -i to override. + +Now mount the newly created filesystem so we can create our index file +mount /dev/drbd1 /mnt/ +cat <<-END >/mnt/index.html +<html> +<body>My Test Site - drbd</body> +</html> +END +umount /dev/drbd1 +[root@pcmk-1 ~]# mount /dev/drbd1 /mnt/ +[root@pcmk-1 ~]# cat <<-END >/mnt/index.html +> <html> +> <body>My Test Site - drbd</body> +> </html> +> END +[root@pcmk-1 ~]# umount /dev/drbd1 + + + And finally, confirm the data is in sync between the two nodes + + + +[root@pcmk-1 ~]# drbdadm verify wwwdata +[root@pcmk-1 ~]# echo $? +0 + +
+ +
+ +
+ Configure the Cluster for DRBD + + One handy feature of the crm shell is that you can use it in interactive mode to make several changes atomically. + + + First we launch the shell. The prompt will change to indicate you’re in interactive mode. + + + +[root@pcmk-1 ~]# crm +cib crm(live)# + + + Next we must create a working copy or the current configuration. This is where all our changes will go. The cluster will not see any of them until we say its ok. Notice again how the prompt changes, this time to indicate that we’re no longer looking at the live cluster. + + + +cib new drbd +cib crm(live)# cib new drbd +INFO: drbd shadow CIB created +crm(drbd)# + + + Now we can create our DRBD clone and display the revised configuration. + + + +configure primitive wwwdrbd ocf:linbit:drbd params drbd_resource=wwwdata op monitor interval=60s +configure ms WebData wwwdrbd meta master-max=1 master-node-max=1 \ +        clone-max=2 clone-node-max=1 notify=true +configure show +crm(drbd)# configure primitive ocf:linbit:drbd WebData params drbd_resource=wwwdata op monitor interval=60s +crm(drbd)# configure ms WebDataClone WebData meta master-max=1 master-node-max=1 \ +        clone-max=2 clone-node-max=1 notify=true +crm(drbd)# configure show +node pcmk-1 +node pcmk-2 +primitive WebData ocf:linbit:drbd \ + params drbd_resource="wwwdata" \ + op monitor interval="60s" +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +ms WebDataClone WebData \ + meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" +location prefer-pcmk-1 WebSite 50: pcmk-1 +colocation website-with-ip inf: WebSite ClusterIP +order apache-after-ip inf: ClusterIP WebSite +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” + + + Once we’re happy with the changes, we can tell the cluster to start using them and use crm_mon to check everything is functioning. + + + +crm(drbd)# cib commit drbd +INFO: commited 'drbd' shadow CIB to the cluster +crm(drbd)# quit +bye +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Tue Sep  1 09:37:13 2009 +Stack: openais +Current DC: pcmk-1 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +3 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-1 +WebSite (ocf::heartbeat:apache):        Started pcmk-1 +Master/Slave Set: WebDataClone + Masters: [ pcmk-2 ] + Slaves: [ pcmk-1 ] + + + + Include details on adding a second DRBD resource + + + + + + Now that DRBD is functioning we can configure a Filesystem resource to use it. In addition to the filesystem’s definition, we also need to tell the cluster where it can be located (only on the DRBD Primary) and when it is allowed to start (after the Primary was promoted). + + + Once again we’ll use the shell’s interactive mode + + + +[root@pcmk-1 ~]# crm +crm(live)# cib new fs +INFO: fs shadow CIB created +crm(fs)# configure primitive WebFS ocf:heartbeat:Filesystem params device="/dev/mapper/VolGroup-drbd--demo" directory="/var/www/html" fstype="ext4" +crm(fs)# configure colocation fs_on_drbd inf: WebFS WebDataClone:Master +crm(fs)# configure order WebFS-after-WebData inf: WebDataClone:promote WebFS:start + + + We also need to tell the cluster that Apache needs to run on the same machine as the filesystem and that it must be active before Apache can start. + + + +crm(fs)# configure colocation WebSite-with-WebFS inf: WebSite WebFS +crm(fs)# configure order WebSite-after-WebFS inf: WebFS WebSite +[root@pcmk-1 ~]# crm configure show +node pcmk-1 +node pcmk-2 +primitive WebData ocf:linbit:drbd \ +        params drbd_resource="wwwdata" \ +        op monitor interval="60s" +primitive WebFS ocf:heartbeat:Filesystem \ +        params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype="ext4" +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip="192.168.122.101" cidr_netmask="32" \ +        op monitor interval="30s" +ms WebDataClone WebData \ +        meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" +location prefer-pcmk-1 WebSite 50: pcmk-1 +colocation WebSite-with-WebFS inf: WebSite WebFS +colocation fs_on_drbd inf: WebFS WebDataClone:Master +colocation website-with-ip inf: WebSite ClusterIP +order WebFS-after-WebData inf: WebDataClone:promote WebFS:start +order WebSite-after-WebFS inf: WebFS WebSite +order apache-after-ip inf: ClusterIP WebSite +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled="false" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” + + + After reviewing the new configuration, we again upload it and watch the cluster put it into effect. + + + +crm(fs)# cib commit fs +INFO: commited 'fs' shadow CIB to the cluster +crm(fs)# quit +bye +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Tue Sep  1 10:08:44 2009 +Stack: openais +Current DC: pcmk-1 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +4 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-1 +WebSite (ocf::heartbeat:apache): Started pcmk-1 +Master/Slave Set: WebDataClone +        Masters: [ pcmk-1 ] +        Slaves: [ pcmk-2 ] +WebFS (ocf::heartbeat:Filesystem): Started pcmk-1 + +
