xfs: use background worker pool when transactions can't get free space

In xfs_trans_alloc, if the block reservation call returns ENOSPC, we
call xfs_blockgc_free_space with a NULL icwalk structure to try to free
space.  Each frontend thread that encounters this situation starts its
own walk of the inode cache to see if it can find anything, which is
wasteful since we don't have any additional selection criteria.  For
this one common case, create a function that reschedules all pending
background work immediately and flushes the workqueue so that the scan
can run in parallel.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>

4 files changed, 31 insertions, 4 deletions

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 41bd84fd9e87..93ab83dfa36e 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1501,6 +1501,34 @@ xfs_blockgc_free_space(
 }
 
 /*
+ * Reclaim all the free space that we can by scheduling the background blockgc
+ * and inodegc workers immediately and waiting for them all to clear.
+ */
+void
+xfs_blockgc_flush_all(
+	struct xfs_mount	*mp)
+{
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+
+	trace_xfs_blockgc_flush_all(mp, __return_address);
+
+	/*
+	 * For each blockgc worker, move its queue time up to now.  If it
+	 * wasn't queued, it will not be requeued.  Then flush whatever's
+	 * left.
+	 */
+	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
+		mod_delayed_work(pag->pag_mount->m_blockgc_wq,
+				&pag->pag_blockgc_work, 0);
+
+	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
+		flush_delayed_work(&pag->pag_blockgc_work);
+
+	xfs_inodegc_flush(mp);
+}
+
+/*
  * Run cow/eofblocks scans on the supplied dquots.  We don't know exactly which
  * quota caused an allocation failure, so we make a best effort by including
  * each quota under low free space conditions (less than 1% free space) in the
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 8175148afd50..18c2d224aa78 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -59,6 +59,7 @@ int xfs_blockgc_free_dquots(struct xfs_mount *mp, struct xfs_dquot *udqp,
 		unsigned int iwalk_flags);
 int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int iwalk_flags);
 int xfs_blockgc_free_space(struct xfs_mount *mp, struct xfs_icwalk *icm);
+void xfs_blockgc_flush_all(struct xfs_mount *mp);
 
 void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
 void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 3440046facc7..4a6616490315 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -198,6 +198,7 @@ DEFINE_FS_EVENT(xfs_fs_sync_fs);
 DEFINE_FS_EVENT(xfs_blockgc_start);
 DEFINE_FS_EVENT(xfs_blockgc_stop);
 DEFINE_FS_EVENT(xfs_blockgc_worker);
+DEFINE_FS_EVENT(xfs_blockgc_flush_all);
 
 DECLARE_EVENT_CLASS(xfs_ag_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno),
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 87bffd12c20c..83abaa219616 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -295,10 +295,7 @@ retry:
 		 * Do not perform a synchronous scan because callers can hold
 		 * other locks.
 		 */
-		error = xfs_blockgc_free_space(mp, NULL);
-		if (error)
-			return error;
-
+		xfs_blockgc_flush_all(mp);
 		want_retry = false;
 		goto retry;
 	}