When the client re-mounts the gluster volume, the process changes as follows:
The process PID does not change:
16683 Root 0 398m 16m 2796 S 0.0 0.2 2:31.58/usr/sbin/glusterd--pid-file=/run/glusterd.pid
The following process PID will change and regenerate:
Root 10068 7.9 0.4 302108 39204? SSL 17:19 0:40/usr/sbin/glusterfs--volfile-id=/tank--volfile-server=lab21/mnt/dzq
Root 10093 0.0 0.6 232236 53316? SSL 17:19 0:00/usr/sbin/glusterfs-s localhost--volfile-id gluster/nfs-p/var/lib/glusterd/nfs/run/nfs.pid-l/var/l Og/glusterfs/nfs.log-s/var/run/52fcb2d9e219d2dee4f280489ef3c9d4.socket
Root 10097 0.0 0.2 321604 20108? SSL 17:19 0:00/usr/sbin/glusterfs-s localhost--volfile-id gluster/glustershd-p/var/lib/glusterd/glustershd/run/glu Stershd.pid-l/var/log/glusterfs/glustershd.log-s/var/run/dda19e05b0f00927c31e8b28c8a07f08.socket-- Xlator-option *replicate*.node-uuid=2e830972-f2d2-4da9-8a03-e11e49cfc39e
When setting up CACHE-SIZE=2GB, the following process of the client will open up a corresponding size of physical memory space:
11193 Root 0 2346m 2.0g 2744 S 0.0 26.6 1:39.68/usr/sbin/glusterfs--volfile-id=/tank--volfile-server=lab21 /mnt/dzq
In practice, the client has only one process, and the other above is due to the fact that the Glusterd service is not shutting down:
/usr/sbin/glusterfs--volfile-id=/tank--volfile-server=lab21/mnt/dzq
This article is from the "Members Doukua" blog, make sure to keep this source http://dangzhiqiang.blog.51cto.com/7961271/1653801
Glusterfs Client Process profiling