Whamcloud - gitweb
LU-1279 kernel: Fix concurrent module loading deadlocks 29/11229/6
authorLi Wei <wei.g.li@intel.com>
Fri, 25 Jul 2014 16:14:51 +0000 (00:14 +0800)
committerOleg Drokin <oleg.drokin@intel.com>
Fri, 29 Aug 2014 01:42:10 +0000 (01:42 +0000)
commitfa0b1c66c2527e50cc6d7e4ad4961938155d618e
tree4866df8738b816f8e1611f490c6387c499f5e543
parent06d395dde23c56cf05be0ef2687df87fdb9d1ece
LU-1279 kernel: Fix concurrent module loading deadlocks

Concurrently starting multiple OSTs on a single OSS frequently
triggers 30s deadlocks on module_mutex.  This RHEL 6 kernel bug
applies to any module that results in additional request_module()
calls in its init callback.  In Lustre, at least ptlrpc and libcfs are
affected.  (RHEL 7 should have enough fixes in this area, but testing
needs to be done.)  This patch adds a fix adapted from a number of
upstream commits to the RHEL 6 kernel patch series.

Change-Id: Ibdd384fd7622a0b4fcbf4cb5fdb864de87fcc25e
Signed-off-by: Li Wei <wei.g.li@intel.com>
Reviewed-on: http://review.whamcloud.com/11229
Tested-by: Jenkins
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
lustre/kernel_patches/patches/module-load-deadlock-rhel6.patch [new file with mode: 0644]
lustre/kernel_patches/series/2.6-rhel6.series