[RHGS] high mem/cpu usage, brick processes not starting while testing CRS scaling with multiplexing

Solution Verified - Updated -

Issue

When testing scaling possibilities of RHGS used as container ready storage with multiplexing, glusterd is failing during provisioning after starting/creating 100-200+ volumes.

Symptoms:

  • all gluster commands end on timeout
  • inconsistent number of /usr/sbin/glusterfsd processes across the cluster
  • glusterd in stale state on some nodes. Running systemctl start/stop/restart has no effect. Only way to stop it is (p)kill -9

Environment

  • Red Hat Gluster Storage 3.3.x

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.

Current Customers and Partners

Log in for full access

Log In

New to Red Hat?

Learn more about Red Hat subscriptions

Using a Red Hat product through a public cloud?

How to access this content