Red Hat Training

A Red Hat training course is available for Red Hat Enterprise Linux

A.4. Tracing GFS2 Performance Data

With PCP installed and the GFS2 PMDA enabled, the easiest way to start looking at the performance metrics available for PCP and GFS2 is to make use of the pminfo tool. The pminfo command line tool displays information about available performance metrics. Normally pminfo operates using the local metric namespace but you can change this to view the metrics on a remote host by using the -h flag, For further information on the pminfo tool, see the pminfo(1) man page.
The following command displays a list of all available GFS2 metrics provided by the GFS2 PMDA. 
# pminfo gfs2
You can specify the -T flag order to obtain help information and descriptions for each metric along with the -f flag to obtain a current reading of the performance value that corresponds to each metric. You can do this for a group of metrics or an individual metric. Most metric data is provided for each mounted GFS2 file system on the system at time of probing. 
# pminfo -t gfs2.glocks
gfs2.glocks.total [Count of total observed incore GFS2 global locks] 
gfs2.glocks.shared [GFS2 global locks in shared state] 
gfs2.glocks.unlocked [GFS2 global locks in unlocked state] 
gfs2.glocks.deferred [GFS2 global locks in deferred state] 
gfs2.glocks.exclusive [GFS2 global locks in exclusive state] 

# pminfo -T gfs2.glocks.total

gfs2.glocks.total 
Help: 
Count of total incore GFS2 glock data structures based on parsing the contents 
of the /sys/kernel/debug/gfs2/bdev/glocks files. 

# pminfo -f gfs2.glocks.total

gfs2.glocks.total 
    inst [0 or "testcluster:clvmd_gfs2"] value 74
There are six different groups of GFS2 metrics, are arranged so that each different group is a new leaf node from the root GFS2 metric using a '.' as a separator; this is true for all PCP metrics. Table A.2, “PCP Metric Groups for GFS2” outlines the types of metrics that are available in each of the groups. With each metric, additional information can be found by using the pminfo tool with the -T flag.

Table A.2. PCP Metric Groups for GFS2

Metric GroupMetric Provided
gfs2.sbstats.* Timing metrics regarding the information collected from the superblock stats file (sbstats) for each GFS2 file system currently mounted on the system.
gfs2.glocks.* Metrics regarding the information collected from the glock stats file (glocks) which count the number of glocks in each state that currently exists for each GFS2 file system currently mounted on the system.
gfs2.glstats.* Metrics regarding the information collected from the glock stats file (glstats) which count the number of each type of glock that currently exists for each GFS2 file system currently mounted on the system.
gfs2.tracepoints.* Metrics regarding the output from the GFS2 debugfs tracepoints for each file system currently mounted on the system. Each sub-type of these metrics (one of each GFS2 tracepoint) can be individually controlled whether on or off using the control metrics.
gfs2.worst_glock.* A computed metric making use of the data from the gfs2_glock_lock_time tracepoint to calculate a perceived “current worst glock” for each mounted file system. This metric is useful for discovering potential lock contention and file system slows down if the same lock is suggested multiple times.
gfs2.latency.grant.* A computed metric making use of the data from both the gfs2_glock_queue and gfs2_glock_state_change tracepoints to calculate an average latency in microseconds for glock grant requests to be completed for each mounted file system. This metric is useful for discovering potential slowdowns on the file system when the grant latency increases.
gfs2.latency.demote.* A computed metric making use of the data from both the gfs2_glock_state_change and gfs2_demote_rq tracepoints to calculate an average latency in microseconds for glock demote requests to be completed for each mounted file system. This metric is useful for discovering potential slowdowns on the file system when the demote latency increases.
gfs2.latency.queue.* A computed metric making use of the data from the gfs2_glock_queue tracepoint to calculate an average latency in microseconds for glock queue requests to be completed for each mounted file system.
gfs2.control.* Configuration metrics which are used to control what tracepoint metrics are currently enabled or disabled and are toggled by means of the pmstore tool. These configuration metrics are described in Section A.5, “Metric Configuration (using pmstore)”.