+ Testing Migration + + We could shut down the active node again, but another way to safely simulate recovery is to put the node into what is called “standby mode”. Nodes in this state tell the cluster that they are not allowed to run resources. Any resources found active there will be moved elsewhere. This feature can be particularly useful when updating the resources’ packages. + + + Put the local node into standby mode and observe the cluster move all the resources to the other node. Note also that the node’s status will change to indicate that it can no longer host resources. + + + +[root@pcmk-1 ~]# crm node standby +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Tue Sep  1 10:09:57 2009 +Stack: openais +Current DC: pcmk-1 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +4 Resources configured. +============ + +Node pcmk-1: standby +Online: [ pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 +WebSite (ocf::heartbeat:apache):        Started pcmk-2 +Master/Slave Set: WebDataClone +        Masters: [ pcmk-2 ] +        Stopped: [ WebData:1 ] +WebFS   (ocf::heartbeat:Filesystem):    Started pcmk-2 + + + Once we’ve done everything we needed to on pcmk-1 (in this case nothing, we just wanted to see the resources move), we can allow the node to be a full cluster member again. + + + +[root@pcmk-1 ~]# crm node online +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Tue Sep  1 10:13:25 2009 +Stack: openais +Current DC: pcmk-1 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +4 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +ClusterIP        (ocf::heartbeat:IPaddr):        Started pcmk-2 +WebSite (ocf::heartbeat:apache):        Started pcmk-2 +Master/Slave Set: WebDataClone +        Masters: [ pcmk-2 ] +        Slaves: [ pcmk-1 ] +WebFS   (ocf::heartbeat:Filesystem):    Started pcmk-2 + + + Notice that our resource stickiness settings prevent the services from migrating back to pcmk-1. + + + Conversion to Active/Active + + + The primary requirement for an Active/Active cluster is that the data required for your services are available, simultaneously, on both machines. Pacemaker makes no requirement on how this is achieved, you could use a SAN if you had one available, however since DRBD supports multiple Primaries, we can also use that. + + + The only hitch is that we need to use a cluster-aware filesystem (and the one we used earlier with DRBD, ext4, is not one of those). Both OCFS2 and GFS2 are supported, however here we will use GFS2 which comes with Fedora 12. + +
+ +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Stonith.xml b/doc/Clusters_from_Scratch/en-US/Ch-Stonith.xml new file mode 100644 index 0000000000..4cade893d7 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-Stonith.xml @@ -0,0 +1,161 @@ + + +%BOOK_ENTITIES; +]> + + Configure STONITH +
+ Why You Need STONITH + + STONITH is an acronym for Shoot-The-Other-Node-In-The-Head and it protects your data from being corrupted by rouge nodes or concurrent access. + + + Just because a node is unresponsive, this doesn’t mean it isn’t accessing your data. The only way to be 100% sure that your data is safe, is to use STONITH so we can be certain that the node is truly offline, before allowing the data to be accessed from another node. + + + STONITH also has a role to play in the event that a clustered service cannot be stopped. In this case, the cluster uses STONITH to force the whole node offline, thereby making it safe to start the service elsewhere. + +
+ +
+ What STONITH Device Should You Use + + It is crucial that the STONITH device can allow the cluster to differentiate between a node failure and a network one. + + + The biggest mistake people make in choosing a STONITH device is to use remote power switch (such as many onboard IMPI controllers) that shares power with the node it controls. In such cases, the cluster cannot be sure if the node is really offline, or active and suffering from a network fault. + + + Likewise, any device that relies on the machine being active (such as SSH-based “devices” used during testing) are inappropriate. + +
+ +
+ Configuring STONITH + + + + Find the correct driver: stonith -L + + + + + Since every device is different, the parameters needed to configure it will vary. To find out the parameters required by the device: stonith -t {type} -n + + + + + Hopefully the developers chose names that make sense, if not you can query for some additional information by finding an active cluster node and running: + + +lrmadmin -M stonith {type} pacemaker + + + The output should be XML formatted text containing additional parameter descriptions + + + + + Create a file called stonith.xml containing a primitive resource with a class of stonith, a type of {type} and a parameter for each of the values returned in step 2 + + + + + Create a clone from the primitive resource if the device can shoot more than one node and supports multiple simultaneous connections. + + + + + Upload it into the CIB using cibadmin: cibadmin -C -o resources --xml-file stonith.xml + + + +
