diff --git a/doc/Pacemaker_Explained/en-US/Ch-Options.txt b/doc/Pacemaker_Explained/en-US/Ch-Options.txt index a2fbfe2473..df6b71aae4 100644 --- a/doc/Pacemaker_Explained/en-US/Ch-Options.txt +++ b/doc/Pacemaker_Explained/en-US/Ch-Options.txt @@ -1,409 +1,410 @@ = Cluster-Wide Configuration = == CIB Properties == Certain settings are defined by CIB properties (that is, attributes of the +cib+ tag) rather than with the rest of the cluster configuration in the +configuration+ section. The reason is simply a matter of parsing. These options are used by the configuration database which is, by design, mostly ignorant of the content it holds. So the decision was made to place them in an easy-to-find location. .CIB Properties [width="95%",cols="2m,5<",options="header",align="center"] |========================================================= |Field |Description | admin_epoch | indexterm:[Configuration Version,Cluster] indexterm:[Cluster,Option,Configuration Version] indexterm:[admin_epoch,Cluster Option] indexterm:[Cluster,Option,admin_epoch] When a node joins the cluster, the cluster performs a check to see which node has the best configuration. It asks the node with the highest (+admin_epoch+, +epoch+, +num_updates+) tuple to replace the configuration on all the nodes -- which makes setting them, and setting them correctly, very important. +admin_epoch+ is never modified by the cluster; you can use this to make the configurations on any inactive nodes obsolete. _Never set this value to zero_. In such cases, the cluster cannot tell the difference between your configuration and the "empty" one used when nothing is found on disk. | epoch | indexterm:[epoch,Cluster Option] indexterm:[Cluster,Option,epoch] The cluster increments this every time the configuration is updated (usually by the administrator). | num_updates | indexterm:[num_updates,Cluster Option] indexterm:[Cluster,Option,num_updates] The cluster increments this every time the configuration or status is updated (usually by the cluster) and resets it to 0 when epoch changes. | validate-with | indexterm:[validate-with,Cluster Option] indexterm:[Cluster,Option,validate-with] Determines the type of XML validation that will be done on the configuration. If set to +none+, the cluster will not verify that updates conform to the DTD (nor reject ones that don't). This option can be useful when operating a mixed-version cluster during an upgrade. |cib-last-written | indexterm:[cib-last-written,Cluster Property] indexterm:[Cluster,Property,cib-last-written] Indicates when the configuration was last written to disk. Maintained by the cluster; for informational purposes only. |have-quorum | indexterm:[have-quorum,Cluster Property] indexterm:[Cluster,Property,have-quorum] Indicates if the cluster has quorum. If false, this may mean that the cluster cannot start resources or fence other nodes (see +no-quorum-policy+ below). Maintained by the cluster. |dc-uuid | indexterm:[dc-uuid,Cluster Property] indexterm:[Cluster,Property,dc-uuid] Indicates which cluster node is the current leader. Used by the cluster when placing resources and determining the order of some events. Maintained by the cluster. |========================================================= === Working with CIB Properties === Although these fields can be written to by the user, in most cases the cluster will overwrite any values specified by the user with the "correct" ones. To change the ones that can be specified by the user, for example +admin_epoch+, one should use: ---- # cibadmin --modify --crm_xml '' ---- A complete set of CIB properties will look something like this: .Attributes set for a cib object ====== [source,XML] ------- ------- ====== +[[s-cluster-options]] == Cluster Options == Cluster options, as you might expect, control how the cluster behaves when confronted with certain situations. They are grouped into sets within the +crm_config+ section, and, in advanced configurations, there may be more than one set. (This will be described later in the section on <> where we will show how to have the cluster use different sets of options during working hours than during weekends.) For now, we will describe the simple case where each option is present at most once. You can obtain an up-to-date list of cluster options, including their default values, by running the `man pengine` and `man crmd` commands. .Cluster Options [width="95%",cols="5m,2,11>). | enable-startup-probes | TRUE | indexterm:[enable-startup-probes,Cluster Option] indexterm:[Cluster,Option,enable-startup-probes] Should the cluster check for active resources during startup? | maintenance-mode | FALSE | indexterm:[maintenance-mode,Cluster Option] indexterm:[Cluster,Option,maintenance-mode] Should the cluster refrain from monitoring, starting and stopping resources? | stonith-enabled | TRUE | indexterm:[stonith-enabled,Cluster Option] indexterm:[Cluster,Option,stonith-enabled] Should failed nodes and nodes with resources that can't be stopped be shot? If you value your data, set up a STONITH device and enable this. If true, or unset, the cluster will refuse to start resources unless one or more STONITH resources have been configured. If false, unresponsive nodes are immediately assumed to be running no resources, and resource takeover to online nodes starts without any further protection (which means _data loss_ if the unresponsive node still accesses shared storage, for example). See also the +requires+ meta-attribute in <>. | stonith-action | reboot | indexterm:[stonith-action,Cluster Option] indexterm:[Cluster,Option,stonith-action] Action to send to STONITH device. Allowed values are +reboot+ and +off+. The value +poweroff+ is also allowed, but is only used for legacy devices. | stonith-timeout | 60s | indexterm:[stonith-timeout,Cluster Option] indexterm:[Cluster,Option,stonith-timeout] How long to wait for STONITH actions (reboot, on, off) to complete | concurrent-fencing | FALSE | indexterm:[concurrent-fencing,Cluster Option] indexterm:[Cluster,Option,concurrent-fencing] Is the cluster allowed to initiate multiple fence actions concurrently? | cluster-delay | 60s | indexterm:[cluster-delay,Cluster Option] indexterm:[Cluster,Option,cluster-delay] Estimated maximum round-trip delay over the network (excluding action execution). If the TE requires an action to be executed on another node, it will consider the action failed if it does not get a response from the other node in this time (after considering the action's own timeout). The "correct" value will depend on the speed and load of your network and cluster nodes. | dc-deadtime | 20s | indexterm:[dc-deadtime,Cluster Option] indexterm:[Cluster,Option,dc-deadtime] How long to wait for a response from other nodes during startup. The "correct" value will depend on the speed/load of your network and the type of switches used. | cluster-recheck-interval | 15min | indexterm:[cluster-recheck-interval,Cluster Option] indexterm:[Cluster,Option,cluster-recheck-interval] Polling interval for time-based changes to options, resource parameters and constraints. The Cluster is primarily event-driven, but your configuration can have elements that take effect based on the time of day. To ensure these changes take effect, we can optionally poll the cluster's status for changes. A value of 0 disables polling. Positive values are an interval (in seconds unless other SI units are specified, e.g. 5min). | pe-error-series-max | -1 | indexterm:[pe-error-series-max,Cluster Option] indexterm:[Cluster,Option,pe-error-series-max] The number of PE inputs resulting in ERRORs to save. Used when reporting problems. A value of -1 means unlimited (report all). | pe-warn-series-max | -1 | indexterm:[pe-warn-series-max,Cluster Option] indexterm:[Cluster,Option,pe-warn-series-max] The number of PE inputs resulting in WARNINGs to save. Used when reporting problems. A value of -1 means unlimited (report all). | pe-input-series-max | -1 | indexterm:[pe-input-series-max,Cluster Option] indexterm:[Cluster,Option,pe-input-series-max] The number of "normal" PE inputs to save. Used when reporting problems. A value of -1 means unlimited (report all). | remove-after-stop | FALSE | indexterm:[remove-after-stop,Cluster Option] indexterm:[Cluster,Option,remove-after-stop] _Advanced Use Only:_ Should the cluster remove resources from the LRM after they are stopped? Values other than the default are, at best, poorly tested and potentially dangerous. | startup-fencing | TRUE | indexterm:[startup-fencing,Cluster Option] indexterm:[Cluster,Option,startup-fencing] _Advanced Use Only:_ Should the cluster shoot unseen nodes? Not using the default is very unsafe! | election-timeout | 2min | indexterm:[election-timeout,Cluster Option] indexterm:[Cluster,Option,election-timeout] _Advanced Use Only:_ If you need to adjust this value, it probably indicates the presence of a bug. | shutdown-escalation | 20min | indexterm:[shutdown-escalation,Cluster Option] indexterm:[Cluster,Option,shutdown-escalation] _Advanced Use Only:_ If you need to adjust this value, it probably indicates the presence of a bug. | crmd-integration-timeout | 3min | indexterm:[crmd-integration-timeout,Cluster Option] indexterm:[Cluster,Option,crmd-integration-timeout] _Advanced Use Only:_ If you need to adjust this value, it probably indicates the presence of a bug. | crmd-finalization-timeout | 30min | indexterm:[crmd-finalization-timeout,Cluster Option] indexterm:[Cluster,Option,crmd-finalization-timeout] _Advanced Use Only:_ If you need to adjust this value, it probably indicates the presence of a bug. | crmd-transition-delay | 0s | indexterm:[crmd-transition-delay,Cluster Option] indexterm:[Cluster,Option,crmd-transition-delay] _Advanced Use Only:_ Delay cluster recovery for the configured interval to allow for additional/related events to occur. Useful if your configuration is sensitive to the order in which ping updates arrive. Enabling this option will slow down cluster recovery under all conditions. |default-resource-stickiness | 0 | indexterm:[default-resource-stickiness,Cluster Option] indexterm:[Cluster,Option,default-resource-stickiness] _Deprecated:_ See <> instead | is-managed-default | TRUE | indexterm:[is-managed-default,Cluster Option] indexterm:[Cluster,Option,is-managed-default] _Deprecated:_ See <> instead | default-action-timeout | 20s | indexterm:[default-action-timeout,Cluster Option] indexterm:[Cluster,Option,default-action-timeout] _Deprecated:_ See <> instead |========================================================= === Querying and Setting Cluster Options === indexterm:[Querying,Cluster Option] indexterm:[Setting,Cluster Option] indexterm:[Cluster,Querying Options] indexterm:[Cluster,Setting Options] Cluster options can be queried and modified using the `crm_attribute` tool. To get the current value of +cluster-delay+, you can run: ---- # crm_attribute --query --name cluster-delay ---- which is more simply written as ---- # crm_attribute -G -n cluster-delay ---- If a value is found, you'll see a result like this: ---- # crm_attribute -G -n cluster-delay scope=crm_config name=cluster-delay value=60s ---- If no value is found, the tool will display an error: ---- # crm_attribute -G -n clusta-deway scope=crm_config name=clusta-deway value=(null) Error performing operation: No such device or address ---- To use a different value (for example, 30 seconds), simply run: ---- # crm_attribute --name cluster-delay --update 30s ---- To go back to the cluster's default value, you can delete the value, for example: ---- # crm_attribute --name cluster-delay --delete Deleted crm_config option: id=cib-bootstrap-options-cluster-delay name=cluster-delay ---- === When Options are Listed More Than Once === If you ever see something like the following, it means that the option you're modifying is present more than once. .Deleting an option that is listed twice ======= ------ # crm_attribute --name batch-limit --delete Multiple attributes match name=batch-limit in crm_config: Value: 50 (set=cib-bootstrap-options, id=cib-bootstrap-options-batch-limit) Value: 100 (set=custom, id=custom-batch-limit) Please choose from one of the matches above and supply the 'id' with --id ------- ======= In such cases, follow the on-screen instructions to perform the requested action. To determine which value is currently being used by the cluster, refer to <>. diff --git a/doc/Pacemaker_Explained/en-US/Ch-Resources.txt b/doc/Pacemaker_Explained/en-US/Ch-Resources.txt index 9453954d8e..bb4f101013 100644 --- a/doc/Pacemaker_Explained/en-US/Ch-Resources.txt +++ b/doc/Pacemaker_Explained/en-US/Ch-Resources.txt @@ -1,835 +1,838 @@ = Cluster Resources = == What is a Cluster Resource? == indexterm:[Resource] A resource is a service made highly available by a cluster. The simplest type of resource, a 'primitive' resource, is described in this chapter. More complex forms, such as groups and clones, are described in later chapters. Every primitive resource has a 'resource agent'. A resource agent is an external program that abstracts the service it provides and present a consistent view to the cluster. This allows the cluster to be agnostic about the resources it manages. The cluster doesn't need to understand how the resource works because it relies on the resource agent to do the right thing when given a `start`, `stop` or `monitor` command. For this reason, it is crucial that resource agents are well-tested. Typically, resource agents come in the form of shell scripts. However, they can be written using any technology (such as C, Python or Perl) that the author is comfortable with. [[s-resource-supported]] == Resource Classes == indexterm:[Resource,class] Pacemaker supports several classes of agents: * OCF * LSB * Upstart * Systemd * Service * Fencing * Nagios Plugins === Open Cluster Framework === indexterm:[Resource,OCF] indexterm:[OCF,Resources] indexterm:[Open Cluster Framework,Resources] The OCF standard footnote:[See http://www.opencf.org/cgi-bin/viewcvs.cgi/specs/ra/resource-agent-api.txt?rev=HEAD -- at least as it relates to resource agents. The Pacemaker implementation has been somewhat extended from the OCF specs, but none of those changes are incompatible with the original OCF specification.] is basically an extension of the Linux Standard Base conventions for init scripts to: * support parameters, * make them self-describing, and * make them extensible OCF specs have strict definitions of the exit codes that actions must return. footnote:[ The resource-agents source code includes the `ocf-tester` script, which can be useful in this regard. ] The cluster follows these specifications exactly, and giving the wrong exit code will cause the cluster to behave in ways you will likely find puzzling and annoying. In particular, the cluster needs to distinguish a completely stopped resource from one which is in some erroneous and indeterminate state. Parameters are passed to the resource agent as environment variables, with the special prefix +OCF_RESKEY_+. So, a parameter which the user thinks of as +ip+ will be passed to the resource agent as +OCF_RESKEY_ip+. The number and purpose of the parameters is left to the resource agent; however, the resource agent should use the `meta-data` command to advertise any that it supports. The OCF class is the most preferred as it is an industry standard, highly flexible (allowing parameters to be passed to agents in a non-positional manner) and self-describing. For more information, see the http://www.linux-ha.org/wiki/OCF_Resource_Agents[reference] and <>. === Linux Standard Base === indexterm:[Resource,LSB] indexterm:[LSB,Resources] indexterm:[Linux Standard Base,Resources] LSB resource agents are those found in +/etc/init.d+. Generally, they are provided by the OS distribution and, in order to be used with the cluster, they must conform to the LSB Spec. footnote:[ See http://refspecs.linux-foundation.org/LSB_3.0.0/LSB-Core-generic/LSB-Core-generic/iniscrptact.html for the LSB Spec as it relates to init scripts. ] [WARNING] ==== Many distributions claim LSB compliance but ship with broken init scripts. For details on how to check whether your init script is LSB-compatible, see <>. Common problematic violations of the LSB standard include: * Not implementing the status operation at all * Not observing the correct exit status codes for `start/stop/status` actions * Starting a started resource returns an error * Stopping a stopped resource returns an error ==== [IMPORTANT] ==== Remember to make sure the computer is _not_ configured to start any services at boot time -- that should be controlled by the cluster. ==== === Systemd === indexterm:[Resource,Systemd] indexterm:[Systemd,Resources] Some newer distributions have replaced the old http://en.wikipedia.org/wiki/Init#SysV-style["SysV"] style of initialization daemons and scripts with an alternative called http://www.freedesktop.org/wiki/Software/systemd[Systemd]. Pacemaker is able to manage these services _if they are present_. Instead of init scripts, systemd has 'unit files'. Generally, the services (unit files) are provided by the OS distribution, but there are online guides for converting from init scripts. footnote:[For example, http://0pointer.de/blog/projects/systemd-for-admins-3.html] [IMPORTANT] ==== Remember to make sure the computer is _not_ configured to start any services at boot time -- that should be controlled by the cluster. ==== === Upstart === indexterm:[Resource,Upstart] indexterm:[Upstart,Resources] Some newer distributions have replaced the old http://en.wikipedia.org/wiki/Init#SysV-style["SysV"] style of initialization daemons (and scripts) with an alternative called http://upstart.ubuntu.com/[Upstart]. Pacemaker is able to manage these services _if they are present_. Instead of init scripts, upstart has 'jobs'. Generally, the services (jobs) are provided by the OS distribution. [IMPORTANT] ==== Remember to make sure the computer is _not_ configured to start any services at boot time -- that should be controlled by the cluster. ==== === System Services === indexterm:[Resource,System Services] indexterm:[System Service,Resources] Since there are various types of system services (+systemd+, +upstart+, and +lsb+), Pacemaker supports a special +service+ alias which intelligently figures out which one applies to a given cluster node. This is particularly useful when the cluster contains a mix of +systemd+, +upstart+, and +lsb+. In order, Pacemaker will try to find the named service as: . an LSB init script . a Systemd unit file . an Upstart job === STONITH === indexterm:[Resource,STONITH] indexterm:[STONITH,Resources] The STONITH class is used exclusively for fencing-related resources. This is discussed later in <>. === Nagios Plugins === indexterm:[Resource,Nagios Plugins] indexterm:[Nagios Plugins,Resources] Nagios Plugins footnote:[The project has two independent forks, hosted at https://www.nagios-plugins.org/ and https://www.monitoring-plugins.org/. Output from both projects' plugins is similar, so plugins from either project can be used with pacemaker.] allow us to monitor services on remote hosts. Pacemaker is able to do remote monitoring with the plugins _if they are present_. A common use case is to configure them as resources belonging to a resource container (usually a virtual machine), and the container will be restarted if any of them has failed. Another use is to configure them as ordinary resources to be used for monitoring hosts or services via the network. The supported parameters are same as the long options of the plugin. [[primitive-resource]] == Resource Properties == These values tell the cluster which resource agent to use for the resource, where to find that resource agent and what standards it conforms to. .Properties of a Primitive Resource [width="95%",cols="1m,6<",options="header",align="center"] |========================================================= |Field |Description |id |Your name for the resource indexterm:[id,Resource] indexterm:[Resource,Property,id] |class |The standard the resource agent conforms to. Allowed values: +lsb+, +nagios+, +ocf+, +service+, +stonith+, +systemd+, +upstart+ indexterm:[class,Resource] indexterm:[Resource,Property,class] |type |The name of the Resource Agent you wish to use. E.g. +IPaddr+ or +Filesystem+ indexterm:[type,Resource] indexterm:[Resource,Property,type] |provider |The OCF spec allows multiple vendors to supply the same resource agent. To use the OCF resource agents supplied by the Heartbeat project, you would specify +heartbeat+ here. indexterm:[provider,Resource] indexterm:[Resource,Property,provider] |========================================================= The XML definition of a resource can be queried with the `crm_resource` tool. For example: ---- # crm_resource --resource Email --query-xml ---- might produce: .A system resource definition ===== [source,XML] ===== [NOTE] ===== One of the main drawbacks to system services (LSB, systemd or Upstart) resources is that they do not allow any parameters! ===== //// See https://tools.ietf.org/html/rfc5737 for choice of example IP address //// .An OCF resource definition ===== [source,XML] ------- ------- ===== [[s-resource-options]] == Resource Options == Resources have two types of options: 'meta-attributes' and 'instance attributes'. Meta-attributes apply to any type of resource, while instance attributes are specific to each resource agent. === Resource Meta-Attributes === Meta-attributes are used by the cluster to decide how a resource should behave and can be easily set using the `--meta` option of the `crm_resource` command. .Meta-attributes of a Primitive Resource [width="95%",cols="2m,2,5> resources, they will not be promoted to