|Index|Analyzing System Metrics with Performance Co-Pilot
SUSE Linux Enterprise Server 16.1

Analyzing System Metrics with Performance Co-Pilot

Publication Date: 05 Nov 2026

The Performance Co-Pilot (PCP) analysis toolkit collects, processes and analyzes system performance metrics, either in real time or from archived logs. SUSE Linux Enterprise Server provides PCP as regular packages, so you install and configure it like any other system service, without needing a container runtime. Use PCP to monitor a single system locally or to centralize monitoring of several remote systems on one host.

Prerequisites

  • A running, registered instance of SUSE Linux Enterprise Server

1 What is Performance Co-Pilot analysis toolkit?

 

Performance data is collected by performance metrics domain agents (PMDAs), one per subsystem such as the kernel, disks or a database. Each PMDA passes its metrics to the pmcd daemon, which is the single point of contact for all other PCP tools. pmlogger is the tool that turns those live metrics into an archive you can query later, and pminfo queries them directly, without logging anything.

2 Installing PCP

 

This chapter covers installing pcp via Zypper in standard mode or via transactional-update in immutable mode.

2.1 Installing PCP in standard mode

 

Install the pcp package with Zypper: 

> sudo zypper install pcp

Alternatively, install the pcp-zeroconf package instead. It installs pcp as a dependency and additionally enables and starts pmcd, pmlogger and pmproxy automatically, with a shorter, 10-second sampling interval. Use it if you want local monitoring running immediately without configuring the services yourself, as described in Section 3, “Enabling PCP services”: 

> sudo zypper install pcp-zeroconf

2.2 Installing PCP in immutable mode

 

On the immutable mode of SLES, install either package through transactional-update instead: 

> sudo transactional-update pkg install pcp

Or, for the zero-configuration variant: 

> sudo transactional-update pkg install pcp-zeroconf

Changes take effect only after a reboot: 

> sudo reboot

3 Enabling PCP services

 

Installing the pcp package installs several systemd services, all disabled by default. PCP provides the following services:

pmcd

The Performance Metrics Collector Daemon. It coordinates the gathering and exporting of performance statistics in response to requests from PCP tools, and is required by every other PCP service. By default, it listens only on the local host, on port 44321.

pmlogger

Records the metrics exported by pmcd to archive logs, by default under /var/log/pcp/pmlogger/HOSTNAME/.

pmproxy

Exposes a REST API (PMWEBAPI) to access metrics remotely, on port 44322 by default. Unlike pmcd, it listens on all interfaces by default.

pmie

The inference engine. It evaluates the exported metrics against a set of rules and can trigger an action, for example, an alert, when a rule matches.

Enable and start the services you need with systemctl. For example, to enable local metric collection and logging: 

> sudo systemctl enable --now pmcd pmlogger

Add pmproxy or pmie to the same command if you need the REST API or the inference engine.

By default, pmcd only accepts connections from the local host, and firewalld does not open a port for either pmcd or pmproxy. If you need to reach either service from another system, open the corresponding port: 

> sudo firewall-cmd --add-port=PORT/tcp --permanent
> sudo firewall-cmd --reload

Use port 44321 for pmcd and 44322 for pmproxy. Allowing remote connections to pmcd also requires changing PMCD_LOCAL, as described in Section 4, “Configuring pmcd and pmlogger”.

4 Configuring pmcd and pmlogger

 

Every PCP service has a default configuration that might not suit your needs. To customize a service, edit its configuration file directly and restart the service. For example, to customize pmcd, run: 

> sudo vi /etc/sysconfig/pmcd
> sudo systemctl restart pmcd

4.1 Configuring the pmcd daemon

 

The pmcd daemon configuration is stored in the /etc/sysconfig/pmcd file. The file stores environment variables that modify the behavior of the pmcd daemon.

You can add the following variables to the /etc/sysconfig/pmcd file to configure the pmcd daemon:

PMCD_LOCAL

Defines whether a remote host can connect to the pmcd daemon. If set to 0, remote connections to the daemon are allowed. If set to 1, the daemon listens only on the local host. The default value is 1.

PMCD_MAXPENDING

Defines the maximum count of pending connections to the agent. The default value is 5.