+ Example + + Assuming we have an IBM BladeCenter containing our two nodes and the management interface is active on 192.168.122.31, then we would chose the external/ibmrsa driver in step 2 and obtain the following list of parameters + + + +stonith -t external/ibmrsa -n +[root@pcmk-1 ~]# stonith -t external/ibmrsa -n +hostname  ipaddr  userid  passwd  type + + + Assuming we know the username and password for the management interface, we would create a STONITH resource with the shell + + + +[root@pcmk-1 ~]# crm +crm(live)# cib new stonith +INFO: stonith shadow CIB created +crm(stonith)# configure primitive rsa-fencing stonith::external/ibmrsa \ +        params hostname=”pcmk-1 pcmk-2" ipaddr=192.168.122.31 userid=mgmt passwd=abc123 type=ibm \ +        op monitor interval="60s" +crm(stonith)# configure clone Fencing rsa-fencing + + + And finally, since we disabled it earlier, we need to re-enable STONITH + + + +crm(stonith)# configure property stonith-enabled="true" +crm(stonith)# configure show +node pcmk-1 +node pcmk-2 +primitive WebData ocf:linbit:drbd \ +        params drbd_resource="wwwdata" \ +        op monitor interval="60s" +primitive WebFS ocf:heartbeat:Filesystem \ +        params device="/dev/drbd/by-res/wwwdata" directory="/var/www/html" fstype=”gfs2” +primitive WebSite ocf:heartbeat:apache \ +        params configfile="/etc/httpd/conf/httpd.conf" \ +        op monitor interval="1min" +primitive ClusterIP ocf:heartbeat:IPaddr2 \ +        params ip=”192.168.122.101” cidr_netmask=”32” clusterip_hash=”sourceip” \ +        op monitor interval="30s" +primitive dlm ocf:pacemaker:controld \ +        op monitor interval="120s" +primitive gfs-control ocf:pacemaker:controld \ +   params daemon=”gfs_controld.pcmk” args=”-g 0” \ +        op monitor interval="120s" +primitive rsa-fencing stonith::external/ibmrsa \ + params hostname=”pcmk-1 pcmk-2" ipaddr=192.168.122.31 userid=mgmt passwd=abc123 type=ibm \ + op monitor interval="60s" +ms WebDataClone WebData \ +        meta master-max="2" master-node-max="1" clone-max="2" clone-node-max="1" notify="true" +clone Fencing rsa-fencing +clone WebFSClone WebFS +clone WebIP ClusterIP  \ +        meta globally-unique=”true” clone-max=”2” clone-node-max=”2” +clone WebSiteClone WebSite +clone dlm-clone dlm \ +        meta interleave="true" +clone gfs-clone gfs-control \ +        meta interleave="true" +colocation WebFS-with-gfs-control inf: WebFSClone gfs-clone +colocation WebSite-with-WebFS inf: WebSiteClone WebFSClone +colocation fs_on_drbd inf: WebFSClone WebDataClone:Master +colocation gfs-with-dlm inf: gfs-clone dlm-clone +colocation website-with-ip inf: WebSiteClone WebIP +order WebFS-after-WebData inf: WebDataClone:promote WebFSClone:start +order WebSite-after-WebFS inf: WebFSClone WebSiteClone +order apache-after-ip inf: WebIP WebSiteClone +order start-WebFS-after-gfs-control inf: gfs-clone WebFSClone +order start-gfs-after-dlm inf: dlm-clone gfs-clone +property $id="cib-bootstrap-options" \ +        dc-version="1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7" \ +        cluster-infrastructure="openais" \ +        expected-quorum-votes=”2” \ +        stonith-enabled="true" \ +        no-quorum-policy="ignore" +rsc_defaults $id="rsc-options" \ +        resource-stickiness=”100” + +
+ +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Tools.xml b/doc/Clusters_from_Scratch/en-US/Ch-Tools.xml new file mode 100644 index 0000000000..3ceb283a5b --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-Tools.xml @@ -0,0 +1,122 @@ + + +%BOOK_ENTITIES; +]> + + Using Pacemaker Tools + + In the dark past, configuring Pacemaker required the administrator to read and write XML. In true UNIX style, there were also a number of different commands that specialized in different aspects of querying and updating the cluster. + + + Since Pacemaker 1.0, this has all changed and we have an integrated, scriptable, cluster shell that hides all the messy XML scaffolding. It even allows you to queue up several changes at once and commit them atomically. + + + Take some time to familiarize yourself with what it can do. + + + +[root@pcmk-1 ~]# crm --help + +usage: +    crm [-D display_type] +    crm [-D display_type] args +    crm [-D display_type] [-f file] + +    Use crm without arguments for an interactive session. +    Supply one or more arguments for a "single-shot" use. +    Specify with -f a file which contains a script. Use '-' for +    standard input or use pipe/redirection. + +    crm displays cli format configurations using a color scheme +    and/or in uppercase. Pick one of "color" or "uppercase", or +    use "-D color,uppercase" if you want colorful uppercase. +    Get plain output by "-D plain". The default may be set in +    user preferences (options). + +Examples: + +    # crm -f stopapp2.cli +    # crm < stopapp2.cli +    # crm resource stop global_www +    # crm status + + + The primary tool for monitoring the status of the cluster is crm_mon (also available as crm status). It can be run in a variety of modes and has a number of output options. To find out about any of the tools that come with Pacemaker, simply invoke them with the --help option or consult the included man pages. Both sets of output are created from the tool, and so will always be in sync with each other and the tool itself. + + + Additionally, the Pacemaker version and supported cluster stack(s) is available via the --version option. + + + +[root@pcmk-1 ~]# crm_mon --version +crm_mon 1.0.5 for OpenAIS and Heartbeat (Build: 462f1569a43740667daf7b0f6b521742e9eb8fa7) + +Written by Andrew Beekhof +[root@pcmk-1 ~]# crm_mon --help +crm_mon - Provides a summary of cluster's current state. + +Outputs varying levels of detail in a number of different formats. + +Usage: crm_mon mode [options] +Options: + -?, --help                 This text + -$, --version             Version information + -V, --verbose             Increase debug output + +Modes: + -h, --as-html=value        Write cluster status to the named file + -w, --web-cgi             Web mode with output suitable for cgi + -s, --simple-status       Display the cluster status once as a simple one line output (suitable for nagios) + -S, --snmp-traps=value    Send SNMP traps to this station + -T, --mail-to=value        Send Mail alerts to this user.  See also --mail-from, --mail-host, --mail-prefix + +Display Options: + -n, --group-by-node       Group resources by node + -r, --inactive             Display inactive resources + -f, --failcounts           Display resource fail counts + -o, --operations           Display resource operation history + -t, --timing-details       Display resource operation history with timing details + + +Additional Options: + -i, --interval=value           Update frequency in seconds + -1, --one-shot                 Display the cluster status once on the console and exit + -N, --disable-ncurses          Disable the use of ncurses + -d, --daemonize                Run in the background as a daemon + -p, --pid-file=value           (Advanced) Daemon pid file location + -F, --mail-from=value          Mail alerts should come from the named user + -H, --mail-host=value          Mail alerts should be sent via the named host + -P, --mail-prefix=value        Subjects for mail alerts should start with this string + -E, --external-agent=value     A program to run when resource operations take place. + -e, --external-recipient=value A recipient for your program (assuming you want the program to send something to someone). + +Examples: + +Display the cluster´s status on the console with updates as they occur: +        # crm_mon + +Display the cluster´s status on the console just once then exit: +        # crm_mon + +Display your cluster´s status, group resources by node, and include inactive resources in the list: +        # crm_mon --group-by-node --inactive + +Start crm_mon as a background daemon and have it write the cluster´s status to an HTML file: +        # crm_mon --daemonize --as-html /path/to/docroot/filename.html + +Start crm_mon as a background daemon and have it send email alerts: +        # crm_mon --daemonize --mail-to user@example.com --mail-host mail.example.com + +Start crm_mon as a background daemon and have it send SNMP alerts: +        # crm_mon --daemonize --snmp-traps snmptrapd.example.com + +Report bugs to pacemaker@oss.clusterlabs.org + + + + If the SNMP and/or email options are not listed, then Pacemaker was not built to support them. This may be by the choice of your distribution or the required libraries may not have been available. Please contact whoever supplied you with the packages for more details. + + + + diff --git a/doc/Clusters_from_Scratch/en-US/Ch-Verification.xml b/doc/Clusters_from_Scratch/en-US/Ch-Verification.xml new file mode 100644 index 0000000000..6ce337ef2b --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Ch-Verification.xml @@ -0,0 +1,108 @@ + + +%BOOK_ENTITIES; +]> + + Verify Cluster Installation +
+ Verify Corosync Installation + + Start Corosync on the first node + + + +[root@pcmk-1 ~]# /etc/init.d/corosync start +Starting Corosync Cluster Engine (corosync): [ OK ] + + + Check the cluster started correctly and that an initial membership was able to form + + + +[root@pcmk-1 ~]# grep -e "corosync.