xfs: introduce xfs_inodegc_push()

The current blocking mechanism for pushing the inodegc queue out to
disk can result in systems becoming unusable when there is a long
running inodegc operation. This is because the statfs()
implementation currently issues a blocking flush of the inodegc
queue and a significant number of common system utilities will call
statfs() to discover something about the underlying filesystem.

This can result in userspace operations getting stuck on inodegc
progress, and when trying to remove a heavily reflinked file on slow
storage with a full journal, this can result in delays measuring in
hours.

Avoid this problem by adding "push" function that expedites the
flushing of the inodegc queue, but doesn't wait for it to complete.

Convert xfs_fs_statfs() and xfs_qm_scall_getquota() to use this
mechanism so they don't block but still ensure that queued
operations are expedited.

Fixes: ab23a7768739 ("xfs: per-cpu deferred inode inactivation queues")
Reported-by: Chris Dunlop <chris@onthe.net.au>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
[djwong: fix _getquota_next to use _inodegc_push too]
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 7867022..2609825 100644 (file)
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1862,19 +1862,29 @@ xfs_inodegc_worker(
 }
 
 /*
- * Force all currently queued inode inactivation work to run immediately and
- * wait for the work to finish.
+ * Expedite all pending inodegc work to run immediately. This does not wait for
+ * completion of the work.
  */
 void
-xfs_inodegc_flush(
+xfs_inodegc_push(
        struct xfs_mount        *mp)
 {
        if (!xfs_is_inodegc_enabled(mp))
                return;
+       trace_xfs_inodegc_push(mp, __return_address);
+       xfs_inodegc_queue_all(mp);
+}
 
+/*
+ * Force all currently queued inode inactivation work to run immediately and
+ * wait for the work to finish.
+ */
+void
+xfs_inodegc_flush(
+       struct xfs_mount        *mp)
+{
+       xfs_inodegc_push(mp);
        trace_xfs_inodegc_flush(mp, __return_address);
-
-       xfs_inodegc_queue_all(mp);
        flush_workqueue(mp->m_inodegc_wq);
 }
 

diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 2e4cfdd..6cd1807 100644 (file)
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -76,6 +76,7 @@ void xfs_blockgc_stop(struct xfs_mount *mp);
 void xfs_blockgc_start(struct xfs_mount *mp);
 
 void xfs_inodegc_worker(struct work_struct *work);
+void xfs_inodegc_push(struct xfs_mount *mp);
 void xfs_inodegc_flush(struct xfs_mount *mp);
 void xfs_inodegc_stop(struct xfs_mount *mp);
 void xfs_inodegc_start(struct xfs_mount *mp);

diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 74ac9ca..392cb39 100644 (file)
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -454,9 +454,12 @@ xfs_qm_scall_getquota(
        struct xfs_dquot        *dqp;
        int                     error;
 
-       /* Flush inodegc work at the start of a quota reporting scan. */
+       /*
+        * Expedite pending inodegc work at the start of a quota reporting
+        * scan but don't block waiting for it to complete.
+        */
        if (id == 0)
-               xfs_inodegc_flush(mp);
+               xfs_inodegc_push(mp);
 
        /*
         * Try to get the dquot. We don't want it allocated on disk, so don't
@@ -498,7 +501,7 @@ xfs_qm_scall_getquota_next(
 
        /* Flush inodegc work at the start of a quota reporting scan. */
        if (*id == 0)
-               xfs_inodegc_flush(mp);
+               xfs_inodegc_push(mp);
 
        error = xfs_qm_dqget_next(mp, *id, type, &dqp);
        if (error)

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 90d9c41..aa977c7 100644 (file)
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -797,8 +797,11 @@ xfs_fs_statfs(
        xfs_extlen_t            lsize;
        int64_t                 ffree;
 
-       /* Wait for whatever inactivations are in progress. */
-       xfs_inodegc_flush(mp);
+       /*
+        * Expedite background inodegc but don't wait. We do not want to block
+        * here waiting hours for a billion extent file to be truncated.
+        */
+       xfs_inodegc_push(mp);
 
        statp->f_type = XFS_SUPER_MAGIC;
        statp->f_namelen = MAXNAMELEN - 1;

diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index d320265..0fa1b7a 100644 (file)
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -240,6 +240,7 @@ DEFINE_EVENT(xfs_fs_class, name,                                    \
        TP_PROTO(struct xfs_mount *mp, void *caller_ip), \
        TP_ARGS(mp, caller_ip))
 DEFINE_FS_EVENT(xfs_inodegc_flush);
+DEFINE_FS_EVENT(xfs_inodegc_push);
 DEFINE_FS_EVENT(xfs_inodegc_start);
 DEFINE_FS_EVENT(xfs_inodegc_stop);
 DEFINE_FS_EVENT(xfs_inodegc_queue);