RHEL5 kswapd using about 100% system cpu - even though no swap space was used

Solution Verified - Updated -

Issue

  • Several Red Hat Enterprise Linux 5.4, 64-bit cluster nodes are seeing spikes in kswapd, where it is using 100% system CPU.

  • The kswapd used about 100% system cpu - even though no swap space was used

  • The /proc filesystem became partially unaccessible.
  • Because of the inability to access /proc, many processes froze when they tried to access the /proc filesystem, e.g. to read their environment (/proc/PID/environ) file.
  • 2-3 nodes per week  out of a 174 node cluster have to be rebooted because of this.  The users of the cluster report that some of their jobs are stuck, and it discovered that the nodes are in this state whenever the problem occurs.

Environment

  • Red Hat Enterprise Linux 5.4
  • Dell PowerEdge R410
  • kernel-2.6.18-164.11.1.el5.x86_64

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase of over 48,000 articles and solutions.

Current Customers and Partners

Log in for full access

Log In
Close

Welcome! Check out the Getting Started with Red Hat page for quick tours and guides for common tasks.