From: Dave Chinner <dchinner@xxxxxxxxxx>
Upstream commit: aa292847b9fc6e187547110de833a7d3131bbddf
Almost all metadata allocations come from shallow stack usage
situations. Avoid the overhead of switching the allocation to a
workqueue as we are not in danger of running out of stack when
making these allocations. Metadata allocations are already marked
through the args that are passed down, so this is trivial to do.
Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
Reported-by: Mel Gorman <mgorman@xxxxxxx>
Tested-by: Mel Gorman <mgorman@xxxxxxx>
Signed-off-by: Ben Myers <bpm@xxxxxxx>
---
fs/xfs/xfs_alloc.c | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index de5a353..5d830cf 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -2441,13 +2441,22 @@ xfs_alloc_vextent_worker(
current_restore_flags_nested(&pflags, PF_FSTRANS);
}
-
-int /* error */
+/*
+ * Data allocation requests often come in with little stack to work on. Push
+ * them off to a worker thread so there is lots of stack to use. Metadata
+ * requests, OTOH, are generally from low stack usage paths, so avoid the
+ * context switch overhead here.
+ */
+int
xfs_alloc_vextent(
- xfs_alloc_arg_t *args) /* allocation argument structure */
+ struct xfs_alloc_arg *args)
{
DECLARE_COMPLETION_ONSTACK(done);
+ if (!args->userdata)
+ return __xfs_alloc_vextent(args);
+
+
args->done = &done;
INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker);
queue_work(xfs_alloc_wq, &args->work);
--
1.7.10
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
