In commit 0030807c66("xfs: revert to using a kthread for AIL pushing"),
AIL pushing is revert back to use a kthread. But unfortunately, it
introduced a regression: there are unnecessary AIL push wakeups during
idle, ~20 wakeups/s. This change remove the wakeups by reverting a bit
more: set "tout" value as zero during idle.
Signed-off-by: JiSheng Zhang <jszhang3@xxxxxxxxxxxxxxxx>
---
fs/xfs/xfs_trans_ail.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index ed9252b..2014387 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -508,7 +508,7 @@ out_done:
ailp->xa_last_pushed_lsn = 0;
ailp->xa_log_flush = 0;
- tout = 50;
+ tout = 0;
} else if (XFS_LSN_CMP(lsn, target) >= 0) {
/*
* We reached the target so wait a bit longer for I/O to
--
1.7.8.3
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
