Google Git
Sign in
apache / mesos-site / a3206036349e280dd43d9f4f1f6569976655da20 / . / content / documentation / monitoring / index.html
blob: a8b82222172d1ea1223cc7a6c4e38b824d72085b [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>Apache Mesos - Observability Metrics</title>
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta property="og:locale" content="en_US"/>
<meta property="og:type" content="website"/>
<meta property="og:title" content="Apache Mesos"/>
<meta property="og:site_name" content="Apache Mesos"/>
<meta property="og:url" content="http://mesos.apache.org/"/>
<meta property="og:image" content="http://mesos.apache.org/assets/img/mesos_logo_fb_preview.png"/>
<meta property="og:description"
content="Apache Mesos abstracts resources away from machines,
enabling fault-tolerant and elastic distributed systems
to easily be built and run effectively."/>
<meta name="twitter:card" content="summary"/>
<meta name="twitter:site" content="@ApacheMesos"/>
<meta name="twitter:title" content="Apache Mesos"/>
<meta name="twitter:image" content="http://mesos.apache.org/assets/img/mesos_logo_fb_preview.png"/>
<meta name="twitter:description"
content="Apache Mesos abstracts resources away from machines,
enabling fault-tolerant and elastic distributed systems
to easily be built and run effectively."/>
<link href="//netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
<link rel="alternate" type="application/atom+xml" title="Apache Mesos Blog" href="/blog/feed.xml">
<link href="../../assets/css/main.css" media="screen" rel="stylesheet" type="text/css" />
<!-- Google Analytics Magic -->
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-20226872-1']);
_gaq.push(['_setDomainName', 'apache.org']);
_gaq.push(['_trackPageview']);
(function() {
var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
})();
</script>
</head>
<body>
<!-- magical breadcrumbs -->
<div class="topnav">
<div class="container">
<ul class="breadcrumb">
<li>
<div class="dropdown">
<a data-toggle="dropdown" href="#">Apache Software Foundation <span class="caret"></span></a>
<ul class="dropdown-menu" role="menu" aria-labelledby="dLabel">
<li><a href="http://www.apache.org">Apache Homepage</a></li>
<li><a href="http://www.apache.org/licenses/">License</a></li>
<li><a href="http://www.apache.org/foundation/sponsorship.html">Sponsorship</a></li>
<li><a href="http://www.apache.org/foundation/thanks.html">Thanks</a></li>
<li><a href="http://www.apache.org/security/">Security</a></li>
</ul>
</div>
</li>
<li><a href="http://mesos.apache.org">Apache Mesos</a></li>
<li><a href="/documentation
/">Documentation
</a></li>
</ul><!-- /.breadcrumb -->
</div><!-- /.container -->
</div><!-- /.topnav -->
<!-- navbar excitement -->
<div class="navbar navbar-default navbar-static-top" role="navigation">
<div class="container">
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#mesos-menu" aria-expanded="false">
<span class="sr-only">Toggle navigation</span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<a class="navbar-brand" href="/"><img src="/assets/img/mesos_logo.png" alt="Apache Mesos logo"/></a>
</div><!-- /.navbar-header -->
<div class="navbar-collapse collapse" id="mesos-menu">
<ul class="nav navbar-nav navbar-right">
<li><a href="/gettingstarted/">Getting Started</a></li>
<li><a href="/blog/">Blog</a></li>
<li><a href="/documentation/latest/">Documentation</a></li>
<li><a href="/downloads/">Downloads</a></li>
<li><a href="/community/">Community</a></li>
</ul>
</div><!-- /#mesos-menu -->
</div><!-- /.container -->
</div><!-- /.navbar -->
<div class="content">
<div class="container">
<div class="row-fluid">
<div class="col-md-4">
<h4>If you're new to Mesos</h4>
<p>See the <a href="/gettingstarted/">getting started</a> page for more
information about downloading, building, and deploying Mesos.</p>
<h4>If you'd like to get involved or you're looking for support</h4>
<p>See our <a href="/community/">community</a> page for more details.</p>
</div>
<div class="col-md-8">
<h1>Mesos Observability Metrics</h1>
<p>This document describes the observability metrics provided by Mesos master and
agent nodes. This document also provides some initial guidance on which metrics
you should monitor to detect abnormal situations in your cluster.</p>
<h2>Overview</h2>
<p>Mesos master and agent nodes report a set of statistics and metrics that enable
cluster operators to monitor resource usage and detect abnormal situations early. The
information reported by Mesos includes details about available resources, used
resources, registered frameworks, active agents, and task state. You can use
this information to create automated alerts and to plot different metrics over
time inside a monitoring dashboard.</p>
<p>Metric information is not persisted to disk at either master or agent
nodes, which means that metrics will be reset when masters and agents