master) * +master:+ Allow the resource to be started and, if appropriate, promoted indexterm:[target-role,Resource Option] indexterm:[Resource,Option,target-role] |is-managed |TRUE |Is the cluster allowed to start and stop the resource? Allowed values: +true+, +false+ indexterm:[is-managed,Resource Option] indexterm:[Resource,Option,is-managed] |resource-stickiness |value of +resource-stickiness+ in the +rsc_defaults+ section |How much does the resource prefer to stay where it is? indexterm:[resource-stickiness,Resource Option] indexterm:[Resource,Option,resource-stickiness] |requires |fencing (unless +stonith-enabled+ is +false+ or +class+ is +stonith+, in which case it defaults to quorum) |Conditions under which the resource can be started ('Since 1.1.8') Allowed values: * +nothing:+ can always be started * +quorum:+ The cluster can only start this resource if a majority of the configured nodes are active * +fencing:+ The cluster can only start this resource if a majority of the configured nodes are active _and_ any failed or unknown nodes have been powered off * +unfencing:+ The cluster can only start this resource if a majority of the configured nodes are active _and_ any failed or unknown nodes have been powered off _and_ only on nodes that have been 'unfenced' indexterm:[requires,Resource Option] indexterm:[Resource,Option,requires] |migration-threshold |INFINITY |How many failures may occur for this resource on a node, before this node is marked ineligible to host this resource. A value of INFINITY indicates that this feature is disabled. indexterm:[migration-threshold,Resource Option] indexterm:[Resource,Option,migration-threshold] |failure-timeout |0 |How many seconds to wait before acting as if the failure had not occurred, and potentially allowing the resource back to the node on which it failed. A value of 0 indicates that this feature is disabled. + As with any time-based actions, this is not guaranteed to be checked more + frequently than the value of +cluster-recheck-interval+ (see + <>). indexterm:[failure-timeout,Resource Option] indexterm:[Resource,Option,failure-timeout] |multiple-active |stop_start |What should the cluster do if it ever finds the resource active on more than one node? Allowed values: * +block:+ mark the resource as unmanaged * +stop_only:+ stop all active instances and leave them that way * +stop_start:+ stop all active instances and start the resource in one location only indexterm:[multiple-active,Resource Option] indexterm:[Resource,Option,multiple-active] |remote-node | |The name of the remote-node this resource defines. This both enables the resource as a remote-node and defines the unique name used to identify the remote-node. If no other parameters are set, this value will also be assumed as the hostname to connect to at the port specified by +remote-port+. +WARNING:+ This value cannot overlap with any resource or node IDs. If not specified, this feature is disabled. |remote-port |3121 |Port to use for the guest connection to pacemaker_remote |remote-addr |value of +remote-node+ |The IP address or hostname to connect to if remote-node's name is not the hostname of the guest. |+remote-connect-timeout+ |60s |How long before a pending guest connection will time out. |========================================================= [NOTE] ==== Support for remote nodes was added in pacemaker 1.1.10. If you are using an earlier version, options related to remote nodes will not be available. ==== As an example of setting resource options, if you performed the following commands on an LSB Email resource: ------- # crm_resource --meta --resource Email --set-parameter priority --parameter-value 100 # crm_resource -m -r Email -p multiple-active -v block ------- the resulting resource definition might be: .An LSB resource with cluster options ===== [source,XML] ------- ------- ===== [[s-resource-defaults]] === Setting Global Defaults for Resource Meta-Attributes === To set a default value for a resource option, add it to the +rsc_defaults+ section with `crm_attribute`. For example, ---- # crm_attribute --type rsc_defaults --name is-managed --update false ---- would prevent the cluster from starting or stopping any of the resources in the configuration (unless of course the individual resources were specifically enabled by having their +is-managed+ set to +true+). === Resource Instance Attributes === The resource agents of some resource classes (lsb, systemd and upstart 'not' among them) can be given parameters which determine how they behave and which instance of a service they control. If your resource agent supports parameters, you can add them with the `crm_resource` command. For example, ---- # crm_resource --resource Public-IP --set-parameter ip --parameter-value 192.0.2.2 ---- would create an entry in the resource like this: .An example OCF resource with instance attributes ===== [source,XML] ------- ------- ===== For an OCF resource, the result would be an environment variable called +OCF_RESKEY_ip+ with a value of +192.0.2.2+. The list of instance attributes supported by an OCF resource agent can be found by calling the resource agent with the `meta-data` command. The output contains an XML description of all the supported attributes, their purpose and default values. .Displaying the metadata for the Dummy resource agent template ===== ---- # export OCF_ROOT=/usr/lib/ocf # $OCF_ROOT/resource.d/pacemaker/Dummy meta-data ---- [source,XML] ------- 1.0 This is a Dummy Resource Agent. It does absolutely nothing except keep track of whether its running or not. Its purpose in life is for testing and to serve as a template for RA writers. NB: Please pay attention to the timeouts specified in the actions section below. They should be meaningful for the kind of resource the agent manages. They should be the minimum advised timeouts, but they shouldn't/cannot cover _all_ possible resource instances. So, try to be neither overly generous nor too stingy, but moderate. The minimum timeouts should never be below 10 seconds. Example stateless resource agent Location to store the resource state in. State file Fake attribute that can be changed to cause a reload Fake attribute that can be changed to cause a reload Number of seconds to sleep during operations. This can be used to test how the cluster reacts to operation timeouts. Operation sleep duration in seconds. ------- ===== == Resource Operations == indexterm:[Resource,Action] 'Operations' are actions the cluster can perform on a resource by calling the resource agent. Resource agents must support certain common operations such as start, stop and monitor, and may implement any others. Some operations are generated by the cluster itself, for example, stopping and starting resources as needed. You can configure operations in the cluster configuration. As an example, by default the cluster will 'not' ensure your resources stay healthy once they are started. footnote:[Currently, anyway. Automatic monitoring operations may be added in a future version of Pacemaker.] To instruct the cluster to do this, you need to add a +monitor+ operation to the resource's definition. .An OCF resource with a recurring health check ===== [source,XML] ------- ------- ===== .Properties of an Operation [width="95%",cols="2m,3,6>. indexterm:[interval,Action Property] indexterm:[Action,Property,interval] |timeout | |How long to wait before declaring the action has failed indexterm:[timeout,Action Property] indexterm:[Action,Property,timeout] |on-fail |restart '(except for stop operations, which default to' fence 'when STONITH is enabled and' block 'otherwise)' |The action to take if this action ever fails. Allowed values: * +ignore:+ Pretend the resource did not fail. * +block:+ Don't perform any further operations on the resource. * +stop:+ Stop the resource and do not start it elsewhere. * +restart:+ Stop the resource and start it again (possibly on a different node). * +fence:+ STONITH the node on which the resource failed. * +standby:+ Move _all_ resources away from the node on which the resource failed. indexterm:[on-fail,Action Property] indexterm:[Action,Property,on-fail] |enabled |TRUE |If +false+, ignore this operation definition. This is typically used to pause a particular recurring monitor operation; for instance, it can complement the respective resource being unmanaged (+is-managed=false+), as this alone will <>. Disabling the operation does not suppress all actions of the given type. Allowed values: +true+, +false+. indexterm:[enabled,Action Property] indexterm:[Action,Property,enabled] |record-pending | |If +true+, the intention to perform the operation is recorded so that GUIs and CLI tools can indicate that an operation is in progress. This is best set as an 'operation default' (see next section). Allowed values: +true+, +false+. indexterm:[enabled,Action Property] indexterm:[Action,Property,enabled] |role | |Run the operation only on node(s) that the cluster thinks should be in the specified role. This only makes sense for recurring monitor operations. Allowed (case-sensitive) values: +Stopped+, +Started+, and in the case of <> resources, +Slave+ and +Master+. indexterm:[role,Action Property] indexterm:[Action,Property,role] |========================================================= [[s-resource-monitoring]] === Monitoring Resources for Failure === When Pacemaker first starts a resource, it runs one-time monitor operations (referred to as 'probes') to ensure the resource is running where it's supposed to be, and not running where it's not supposed to be. (This behavior can be affected by the +resource-discovery+ location constraint property.) Other than those initial probes, Pacemaker will not (by default) check that the resource continues to stay healthy. As in the example above, you must configure monitor operations explicitly to perform these checks. By default, a monitor operation will ensure that the resource is running where it is supposed to. The +target-role+ property can be used for further checking. For example, if a resource has one monitor operation with +interval=10 role=Started+ and a second monitor operation with +interval=11 role=Stopped+, the cluster will run the first monitor on any nodes it thinks 'should' be running the resource, and the second monitor on any nodes that it thinks 'should not' be running the resource (for the truly paranoid, who want to know when an administrator manually starts a service by mistake). [[s-monitoring-unmanaged]] === Monitoring Resources When Administration is Disabled === Recurring monitor operations behave differently under various administrative settings: * When a resource is unmanaged (by setting +is-managed=false+): No monitors will be stopped. + If the unmanaged resource is stopped on a node where the cluster thinks it should be running, the cluster will detect and report that