[PATCH 3.17 066/319] rbd: rbd workqueues need a resque worker

From: Greg Kroah-Hartman
Date: Tue Nov 11 2014 - 20:22:52 EST


3.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ilya Dryomov <idryomov@xxxxxxxxxx>

commit 792c3a914910bd34302c5345578f85cfcb5e2c01 upstream.

Need to use WQ_MEM_RECLAIM for our workqueues to prevent I/O lockups
under memory pressure - we sit on the memory reclaim path.

Signed-off-by: Ilya Dryomov <idryomov@xxxxxxxxxx>
Tested-by: Micha Krause <micha@xxxxxxxxxx>
Reviewed-by: Sage Weil <sage@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
drivers/block/rbd.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -5087,7 +5087,8 @@ static int rbd_dev_device_setup(struct r
set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only);

- rbd_dev->rq_wq = alloc_workqueue("%s", 0, 0, rbd_dev->disk->disk_name);
+ rbd_dev->rq_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+ rbd_dev->disk->disk_name);
if (!rbd_dev->rq_wq) {
ret = -ENOMEM;
goto err_out_mapping;


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/