are restarted. Similarly, if the current leading master fails and a new
leading master is elected, metrics at the new master will be reset.</p>
<h2>Metric Types</h2>
<p>Mesos provides two different kinds of metrics: counters and gauges.</p>
<p><strong>Counters</strong> keep track of discrete events and are monotonically increasing. The
value of a metric of this type is always a natural number. Examples include the
number of failed tasks and the number of agent registrations. For some metrics
of this type, the rate of change is often more useful than the value itself.</p>
<p><strong>Gauges</strong> represent an instantaneous sample of some magnitude. Examples include
the amount of used memory in the cluster and the number of connected agents. For
some metrics of this type, it is often useful to determine whether the value is
above or below a threshold for a sustained period of time.</p>
<p>The tables in this document indicate the type of each available metric.</p>
<h2>Master Nodes</h2>
<p>Metrics from each master node are available via the
<a href="/documentation/latest/./endpoints/metrics/snapshot/">/metrics/snapshot</a> master endpoint. The response
is a JSON object that contains metrics names and values as key-value pairs.</p>
<h3>Observability metrics</h3>
<p>This section lists all available metrics from Mesos master nodes grouped by
category.</p>
<h4>Resources</h4>
<p>The following metrics provide information about the total resources available in
the cluster and their current usage. High resource usage for sustained periods
of time may indicate that you need to add capacity to your cluster or that a
framework is misbehaving.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>master/cpus_percent</code>
</td>
<td>Percentage of allocated CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/cpus_used</code>
</td>
<td>Number of allocated CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/cpus_total</code>
</td>
<td>Number of CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/cpus_revocable_percent</code>
</td>
<td>Percentage of allocated revocable CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/cpus_revocable_total</code>
</td>
<td>Number of revocable CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/cpus_revocable_used</code>
</td>
<td>Number of allocated revocable CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/disk_percent</code>
</td>
<td>Percentage of allocated disk space</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/disk_used</code>
</td>
<td>Allocated disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/disk_total</code>
</td>
<td>Disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/disk_revocable_percent</code>
</td>
<td>Percentage of allocated revocable disk space</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/disk_revocable_total</code>
</td>
<td>Revocable disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/disk_revocable_used</code>
</td>
<td>Allocated revocable disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/gpus_percent</code>
</td>
<td>Percentage of allocated GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/gpus_used</code>
</td>
<td>Number of allocated GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/gpus_total</code>
</td>
<td>Number of GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/gpus_revocable_percent</code>
</td>
<td>Percentage of allocated revocable GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/gpus_revocable_total</code>
</td>
<td>Number of revocable GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/gpus_revocable_used</code>
</td>
<td>Number of allocated revocable GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/mem_percent</code>
</td>
<td>Percentage of allocated memory</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/mem_used</code>
</td>
<td>Allocated memory in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/mem_total</code>
</td>
<td>Memory in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/mem_revocable_percent</code>
</td>
<td>Percentage of allocated revocable memory</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/mem_revocable_total</code>
</td>
<td>Revocable memory in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/mem_revocable_used</code>
</td>
<td>Allocated revocable memory in MB</td>
<td>Gauge</td>
</tr>
</table>
<h4>Master</h4>
<p>The following metrics provide information about whether a master is currently
elected and how long it has been running. A cluster with no elected master
for sustained periods of time indicates a malfunctioning cluster. This
points to either leadership election issues (so check the connection to
ZooKeeper) or a flapping Master process. A low uptime value indicates that the
master has restarted recently.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>master/elected</code>
