Commit f85d9f2d authored by Lars Ellenberg's avatar Lars Ellenberg Committed by Jens Axboe

drbd: fix "endless" transfer log walk in protocol A

Don't remember a DRBD request as ack_pending, if it is not.

In protocol A, we usually clear RQ_NET_PENDING at the same time we set
RQ_NET_SENT, so when deciding to remember it as ack_pending,
mod_rq_state needs to look at the current request state,
not at the previous state before the current modification was applied.

This should prevent advance_conn_req_ack_pending() from walking the full
transfer log just to find NULL in protocol A, which would cause serious
performance degradation with many "in-flight" requests, e.g. when
working via DRBD-proxy, or with a huge bandwidth-delay product.
Signed-off-by: default avatarPhilipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: default avatarLars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
parent 70644786
...@@ -458,7 +458,7 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m, ...@@ -458,7 +458,7 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
atomic_add(req->i.size >> 9, &device->ap_in_flight); atomic_add(req->i.size >> 9, &device->ap_in_flight);
set_if_null_req_not_net_done(peer_device, req); set_if_null_req_not_net_done(peer_device, req);
} }
if (s & RQ_NET_PENDING) if (req->rq_state & RQ_NET_PENDING)
set_if_null_req_ack_pending(peer_device, req); set_if_null_req_ack_pending(peer_device, req);
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment