Page MenuHomeClusterLabs Projects

Ch-Utilization.pot
No OneTemporary

Ch-Utilization.pot

#
# AUTHOR <EMAIL@ADDRESS>, YEAR.
#
msgid ""
msgstr ""
"Project-Id-Version: 0\n"
"POT-Creation-Date: 2018-05-14 18:03-0500\n"
"PO-Revision-Date: 2018-05-14 18:03-0500\n"
"Last-Translator: Automatically generated\n"
"Language-Team: None\n"
"MIME-Version: 1.0\n"
"Content-Type: application/x-publican; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
#. Tag: title
#, no-c-format
msgid "Utilization and Placement Strategy"
msgstr ""
#. Tag: para
#, no-c-format
msgid "Pacemaker decides where to place a resource according to the resource allocation scores on every node. The resource will be allocated to the node where the resource has the highest score."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If the resource allocation scores on all the nodes are equal, by the default placement strategy, Pacemaker will choose a node with the least number of allocated resources for balancing the load. If the number of resources on each node is equal, the first eligible node listed in the CIB will be chosen to run the resource."
msgstr ""
#. Tag: para
#, no-c-format
msgid "Often, in real-world situations, different resources use significantly different proportions of a node’s capacities (memory, I/O, etc.). We cannot balance the load ideally just according to the number of resources allocated to a node. Besides, if resources are placed such that their combined requirements exceed the provided capacity, they may fail to start completely or run with degraded performance."
msgstr ""
#. Tag: para
#, no-c-format
msgid "To take these factors into account, Pacemaker allows you to configure:"
msgstr ""
#. Tag: para
#, no-c-format
msgid "The capacity a certain node provides."
msgstr ""
#. Tag: para
#, no-c-format
msgid "The capacity a certain resource requires."
msgstr ""
#. Tag: para
#, no-c-format
msgid "An overall strategy for placement of resources."
msgstr ""
#. Tag: title
#, no-c-format
msgid "Utilization attributes"
msgstr ""
#. Tag: para
#, no-c-format
msgid "To configure the capacity that a node provides or a resource requires, you can use <emphasis>utilization attributes</emphasis> in <literal>node</literal> and <literal>resource</literal> objects. You can name utilization attributes according to your preferences and define as many name/value pairs as your configuration needs. However, the attributes' values must be integers."
msgstr ""
#. Tag: title
#, no-c-format
msgid "Specifying CPU and RAM capacities of two nodes"
msgstr ""
#. Tag: programlisting
#, no-c-format
msgid "&lt;node id=\"node1\" type=\"normal\" uname=\"node1\"&gt;\n"
" &lt;utilization id=\"node1-utilization\"&gt;\n"
" &lt;nvpair id=\"node1-utilization-cpu\" name=\"cpu\" value=\"2\"/&gt;\n"
" &lt;nvpair id=\"node1-utilization-memory\" name=\"memory\" value=\"2048\"/&gt;\n"
" &lt;/utilization&gt;\n"
"&lt;/node&gt;\n"
"&lt;node id=\"node2\" type=\"normal\" uname=\"node2\"&gt;\n"
" &lt;utilization id=\"node2-utilization\"&gt;\n"
" &lt;nvpair id=\"node2-utilization-cpu\" name=\"cpu\" value=\"4\"/&gt;\n"
" &lt;nvpair id=\"node2-utilization-memory\" name=\"memory\" value=\"4096\"/&gt;\n"
" &lt;/utilization&gt;\n"
"&lt;/node&gt;"
msgstr ""
#. Tag: title
#, no-c-format
msgid "Specifying CPU and RAM consumed by several resources"
msgstr ""
#. Tag: programlisting
#, no-c-format
msgid "&lt;primitive id=\"rsc-small\" class=\"ocf\" provider=\"pacemaker\" type=\"Dummy\"&gt;\n"
" &lt;utilization id=\"rsc-small-utilization\"&gt;\n"
" &lt;nvpair id=\"rsc-small-utilization-cpu\" name=\"cpu\" value=\"1\"/&gt;\n"
" &lt;nvpair id=\"rsc-small-utilization-memory\" name=\"memory\" value=\"1024\"/&gt;\n"
" &lt;/utilization&gt;\n"
"&lt;/primitive&gt;\n"
"&lt;primitive id=\"rsc-medium\" class=\"ocf\" provider=\"pacemaker\" type=\"Dummy\"&gt;\n"
" &lt;utilization id=\"rsc-medium-utilization\"&gt;\n"
" &lt;nvpair id=\"rsc-medium-utilization-cpu\" name=\"cpu\" value=\"2\"/&gt;\n"
" &lt;nvpair id=\"rsc-medium-utilization-memory\" name=\"memory\" value=\"2048\"/&gt;\n"
" &lt;/utilization&gt;\n"
"&lt;/primitive&gt;\n"
"&lt;primitive id=\"rsc-large\" class=\"ocf\" provider=\"pacemaker\" type=\"Dummy\"&gt;\n"
" &lt;utilization id=\"rsc-large-utilization\"&gt;\n"
" &lt;nvpair id=\"rsc-large-utilization-cpu\" name=\"cpu\" value=\"3\"/&gt;\n"
" &lt;nvpair id=\"rsc-large-utilization-memory\" name=\"memory\" value=\"3072\"/&gt;\n"
" &lt;/utilization&gt;\n"
"&lt;/primitive&gt;"
msgstr ""
#. Tag: para
#, no-c-format