*network interface" -e "Corosync Cluster Engine" -e "Successfully read main configuration file" /var/log/messages +Aug 27 09:05:34 pcmk-1 corosync[1540]: [MAIN  ] Corosync Cluster Engine ('1.1.0'): started and ready to provide service. +Aug 27 09:05:34 pcmk-1 corosync[1540]: [MAIN  ] Successfully read main configuration file '/etc/corosync/corosync.conf'. +[root@pcmk-1 ~]# grep TOTEM /var/log/messages +Aug 27 09:05:34 pcmk-1 corosync[1540]: [TOTEM ] Initializing transport (UDP/IP). +Aug 27 09:05:34 pcmk-1 corosync[1540]: [TOTEM ] Initializing transmit/receive security: libtomcrypt SOBER128/SHA1HMAC (mode 0). +Aug 27 09:05:35 pcmk-1 corosync[1540]: [TOTEM ] The network interface [192.168.122.101] is now up. +Aug 27 09:05:35 pcmk-1 corosync[1540]: [TOTEM ] A processor joined or left the membership and a new membership was formed. + + + With one node functional, its now safe to start Corosync on the second node as well. + + + +[root@pcmk-1 ~]# ssh pcmk-2 -- /etc/init.d/corosync start +Starting Corosync Cluster Engine (corosync): [ OK ] +[root@pcmk-1 ~]# + + + Check the cluster formed correctly + + + +[root@pcmk-1 ~]# grep TOTEM /var/log/messages +Aug 27 09:05:34 pcmk-1 corosync[1540]: [TOTEM ] Initializing transport (UDP/IP). +Aug 27 09:05:34 pcmk-1 corosync[1540]: [TOTEM ] Initializing transmit/receive security: libtomcrypt SOBER128/SHA1HMAC (mode 0). +Aug 27 09:05:35 pcmk-1 corosync[1540]: [TOTEM ] The network interface [192.168.122.101] is now up. +Aug 27 09:05:35 pcmk-1 corosync[1540]: [TOTEM ] A processor joined or left the membership and a new membership was formed. +Aug 27 09:12:11 pcmk-1 corosync[1540]: [TOTEM ] A processor joined or left the membership and a new membership was formed. + +
+ +
+ Verify Pacemaker Installation + + Now that we have confirmed that Corosync is functional we can check the rest of the stack. + + + +[root@pcmk-1 ~]# grep pcmk_startup /var/log/messages +Aug 27 09:05:35 pcmk-1 corosync[1540]:   [pcmk  ] info: pcmk_startup: CRM: Initialized +Aug 27 09:05:35 pcmk-1 corosync[1540]:   [pcmk  ] Logging: Initialized pcmk_startup +Aug 27 09:05:35 pcmk-1 corosync[1540]:   [pcmk  ] info: pcmk_startup: Maximum core file size is: 18446744073709551615 +Aug 27 09:05:35 pcmk-1 corosync[1540]:   [pcmk  ] info: pcmk_startup: Service: 9 +Aug 27 09:05:35 pcmk-1 corosync[1540]:   [pcmk  ] info: pcmk_startup: Local hostname: pcmk-1 + + + Now verify the Pacemaker processes have been started + + + +[root@pcmk-1 ~]# ps axf +  PID TTY      STAT   TIME COMMAND +    2 ?        S<     0:00 [kthreadd] +    3 ?        S<     0:00  \_ [migration/0] +... lots of processes ... + 2166 pts/0    SLl    0:01 /usr/sbin/corosync + 2172 ?        SLs    0:00  \_ /usr/lib64/heartbeat/stonithd + 2173 pts/0    S      0:00  \_ /usr/lib64/heartbeat/cib + 2174 pts/0    S      0:00  \_ /usr/lib64/heartbeat/lrmd + 2175 pts/0    S      0:00  \_ /usr/lib64/heartbeat/attrd + 2176 pts/0    S      0:00  \_ /usr/lib64/heartbeat/pengine + 2177 pts/0    S      0:00  \_ /usr/lib64/heartbeat/crmd + + + And finally, check for any ERRORs during startup, there shouldn’t be any, and display the cluster’s status. + + + +[root@pcmk-1 ~]# grep ERROR: /var/log/messages | grep -v unpack_resources +[root@pcmk-1 ~]# crm_mon +============ +Last updated: Thu Aug 27 16:54:55 2009 +Stack: openais +Current DC: pcmk-1 - partition with quorum +Version: 1.0.5-462f1569a43740667daf7b0f6b521742e9eb8fa7 +2 Nodes configured, 2 expected votes +0 Resources configured. +============ + +Online: [ pcmk-1 pcmk-2 ] + +
+ + + diff --git a/doc/Clusters_from_Scratch/en-US/Clusters_from_Scratch.ent b/doc/Clusters_from_Scratch/en-US/Clusters_from_Scratch.ent new file mode 100644 index 0000000000..62f87fe3d7 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Clusters_from_Scratch.ent @@ -0,0 +1,4 @@ + + + + diff --git a/doc/Clusters_from_Scratch/en-US/Clusters_from_Scratch.xml b/doc/Clusters_from_Scratch/en-US/Clusters_from_Scratch.xml new file mode 100644 index 0000000000..1d49ecf9f9 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Clusters_from_Scratch.xml @@ -0,0 +1,25 @@ + + +%BOOK_ENTITIES; +]> + + + + + + + + + + + + + + + + + + + + diff --git a/doc/Clusters_from_Scratch/en-US/Preface.xml b/doc/Clusters_from_Scratch/en-US/Preface.xml new file mode 100644 index 0000000000..78f61530a5 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Preface.xml @@ -0,0 +1,13 @@ + + +%BOOK_ENTITIES; +]> + + Preface + + + + + + diff --git a/doc/Clusters_from_Scratch/en-US/Revision_History.xml b/doc/Clusters_from_Scratch/en-US/Revision_History.xml new file mode 100644 index 0000000000..4d92648a08 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/Revision_History.xml @@ -0,0 +1,27 @@ + + +%BOOK_ENTITIES; +]> + + Revision History + + + + 0 + Fri Apr 23 2010 + + Dude + McPants + Dude.McPants@example.com + + + + Initial creation of book by publican + + + + + + + diff --git a/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-big.dot b/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-big.dot new file mode 100644 index 0000000000..40ced22ccc --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-big.dot @@ -0,0 +1,83 @@ +digraph "g" { +"Cancel drbd0:0_monitor_10000 frigg" -> "drbd0:0_demote_0 frigg" [ style = bold] +"Cancel drbd0:0_monitor_10000 frigg" [ style=bold color="green" fontcolor="black" ] +"Cancel drbd0:1_monitor_12000 odin" -> "drbd0:1_promote_0 odin" [ style = bold] +"Cancel drbd0:1_monitor_12000 odin" [ style=bold color="green" fontcolor="black" ] +"IPaddr0_monitor_5000 odin" [ style=bold color="green" fontcolor="black" ] +"IPaddr0_start_0 odin" -> "IPaddr0_monitor_5000 odin" [ style = bold] +"IPaddr0_start_0 odin" -> "MailTo_start_0 odin" [ style = bold] +"IPaddr0_start_0 