</td>
<td>Whether this is the elected master</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/uptime_secs</code>
</td>
<td>Uptime in seconds</td>
<td>Gauge</td>
</tr>
</table>
<h4>System</h4>
<p>The following metrics provide information about the resources available on this
master node and their current usage. High resource usage in a master node for
sustained periods of time may degrade the performance of the cluster.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>system/cpus_total</code>
</td>
<td>Number of CPUs available in this master node</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/load_15min</code>
</td>
<td>Load average for the past 15 minutes</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/load_5min</code>
</td>
<td>Load average for the past 5 minutes</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/load_1min</code>
</td>
<td>Load average for the past minute</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/mem_free_bytes</code>
</td>
<td>Free memory in bytes</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/mem_total_bytes</code>
</td>
<td>Total memory in bytes</td>
<td>Gauge</td>
</tr>
</table>
<h4>Agents</h4>
<p>The following metrics provide information about agent events, agent counts, and
agent states. A low number of active agents may indicate that agents are
unhealthy or that they are not able to connect to the elected master.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>master/slave_registrations</code>
</td>
<td>Number of agents that were able to cleanly re-join the cluster and
connect back to the master after the master is disconnected.</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/slave_removals</code>
</td>
<td>Number of agent removed for various reasons, including maintenance</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/slave_reregistrations</code>
</td>
<td>Number of agent re-registrations</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/slave_unreachable_scheduled</code>
</td>
<td>Number of agents which have failed their health check and are scheduled
to be marked unreachable. They will not be marked unreachable immediately due to the Agent
Removal Rate-Limit, but <code>master/slave_unreachable_completed</code>
will start increasing as they do get removed.</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/slave_unreachable_canceled</code>
</td>
<td>Number of times that an agent was due to be marked unreachable but this
transition was cancelled. This happens when the agent removal rate limit
is enabled and the agent sends a <code>PONG</code> response message to the
master before the rate limit allows the agent to be marked unreachable.</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/slave_unreachable_completed</code>
</td>
<td>Number of agents that were marked as unreachable because they failed
health checks. These are agents which were not heard from despite the
agent-removal rate limit, and have been marked as unreachable in the
master's agent registry.</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/slaves_active</code>
</td>
<td>Number of active agents</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/slaves_connected</code>
</td>
<td>Number of connected agents</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/slaves_disconnected</code>
</td>
<td>Number of disconnected agents</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/slaves_inactive</code>
</td>
<td>Number of inactive agents</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/slaves_inactive</code>
</td>
<td>Number of unreachable agents. Unreachable agents are periodically
garbage collected from the registry, which will cause this value to
decrease.</td>
<td>Gauge</td>
</tr>
</table>
<h4>Frameworks</h4>
<p>The following metrics provide information about the registered frameworks in the
cluster. No active or connected frameworks may indicate that a scheduler is not
registered or that it is misbehaving.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>master/frameworks_active</code>
</td>
<td>Number of active frameworks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/frameworks_connected</code>
</td>
<td>Number of connected frameworks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/frameworks_disconnected</code>
</td>
<td>Number of disconnected frameworks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/frameworks_inactive</code>
</td>
<td>Number of inactive frameworks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/outstanding_offers</code>
</td>
<td>Number of outstanding resource offers</td>
<td>Gauge</td>
</tr>
</table>
<h4>Tasks</h4>
<p>The following metrics provide information about active and terminated tasks. A
high rate of lost tasks may indicate that there is a problem with the cluster.