msgid "A node is considered eligible for a resource if it has sufficient free capacity to satisfy the resource’s requirements. The nature of the required or provided capacities is completely irrelevant to Pacemaker — it just makes sure that all capacity requirements of a resource are satisfied before placing a resource to a node."
msgstr ""
#. Tag: title
#, no-c-format
msgid "Placement Strategy"
msgstr ""
#. Tag: para
#, no-c-format
msgid "After you have configured the capacities your nodes provide and the capacities your resources require, you need to set the <literal>placement-strategy</literal> in the global cluster options, otherwise the capacity configurations have <emphasis>no effect</emphasis>."
msgstr ""
#. Tag: para
#, no-c-format
msgid "Four values are available for the <literal>placement-strategy</literal>:"
msgstr ""
#. Tag: term
#, no-c-format
msgid "<literal>default</literal>"
msgstr ""
#. Tag: para
#, no-c-format
msgid "Utilization values are not taken into account at all. Resources are allocated according to allocation scores. If scores are equal, resources are evenly distributed across nodes."
msgstr ""
#. Tag: term
#, no-c-format
msgid "<literal>utilization</literal>"
msgstr ""
#. Tag: para
#, no-c-format
msgid "Utilization values are taken into account <emphasis>only</emphasis> when deciding whether a node is considered eligible (i.e. whether it has sufficient free capacity to satisfy the resource’s requirements). Load-balancing is still done based on the number of resources allocated to a node."
msgstr ""
#. Tag: term
#, no-c-format
msgid "<literal>balanced</literal>"
msgstr ""
#. Tag: para
#, no-c-format
msgid "Utilization values are taken into account when deciding whether a node is eligible to serve a resource <emphasis>and</emphasis> when load-balancing, so an attempt is made to spread the resources in a way that optimizes resource performance."
msgstr ""
#. Tag: term
#, no-c-format
msgid "<literal>minimal</literal>"
msgstr ""
#. Tag: para
#, no-c-format
msgid "Utilization values are taken into account <emphasis>only</emphasis> when deciding whether a node is eligible to serve a resource. For load-balancing, an attempt is made to concentrate the resources on as few nodes as possible, thereby enabling possible power savings on the remaining nodes."
msgstr ""
#. Tag: para
#, no-c-format
msgid "Set <literal>placement-strategy</literal> with <literal>crm_attribute</literal>:"
msgstr ""
#. Tag: screen
#, no-c-format
msgid "# crm_attribute --name placement-strategy --update balanced"
msgstr ""
#. Tag: para
#, no-c-format
msgid "Now Pacemaker will ensure the load from your resources will be distributed evenly throughout the cluster, without the need for convoluted sets of colocation constraints."
msgstr ""
#. Tag: title
#, no-c-format
msgid "Allocation Details"
msgstr ""
#. Tag: title
#, no-c-format
msgid "Which node is preferred to get consumed first when allocating resources?"
msgstr ""
#. Tag: para
#, no-c-format
msgid "The node with the highest node weight gets consumed first. Node weight is a score maintained by the cluster to represent node health."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If multiple nodes have the same node weight:"
msgstr ""
#. Tag: para
#, no-c-format
msgid "If <literal>placement-strategy</literal> is <literal>default</literal> or <literal>utilization</literal>, the node that has the least number of allocated resources gets consumed first."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If their numbers of allocated resources are equal, the first eligible node listed in the CIB gets consumed first."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If <literal>placement-strategy</literal> is <literal>balanced</literal>, the node that has the most free capacity gets consumed first."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If the free capacities of the nodes are equal, the node that has the least number of allocated resources gets consumed first."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If <literal>placement-strategy</literal> is <literal>minimal</literal>, the first eligible node listed in the CIB gets consumed first."
msgstr ""
#. Tag: title
#, no-c-format
msgid "Which node has more free capacity?"
msgstr ""
#. Tag: para
#, no-c-format
msgid "If only one type of utilization attribute has been defined, free capacity is a simple numeric comparison."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If multiple types of utilization attributes have been defined, then the node that is numerically highest in the the most attribute types has the most free capacity. For example:"