odin" -> "group_running_0" [ style = bold] +"IPaddr0_start_0 odin" [ style=bold color="green" fontcolor="black" ] +"MailTo_start_0 odin" -> "group_running_0" [ style = bold] +"MailTo_start_0 odin" [ style=bold color="green" fontcolor="black" ] +"drbd0:0_demote_0 frigg" -> "drbd0:0_monitor_12000 frigg" [ style = bold] +"drbd0:0_demote_0 frigg" -> "ms_drbd_demoted_0" [ style = bold] +"drbd0:0_demote_0 frigg" [ style=bold color="green" fontcolor="black" ] +"drbd0:0_monitor_12000 frigg" [ style=bold color="green" fontcolor="black" ] +"drbd0:0_post_notify_demote_0 frigg" -> "ms_drbd_confirmed-post_notify_demoted_0" [ style = bold] +"drbd0:0_post_notify_demote_0 frigg" [ style=bold color="green" fontcolor="black" ] +"drbd0:0_post_notify_promote_0 frigg" -> "ms_drbd_confirmed-post_notify_promoted_0" [ style = bold] +"drbd0:0_post_notify_promote_0 frigg" [ style=bold color="green" fontcolor="black" ] +"drbd0:0_pre_notify_demote_0 frigg" -> "ms_drbd_confirmed-pre_notify_demote_0" [ style = bold] +"drbd0:0_pre_notify_demote_0 frigg" [ style=bold color="green" fontcolor="black" ] +"drbd0:0_pre_notify_promote_0 frigg" -> "ms_drbd_confirmed-pre_notify_promote_0" [ style = bold] +"drbd0:0_pre_notify_promote_0 frigg" [ style=bold color="green" fontcolor="black" ] +"drbd0:1_monitor_10000 odin" [ style=bold color="green" fontcolor="black" ] +"drbd0:1_post_notify_demote_0 odin" -> "ms_drbd_confirmed-post_notify_demoted_0" [ style = bold] +"drbd0:1_post_notify_demote_0 odin" [ style=bold color="green" fontcolor="black" ] +"drbd0:1_post_notify_promote_0 odin" -> "ms_drbd_confirmed-post_notify_promoted_0" [ style = bold] +"drbd0:1_post_notify_promote_0 odin" [ style=bold color="green" fontcolor="black" ] +"drbd0:1_pre_notify_demote_0 odin" -> "ms_drbd_confirmed-pre_notify_demote_0" [ style = bold] +"drbd0:1_pre_notify_demote_0 odin" [ style=bold color="green" fontcolor="black" ] +"drbd0:1_pre_notify_promote_0 odin" -> "ms_drbd_confirmed-pre_notify_promote_0" [ style = bold] +"drbd0:1_pre_notify_promote_0 odin" [ style=bold color="green" fontcolor="black" ] +"drbd0:1_promote_0 odin" -> "drbd0:1_monitor_10000 odin" [ style = bold] +"drbd0:1_promote_0 odin" -> "ms_drbd_promoted_0" [ style = bold] +"drbd0:1_promote_0 odin" [ style=bold color="green" fontcolor="black" ] +"group_running_0" [ style=bold color="green" fontcolor="orange" ] +"group_start_0" -> "IPaddr0_start_0 odin" [ style = bold] +"group_start_0" -> "MailTo_start_0 odin" [ style = bold] +"group_start_0" -> "group_running_0" [ style = bold] +"group_start_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_confirmed-post_notify_demoted_0" -> "drbd0:0_monitor_12000 frigg" [ style = bold] +"ms_drbd_confirmed-post_notify_demoted_0" -> "drbd0:1_monitor_10000 odin" [ style = bold] +"ms_drbd_confirmed-post_notify_demoted_0" -> "ms_drbd_pre_notify_promote_0" [ style = bold] +"ms_drbd_confirmed-post_notify_demoted_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_confirmed-post_notify_promoted_0" -> "drbd0:0_monitor_12000 frigg" [ style = bold] +"ms_drbd_confirmed-post_notify_promoted_0" -> "drbd0:1_monitor_10000 odin" [ style = bold] +"ms_drbd_confirmed-post_notify_promoted_0" -> "group_start_0" [ style = bold] +"ms_drbd_confirmed-post_notify_promoted_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_confirmed-pre_notify_demote_0" -> "ms_drbd_demote_0" [ style = bold] +"ms_drbd_confirmed-pre_notify_demote_0" -> "ms_drbd_post_notify_demoted_0" [ style = bold] +"ms_drbd_confirmed-pre_notify_demote_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_confirmed-pre_notify_promote_0" -> "ms_drbd_post_notify_promoted_0" [ style = bold] +"ms_drbd_confirmed-pre_notify_promote_0" -> "ms_drbd_promote_0" [ style = bold] +"ms_drbd_confirmed-pre_notify_promote_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_demote_0" -> "drbd0:0_demote_0 frigg" [ style = bold] +"ms_drbd_demote_0" -> "ms_drbd_demoted_0" [ style = bold] +"ms_drbd_demote_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_demoted_0" -> "ms_drbd_post_notify_demoted_0" [ style = bold] +"ms_drbd_demoted_0" -> "ms_drbd_promote_0" [ style = bold] +"ms_drbd_demoted_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_post_notify_demoted_0" -> "drbd0:0_post_notify_demote_0 frigg" [ style = bold] +"ms_drbd_post_notify_demoted_0" -> "drbd0:1_post_notify_demote_0 odin" [ style = bold] +"ms_drbd_post_notify_demoted_0" -> "ms_drbd_confirmed-post_notify_demoted_0" [ style = bold] +"ms_drbd_post_notify_demoted_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_post_notify_promoted_0" -> "drbd0:0_post_notify_promote_0 frigg" [ style = bold] +"ms_drbd_post_notify_promoted_0" -> "drbd0:1_post_notify_promote_0 odin" [ style = bold] +"ms_drbd_post_notify_promoted_0" -> "ms_drbd_confirmed-post_notify_promoted_0" [ style = bold] +"ms_drbd_post_notify_promoted_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_pre_notify_demote_0" -> "drbd0:0_pre_notify_demote_0 frigg" [ style = bold] +"ms_drbd_pre_notify_demote_0" -> "drbd0:1_pre_notify_demote_0 odin" [ style = bold] +"ms_drbd_pre_notify_demote_0" -> "ms_drbd_confirmed-pre_notify_demote_0" [ style = bold] +"ms_drbd_pre_notify_demote_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_pre_notify_promote_0" -> "drbd0:0_pre_notify_promote_0 frigg" [ style = bold] +"ms_drbd_pre_notify_promote_0" -> "drbd0:1_pre_notify_promote_0 odin" [ style = bold] +"ms_drbd_pre_notify_promote_0" -> "ms_drbd_confirmed-pre_notify_promote_0" [ style = bold] +"ms_drbd_pre_notify_promote_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_promote_0" -> "drbd0:1_promote_0 odin" [ style = bold] +"ms_drbd_promote_0" [ style=bold color="green" fontcolor="orange" ] +"ms_drbd_promoted_0" -> "group_start_0" [ style = bold] +"ms_drbd_promoted_0" -> "ms_drbd_post_notify_promoted_0" [ style = bold] +"ms_drbd_promoted_0" [ style=bold color="green" fontcolor="orange" ] +} diff --git a/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-big.svg b/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-big.svg new file mode 100644 index 0000000000..7964fcfd30 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-big.svg @@ -0,0 +1,418 @@ + + + + + + +g + + +Cancel drbd0:0_monitor_10000 frigg + +Cancel drbd0:0_monitor_10000 frigg + + +drbd0:0_demote_0 frigg + +drbd0:0_demote_0 frigg + + +Cancel drbd0:0_monitor_10000 frigg->drbd0:0_demote_0 frigg + + + + +drbd0:0_monitor_12000 frigg + +drbd0:0_monitor_12000 frigg + + +drbd0:0_demote_0 frigg->drbd0:0_monitor_12000 frigg + + + + +ms_drbd_demoted_0 + +ms_drbd_demoted_0 + + +drbd0:0_demote_0 frigg->ms_drbd_demoted_0 + + + + +Cancel drbd0:1_monitor_12000 odin + +Cancel drbd0:1_monitor_12000 odin + + +drbd0:1_promote_0 odin + +drbd0:1_promote_0 odin + + +Cancel drbd0:1_monitor_12000 odin->drbd0:1_promote_0 odin + + + + +drbd0:1_monitor_10000 odin + +drbd0:1_monitor_10000 odin + + +drbd0:1_promote_0 odin->drbd0:1_monitor_10000 odin + + + + +ms_drbd_promoted_0 + +ms_drbd_promoted_0 + + +drbd0:1_promote_0 odin->ms_drbd_promoted_0 + + + + +IPaddr0_monitor_5000 odin + +IPaddr0_monitor_5000 odin + + +IPaddr0_start_0 odin + +IPaddr0_start_0 odin + + +IPaddr0_start_0 odin->IPaddr0_monitor_5000 odin + + + + +MailTo_start_0 odin + +MailTo_start_0 odin + + +IPaddr0_start_0 odin->MailTo_start_0 odin + + + + +group_running_0 + +group_running_0 + + +IPaddr0_start_0 odin->group_running_0 + + + + +MailTo_start_0 odin->group_running_0 + + + + +ms_drbd_post_notify_demoted_0 + +ms_drbd_post_notify_demoted_0 + + +ms_drbd_demoted_0->ms_drbd_post_notify_demoted_0 + + + + +ms_drbd_promote_0 + +ms_drbd_promote_0 + + +ms_drbd_demoted_0->ms_drbd_promote_0 + + + + +drbd0:0_post_notify_demote_0 frigg + +drbd0:0_post_notify_demote_0 frigg + + +ms_drbd_confirmed-post_notify_demoted_0 + +ms_drbd_confirmed-post_notify_demoted_0 + + +drbd0:0_post_notify_demote_0 frigg->ms_drbd_confirmed-post_notify_demoted_0 + + + + +ms_drbd_confirmed-post_notify_demoted_0->drbd0:0_monitor_12000 frigg + + + + +ms_drbd_confirmed-post_notify_demoted_0->drbd0:1_monitor_10000 odin + + + + +ms_drbd_pre_notify_promote_0 + +ms_drbd_pre_notify_promote_0 + + +ms_drbd_confirmed-post_notify_demoted_0->ms_drbd_pre_notify_promote_0 + + + + +drbd0:0_post_notify_promote_0 frigg + +drbd0:0_post_notify_promote_0 frigg + + +ms_drbd_confirmed-post_notify_promoted_0 + +ms_drbd_confirmed-post_notify_promoted_0 + + +drbd0:0_post_notify_promote_0 frigg->ms_drbd_confirmed-post_notify_promoted_0 + + + + +ms_drbd_confirmed-post_notify_promoted_0->drbd0:0_monitor_12000 frigg + + + + +ms_drbd_confirmed-post_notify_promoted_0->drbd0:1_monitor_10000 odin + + + + +group_start_0 + +group_start_0 + + +ms_drbd_confirmed-post_notify_promoted_0->group_start_0 + + + + +drbd0:0_pre_notify_demote_0 frigg + +drbd0:0_pre_notify_demote_0 frigg + + +ms_drbd_confirmed-pre_notify_demote_0 + +ms_drbd_confirmed-pre_notify_demote_0 + + +drbd0:0_pre_notify_demote_0 frigg->ms_drbd_confirmed-pre_notify_demote_0 + + + + +ms_drbd_demote_0 + +ms_drbd_demote_0 + + +ms_drbd_confirmed-pre_notify_demote_0->ms_drbd_demote_0 + + + + +ms_drbd_confirmed-pre_notify_demote_0->ms_drbd_post_notify_demoted_0 + + + + +drbd0:0_pre_notify_promote_0 frigg + +drbd0:0_pre_notify_promote_0 frigg + + +ms_drbd_confirmed-pre_notify_promote_0 + +ms_drbd_confirmed-pre_notify_promote_0 + + +drbd0:0_pre_notify_promote_0 frigg->ms_drbd_confirmed-pre_notify_promote_0 + + + + +ms_drbd_post_notify_promoted_0 + +ms_drbd_post_notify_promoted_0 + + +ms_drbd_confirmed-pre_notify_promote_0->ms_drbd_post_notify_promoted_0 + + + + +ms_drbd_confirmed-pre_notify_promote_0->ms_drbd_promote_0 + + + + +drbd0:1_post_notify_demote_0 odin + +drbd0:1_post_notify_demote_0 odin + + +drbd0:1_post_notify_demote_0 odin->ms_drbd_confirmed-post_notify_demoted_0 + + + + +drbd0:1_post_notify_promote_0 odin + +drbd0:1_post_notify_promote_0 odin + + +drbd0:1_post_notify_promote_0 odin->ms_drbd_confirmed-post_notify_promoted_0 + + + + +drbd0:1_pre_notify_demote_0 odin + +drbd0:1_pre_notify_demote_0 odin + + +drbd0:1_pre_notify_demote_0 odin->ms_drbd_confirmed-pre_notify_demote_0 + + + + +drbd0:1_pre_notify_promote_0 odin + +drbd0:1_pre_notify_promote_0 odin + + +drbd0:1_pre_notify_promote_0 odin->ms_drbd_confirmed-pre_notify_promote_0 + + + + +ms_drbd_promoted_0->group_start_0 + + + + +ms_drbd_promoted_0->ms_drbd_post_notify_promoted_0 + + + + +group_start_0->IPaddr0_start_0 odin + + + + +group_start_0->MailTo_start_0 odin + + + + +group_start_0->group_running_0 + + + + +ms_drbd_pre_notify_promote_0->drbd0:0_pre_notify_promote_0 frigg + + + + +ms_drbd_pre_notify_promote_0->ms_drbd_confirmed-pre_notify_promote_0 + + + + +ms_drbd_pre_notify_promote_0->drbd0:1_pre_notify_promote_0 odin + + + + +ms_drbd_demote_0->drbd0:0_demote_0 frigg + + + + +ms_drbd_demote_0->ms_drbd_demoted_0 + + + + +ms_drbd_post_notify_demoted_0->drbd0:0_post_notify_demote_0 frigg + + + + +ms_drbd_post_notify_demoted_0->ms_drbd_confirmed-post_notify_demoted_0 + + + + +ms_drbd_post_notify_demoted_0->drbd0:1_post_notify_demote_0 odin + + + + +ms_drbd_post_notify_promoted_0->drbd0:0_post_notify_promote_0 frigg + + + + +ms_drbd_post_notify_promoted_0->ms_drbd_confirmed-post_notify_promoted_0 + + + + +ms_drbd_post_notify_promoted_0->drbd0:1_post_notify_promote_0 odin + + + + +ms_drbd_promote_0->drbd0:1_promote_0 odin + + + + +ms_drbd_pre_notify_demote_0 + +ms_drbd_pre_notify_demote_0 + + +ms_drbd_pre_notify_demote_0->drbd0:0_pre_notify_demote_0 frigg + + + + +ms_drbd_pre_notify_demote_0->ms_drbd_confirmed-pre_notify_demote_0 + + + + +ms_drbd_pre_notify_demote_0->drbd0:1_pre_notify_demote_0 odin + + + + + diff --git a/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-small.dot b/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-small.dot new file mode 100644 index 0000000000..3fef81e789 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-small.dot @@ -0,0 +1,31 @@ + digraph "g" { +"rsc1_monitor_0 pcmk-2" -> "probe_complete pcmk-2" [ style = bold] +"rsc1_monitor_0 pcmk-2" [ style=bold color="green" fontcolor="black" ] +"rsc1_stop_0 pcmk-1" [ style=dashed color="red" fontcolor="black" ] +"rsc1_start_0 pcmk-2" [ style=dashed color="red" fontcolor="black" ] +"rsc1_stop_0 pcmk-1" -> "rsc1_start_0 pcmk-2" [ style = dashed ] +"rsc1_stop_0 pcmk-1" -> "all_stopped" [ style = dashed ] +"probe_complete" -> "rsc1_start_0 pcmk-2" [ style = dashed ] + +"rsc2_monitor_0 pcmk-2" -> "probe_complete pcmk-2" [ style = bold] +"rsc2_monitor_0 pcmk-2" [ style=bold color="green" fontcolor="black" ] +"rsc2_stop_0 pcmk-1" [ style=dashed color="red" fontcolor="black" ] +"rsc2_start_0 pcmk-2" [ style=dashed color="red" fontcolor="black" ] +"rsc2_stop_0 pcmk-1" -> "rsc2_start_0 pcmk-2" [ style = dashed ] +"rsc2_stop_0 pcmk-1" -> "all_stopped" [ style = dashed ] +"probe_complete" -> "rsc2_start_0 pcmk-2" [ style = dashed ] + +"rsc3_monitor_0 pcmk-2" -> "probe_complete pcmk-2" [ style = bold] +"rsc3_monitor_0 pcmk-2" [ style=bold color="green" fontcolor="black" ] +"rsc3_stop_0 pcmk-1" [ style=dashed color="blue" fontcolor="orange" ] +"rsc3_start_0 pcmk-2" [ style=dashed color="blue" fontcolor="black" ] +"rsc3_stop_0 pcmk-1" -> "all_stopped" [ style = dashed ] +"probe_complete" -> "rsc3_start_0 pcmk-2" [ style = dashed ] + +"probe_complete pcmk-2" -> "probe_complete" [ style = bold] +"probe_complete pcmk-2" [ style=bold color="green" fontcolor="black" ] +"probe_complete" [ style=bold color="green" fontcolor="orange" ] + +"all_stopped" [ style=dashed color="red" fontcolor="orange" ] + +} diff --git a/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-small.svg b/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-small.svg new file mode 100644 index 0000000000..a020d564f8 --- /dev/null +++ b/doc/Clusters_from_Scratch/en-US/images/Policy-Engine-small.svg @@ -0,0 +1,133 @@ + + + + + + +g + + +rsc1_monitor_0 pcmk-2 + +rsc1_monitor_0 pcmk-2 + + +probe_complete pcmk-2 + +probe_complete pcmk-2 + + +rsc1_monitor_0 pcmk-2->probe_complete pcmk-2 + + + + +probe_complete + +probe_complete + + +probe_complete pcmk-2->probe_complete + + + + +rsc1_stop_0 pcmk-1 + +rsc1_stop_0 pcmk-1 + + +rsc1_start_0 pcmk-2 + +rsc1_start_0 pcmk-2 + + +rsc1_stop_0 pcmk-1->rsc1_start_0 pcmk-2 + + + + +all_stopped + +all_stopped + + +rsc1_stop_0 pcmk-1->all_stopped + + + + +probe_complete->rsc1_start_0 pcmk-2 + + + + +rsc2_start_0 pcmk-2 + +rsc2_start_0 pcmk-2 + + +probe_complete->rsc2_start_0 pcmk-2 + + + + +rsc3_start_0 pcmk-2 + +rsc3_start_0 pcmk-2 + + +probe_complete->rsc3_start_0 pcmk-2 + + + + +rsc2_monitor_0 pcmk-2 + +rsc2_monitor_0 pcmk-2 + + +rsc2_monitor_0 pcmk-2->probe_complete pcmk-2 + + + + +rsc2_stop_0 pcmk-1 + +rsc2_stop_0 pcmk-1 + + +rsc2_stop_0 pcmk-1->all_stopped + + + + +rsc2_stop_0 pcmk-1->rsc2_start_0 pcmk-2 + + + + +rsc3_monitor_0 pcmk-2 + +rsc3_monitor_0 pcmk-2 + + +rsc3_monitor_0 pcmk-2->probe_complete pcmk-2 + + + + +rsc3_stop_0 pcmk-1 + +rsc3_stop_0 pcmk-1 + + +rsc3_stop_0 pcmk-1->all_stopped + + + + + diff --git a/doc/Clusters_from_Scratch/publican.cfg.in b/doc/Clusters_from_Scratch/publican.cfg.in new file mode 100644 index 0000000000..816267d7e0 --- /dev/null +++ b/doc/Clusters_from_Scratch/publican.cfg.in @@ -0,0 +1,14 @@ +# Config::Simple 4.59 +# Fri Apr 23 15:33:52 2010 + +docname: Clusters_from_Scratch +xml_lang: en-US +#edition: 1 +type: Book +version: @PACKAGE_SERIES@ +brand: @PUBLICAN_BRAND@ +product: Pacemaker + +chunk_first: 0 +chunk_section_depth: 3 +generate_section_toc_level: 4