Bug #28751 Lots of memory locked in memory causes high kswapd
Submitted: 29 May 2007 15:42 Modified: 11 Jun 2007 20:36
Reporter: Tomas Ulin Email Updates:
Status: Closed Impact on me:
Category:MySQL Cluster: Cluster (NDB) storage engine Severity:S3 (Non-critical)
Version: OS:Any
Assigned to: Tomas Ulin CPU Architecture:Any

[29 May 2007 15:42] Tomas Ulin
We observe high kswapd on some systems when ndbd has lots of memory locked in memory (close to system limit)

We see that using O_DIRECT writes lowers kswapd

How to repeat:

Suggested fix:
optionally enable O_DIRECT writing for LCP, redo log, and backup
(disk data already uses O_DIRECT)

is has been noticed that switching of NUMA removes kswapd as well
[5 Jun 2007 15:33] Bugs System
A patch for this bug has been committed. After review, it may
be pushed to the relevant source trees for release in the next
version. You can access the patch from:

[11 Jun 2007 11:39] Bugs System
Pushed into 5.1.20-beta
[11 Jun 2007 20:36] Jon Stephens
Thank you for your bug report. This issue has been committed to our source repository of that product and will be incorporated into the next release.

If necessary, you can access the source repository and build the latest available version, including the bug fix. More information about accessing the source trees is available at


Documented bugfix in 5.1.20 and telco-6.1.11 changelogs.
[3 Jul 2007 6:47] Jon Stephens
Also documented for telco-6.2.3 release.