PMCD_ROOT_AGENT

If the pmdaroot is enabled (the value is set to 1), adding a new PDMA does not trigger restarting of other PMDAs. If pmdaroot is not enabled, pmcd will require restarting all PMDAs when a new PMDA is added. The default value is 1.

PMCD_RESTART_AGENTS

If set to 1, the pmcd daemon tries to restart any exited PMDA. Enable this option only if you have enabled pmdaroot, as pmcd itself does not have privileges to restart PMDA. The default value is 1.

PMCD_WAIT_TIMEOUT

Defines the maximum time in seconds pmcd can wait to accept a connection. After this time, the connection is reported as failed. The default value is 60.

PCP_NSS_INIT_MODE

Defines the mode in which pmcd initializes the NSS certificate database when secured connections are used. The default value is readonly. You can set the mode to readwrite, but if the initialization fails, the default value is used as a fallback.

For example, to allow remote connections and increase the connection timeout, change only these two lines and leave the rest at their default: 

PMCD_LOCAL=0
PMCD_WAIT_TIMEOUT=70

4.2 Setting pmlogger variables

 

The custom configuration for the pmlogger is stored in the following configuration files:

  • /etc/sysconfig/pmlogger

  • /etc/pcp/pmlogger/control.d/local

4.2.1 The /etc/sysconfig/pmlogger file

 

You can use the following attributes to configure the pmlogger:

PMLOGGER_LOCAL

Defines whether pmlogger allows connections from remote hosts. If set to 1, pmlogger allows connections from a local host only. The default value is 1.

PMLOGGER_MAXPENDING

Defines the maximum count of pending connections. The default value is 5.

PMLOGGER_INTERVAL

Defines the default sampling interval pmlogger uses. The default value is 60 s, unless pcp-zeroconf is installed, in which case the default is 10 s. The pmlogger command line overrides this value.

PMLOGGER_CHECK_SKIP_LOGCONF

Setting this option to yes disables the regeneration and checking of the pmlogger configuration if the configuration pmlogger comes from pmlogconf. The default behavior is to regenerate configuration files and check for changes every time pmlogger is started.

PMLOGGER_CHECK_SKIP_JANITOR

By default, pmlogger_check also runs pmlogger_janitor to detect pmlogger processes or files that became detached from the control files that used to manage them. Setting this option to yes disables pmlogger_janitor, which can be useful for QA or other special testing.

An example follows: 

PMLOGGER_LOCAL=1
PMLOGGER_MAXPENDING=5
PMLOGGER_INTERVAL=10
PMLOGGER_CHECK_SKIP_LOGCONF=yes

4.2.2 The /etc/pcp/pmlogger/control.d/local file

 

The file /etc/pcp/pmlogger/control.d/local stores specifications of the host, which metrics should be logged, the logging frequency (default is 24 hours), and pmlogger options. For example: 

# === VARIABLE ASSIGNMENTS ===
#
# DO NOT REMOVE OR EDIT THE FOLLOWING LINE
$version=1.1

# Uncomment one of the lines below to enable/disable compression behaviour
# that is different to the pmlogger_daily default.
# Value is days before compressing archives, 0 is immediate compression,
# "never" or "forever" suppresses compression.
#
#$PCP_COMPRESSAFTER=0
#$PCP_COMPRESSAFTER=3
#$PCP_COMPRESSAFTER=never

# === LOGGER CONTROL SPECIFICATIONS ===
#
#Host           P?  S?  directory                       args

# local primary logger
LOCALHOSTNAME   y   n   PCP_ARCHIVE_DIR/LOCALHOSTNAME   -r -T24h10m -c config.default -v 100Mb
Note
Note: Local host by default

The LOCALHOSTNAME entry shown above logs metrics from the local host only. To collect metrics from a remote client instead, see Section 5.3, “Recording metrics from remote systems”.

5 Managing PCP metrics

 

To check the local setup, use pminfo to list metrics and the pcp command. You can also collect metrics from remote systems on one central host.

5.1 Listing PCP metrics

 

When pmcd is running, use the command pminfo to list metrics. It requires no special privileges. For example, to list all available performance metrics, run: 

> pminfo

You can list a group of related metrics by specifying the metrics prefix: 

> pminfo METRIC_PREFIX

For example, to list all metrics related to disks, use: 

> pminfo disk

disk.dev.r_await
disk.dm.await
disk.dm.r_await
disk.md.await
disk.md.r_await
...