msgstr ""
#. Tag: para
#, no-c-format
msgid "If <literal>nodeA</literal> has more free <literal>cpus</literal>, and <literal>nodeB</literal> has more free <literal>memory</literal>, then their free capacities are equal."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If <literal>nodeA</literal> has more free <literal>cpus</literal>, while <literal>nodeB</literal> has more free <literal>memory</literal> and <literal>storage</literal>, then <literal>nodeB</literal> has more free capacity."
msgstr ""
#. Tag: title
#, no-c-format
msgid "Which resource is preferred to be assigned first?"
msgstr ""
#. Tag: para
#, no-c-format
msgid "The resource that has the highest <literal>priority</literal> (see <xref linkend=\"s-resource-options\" />) gets allocated first."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If their priorities are equal, check whether they are already running. The resource that has the highest score on the node where it’s running gets allocated first, to prevent resource shuffling."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If the scores above are equal or the resources are not running, the resource has the highest score on the preferred node gets allocated first."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If the scores above are equal, the first runnable resource listed in the CIB gets allocated first."
msgstr ""
#. Tag: title
#, no-c-format
msgid "Limitations and Workarounds"
msgstr ""
#. Tag: para
#, no-c-format
msgid "The type of problem Pacemaker is dealing with here is known as the <ulink url=\"http://en.wikipedia.org/wiki/Knapsack_problem\">knapsack problem</ulink> and falls into the <ulink url=\"http://en.wikipedia.org/wiki/NP-complete\">NP-complete</ulink> category of computer science problems — a fancy way of saying \"it takes a really long time to solve\"."
msgstr ""
#. Tag: para
#, no-c-format
msgid "Clearly in a HA cluster, it’s not acceptable to spend minutes, let alone hours or days, finding an optimal solution while services remain unavailable."
msgstr ""
#. Tag: para
#, no-c-format
msgid "So instead of trying to solve the problem completely, Pacemaker uses a <emphasis>best effort</emphasis> algorithm for determining which node should host a particular service. This means it arrives at a solution much faster than traditional linear programming algorithms, but by doing so at the price of leaving some services stopped."
msgstr ""
#. Tag: para
#, no-c-format
msgid "In the contrived example at the start of this section:"
msgstr ""
#. Tag: para
#, no-c-format
msgid "<literal>rsc-small</literal> would be allocated to <literal>node1</literal>"
msgstr ""
#. Tag: para
#, no-c-format
msgid "<literal>rsc-medium</literal> would be allocated to <literal>node2</literal>"
msgstr ""
#. Tag: para
#, no-c-format
msgid "<literal>rsc-large</literal> would remain inactive"
msgstr ""
#. Tag: para
#, no-c-format
msgid "Which is not ideal."
msgstr ""
#. Tag: para
#, no-c-format
msgid "There are various approaches to dealing with the limitations of pacemaker’s placement strategy:"
msgstr ""
#. Tag: term
#, no-c-format
msgid "Ensure you have sufficient physical capacity."
msgstr ""
#. Tag: para
#, no-c-format
msgid "It might sound obvious, but if the physical capacity of your nodes is (close to) maxed out by the cluster under normal conditions, then failover isn’t going to go well. Even without the utilization feature, you’ll start hitting timeouts and getting secondary failures."
msgstr ""
#. Tag: term
#, no-c-format
msgid "Build some buffer into the capabilities advertised by the nodes."
msgstr ""
#. Tag: para
#, no-c-format
msgid "Advertise slightly more resources than we physically have, on the (usually valid) assumption that a resource will not use 100% of the configured amount of CPU, memory and so forth <emphasis>all</emphasis> the time. This practice is sometimes called <emphasis>overcommit</emphasis>."
msgstr ""
#. Tag: term
#, no-c-format
msgid "Specify resource priorities."
msgstr ""
#. Tag: para
#, no-c-format
msgid "If the cluster is going to sacrifice services, it should be the ones you care about (comparatively) the least. Ensure that resource priorities are properly set so that your most important resources are scheduled first."
msgstr ""

File Metadata

Mime Type
text/x-po
Expires
Thu, Oct 16, 3:08 PM (23 h, 1 m)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
2435867
Default Alt Text
Ch-Utilization.pot (13 KB)

Event Timeline