The task states listed here match those of the task state machine.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>master/tasks_error</code>
</td>
<td>Number of tasks that were invalid</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/tasks_failed</code>
</td>
<td>Number of failed tasks</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/tasks_finished</code>
</td>
<td>Number of finished tasks</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/tasks_killed</code>
</td>
<td>Number of killed tasks</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/tasks_killing</code>
</td>
<td>Number of tasks currently being killed</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/tasks_lost</code>
</td>
<td>Number of lost tasks</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/tasks_running</code>
</td>
<td>Number of running tasks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/tasks_staging</code>
</td>
<td>Number of staging tasks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/tasks_starting</code>
</td>
<td>Number of starting tasks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/tasks_unreachable</code>
</td>
<td>Number of unreachable tasks</td>
<td>Gauge</td>
</tr>
</table>
<h4>Messages</h4>
<p>The following metrics provide information about messages between the master and
the agents and between the framework and the executors. A high rate of dropped
messages may indicate that there is a problem with the network.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>master/invalid_executor_to_framework_messages</code>
</td>
<td>Number of invalid executor to framework messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/invalid_framework_to_executor_messages</code>
</td>
<td>Number of invalid framework to executor messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/invalid_status_update_acknowledgements</code>
</td>
<td>Number of invalid status update acknowledgements</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/invalid_status_updates</code>
</td>
<td>Number of invalid status updates</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/dropped_messages</code>
</td>
<td>Number of dropped messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_authenticate</code>
</td>
<td>Number of authentication messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_deactivate_framework</code>
</td>
<td>Number of framework deactivation messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_decline_offers</code>
</td>
<td>Number of offers declined</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_executor_to_framework</code>
</td>
<td>Number of executor to framework messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_exited_executor</code>
</td>
<td>Number of terminated executor messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_framework_to_executor</code>
</td>
<td>Number of messages from a framework to an executor</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_kill_task</code>
</td>
<td>Number of kill task messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_launch_tasks</code>
</td>
<td>Number of launch task messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_reconcile_tasks</code>
</td>
<td>Number of reconcile task messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_register_framework</code>
</td>
<td>Number of framework registration messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_register_slave</code>
</td>
<td>Number of agent registration messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_reregister_framework</code>
</td>
<td>Number of framework re-registration messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_reregister_slave</code>
</td>
<td>Number of agent re-registration messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_resource_request</code>
</td>
<td>Number of resource request messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_revive_offers</code>
</td>
<td>Number of offer revival messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_status_update</code>
</td>
<td>Number of status update messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_status_update_acknowledgement</code>
</td>
<td>Number of status update acknowledgement messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_unregister_framework</code>
</td>
<td>Number of framework unregistration messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_unregister_slave</code>
</td>
<td>Number of agent unregistration messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/messages_update_slave</code>
</td>
<td>Number of update agent messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/recovery_slave_removals</code>
</td>
<td>Number of agents not re-registered during master failover</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/slave_removals/reason_registered</code>
</td>
<td>Number of agents removed when new agents registered at the same address</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/slave_removals/reason_unhealthy</code>
</td>
<td>Number of agents failed due to failed health checks</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/slave_removals/reason_unregistered</code>
</td>
<td>Number of agents unregistered</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/valid_framework_to_executor_messages</code>
</td>
<td>Number of valid framework to executor messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/valid_status_update_acknowledgements</code>
</td>
<td>Number of valid status update acknowledgement messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/valid_status_updates</code>
