The non-blockig behaviour in xfs_vm_writepage currently is conditional on
having both the WB_SYNC_NONE sync_mode and the nonblocking flag set.
The latter used to be used by both pdflush, kswapd and a few other places
in older kernels, but has been fading out starting with the introduction
of the per-bdi flusher threads.
Enable the non-blocking behaviour for all WB_SYNC_NONE calls to get back
the behaviour we want.
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Alex Elder <aelder@xxxxxxx>
Index: xfs/fs/xfs/linux-2.6/xfs_aops.c
===================================================================
--- xfs.orig/fs/xfs/linux-2.6/xfs_aops.c 2011-07-06 09:12:22.466600907 +0200
+++ xfs/fs/xfs/linux-2.6/xfs_aops.c 2011-07-06 09:12:26.069934110 +0200
@@ -960,7 +960,7 @@ xfs_vm_writepage(
offset = page_offset(page);
type = IO_OVERWRITE;
- if (wbc->sync_mode == WB_SYNC_NONE && wbc->nonblocking)
+ if (wbc->sync_mode == WB_SYNC_NONE)
nonblocking = 1;
do {
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