it is not, but it will not consider the monitor failed, and will not try to start the resource until it is managed again. + Starting the unmanaged resource on a different node is strongly discouraged and will at least cause the cluster to consider the resource failed, and may require the resource's +target-role+ to be set to +Stopped+ then +Started+ to be recovered. * When a node is put into standby: All resources will be moved away from the node, and all monitor operations will be stopped on the node, except those with +role=Stopped+. Monitor operations with +role=Stopped+ will be started on the node if appropriate. * When the cluster is put into maintenance mode: All resources will be marked as unmanaged. All monitor operations will be stopped, except those with +role=Stopped+. As with single unmanaged resources, starting a resource on a node other than where the cluster expects it to be will cause problems. [[s-operation-defaults]] === Setting Global Defaults for Operations === You can change the global default values for operation properties in a given cluster. These are defined in an +op_defaults+ section of the CIB's +configuration+ section, and can be set with `crm_attribute`. For example, ---- # crm_attribute --type op_defaults --name timeout --update 20s ---- would default each operation's +timeout+ to 20 seconds. If an operation's definition also includes a value for +timeout+, then that value would be used for that operation instead. === When Implicit Operations Take a Long Time === The cluster will always perform a number of implicit operations: +start+, +stop+ and a non-recurring +monitor+ operation used at startup to check whether the resource is already active. If one of these is taking too long, then you can create an entry for them and specify a longer timeout. .An OCF resource with custom timeouts for its implicit actions ===== [source,XML] ------- ------- ===== === Multiple Monitor Operations === Provided no two operations (for a single resource) have the same name and interval, you can have as many monitor operations as you like. In this way, you can do a superficial health check every minute and progressively more intense ones at higher intervals. To tell the resource agent what kind of check to perform, you need to provide each monitor with a different value for a common parameter. The OCF standard creates a special parameter called +OCF_CHECK_LEVEL+ for this purpose and dictates that it is "made available to the resource agent without the normal +OCF_RESKEY+ prefix". Whatever name you choose, you can specify it by adding an +instance_attributes+ block to the +op+ tag. It is up to each resource agent to look for the parameter and decide how to use it. .An OCF resource with two recurring health checks, performing different levels of checks specified via +OCF_CHECK_LEVEL+. ===== [source,XML] ------- ------- ===== === Disabling a Monitor Operation === The easiest way to stop a recurring monitor is to just delete it. However, there can be times when you only want to disable it temporarily. In such cases, simply add +enabled="false"+ to the operation's definition. .Example of an OCF resource with a disabled health check ===== [source,XML] ------- ------- ===== This can be achieved from the command line by executing: ---- # cibadmin --modify --xml-text '' ---- Once you've done whatever you needed to do, you can then re-enable it with ---- # cibadmin --modify --xml-text '' ---- diff --git a/doc/Pacemaker_Remote/en-US/Ch-Options.txt b/doc/Pacemaker_Remote/en-US/Ch-Options.txt index f04b8b6e94..5faaaf2713 100644 --- a/doc/Pacemaker_Remote/en-US/Ch-Options.txt +++ b/doc/Pacemaker_Remote/en-US/Ch-Options.txt @@ -1,121 +1,121 @@ = Configuration Explained = The walk-through examples use some of these options, but don't explain exactly what they mean or do. This section is meant to be the go-to resource for all the options available for configuring pacemaker_remote-based nodes. (((configuration))) == Resource Meta-Attributes for Guest Nodes == When configuring a virtual machine to use as a guest node, these are the metadata options available to enable the resource as a guest node and define its connection parameters. .Meta-attributes for configuring VM resources as guest nodes [width="95%",cols="2m,1,4<",options="header",align="center"] |========================================================= |Option |Default |Description |remote-node |'none' |The node name of the guest node this resource defines. This both enables the resource as a guest node and defines the unique name used to identify the guest node. If no other parameters are set, this value will also be assumed as the hostname to use when connecting to pacemaker_remote on the VM. This value *must not* overlap with any resource or node IDs. |remote-port |3121 |The port on the virtual machine that the cluster will use to connect to pacemaker_remote. |remote-addr |'value of' +remote-node+ |The IP address or hostname to use when connecting to pacemaker_remote on the VM. |remote-connect-timeout |60s |How long before a pending guest connection will time out. |========================================================= == Connection Resources for Remote Nodes == A remote node is defined by a connection resource. That connection resource has instance attributes that define where the remote node is located on the network and how to communicate with it. Descriptions of these instance attributes can be retrieved using the following `pcs` command: ---- # pcs resource describe remote ocf:pacemaker:remote - remote resource agent Resource options: server: Server location to connect to. This can be an ip address or hostname. port: tcp port to connect to. - reconnect_interval: Time in seconds to wait before attempting to reconnect to - a remote node after an active connection to the remote - node has been severed. This wait is recurring. If - reconnect fails after the wait period, a new reconnect - attempt will be made after observing the wait time. When - this option is in use, pacemaker will keep attempting to - reach out and connect to the remote node indefinitely - after each wait interval. + reconnect_interval: Interval in seconds at which Pacemaker will attempt to + reconnect to a remote node after an active connection to + the remote node has been severed. When this value is + nonzero, Pacemaker will retry the connection + indefinitely, at the specified interval. As with any + time-based actions, this is not guaranteed to be checked + more frequently than the value of the + cluster-recheck-interval cluster option. ---- When defining a remote node's connection resource, it is common and recommended to name the connection resource the same as the remote node's hostname. By default, if no *server* option is provided, the cluster will attempt to contact the remote node using the resource name as the hostname. Example defining a remote node with the hostname *remote1*: ---- # pcs resource create remote1 remote ---- Example defining a remote node to connect to a specific IP address and port: ---- # pcs resource create remote1 remote server=192.168.122.200 port=8938 ---- == Environment Variables for Daemon Start-up == Authentication and encryption of the connection between cluster nodes and nodes running pacemaker_remote is achieved using with https://en.wikipedia.org/wiki/TLS-PSK[TLS-PSK] encryption/authentication over TCP (port 3121 by default). This means that both the cluster node and remote node must share the same private key. By default, this key is placed at +/etc/pacemaker/authkey+ on each node. You can change the default port and/or key location for Pacemaker and pacemaker_remote via environment variables. These environment variables can be enabled by placing them in the +/etc/sysconfig/pacemaker+ file. ---- #==#==# Pacemaker Remote # Use a custom directory for finding the authkey. PCMK_authkey_location=/etc/pacemaker/authkey # # Specify a custom port for Pacemaker Remote connections PCMK_remote_port=3121 ---- == Removing Remote Nodes and Guest Nodes == If the resource creating a guest node, or the *ocf:pacemaker:remote* resource creating a connection to a remote node, is removed from the configuration, the affected node will continue to show up in output as an offline node. If you want to get rid of that output, run (replacing $NODE_NAME appropriately): ---- # crm_node --force --remove $NODE_NAME ---- [WARNING] ========= Be absolutely sure that the node's resource has been deleted from the configuration first. ========= diff --git a/extra/resources/ClusterMon b/extra/resources/ClusterMon index 8efdf1beae..5d1472d1a9 100644 --- a/extra/resources/ClusterMon +++ b/extra/resources/ClusterMon @@ -1,267 +1,267 @@ #!/bin/bash # # # ClusterMon OCF RA. # Starts crm_mon in background which logs cluster status as # html to the specified file. # # Copyright (c) 2004 SUSE LINUX AG, Lars Marowsky-Brée # All Rights Reserved. # # This program is free software; you can redistribute it and/or modify # it under the terms of version 2 of the GNU General Public License as # published by the Free Software Foundation. # # This program is distributed in the hope that it would be useful, but # WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. # # Further, this software is distributed without any warranty that it is # free of the rightful claim of any third person regarding infringement # or the like. Any license provided herein, whether implied or # otherwise, applies only to this software file. Patent licenses, if # any, provided herein do not apply to combinations of this program with # other software, or any other product whatsoever. # # You should have received a copy of the GNU General Public License # along with this program; if not, write the Free Software Foundation, # Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. # # OCF instance parameters: # OCF_RESKEY_user # OCF_RESKEY_pidfile # OCF_RESKEY_update # OCF_RESKEY_extra_options # OCF_RESKEY_htmlfile ####################################################################### # Initialization: : ${OCF_FUNCTIONS=${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs} . ${OCF_FUNCTIONS} : ${__OCF_ACTION=$1} ####################################################################### meta_data() { cat < - + 1.0 This is a ClusterMon Resource Agent. It outputs current cluster status to the html. Runs crm_mon in the background, recording the cluster status to an HTML file The user we want to run crm_mon as The user we want to run crm_mon as How frequently should we update the cluster status Update interval Additional options to pass to crm_mon. Eg. -n -r Extra options PID file location to ensure only one instance is running PID file Location to write HTML output to. HTML output END } ####################################################################### ClusterMon_usage() { cat </dev/null 2>&1; rc=$? case $rc in 0) exit $OCF_SUCCESS;; 1) exit $OCF_NOT_RUNNING;; *) exit $OCF_ERR_GENERIC;; esac fi fi exit $OCF_NOT_RUNNING } CheckOptions() { while getopts Vi:nrh:cdp: OPTION do case $OPTION in V|n|r|c|d);; i) ocf_log warn "You should not have specified the -i option, since OCF_RESKEY_update is set already!";; h) ocf_log warn "You should not have specified the -h option, since OCF_RESKEY_htmlfile is set already!";; p) ocf_log warn "You should not have specified the -p option, since OCF_RESKEY_pidfile is set already!";; *) return $OCF_ERR_ARGS;; esac done if [ $? -ne 0 ]; then return $OCF_ERR_ARGS fi # We should have eaten all options at this stage shift $(($OPTIND -1)) if [ $# -gt 0 ]; then false else true fi } ClusterMon_validate() { # Existence of the user if [ ! -z $OCF_RESKEY_user ]; then getent passwd "$OCF_RESKEY_user" >/dev/null if [ $? -eq 0 ]; then : Yes, user exists. We can further check his permission on crm_mon if necessary else ocf_log err "The user $OCF_RESKEY_user does not exist!" exit $OCF_ERR_ARGS fi fi # Pidfile better be an absolute path case $OCF_RESKEY_pidfile in /*) ;; *) ocf_log warn "You should have pidfile($OCF_RESKEY_pidfile) of absolute path!" ;; esac # Check the update interval if ocf_is_decimal "$OCF_RESKEY_update" && [ $OCF_RESKEY_update -gt 0 ]; then : else ocf_log err "Invalid update interval $OCF_RESKEY_update. It should be positive integer!" exit $OCF_ERR_ARGS fi if CheckOptions $OCF_RESKEY_extra_options; then : else ocf_log err "Invalid options $OCF_RESKEY_extra_options!" exit $OCF_ERR_ARGS fi # Htmlfile better be an absolute path case $OCF_RESKEY_htmlfile in /*) ;; *) ocf_log warn "You should have htmlfile($OCF_RESKEY_htmlfile) of absolute path!" ;; esac echo "Validate OK" return $OCF_SUCCESS } if [ $# -ne 1 ]; then ClusterMon_usage exit $OCF_ERR_ARGS fi : ${OCF_RESKEY_update:="15000"} : ${OCF_RESKEY_pidfile:="/tmp/ClusterMon_${OCF_RESOURCE_INSTANCE}.pid"} : ${OCF_RESKEY_htmlfile:="/tmp/ClusterMon_${OCF_RESOURCE_INSTANCE}.html"} OCF_RESKEY_update=`expr $OCF_RESKEY_update / 1000` case $__OCF_ACTION in meta-data) meta_data exit $OCF_SUCCESS ;; start) ClusterMon_start ;; stop) ClusterMon_stop ;; monitor) ClusterMon_monitor ;; validate-all) ClusterMon_validate ;; usage|help) ClusterMon_usage exit $OCF_SUCCESS ;; *) ClusterMon_usage exit $OCF_ERR_UNIMPLEMENTED ;; esac exit $? diff --git a/extra/resources/HealthCPU b/extra/resources/HealthCPU index 32a10ad3e7..c5fbb5372a 100644 --- a/extra/resources/HealthCPU +++ b/extra/resources/HealthCPU @@ -1,222 +1,222 @@ #!/bin/sh # # # HealthCPU OCF RA. Measures CPUs idling and writes # #health-cpu status into the CIB # # Copyright (c) 2009 Michael Schwartzkopff # in collaboration with the Bull company. Merci! # # All Rights Reserved. # # This program is free software; you can redistribute it and/or modify # it under the terms of version 2 of the GNU General Public License as # published by the Free Software Foundation. # # This program is distributed in the hope that it would be useful, but # WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. # # Further, this software is distributed without any warranty that it is # free of the rightful claim of any third person regarding infringement # or the like. Any license provided herein, whether implied or # otherwise, applies only to this software file. Patent licenses, if # any, provided herein do not apply to combinations of this program with # other software, or any other product whatsoever. # # You should have received a copy of the GNU General Public License # along with this program; if not, write the Free Software Foundation, # Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. # ################################ # # TODO: Enter default values # Error handling in getting uptime # ################################## ####################################################################### # Initialization: : ${OCF_FUNCTIONS=${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs} . ${OCF_FUNCTIONS} : ${__OCF_ACTION=$1} ####################################################################### meta_data() { cat < -0.1 +1.0 Systhem health agent that measures the CPU idling and updates the #health-cpu attribute. System health CPU usage Location to store the resource state in. State file Lower (!) limit of idle percentage to switch the health attribute to yellow. I.e. the #health-cpu will go yellow if the %idle of the CPU falls below 50%. Lower limit for yellow health attribute Lower (!) limit of idle percentage to switch the health attribute to red. I.e. the #health-cpu will go red if the %idle of the CPU falls below 10%. Lower limit for red health attribute END } ####################################################################### # don't exit on TERM, to test that lrmd makes sure that we do exit trap sigterm_handler TERM sigterm_handler() { ocf_log info "They use TERM to bring us down. No such luck." return } dummy_usage() { cat < -0.1 +1.0 Systhem health agent that checks the S.M.A.R.T. status of the given drives and updates the #health-smart attribute. SMART health status Location to store the resource state in. State file The drive(s) to check as a SPACE separated list. Enter the full path to the device, e.g. "/dev/sda". Drives to check The device type(s) to assume for the drive(s) being tested as a SPACE separated list. Device types Lower limit of the temperature in deg C of the drive(s). Below this limit the status will be red. Lower limit for the red smart attribute Upper limit of the temperature if deg C of the drives(s). If the drive reports a temperature higher than this value the status of #health-smart will be red. Upper limit for red smart attribute Number of deg C below/above the upper/lower temp limits at which point the status of #health-smart will change to yellow. Deg C below/above the upper limits for yellow smart attribute END } ####################################################################### check_temperature() { if [ $1 -lt ${lower_red_limit} ] ; then ocf_log info "Drive ${DRIVE} ${DEVICE} too cold: ${1} C" $ATTRDUP -n "#health-smart" -U "red" -d "5s" return 1 fi if [ $1 -gt ${upper_red_limit} ] ; then ocf_log info "Drive ${DRIVE} ${DEVICE} too hot: ${1} C" $ATTRDUP -n "#health-smart" -U "red" -d "5s" return 1 fi if [ $1 -lt ${lower_yellow_limit} ] ; then ocf_log info "Drive ${DRIVE} ${DEVICE} quite cold: ${1} C" $ATTRDUP -n "#health-smart" -U "yellow" -d "5s" return 1 fi if [ $1 -gt ${upper_yellow_limit} ] ; then ocf_log info "Drive ${DRIVE} ${DEVICE} quite hot: ${1} C" $ATTRDUP -n "#health-smart" -U "yellow" -d "5s" return 1 fi } init_smart() { #Set temperature defaults if [ -z ${OCF_RESKEY_temp_warning} ]; then yellow_threshold=5 else yellow_threshold=${OCF_RESKEY_temp_warning} fi if [ -z ${OCF_RESKEY_temp_lower_limit} ] ; then lower_red_limit=0 else lower_red_limit=${OCF_RESKEY_temp_lower_limit} fi lower_yellow_limit=$((${lower_red_limit}+${yellow_threshold})) if [ -z ${OCF_RESKEY_temp_upper_limit} ] ; then upper_red_limit=60 else upper_red_limit=${OCF_RESKEY_temp_upper_limit} fi upper_yellow_limit=$((${upper_red_limit}-${yellow_threshold})) #Set disk defaults if [ -z "${OCF_RESKEY_drives}" ] ; then DRIVES="/dev/sda" else DRIVES=${OCF_RESKEY_drives} fi #Test for presence of smartctl if [ ! -x $SMARTCTL ] ; then ocf_log err "${SMARTCTL} not installed." exit $OCF_ERR_INSTALLED fi for DRIVE in $DRIVES; do if [ "${OCF_RESKEY_devices}" ]; then for DEVICE in ${OCF_RESKEY_devices}; do $SMARTCTL -d $DEVICE -i ${DRIVE} | grep -q "SMART support is: Enabled" if [ $? -ne "0" ] ; then ocf_log err "S.M.A.R.T. not enabled for drive "${DRIVE} exit $OCF_ERR_INSTALLED fi done else $SMARTCTL -i ${DRIVE} | grep -q "SMART support is: Enabled" if [ $? -ne "0" ] ; then ocf_log err "S.M.A.R.T. not enabled for drive "${DRIVE} exit $OCF_ERR_INSTALLED fi fi done } HealthSMART_usage() { cat < - + 1.0 This is a SysInfo Resource Agent. It records (in the CIB) various attributes of a node Sample Linux output: arch: i686 os: Linux-2.4.26-gentoo-r14 free_swap: 1999 cpu_info: Intel(R) Celeron(R) CPU 2.40GHz cpu_speed: 4771.02 cpu_cores: 1 cpu_load: 0.00 ram_total: 513 ram_free: 117 root_free: 2.4 #health_disk: red Sample Darwin output: arch: i386 os: Darwin-8.6.2 cpu_info: Intel Core Duo cpu_speed: 2.16 cpu_cores: 2 cpu_load: 0.18 ram_total: 2016 ram_free: 787 root_free: 13 #health_disk: green Units: free_swap: Mb ram_*: Mb cpu_speed (Linux): bogomips cpu_speed (Darwin): Ghz *_free: GB (or user-defined: disk_unit) SysInfo resource agent PID file PID file Interval to allow values to stabilize Dampening Delay Filesystems or Paths to be queried for free disk space as a SPACE separated list - e.g "/dev/sda1 /tmp". Results will be written to an attribute with leading slashes removed, and other slashes replaced with underscore, and the word 'free' appended - e.g for /dev/sda1 it would be 'dev_sda1_free'. Note: The root filesystem '/' is always queried to an attribute named 'root_free' List of Filesytems/Paths to query for free disk space Unit to report disk free space in. Can be one of: B, K, M, G, T, P (case-insensitive) Unit to report disk free space in The amount of free space required in monitored disks. If any of the monitored disks has less than this amount of free space, , with the node attribute "#health_disk" changing to "red", all resources will move away from the node. Set the node-health-strategy property appropriately for this to take effect. If the unit is not specified, it defaults to disk_unit. minimum disk free space required END } ####################################################################### UpdateStat() { name=$1; shift value="$*" printf "%s:\t%s\n" "$name" "$value" if [ "$__OCF_ACTION" = "start" ] ; then ${HA_SBIN_DIR}/attrd_updater ${OCF_RESKEY_delay} -S status -n $name -B "$value" else ${HA_SBIN_DIR}/attrd_updater ${OCF_RESKEY_delay} -S status -n $name -v "$value" fi } SysInfoStats() { UpdateStat arch "`uname -m`" UpdateStat os "`uname -s`-`uname -r`" case `uname -s` in "Darwin") mem=`top -l 1 | grep Mem: | awk '{print $10}'` mem_used=`top -l 1 | grep Mem: | awk '{print $8}'` mem=`SysInfo_mem_units $mem` mem_used=`SysInfo_mem_units $mem_used` mem_total=`expr $mem_used + $mem` cpu_type=`system_profiler SPHardwareDataType | awk -F': ' '/^CPU Type/ {print $2; exit}'` cpu_speed=`system_profiler SPHardwareDataType | awk -F': ' '/^CPU Speed/ {print $2; exit}'` cpu_cores=`system_profiler SPHardwareDataType | awk -F': ' '/^Number Of/ {print $2; exit}'` ;; "Linux") if [ -f /proc/cpuinfo ]; then cpu_type=`awk -F': ' '/model name/ {print $2; exit}' /proc/cpuinfo` cpu_speed=`awk -F': ' '/bogomips/ {print $2; exit}' /proc/cpuinfo` cpu_cores=`grep "^processor" /proc/cpuinfo | wc -l` fi if [ -f /proc/meminfo ]; then # meminfo results are in kB mem=`grep "SwapFree" /proc/meminfo | awk '{print $2"k"}'` if [ ! -z $mem ]; then UpdateStat free_swap `SysInfo_mem_units $mem` fi mem=`grep "Inactive" /proc/meminfo | awk '{print $2"k"}'` mem_total=`grep "MemTotal" /proc/meminfo | awk '{print $2"k"}'` else mem=`top -n 1 | grep Mem: | awk '{print $7}'` fi ;; *) esac if [ x != x"$cpu_type" ]; then UpdateStat cpu_info "$cpu_type" fi if [ x != x"$cpu_speed" ]; then UpdateStat cpu_speed "$cpu_speed" fi if [ x != x"$cpu_cores" ]; then UpdateStat cpu_cores "$cpu_cores" fi loads=`uptime` load15=`echo ${loads} | awk '{print $10}'` UpdateStat cpu_load $load15 if [ ! -z "$mem" ]; then # Massage the memory values UpdateStat ram_total `SysInfo_mem_units $mem_total` UpdateStat ram_free `SysInfo_mem_units $mem` fi # Portability notes: # o tail: explicit "-n" not available in Solaris; instead simplify # 'tail -n ' to the equivalent 'tail -'. for disk in "/" ${OCF_RESKEY_disks}; do unset disk_free disk_label disk_free=`df -h ${disk} | tail -1 | awk '{print $4}'` if [ x != x"$disk_free" ]; then disk_label=`echo $disk | sed -e 's#^/$#root#;s#^/*##;s#/#_#g'` disk_free=`SysInfo_hdd_units $disk_free` UpdateStat ${disk_label}_free $disk_free if [ -n "$MIN_FREE" ]; then if [ $disk_free -le $MIN_FREE ]; then UpdateStat "#health_disk" "red" else UpdateStat "#health_disk" "green" fi fi fi done } SysInfo_megabytes() { # Size in megabytes echo $1 | awk '{ n = $0; sub(/[0-9]+(.