</td>
<td>Number of valid status update messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/task_lost/source_master/reason_invalid_offers</code>
</td>
<td>Number of tasks lost due to invalid offers</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/task_lost/source_master/reason_slave_removed</code>
</td>
<td>Number of tasks lost due to agent removal</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/task_lost/source_slave/reason_executor_terminated</code>
</td>
<td>Number of tasks lost due to executor termination</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>master/valid_executor_to_framework_messages</code>
</td>
<td>Number of valid executor to framework messages</td>
<td>Counter</td>
</tr>
</table>
<h4>Event queue</h4>
<p>The following metrics provide information about different types of events in the
event queue.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>master/event_queue_dispatches</code>
</td>
<td>Number of dispatches in the event queue</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/event_queue_http_requests</code>
</td>
<td>Number of HTTP requests in the event queue</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>master/event_queue_messages</code>
</td>
<td>Number of messages in the event queue</td>
<td>Gauge</td>
</tr>
</table>
<h4>Registrar</h4>
<p>The following metrics provide information about read and write latency to the
agent registrar.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>registrar/state_fetch_ms</code>
</td>
<td>Registry read latency in ms </td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>registrar/state_store_ms</code>
</td>
<td>Registry write latency in ms </td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>registrar/state_store_ms/max</code>
</td>
<td>Maximum registry write latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>registrar/state_store_ms/min</code>
</td>
<td>Minimum registry write latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>registrar/state_store_ms/p50</code>
</td>
<td>Median registry write latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>registrar/state_store_ms/p90</code>
</td>
<td>90th percentile registry write latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>registrar/state_store_ms/p95</code>
</td>
<td>95th percentile registry write latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>registrar/state_store_ms/p99</code>
</td>
<td>99th percentile registry write latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>registrar/state_store_ms/p999</code>
</td>
<td>99.9th percentile registry write latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>registrar/state_store_ms/p9999</code>
</td>
<td>99.99th percentile registry write latency in ms</td>
<td>Gauge</td>
</tr>
</table>
<h4>Replicated log</h4>
<p>The following metrics provide information about the replicated log underneath
the registrar, which is the persistent store for masters.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>registrar/log/recovered</code>
</td>
<td>
Whether the replicated log for the registrar has caught up with the other
masters in the cluster. A cluster is operational as long as a quorum of
"recovered" masters is available in the cluster.
</td>
<td>Gauge</td>
</tr>
</table>
<h4>Allocator</h4>
<p>The following metrics provide information about performance
and resource allocations in the allocator.</p>
<table class="table table-stripped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms</code>
</td>
<td>Allocation algorithm latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms/count</code>
</td>
<td>Number of allocation algorithm latency measurements in the window</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms/max</code>
</td>
<td>Maximum allocation algorithm latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms/min</code>
</td>
<td>Minimum allocation algorithm latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms/p50</code>
</td>
<td>Median allocation algorithm latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms/p90</code>
</td>
<td>90th percentile allocation algorithm latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms/p95</code>
</td>
<td>95th percentile allocation algorithm latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms/p99</code>
</td>
<td>99th percentile allocation algorithm latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms/p999</code>
</td>
<td>99.9th percentile allocation algorithm latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_run_ms/p9999</code>
</td>
<td>99.99th percentile allocation algorithm latency in ms</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/allocation_runs</code>
</td>
<td>Number of times the allocation algorithm has run</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>allocator/mesos/roles/&lt;role&gt;/shares/dominant</code>
</td>
<td>Dominant resource share for the role, exposed as a percentage (0.0-1.0)</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/event_queue_dispatches</code>
</td>
<td>Number of dispatch events in the event queue</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/offer_filters/roles/&lt;role&gt;/active</code>
</td>
<td>Number of active offer filters for all frameworks within the role</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/quota/roles/&lt;role&gt;/resources/&lt;resource&gt;/offered_or_allocated</code>
</td>
<td>Amount of resources considered offered or allocated towards
