diff options
author | Philipp Reisner <philipp.reisner@linbit.com> | 2015-03-16 15:08:29 (GMT) |
---|---|---|
committer | Jens Axboe <axboe@fb.com> | 2015-11-25 16:22:01 (GMT) |
commit | 668700b40a7c8727bbd2b3fd4fd22e0ce3f1aeb6 (patch) | |
tree | 20c6ee044e5d91700bea7c3d3a601ecf3234753d /drivers/block/drbd/drbd_req.c | |
parent | 1c03e52083c8fa6e70a0b921d25d1916f68320fc (diff) | |
download | linux-668700b40a7c8727bbd2b3fd4fd22e0ce3f1aeb6.tar.xz |
drbd: Create a dedicated workqueue for sending acks on the control connection
The intention is to reduce CPU utilization. Recent measurements
unveiled that the current performance bottleneck is CPU utilization
on the receiving node. The asender thread became CPU limited.
One of the main points is to eliminate the idr_for_each_entry() loop
from the sending acks code path.
One exception in that is sending back ping_acks. These stay
in the ack-receiver thread. Otherwise the logic becomes too
complicated for no added value.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'drivers/block/drbd/drbd_req.c')
-rw-r--r-- | drivers/block/drbd/drbd_req.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 3add7c5..7907fb5 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -453,7 +453,7 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m, kref_get(&req->kref); /* wait for the DONE */ if (!(s & RQ_NET_SENT) && (set & RQ_NET_SENT)) { - /* potentially already completed in the asender thread */ + /* potentially already completed in the ack_receiver thread */ if (!(s & RQ_NET_DONE)) { atomic_add(req->i.size >> 9, &device->ap_in_flight); set_if_null_req_not_net_done(peer_device, req); |