lustre/osc: Don't flush active extents.
authorAnn Koehler <amk@cray.com>
Sat, 1 Mar 2014 02:16:44 +0000 (21:16 -0500)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Sat, 1 Mar 2014 03:13:21 +0000 (19:13 -0800)
commit15f13cde9c34f87452e463b13b180c0a948fb8ce
tree901a1c4034a086ebd396e6cb3740cd917df22a14
parent6fd67d8581106f59fdfe07b283477ffd7864dbb9
lustre/osc: Don't flush active extents.

The extent is active so we need to abort and let the caller
re-dirty the page. If we continued on here, and we were the
one making the extent active, we could deadlock waiting for
the page writeback to clear but it won't because the extent
is active and won't be written out.

Signed-off-by: Ann Koehler <amk@cray.com>
Reviewed-on: http://review.whamcloud.com/8278
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4253
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Reviewed-by: Alexey Lyashkov <alexey_lyashkov@xyratex.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drivers/staging/lustre/lustre/osc/osc_cache.c