a role's quota guarantee</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/quota/roles/&lt;role&gt;/resources/&lt;resource&gt;/guarantee</code>
</td>
<td>Amount of resources guaranteed for a role via quota</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/resources/cpus/offered_or_allocated</code>
</td>
<td>Number of CPUs offered or allocated</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/resources/cpus/total</code>
</td>
<td>Number of CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/resources/disk/offered_or_allocated</code>
</td>
<td>Allocated or offered disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/resources/disk/total</code>
</td>
<td>Total disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/resources/mem/offered_or_allocated</code>
</td>
<td>Allocated or offered memory in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>allocator/mesos/resources/mem/total</code>
</td>
<td>Total memory in MB</td>
<td>Gauge</td>
</tr>
</table>
<h3>Basic Alerts</h3>
<p>This section lists some examples of basic alerts that you can use to detect
abnormal situations in a cluster.</p>
<h4>master/uptime_secs is low</h4>
<p>The master has restarted.</p>
<h4>master/uptime_secs &lt; 60 for sustained periods of time</h4>
<p>The cluster has a flapping master node.</p>
<h4>master/tasks_lost is increasing rapidly</h4>
<p>Tasks in the cluster are disappearing. Possible causes include hardware
failures, bugs in one of the frameworks, or bugs in Mesos.</p>
<h4>master/slaves_active is low</h4>
<p>Agents are having trouble connecting to the master.</p>
<h4>master/cpus_percent > 0.9 for sustained periods of time</h4>
<p>Cluster CPU utilization is close to capacity.</p>
<h4>master/mem_percent > 0.9 for sustained periods of time</h4>
<p>Cluster memory utilization is close to capacity.</p>
<h4>master/elected is 0 for sustained periods of time</h4>
<p>No master is currently elected.</p>
<h2>Agent Nodes</h2>
<p>Metrics from each agent node are available via the
<a href="/documentation/latest/./endpoints/metrics/snapshot/">/metrics/snapshot</a> agent endpoint. The response
is a JSON object that contains metrics names and values as key-value pairs.</p>
<h3>Observability Metrics</h3>
<p>This section lists all available metrics from Mesos agent nodes grouped by
category.</p>
<h4>Resources</h4>
<p>The following metrics provide information about the total resources available in
the agent and their current usage.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>slave/cpus_percent</code>
</td>
<td>Percentage of allocated CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/cpus_used</code>
</td>
<td>Number of allocated CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/cpus_total</code>
</td>
<td>Number of CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/cpus_revocable_percent</code>
</td>
<td>Percentage of allocated revocable CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/cpus_revocable_total</code>
</td>
<td>Number of revocable CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/cpus_revocable_used</code>
</td>
<td>Number of allocated revocable CPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/disk_percent</code>
</td>
<td>Percentage of allocated disk space</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/disk_used</code>
</td>
<td>Allocated disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/disk_total</code>
</td>
<td>Disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/gpus_percent</code>
</td>
<td>Percentage of allocated GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/gpus_used</code>
</td>
<td>Number of allocated GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/gpus_total</code>
</td>
<td>Number of GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/gpus_revocable_percent</code>
</td>
<td>Percentage of allocated revocable GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/gpus_revocable_total</code>
</td>
<td>Number of revocable GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/gpus_revocable_used</code>
</td>
<td>Number of allocated revocable GPUs</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/mem_percent</code>
</td>
<td>Percentage of allocated memory</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/disk_revocable_percent</code>
</td>
<td>Percentage of allocated revocable disk space</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/disk_revocable_total</code>
</td>
<td>Revocable disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/disk_revocable_used</code>
</td>
<td>Allocated revocable disk space in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/mem_used</code>
</td>
<td>Allocated memory in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/mem_total</code>
</td>
<td>Memory in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/mem_revocable_percent</code>
</td>
<td>Percentage of allocated revocable memory</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/mem_revocable_total</code>
</td>
<td>Revocable memory in MB</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/mem_revocable_used</code>
</td>
<td>Allocated revocable memory in MB</td>
<td>Gauge</td>
</tr>
</table>
<h4>Agent</h4>
<p>The following metrics provide information about whether an agent is currently
registered with a master and for how long it has been running.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>slave/registered</code>
</td>
<td>Whether this agent is registered with a master</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/uptime_secs</code>
</td>
<td>Uptime in seconds</td>
<td>Gauge</td>
</tr>
</table>