[0-9]+)?/, ""); split(n, a, $0); n=a[1]; if ($0 == "G" || $0 == "") { n *= 1024 }; if (/^kB?/) { n /= 1024 }; printf "%d\n", n }' # Intentionaly round to an integer } SysInfo_mem_units() { mem=$1 if [ -z $1 ]; then return fi mem=$(SysInfo_megabytes "$1") # Round to the next multiple of 50 r=$(($mem % 50)) if [ $r != 0 ]; then mem=$(($mem + 50 - $r)) fi echo $mem } SysInfo_hdd_units() { # Defauts to size in gigabytes case $OCF_RESKEY_disk_unit in [Pp]) echo $(($(SysInfo_megabytes "$1") / 1024 / 1024 / 1024));; [Tt]) echo $(($(SysInfo_megabytes "$1") / 1024 / 1024));; [Gg]) echo $(($(SysInfo_megabytes "$1") / 1024));; [Mm]) echo $(SysInfo_megabytes "$1");; [Kk]) echo $(($(SysInfo_megabytes "$1") * 1024));; [Bb]) echo $(($(SysInfo_megabytes "$1") * 1024 * 1024));; *) ocf_log err "Invalid value for disk_unit: $OCF_RESKEY_disk_unit" echo $(($(SysInfo_megabytes "$1") / 1024));; esac } SysInfo_usage() { cat < $OCF_RESKEY_pidfile SysInfoStats exit $OCF_SUCCESS } SysInfo_stop() { rm $OCF_RESKEY_pidfile exit $OCF_SUCCESS } SysInfo_monitor() { if [ -f $OCF_RESKEY_pidfile ]; then clone=`cat $OCF_RESKEY_pidfile` fi if [ x$clone = x ]; then rm $OCF_RESKEY_pidfile exit $OCF_NOT_RUNNING elif [ $clone = $OCF_RESKEY_clone ]; then SysInfoStats exit $OCF_SUCCESS elif [ x$OCF_RESKEY_CRM_meta_globally_unique = xtrue -o x$OCF_RESKEY_CRM_meta_globally_unique = xTrue -o x$OCF_RESKEY_CRM_meta_globally_unique = xyes -o x$OCF_RESKEY_CRM_meta_globally_unique = xYes ]; then SysInfoStats exit $OCF_SUCCESS fi exit $OCF_NOT_RUNNING } SysInfo_validate() { return $OCF_SUCCESS } if [ $# -ne 1 ]; then SysInfo_usage exit $OCF_ERR_ARGS fi : ${OCF_RESKEY_pidfile:="${HA_VARRUN%%/}/SysInfo-${OCF_RESOURCE_INSTANCE}"} : ${OCF_RESKEY_disk_unit:="G"} : ${OCF_RESKEY_clone:="0"} if [ x != x${OCF_RESKEY_delay} ]; then OCF_RESKEY_delay="-d ${OCF_RESKEY_delay}" else OCF_RESKEY_delay="-d 0" fi MIN_FREE="" if [ -n "$OCF_RESKEY_min_disk_free" ]; then ocf_is_decimal "$OCF_RESKEY_min_disk_free" && OCF_RESKEY_min_disk_free="$OCF_RESKEY_min_disk_free$OCF_RESKEY_disk_unit" MIN_FREE=`SysInfo_hdd_units $OCF_RESKEY_min_disk_free` fi case $__OCF_ACTION in meta-data) meta_data exit $OCF_SUCCESS ;; start) SysInfo_start ;; stop) SysInfo_stop ;; monitor) SysInfo_monitor ;; validate-all) SysInfo_validate ;; usage|help) SysInfo_usage exit $OCF_SUCCESS ;; *) SysInfo_usage exit $OCF_ERR_UNIMPLEMENTED ;; esac exit $? diff --git a/extra/resources/SystemHealth b/extra/resources/SystemHealth index 658d446273..3e76fc3221 100644 --- a/extra/resources/SystemHealth +++ b/extra/resources/SystemHealth @@ -1,252 +1,252 @@ #!/bin/sh # # SystemHealth OCF RA. # # Copyright (c) 2009 International Business Machines (IBM), Mark Hamzy # All Rights Reserved. # # This program is free software; you can redistribute it and/or modify # it under the terms of version 2 of the GNU General Public License as # published by the Free Software Foundation. # # This program is distributed in the hope that it would be useful, but # WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. # # Further, this software is distributed without any warranty that it is # free of the rightful claim of any third person regarding infringement # or the like. Any license provided herein, whether implied or # otherwise, applies only to this software file. Patent licenses, if # any, provided herein do not apply to combinations of this program with # other software, or any other product whatsoever. # # You should have received a copy of the GNU General Public License # along with this program; if not, write the Free Software Foundation, # Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. # ####################################################################### # Initialization: : ${OCF_FUNCTIONS=${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs} . ${OCF_FUNCTIONS} : ${__OCF_ACTION=$1} ####################################################################### meta_data() { cat < -0.1 +1.0 This is a SystemHealth Resource Agent. It is used to monitor the health of a system via IPMI. SystemHealth resource agent END } ####################################################################### SystemHealth_usage() { cat < /dev/null 2>&1 RC=$? if [ $RC != 0 ]; then ocf_log err "servicelog_notify not found!" return $OCF_ERR_INSTALLED fi which ipmiservicelogd > /dev/null 2>&1 RC=$? if [ $RC != 0 ]; then ocf_log err "ipmiservicelogd not found!" return $OCF_ERR_INSTALLED fi test -x $OCF_RESKEY_program RC=$? if [ $RC != 0 ]; then ocf_log err "$OCF_RESKEY_program not found!" return $OCF_ERR_INSTALLED fi } SystemHealth_start() { SystemHealth_monitor RC=$? if [ $RC = $OCF_ERR_GENERIC ]; then return $OCF_ERR_GENERIC elif [ $RC = $OCF_SUCCESS ]; then ocf_log warn "starting an already started SystemHealth" return $OCF_SUCCESS fi service ipmi start > /dev/null 2>&1 RC=$? if [ $RC != 0 ]; then ocf_log err "Could not start service IPMI!" return $OCF_ERR_GENERIC fi ipmiservicelogd smi 0 > /dev/null 2>&1 & RC=$? if [ $RC != 0 ]; then ocf_log err "Could not start ipmiservicelogd!" return $OCF_ERR_GENERIC fi servicelog_notify --add --type=EVENT --command="$OCF_RESKEY_program" --method=num_arg --match='type=4' > /dev/null 2>&1 RC=$? if [ $RC != 0 ]; then ocf_log err "servicelog_notify register handler failed!" return $OCF_ERR_GENERIC fi return $OCF_SUCCESS } SystemHealth_stop() { SystemHealth_monitor RC=$? if [ $RC = $OCF_ERR_GENERIC ]; then return $OCF_ERR_GENERIC elif [ $RC = $OCF_SUCCESS ]; then killall ipmiservicelogd RC1=$? if [ $RC1 != 0 ]; then ocf_log err "Could not stop ipmiservicelogd!" fi servicelog_notify --remove --command="$OCF_RESKEY_program" > /dev/null 2>&1 RC2=$? if [ $RC2 != 0 ]; then ocf_log err "servicelog_notify remove handler failed!" fi if [ $RC1 = 0 -a $RC2 = 0 ]; then return $OCF_SUCCESS else return $OCF_ERR_GENERIC fi elif [ $RC = $OCF_NOT_RUNNING ]; then ocf_log warn "stopping an already stopped SystemHealth" return $OCF_SUCCESS else ocf_log err "SystemHealth_stop: should not be here!" return $OCF_ERR_GENERIC fi } SystemHealth_monitor() { # Monitor _MUST!_ differentiate correctly between running # (SUCCESS), failed (ERROR) or _cleanly_ stopped (NOT RUNNING). # That is THREE states, not just yes/no. if [ ! -f /var/run/ipmiservicelogd.pid0 ]; then ocf_log debug "ipmiservicelogd is not running!" return $OCF_NOT_RUNNING fi ps -p `cat /var/run/ipmiservicelogd.pid0` > /dev/null 2>&1 RC=$? if [ $RC != 0 ]; then ocf_log debug "ipmiservicelogd's pid `cat /var/run/ipmiservicelogd.pid0` is not running!" rm /var/run/ipmiservicelogd.pid0 return $OCF_ERR_GENERIC fi servicelog_notify --list --command="$OCF_RESKEY_program" > /dev/null 2>&1 RC=$? if [ $RC = 0 ]; then return $OCF_SUCCESS else return $OCF_NOT_RUNNING fi } SystemHealth_validate() { SystemHealth_check_tools RC=$? if [ $RC != 0 ]; then return $RC fi return $OCF_SUCCESS } : ${OCF_RESKEY_program=/usr/sbin/notifyServicelogEvent} case $__OCF_ACTION in meta-data) meta_data exit $OCF_SUCCESS ;; usage|help) SystemHealth_usage exit $OCF_SUCCESS ;; esac SystemHealth_check_tools RC=$? if [ $RC != 0 ]; then case $__OCF_ACTION in stop) exit $OCF_SUCCESS;; *) exit $RC;; esac fi case $__OCF_ACTION in start) SystemHealth_start;; stop) SystemHealth_stop;; monitor) SystemHealth_monitor;; reload) ocf_log info "Reloading..." SystemHealth_start ;; validate-all) ;; *) SystemHealth_usage exit $OCF_ERR_UNIMPLEMENTED ;; esac rc=$? ocf_log debug "${OCF_RESOURCE_INSTANCE} $__OCF_ACTION : $rc" exit $rc diff --git a/extra/resources/ifspeed b/extra/resources/ifspeed index a9390dc312..a41377c371 100644 --- a/extra/resources/ifspeed +++ b/extra/resources/ifspeed @@ -1,458 +1,458 @@ #!/bin/bash # # OCF resource agent which monitors state of network interface and records it # as a value in CIB based on summ of speeds of its active (up, link detected, # not blocked) underlying interfaces. # # Copyright (c) 2011 Vladislav Bogdanov # Partially based on 'ping' RA by Andrew Beekhof # # OCF instance parameters: # OCF_RESKEY_name: name of attribute to set in CIB # OCF_RESKEY_iface: network interface to monitor # OCF_RESKEY_bridge_ports: if not null and OCF_RESKEY_iface is a bridge, list of # bridge ports to consider. # Default is all ports which have designated_bridge=root_id # OCF_RESKEY_weight_base: Relative weight of 1Gbps. This can be used to tune # value of resulting CIB attribute. # # Initialization: : ${OCF_FUNCTIONS=${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs} . ${OCF_FUNCTIONS} : ${__OCF_ACTION=$1} # Defaults OCF_RESKEY_name_default="ifspeed" OCF_RESKEY_bridge_ports_default="detect" OCF_RESKEY_weight_base_default=1000 OCF_RESKEY_dampen_default=5 : ${OCF_RESKEY_name=${OCF_RESKEY_name_default}} : ${OCF_RESKEY_bridge_ports=${OCF_RESKEY_bridge_ports_default}} : ${OCF_RESKEY_weight_base=${OCF_RESKEY_weight_base_default}} : ${OCF_RESKEY_dampen=${OCF_RESKEY_dampen_default}} meta_data() { cat < - + 1.0 Every time the monitor action is run, this resource agent records (in the CIB) (relative) speed of network interface it monitors. This RA can monitor physical interfaces, bonds, bridges, vlans and (hopefully) any combination of them. Examples: *) Bridge on top of one 10Gbps interface (eth2) and 802.3ad bonding (bond0) built on two 1Gbps interfaces (eth0 and eth1). *) Active-backup bonding built on top of one physical interface and one vlan on another interface. For STP-enabled bridges this RA tries to some-how guess network topology and by default looks only on ports which are connected to upstream switch. This can be overriden by 'bridge_ports' parameter. Active interfaces in this case are those in "forwarding" state. For balancing bonds this RA summs speeds of underlying "up" slave interfaces (and applies coefficient 0.8 to result). For non-balancing bonds ('active-backup' and probably 'brodcast') only speed of now active slave is used. Network interface speed monitor The name of the attribute to set. This is the name to be used in the constraints. Attribute name Network interface to monitor. Network interface If not null and OCF_RESKEY_iface is a bridge, list of bridge ports to consider. Default is all ports which have designated_bridge=root_id. Bridge ports Relative weight of 1Gbps in interface speed. Can be used to tune how big attribute value will be. Weight of 1Gbps The time to wait (dampening) for further changes to occur. Dampening interval Log what have been done more verbosely. Verbose logging END } usage() { cat </dev/null)" if [ -z "$SP_OUT" ] then modprobe -s ocfs2_stack_user if [ $? != 0 ]; then ocf_log err "Could not load ocfs2_stack_user" return $OCF_ERR_INSTALLED fi fi SP_OUT="$(awk '/^'user'$/{print; exit}' "$LOADED_PLUGINS_FILE" 2>/dev/null)" if [ -z "$SP_OUT" ]; then ocf_log err "Switch to userspace stack unsuccessful" return $OCF_ERR_INSTALLED fi if [ -f "$CLUSTER_STACK_FILE" ]; then echo "$OCF_RESKEY_stack" >"$CLUSTER_STACK_FILE" if [ $? != 0 ]; then ocf_log err "Userspace stack '$OCF_RESKEY_stack' not supported" return $OCF_ERR_INSTALLED fi else ocf_log err "Switch to userspace stack not supported" return $OCF_ERR_INSTALLED fi driver_filesystem ocfs2; rc=$? if [ $rc != 0 ]; then modprobe -s ocfs2 if [ "$?" != 0 ]; then ocf_log err "Unable to load ocfs2 module" return $OCF_ERR_INSTALLED fi fi bringup_daemon return $? } o2cb_stop() { o2cb_monitor; rc=$? case $rc in $OCF_NOT_RUNNING) return $OCF_SUCCESS;; esac ocf_log info "Stopping $OCF_RESOURCE_INSTANCE" kill_daemon if [ $? != 0 ]; then ocf_log err "Unable to unload modules: the cluster is still online" return $OCF_ERR_GENERIC fi unload_filesystem ocfs2 if [ $? = 1 ]; then ocf_log err "Unable to unload ocfs2 module" return $OCF_ERR_GENERIC fi # If we can't find the stack glue, we have nothing to do. [ ! -e "$LOADED_PLUGINS_FILE" ] && return $OCF_SUCCESS while read plugin do unload_module "ocfs2_stack_${plugin}" if [ $? = 1 ]; then ocf_log err "Unable to unload ocfs2_stack_${plugin}" return $OCF_ERR_GENERIC fi done <"$LOADED_PLUGINS_FILE" unload_module "ocfs2_stackglue" if [ $? = 1 ]; then ocf_log err "Unable to unload ocfs2_stackglue" return $OCF_ERR_GENERIC fi # Don't unmount configfs - its always in use by libdlm } o2cb_monitor() { o2cb_validate # Assume that ocfs2_controld will terminate if any of the conditions below are met driver_filesystem configfs; rc=$? if [ $rc != 0 ]; then ocf_log info "configfs not loaded" return $OCF_NOT_RUNNING fi check_filesystem configfs "${OCF_RESKEY_configfs}"; rc=$? if [ $rc != 0 ]; then ocf_log info "configfs not mounted" return $OCF_NOT_RUNNING fi if [ ! -e "$LOADED_PLUGINS_FILE" ]; then ocf_log info "Stack glue driver not loaded" return $OCF_NOT_RUNNING fi grep user "$LOADED_PLUGINS_FILE" >/dev/null 2>&1; rc=$? if [ $rc != 0 ]; then ocf_log err "Wrong stack `cat $LOADED_PLUGINS_FILE`" return $OCF_ERR_INSTALLED fi driver_filesystem ocfs2; rc=$? if [ $rc != 0 ]; then ocf_log info "ocfs2 not loaded" return $OCF_NOT_RUNNING fi status_daemon return $? } o2cb_usage() { echo "usage: $0 {start|stop|monitor|validate-all|meta-data}" echo " Expects to have a fully populated OCF RA-compliant environment set." echo " In particualr, a value for OCF_ROOT" } o2cb_validate() { check_binary ${DAEMON} case ${OCF_RESKEY_CRM_meta_globally_unique} in yes|Yes|true|True|1) ocf_log err "$OCF_RESOURCE_INSTANCE must be configured with the globally_unique=false meta attribute" exit $OCF_ERR_CONFIGURED ;; esac return $OCF_SUCCESS } meta_data() { cat < - + 1.0 OCFS2 daemon resource agent This Resource Agent controls the userspace daemon needed by OCFS2. Location where sysfs is mounted Sysfs location Location where configfs is mounted Configfs location Which userspace stack to use. Known values: pcmk, cman Userspace stack Number of seconds to allow the control daemon to come up Daemon Timeout END } case $__OCF_ACTION in meta-data) meta_data exit $OCF_SUCCESS ;; start) o2cb_start ;; stop) o2cb_stop ;; monitor) o2cb_monitor ;; validate-all) o2cb_validate ;; usage|help) o2cb_usage exit $OCF_SUCCESS ;; *) o2cb_usage exit $OCF_ERR_UNIMPLEMENTED ;; esac exit $? diff --git a/extra/resources/ping b/extra/resources/ping index e2c5e9eefb..26cc0cc5d5 100755 --- a/extra/resources/ping +++ b/extra/resources/ping @@ -1,436 +1,436 @@ #!/bin/sh # # # Ping OCF RA that utilizes the system ping # # Copyright (c) 2009 Andrew Beekhof # All Rights Reserved. # # This program is free software; you can redistribute it and/or modify # it under the terms of version 2 of the GNU General Public License as # published by the Free Software Foundation. # # This program is distributed in the hope that it would be useful, but # WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. # # Further, this software is distributed without any warranty that it is # free of the rightful claim of any third person regarding infringement # or the like. Any license provided herein, whether implied or # otherwise, applies only to this software file. Patent licenses, if # any, provided herein do not apply to combinations of this program with # other software, or any other product whatsoever. # # You should have received a copy of the GNU General Public License # along with this program; if not, write the Free Software Foundation, # Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. # ####################################################################### # Initialization: : ${OCF_FUNCTIONS=${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs} . ${OCF_FUNCTIONS} : ${__OCF_ACTION=$1} ####################################################################### meta_data() { cat < - + 1.0 Every time the monitor action is run, this resource agent records (in the CIB) the current number of nodes the host can connect to using the system fping (preferred) or ping tool. node connectivity PID file PID file The time to wait (dampening) further changes occur Dampening interval The name of the attributes to set. This is the name to be used in the constraints. Attribute name The number by which to multiply the number of connected ping nodes by Value multiplier A space separated list of ping nodes to count. Host list Number of ping attempts, per host, before declaring it dead no. of ping attempts How long, in seconds, to wait before declaring a ping lost ping timeout in seconds A catch all for any other options that need to be passed to ping. Extra Options Resource is failed if the score is less than failure_score. Default never fails. failure_score Use fping rather than ping, if found. If set to 0, fping will not be used even if present. Use fping if available Enables to use default attrd_updater verbose logging on every call. Verbose logging END } ####################################################################### ping_conditional_log() { level=$1; shift if [ ${OCF_RESKEY_debug} = "true" ]; then ocf_log $level "$*" fi } ping_usage() { cat <$f_out 2>$f_err; rc=$? active=`grep alive $f_out|wc -l` case $rc in 0) ;; 1) for h in `grep unreachable $f_out | awk '{print $1}'`; do ping_conditional_log warn "$h is inactive" done ;; *) ocf_log err "Unexpected result for '$cmd' $rc: `tr '\n' ';' < $f_err`" ;; esac rm -f $f_out $f_err return $active } ping_check() { active=0 for host in $OCF_RESKEY_host_list; do p_exe=ping case `uname` in Linux) p_args="-n -q -W $OCF_RESKEY_timeout -c $OCF_RESKEY_attempts";; Darwin) p_args="-n -q -t $OCF_RESKEY_timeout -c $OCF_RESKEY_attempts -o";; *) ocf_log err "Unknown host type: `uname`"; exit $OCF_ERR_INSTALLED;; esac case $host in *:*) p_exe=ping6 esac p_out=`$p_exe $p_args $OCF_RESKEY_options $host 2>&1`; rc=$? case $rc in 0) active=`expr $active + 1`;; 1) ping_conditional_log warn "$host is inactive: $p_out";; *) ocf_log err "Unexpected result for '$p_exe $p_args $OCF_RESKEY_options $host' $rc: $p_out";; esac done return $active } ping_update() { if use_fping; then fping_check active=$? else ping_check active=$? fi score=`expr $active \* $OCF_RESKEY_multiplier` if [ "$__OCF_ACTION" = "start" ] ; then attrd_updater -n $OCF_RESKEY_name -B $score -d $OCF_RESKEY_dampen $attrd_options else attrd_updater -n $OCF_RESKEY_name -v $score -d $OCF_RESKEY_dampen $attrd_options fi rc=$? case $rc in 0) ping_conditional_log debug "Updated $OCF_RESKEY_name = $score" ;; *) ocf_log warn "Could not update $OCF_RESKEY_name = $score: rc=$rc";; esac if [ $rc -ne 0 ]; then return $rc fi if [ -n "$OCF_RESKEY_failure_score" -a "$score" -lt "$OCF_RESKEY_failure_score" ]; then ocf_log warn "$OCF_RESKEY_name is less than failure_score($OCF_RESKEY_failure_score)" return 1 fi return 0 } use_fping() { ocf_is_true "$OCF_RESKEY_use_fping" && have_binary fping; } # return values: # 4 IPv4 # 6 IPv6 # 0 indefinite (i.e. hostname) host_family() { case $1 in *[0-9].*[0-9].*[0-9].*[0-9]) return 4 ;; *:*) return 6 ;; *) return 0 ;; esac } # return values same as host_family plus # 99 ambiguous families hosts_family() { # For fping allow only same IP versions or hostnames family=0 for host in $OCF_RESKEY_host_list; do host_family $host f=$? if [ $family -ne 0 -a $f -ne 0 -a $f -ne $family ] ; then family=99 break fi [ $f -ne 0 ] && family=$f done return $family } : ${OCF_RESKEY_name:="pingd"} : ${OCF_RESKEY_dampen:="5s"} : ${OCF_RESKEY_attempts:="3"} : ${OCF_RESKEY_multiplier:="1"} : ${OCF_RESKEY_debug:="false"} : ${OCF_RESKEY_failure_score:="0"} : ${OCF_RESKEY_use_fping:="1"} : ${OCF_RESKEY_CRM_meta_timeout:="20000"} : ${OCF_RESKEY_CRM_meta_globally_unique:="false"} integer=`echo ${OCF_RESKEY_timeout} | egrep -o '[0-9]*'` case ${OCF_RESKEY_timeout} in *[0-9]ms|*[0-9]msec) OCF_RESKEY_timeout=`expr $integer / 1000`;; *[0-9]m|*[0-9]min) OCF_RESKEY_timeout=`expr $integer \* 60`;; *[0-9]h|*[0-9]hr) OCF_RESKEY_timeout=`expr $integer \* 60 \* 60`;; *) OCF_RESKEY_timeout=$integer;; esac if [ -z ${OCF_RESKEY_timeout} ]; then if [ x"$OCF_RESKEY_host_list" != x ]; then host_count=`echo $OCF_RESKEY_host_list | awk '{print NF}'` OCF_RESKEY_timeout=`expr $OCF_RESKEY_CRM_meta_timeout / $host_count / $OCF_RESKEY_attempts` OCF_RESKEY_timeout=`expr $OCF_RESKEY_timeout / 1100` # Convert to seconds and finish 10% early else OCF_RESKEY_timeout=5 fi fi if [ ${OCF_RESKEY_timeout} -lt 1 ]; then OCF_RESKEY_timeout=5 elif [ ${OCF_RESKEY_timeout} -gt 1000 ]; then # ping actually complains if this value is too high, 5 minutes is plenty OCF_RESKEY_timeout=300 fi if [ ${OCF_RESKEY_CRM_meta_globally_unique} = "false" ]; then : ${OCF_RESKEY_pidfile:="${HA_VARRUN%%/}/ping-${OCF_RESKEY_name}"} else : ${OCF_RESKEY_pidfile:="${HA_VARRUN%%/}/ping-${OCF_RESOURCE_INSTANCE}"} fi # Check the debug option case "${OCF_RESKEY_debug}" in true|True|TRUE|1) OCF_RESKEY_debug=true;; false|False|FALSE|0) OCF_RESKEY_debug=false;; *) ocf_log warn "Value for 'debug' is incorrect. Please specify 'true' or 'false' not: ${OCF_RESKEY_debug}" OCF_RESKEY_debug=false ;; esac attrd_options='-q' if [ ${OCF_RESKEY_debug} = "true" ]; then attrd_options='' fi case $__OCF_ACTION in meta-data) meta_data exit $OCF_SUCCESS ;; start) ping_start;; stop) ping_stop;; monitor) ping_monitor;; validate-all) ping_validate;; usage|help) ping_usage exit $OCF_SUCCESS ;; *) ping_usage exit $OCF_ERR_UNIMPLEMENTED ;; esac exit $? diff --git a/extra/resources/pingd b/extra/resources/pingd index add152642e..6003c02fe0 100644 --- a/extra/resources/pingd +++ b/extra/resources/pingd @@ -1,200 +1,200 @@ #!