You can also specify additional strings to narrow down the list of metrics, for example: 

> pminfo disk.dev

disk.dev.read
disk.dev.write
disk.dev.total
disk.dev.blkread
disk.dev.blkwrite
disk.dev.blktotal
...

To get online help text of a particular metric, use the -t option followed by the metric, for example: 

> pminfo -t kernel.cpu.util.user

kernel.cpu.util.user [percentage of user time across all CPUs, including guest CPU time]

To display a description text of a particular metric, use the -T option followed by the metric, for example: 

> pminfo -T kernel.cpu.util.user

Help:
percentage of user time across all CPUs, including guest CPU time

5.2 Checking local metrics

 

After you enable the PCP services, you can verify that metrics are being recorded properly by running the following command: 

> sudo pcp

Performance Co-Pilot configuration on node1:

 platform: Linux node1 6.12.0-160099.49-default #1 SMP PREEMPT_DYNAMIC Thu Aug 6 09:32:38 UTC 2026 (e38429b) x86_64
 hardware: 2 cpus, 1 disk, 1 node, 3917MB RAM
 timezone: UTC
 services: pmcd pmproxy
     pmcd: Version 6.3.8-1, 9 agents, 1 client
     pmda: root pmcd proc pmproxy xfs linux mmv kvm jbd2
 pmlogger: primary logger: /var/log/pcp/pmlogger/node1/20260607.09.24

Now check if the logs are written to a proper destination: 

> ls PATH_TO_PMLOGGER_LOGS

where PATH_TO_PMLOGGER_LOGS should be /var/log/pcp/pmlogger/HOSTNAME/, with HOSTNAME being the machine's own host name, the output of the hostname command—for example, /var/log/pcp/pmlogger/node1/.

5.3 Recording metrics from remote systems

 

You can collect metrics from several remote systems (clients) on a central monitoring system. Each client needs only pmcd running and reachable. pmlogger on the monitoring system then pulls the metrics from every client and logs them locally.

Procedure 1: Recording metrics from a remote client
 

  1. On each client, install PCP as described in Section 2, “Installing PCP”, then allow remote connections and enable pmcd: 

    > sudo sed -i 's/^PMCD_LOCAL=1/PMCD_LOCAL=0/' /etc/sysconfig/pmcd
> sudo systemctl enable --now pmcd

  2. On each client, open the pmcd port in firewalld: 

    > sudo firewall-cmd --add-port=44321/tcp --permanent
> sudo firewall-cmd --reload

  3. On the monitoring system, create a pmlogger control file for each client under /etc/pcp/pmlogger/control.d/, for example /etc/pcp/pmlogger/control.d/CLIENT, with the following content: 

    $version=1.1

CLIENT_HOSTNAME n n PCP_ARCHIVE_DIR/CLIENT -N -r -T24h10m -c config.default -v 100Mb

    CLIENT_HOSTNAME must be resolvable in DNS; you can use an IP address or a fully qualified domain name (FQDN) instead. For details about the control file format, see Section 4.2.2, “The /etc/pcp/pmlogger/control.d/local file”.

    Warning
    Warning: Silent logging failure from a pre-created archive directory

    Leave PCP_ARCHIVE_DIR/CLIENT (by default, /var/log/pcp/pmlogger/CLIENT) for pmlogger to create itself, with the correct ownership. If it already exists and is owned by root, pmlogger—which runs as the pcp user—cannot write its lock file there, and logging fails without an obvious error.

  4. Trigger a check so pmlogger applies the new control file immediately, instead of waiting for the next scheduled run of pmlogger_check.timer: 

    > sudo systemctl start pmlogger_check.service

  5. Confirm that metrics are being collected from the client: 

    > ls -l /var/log/pcp/pmlogger/CLIENT/

total 288
-rw-r--r--. 1 pcp pcp  35032 Sep  3 16:07 20260903.16.07.0
-rw-r--r--. 1 pcp pcp    904 Sep  3 16:07 20260903.16.07.index
-rw-r--r--. 1 pcp pcp 219161 Sep  3 16:07 20260903.16.07.meta
-rw-r--r--. 1 pcp pcp    276 Sep  3 16:07 Latest
-rw-r--r--. 1 pcp pcp  27174 Sep  3 16:07 pmlogger.log

6 For more information