<h4>System</h4>
<p>The following metrics provide information about the agent system.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>system/cpus_total</code>
</td>
<td>Number of CPUs available</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/load_15min</code>
</td>
<td>Load average for the past 15 minutes</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/load_5min</code>
</td>
<td>Load average for the past 5 minutes</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/load_1min</code>
</td>
<td>Load average for the past minute</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/mem_free_bytes</code>
</td>
<td>Free memory in bytes</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>system/mem_total_bytes</code>
</td>
<td>Total memory in bytes</td>
<td>Gauge</td>
</tr>
</table>
<h4>Executors</h4>
<p>The following metrics provide information about the executor instances running
on the agent.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>containerizer/mesos/container_destroy_errors</code>
</td>
<td>Number of containers destroyed due to launch errors</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/container_launch_errors</code>
</td>
<td>Number of container launch errors</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/executors_preempted</code>
</td>
<td>Number of executors destroyed due to preemption</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/frameworks_active</code>
</td>
<td>Number of active frameworks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/executor_directory_max_allowed_age_secs</code>
</td>
<td>Maximum allowed age in seconds to delete executor directory</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/executors_registering</code>
</td>
<td>Number of executors registering</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/executors_running</code>
</td>
<td>Number of executors running</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/executors_terminated</code>
</td>
<td>Number of terminated executors</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/executors_terminating</code>
</td>
<td>Number of terminating executors</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/recovery_errors</code>
</td>
<td>Number of errors encountered during agent recovery</td>
<td>Gauge</td>
</tr>
</table>
<h4>Tasks</h4>
<p>The following metrics provide information about active and terminated tasks.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>slave/tasks_failed</code>
</td>
<td>Number of failed tasks</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/tasks_finished</code>
</td>
<td>Number of finished tasks</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/tasks_killed</code>
</td>
<td>Number of killed tasks</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/tasks_lost</code>
</td>
<td>Number of lost tasks</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/tasks_running</code>
</td>
<td>Number of running tasks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/tasks_staging</code>
</td>
<td>Number of staging tasks</td>
<td>Gauge</td>
</tr>
<tr>
<td>
<code>slave/tasks_starting</code>
</td>
<td>Number of starting tasks</td>
<td>Gauge</td>
</tr>
</table>
<h4>Messages</h4>
<p>The following metrics provide information about messages between the agents and
the master it is registered with.</p>
<table class="table table-striped">
<thead>
<tr><th>Metric</th><th>Description</th><th>Type</th>
</thead>
<tr>
<td>
<code>slave/invalid_framework_messages</code>
</td>
<td>Number of invalid framework messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/invalid_status_updates</code>
</td>
<td>Number of invalid status updates</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/valid_framework_messages</code>
</td>
<td>Number of valid framework messages</td>
<td>Counter</td>
</tr>
<tr>
<td>
<code>slave/valid_status_updates</code>
</td>
<td>Number of valid status updates</td>
<td>Counter</td>
</tr>
</table>
</div>
</div>
</div><!-- /.container -->
</div><!-- /.content -->
<hr>
<!-- footer -->
<div class="footer">
<div class="container">
<div class="col-md-4 social-blk">
<span class="social">
<a href="https://twitter.com/ApacheMesos"
class="twitter-follow-button"
data-show-count="false" data-size="large">Follow @ApacheMesos</a>
<script>!function(d,s,id){var js,fjs=d.getElementsByTagName(s)[0],p=/^http:/.test(d.location)?'http':'https';if(!d.getElementById(id)){js=d.createElement(s);js.id=id;js.src=p+'://platform.twitter.com/widgets.js';fjs.parentNode.insertBefore(js,fjs);}}(document, 'script', 'twitter-wjs');</script>
<a href="https://twitter.com/intent/tweet?button_hashtag=mesos"
class="twitter-hashtag-button"
data-size="large"
data-related="ApacheMesos">Tweet #mesos</a>
<script>!function(d,s,id){var js,fjs=d.getElementsByTagName(s)[0],p=/^http:/.test(d.location)?'http':'https';if(!d.getElementById(id)){js=d.createElement(s);js.id=id;js.src=p+'://platform.twitter.com/widgets.js';fjs.parentNode.insertBefore(js,fjs);}}(document, 'script', 'twitter-wjs');</script>
</span>
</div>
<div class="col-md-8 trademark">
<p>&copy; 2012-2017 <a href="http://apache.org">The Apache Software Foundation</a>.
Apache Mesos, the Apache feather logo, and the Apache Mesos project logo are trademarks of The Apache Software Foundation.
<p>
</div>
</div><!-- /.container -->
</div><!-- /.footer -->
<!-- JS -->
<script src="//code.jquery.com/jquery-1.11.0.min.js" type="text/javascript"></script>
<script src="//netdna.bootstrapcdn.com/bootstrap/3.1.1/js/bootstrap.min.js" type="text/javascript"></script>
</body>
</html>