/bin/sh # # # pingd OCF Resource Agent # Records (in the CIB) the current number of ping nodes a # cluster node can connect to. # # Copyright (c) 2006 Andrew Beekhof # All Rights Reserved. # # This program is free software; you can redistribute it and/or modify # it under the terms of version 2 of the GNU General Public License as # published by the Free Software Foundation. # # This program is distributed in the hope that it would be useful, but # WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. # # Further, this software is distributed without any warranty that it is # free of the rightful claim of any third person regarding infringement # or the like. Any license provided herein, whether implied or # otherwise, applies only to this software file. Patent licenses, if # any, provided herein do not apply to combinations of this program with # other software, or any other product whatsoever. # # You should have received a copy of the GNU General Public License # along with this program; if not, write the Free Software Foundation, # Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. # ####################################################################### # Initialization: : ${OCF_FUNCTIONS=${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs} . ${OCF_FUNCTIONS} : ${__OCF_ACTION=$1} : ${OCF_RESKEY_name:="pingd"} : ${OCF_RESKEY_interval:="1"} : ${OCF_RESKEY_CRM_meta_interval:=0} upgrade1="This agent (ocf:pacemaker:pingd) has been replaced by the more reliable ocf:pacemaker:ping." upgrade2="Attempting automated conversion, run 'crm ra info ocf:pacemaker:ping' for all configuration options" upgrade3="You will need to remove the existing resource and replace it with one that uses 'ocf:pacemaker:ping' directly" case $__OCF_ACTION in start|monitor) if [ "x" != "x$OCF_RESKEY_host_list" ]; then ocf_log err "$upgrade1" ocf_log err "$upgrade2" ocf_log err "Automatic conversion to ocf:pacemaker:ping failed: no hosts were configured to check for connectivity" ocf_log err "$upgrade3" exit $OCF_ERR_ARGS fi recurring=`crm configure show $OCF_RESOURCE_INSTANCE | grep "op monitor.*interval=\"[1-9]" | sed s/.*interval=// | awk -F\" '{print $2}' | sed s/.*interval=// | awk -F\" '{print $2}' | sort | head -n 1` if [ -z $recurring ]; then ocf_log err "$upgrade1" ocf_log err "$upgrade2" ocf_log err "Automatic conversion to ocf:pacemaker:ping failed: no monitor operation configured" ocf_log err "Without an explicit monitor operation for '$OCF_RESOURCE_INSTANCE', connectivity changes will not be noticed" ocf_log err "Preventing startup to ensure the issue is addressed before it matters" exit $OCF_ERR_ARGS fi if [ $OCF_RESKEY_CRM_meta_interval = 0 ]; then ocf_log warn "$upgrade1" ocf_log warn "$upgrade2" if [ $recurring != $OCF_RESKEY_interval ]; then ocf_log warn "Your monitor operation happens every $recurring, which means that the $OCF_RESKEY_name attribute will be updated with a different frequency than the previously configured ( $OCF_RESKEY_interval )" ocf_log warn "Either change the monitor interval to match or, ideally, switch to the ocf:pacemaker:ping agent and avoid all this compatibility nonsense." fi fi ;; meta-data) cat < - + 1.0 This agent (ocf:pacemaker:pingd) has been replaced by the more reliable ocf:pacemaker:ping. It records (in the CIB) the current number of ping nodes (specified in the 'host_list' parameter) a cluster node can connect to. pingd resource agent PID file PID file The user we want to run pingd as The user we want to run pingd as The time to wait (dampening) further changes occur Dampening interval The name of the instance_attributes set to place the value in. Rarely needs to be specified. Set name The name of the attributes to set. This is the name to be used in the constraints. Attribute name The section place the value in. Rarely needs to be specified. Section name The number by which to multiply the number of connected ping nodes by Value multiplier The list of ping nodes to count. Defaults to all configured ping nodes. Rarely needs to be specified. Host list How often, in seconds, to check for node liveliness ping interval in seconds Number of ping attempts, per host, before declaring it dead no. of ping attempts How long, in seconds, to wait before declaring a ping lost ping timeout in seconds A catch all for any other options that need to be passed to pingd. Extra Options END exit $OCF_SUCCESS ;; esac ${OCF_ROOT}/resource.d/pacemaker/ping $1 exit $? diff --git a/extra/resources/remote b/extra/resources/remote index 447267e778..afd8c79973 100644 --- a/extra/resources/remote +++ b/extra/resources/remote @@ -1,125 +1,125 @@ #!/bin/sh # # # remote OCF RA. This script provides metadata for the internal # pacemaker remote lrmd connection agent. Outside of acting # as a place holder so the remote ra script can be indexed and # providing metadata, this script should never be invoked. The # actual functionality behind the remote lrmd connection lives # within pacemaker's crmd component. # # Copyright (c) 2013 David Vossel # # This program is free software; you can redistribute it and/or modify # it under the terms of version 2 of the GNU General Public License as # published by the Free Software Foundation. # # This program is distributed in the hope that it would be useful, but # WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. # # Further, this software is distributed without any warranty that it is # free of the rightful claim of any third person regarding infringement # or the like. Any license provided herein, whether implied or # otherwise, applies only to this software file. Patent licenses, if # any, provided herein do not apply to combinations of this program with # other software, or any other product whatsoever. # # You should have received a copy of the GNU General Public License # along with this program; if not, write the Free Software Foundation, # Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. # ####################################################################### # Initialization: : ${OCF_FUNCTIONS=${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs} . ${OCF_FUNCTIONS} : ${__OCF_ACTION=$1} ####################################################################### meta_data() { cat < -0.1 +1.0 remote resource agent Server location to connect to. This can be an ip address or hostname. Server location tcp port to connect to. tcp port - Time in seconds to wait before attempting to reconnect to a remote node - after an active connection to the remote node has been severed. This wait - is recurring. If reconnect fails after the wait period, a new reconnect - attempt will be made after observing the wait time. When this option is - in use, pacemaker will keep attempting to reach out and connect to the - remote node indefinitely after each wait interval. + Interval in seconds at which Pacemaker will attempt to reconnect to a + remote node after an active connection to the remote node has been + severed. When this value is nonzero, Pacemaker will retry the connection + indefinitely, at the specified interval. As with any time-based actions, + this is not guaranteed to be checked more frequently than the value of + the cluster-recheck-interval cluster option. reconnect interval END } ####################################################################### remote_usage() { cat < * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * * This library is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #include #ifndef _GNU_SOURCE # define _GNU_SOURCE #endif #include #include #include #include #include #include /* * \internal * \brief Get process ID and name associated with a /proc directory entry * * \param[in] entry Directory entry (must be result of readdir() on /proc) * \param[out] name If not NULL, a char[64] to hold the process name * \param[out] pid If not NULL, will be set to process ID of entry * * \return 0 on success, -1 if entry is not for a process or info not found * * \note This should be called only on Linux systems, as not all systems that * support /proc store process names and IDs in the same way. */ int crm_procfs_process_info(struct dirent *entry, char *name, int *pid) { int fd, local_pid; FILE *file; struct stat statbuf; char key[16] = { 0 }, procpath[128] = { 0 }; /* We're only interested in entries whose name is a PID, * so skip anything non-numeric or that is too long. * * 114 = 128 - strlen("/proc/") - strlen("/status") - 1 */ local_pid = atoi(entry->d_name); if ((local_pid <= 0) || (strlen(entry->d_name) > 114)) { return -1; } if (pid) { *pid = local_pid; } /* Get this entry's file information */ strcpy(procpath, "/proc/"); strcat(procpath, entry->d_name); fd = open(procpath, O_RDONLY); if (fd < 0 ) { return -1; } if (fstat(fd, &statbuf) < 0) { close(fd); return -1; } close(fd); /* We're only interested in subdirectories */ if (!S_ISDIR(statbuf.st_mode)) { return -1; } /* Read the first entry ("Name:") from the process's status file. * We could handle the valgrind case if we parsed the cmdline file * instead, but that's more of a pain than it's worth. */ if (name != NULL) { strcat(procpath, "/status"); file = fopen(procpath, "r"); if (!file) { return -1; } if ((fscanf(file, "%15s%63s", key, name) != 2) || safe_str_neq(key, "Name:")) { fclose(file); return -1; } fclose(file); } return 0; } /* * \internal * \brief Return process ID of a named process * * \param[in] name Process name (as used in /proc/.../status) * * \return Process ID of named process if running, 0 otherwise * * \note This will return 0 if the process is being run via valgrind. * This should be called only on Linux systems. */ int crm_procfs_pid_of(const char *name) { DIR *dp; struct dirent *entry; int pid = 0; char entry_name[64] = { 0 }; dp = opendir("/proc"); if (dp == NULL) { crm_notice("Can not read /proc directory to track existing components"); return 0; } while ((entry = readdir(dp)) != NULL) { if ((crm_procfs_process_info(entry, entry_name, &pid) == 0) && safe_str_eq(entry_name, name) && (crm_pid_active(pid, NULL) == 1)) { crm_info("Found %s active as process %d", name, pid); break; } + pid = 0; } closedir(dp); return pid; }