RHGS3.1 CPU spikes seen when performance.readdir-ahead option is enabled on the volume mounted with the native client
Issue
When executing "find" command on the volume mounted with "Gluster FUSE", cpu usages become very high 90% ~ 100% approximately. After disabling performance.readdir-ahead option on each volume, it became normal.
What's the cause of this symptom and is there a resolution?
Environment
- Red Hat Gluster Storage 3.1
Subscriber exclusive content
A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.