[Cluster-devel] [PATCH v3 0/4] GFS2 shrinker deadlock

[Andreas Gruenbacher <agruenba@redhat.com>]

With the recent gl_object fixes and an additional reference counting bug
fixed in this patch queue, these four remaining shrinker deadlock
avoidance patches now seem ready for mainline.

As explained in the previous posting of this patch queue, when inodes
are evicted, GFS2 currently calls into DLM.  Inode eviction can be
triggered by memory pressure, in the context of a random user-space
process.  If DLM happens to block in the process in question (for
example, it that process is a fence agent), GFS2 and DLM will deadlock.

This patch queue stops GFS2 from calling into DLM on the inode evict
path under memory pressure.  It does so by first decoupling destroying
inodes and putting their associated glocks, which is what ends up
calling into DLM.  Second, when under memory pressure, it moves putting
glocks into work queue context where it cannot block DLM.  Third, when
gfs2_drop_inode determines that an inode's link count has hit zero under
memory pressure, it puts that inode on the delete workqueue (and keeps
the inode in the icache) instead of causing gfs2_evict_inode to delete
the inode immediately.  The delete workqueue will not be processed under
memory pressure, so deleting inodes from there is safe.

Thanks,
Andreas

Andreas Gruenbacher (4):
  gfs2: gfs2_glock_get: Wait on freeing glocks
  gfs2: Get rid of gfs2_set_nlink
  gfs2: gfs2_evict_inode: Put glocks asynchronously
  gfs2: Defer deleting inodes under memory pressure

 fs/gfs2/glock.c | 135 +++++++++++++++++++++++++++++++++++++++++++++++---------
 fs/gfs2/glock.h |   2 +
 fs/gfs2/glops.c |  28 +-----------
 fs/gfs2/super.c |  43 +++++++++++++++++-
 4 files changed, 157 insertions(+), 51 deletions(-)

-- 
2.13.3