summaryrefslogtreecommitdiffstats
path: root/fs/xfs
diff options
context:
space:
mode:
authorBrian Foster <bfoster@redhat.com>2012-06-28 06:52:56 -0400
committerBen Myers <bpm@sgi.com>2012-07-29 16:27:57 -0500
commit8375f922aaa6e7a880022529202fb486315568c3 (patch)
tree5fd3385ae7860ef9dabc84619f64fb85878fa864 /fs/xfs
parent4f59af758f9092bc7b266ca919ce6067170e5172 (diff)
downloadblackbird-op-linux-8375f922aaa6e7a880022529202fb486315568c3.tar.gz
blackbird-op-linux-8375f922aaa6e7a880022529202fb486315568c3.zip
xfs: re-enable xfsaild idle mode and fix associated races
xfsaild idle mode logic currently leads to a couple hangs: 1.) If xfsaild is rescheduled in during an incremental scan (i.e., tout != 0) and the target has been updated since the previous run, we can hit the new target and go into idle mode with a still populated ail. 2.) A wake up is only issued when the target is pushed forward. The wake up can race with xfsaild if it is currently in the process of entering idle mode, causing future wake up events to be lost. These hangs have been reproduced and verified as fixed by running xfstests 273 in a loop on a slightly modified upstream kernel. The kernel is modified to re-enable idle mode as previously implemented (when count == 0) and with a revert of commit 670ce93f, which includes performance improvements that make this harder to reproduce. The solution, the algorithm for which has been outlined by Dave Chinner, is to modify xfsaild to enter idle mode only when the ail is empty and the push target has not been moved forward since the last push. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/xfs_trans_ail.c35
-rw-r--r--fs/xfs/xfs_trans_priv.h1
2 files changed, 33 insertions, 3 deletions
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 9c514483e599..6011ee661339 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -383,6 +383,12 @@ xfsaild_push(
}
spin_lock(&ailp->xa_lock);
+
+ /* barrier matches the xa_target update in xfs_ail_push() */
+ smp_rmb();
+ target = ailp->xa_target;
+ ailp->xa_target_prev = target;
+
lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn);
if (!lip) {
/*
@@ -397,7 +403,6 @@ xfsaild_push(
XFS_STATS_INC(xs_push_ail);
lsn = lip->li_lsn;
- target = ailp->xa_target;
while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) {
int lock_result;
@@ -527,8 +532,32 @@ xfsaild(
__set_current_state(TASK_KILLABLE);
else
__set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(tout ?
- msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT);
+
+ spin_lock(&ailp->xa_lock);
+
+ /*
+ * Idle if the AIL is empty and we are not racing with a target
+ * update. We check the AIL after we set the task to a sleep
+ * state to guarantee that we either catch an xa_target update
+ * or that a wake_up resets the state to TASK_RUNNING.
+ * Otherwise, we run the risk of sleeping indefinitely.
+ *
+ * The barrier matches the xa_target update in xfs_ail_push().
+ */
+ smp_rmb();
+ if (!xfs_ail_min(ailp) &&
+ ailp->xa_target == ailp->xa_target_prev) {
+ spin_unlock(&ailp->xa_lock);
+ schedule();
+ tout = 0;
+ continue;
+ }
+ spin_unlock(&ailp->xa_lock);
+
+ if (tout)
+ schedule_timeout(msecs_to_jiffies(tout));
+
+ __set_current_state(TASK_RUNNING);
try_to_freeze();
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index fb62377d1cbc..53b7c9b0f8f7 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -67,6 +67,7 @@ struct xfs_ail {
struct task_struct *xa_task;
struct list_head xa_ail;
xfs_lsn_t xa_target;
+ xfs_lsn_t xa_target_prev;
struct list_head xa_cursors;
spinlock_t xa_lock;
xfs_lsn_t xa_last_pushed_lsn;
OpenPOWER on IntegriCloud