From: Philipp Reisner <philipp.reisner@linbit.com>
To: linux-kernel@vger.kernel.org, Jens Axboe <axboe@kernel.dk>
Cc: drbd-dev@lists.linbit.com
Subject: [PATCH 13/20] drbd: improve resync request throttling due to sendbuf size
Date: Tue, 1 Jul 2014 18:16:43 +0200 [thread overview]
Message-ID: <1404231410-29852-14-git-send-email-philipp.reisner@linbit.com> (raw)
In-Reply-To: <1404231410-29852-1-git-send-email-philipp.reisner@linbit.com>
From: Lars Ellenberg <lars.ellenberg@linbit.com>
If we throttle resync because the socket sendbuffer is filling up,
tell TCP about it, so it may expand the sendbuffer for us.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
drivers/block/drbd/drbd_worker.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 6532a69..0b5e429 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -592,7 +592,7 @@ static int make_resync_request(struct drbd_device *const device, int cancel)
const sector_t capacity = drbd_get_capacity(device->this_bdev);
int max_bio_size;
int number, rollback_i, size;
- int align, queued, sndbuf;
+ int align, requeue = 0;
int i = 0;
if (unlikely(cancel))
@@ -619,17 +619,22 @@ static int make_resync_request(struct drbd_device *const device, int cancel)
goto requeue;
for (i = 0; i < number; i++) {
- /* Stop generating RS requests, when half of the send buffer is filled */
+ /* Stop generating RS requests when half of the send buffer is filled,
+ * but notify TCP that we'd like to have more space. */
mutex_lock(&connection->data.mutex);
if (connection->data.socket) {
- queued = connection->data.socket->sk->sk_wmem_queued;
- sndbuf = connection->data.socket->sk->sk_sndbuf;
- } else {
- queued = 1;
- sndbuf = 0;
- }
+ struct sock *sk = connection->data.socket->sk;
+ int queued = sk->sk_wmem_queued;
+ int sndbuf = sk->sk_sndbuf;
+ if (queued > sndbuf / 2) {
+ requeue = 1;
+ if (sk->sk_socket)
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ }
+ } else
+ requeue = 1;
mutex_unlock(&connection->data.mutex);
- if (queued > sndbuf / 2)
+ if (requeue)
goto requeue;
next_sector:
--
1.9.1
next prev parent reply other threads:[~2014-07-01 16:19 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-01 16:16 [PATCH 00/20] RFC DRBD fixes Philipp Reisner
2014-07-01 16:16 ` [PATCH 01/20] drbd: drop wrong debugging aid Philipp Reisner
2014-07-01 16:16 ` [PATCH 02/20] drbd: silence -Wmissing-prototypes warnings Philipp Reisner
2014-07-01 16:16 ` [PATCH 03/20] drbd: Remove unnecessary/unused code Philipp Reisner
2014-07-01 16:16 ` [PATCH 04/20] drbd: fix bogus resync stats in /proc/drbd Philipp Reisner
2014-07-01 16:16 ` [PATCH 05/20] drbd: don't implicitly resize Diskless node beyond end of device Philipp Reisner
2014-07-01 16:16 ` [PATCH 06/20] drbd: implement csums-after-crash-only Philipp Reisner
2014-07-01 16:16 ` [PATCH 07/20] drbd: Limit the time we are waiting for the first packet on an accepted socket Philipp Reisner
2014-07-01 16:16 ` [PATCH 08/20] drbd: New net configuration option socket-check-timeout Philipp Reisner
2014-07-01 16:16 ` [PATCH 09/20] drbd: application writes may set-in-sync in protocol != C Philipp Reisner
2014-07-01 16:16 ` [PATCH 10/20] drbd: short-circuit in maybe_pull_ahead Philipp Reisner
2014-07-01 16:16 ` [PATCH 11/20] drivers/block: Use RCU_INIT_POINTER(x, NULL) in drbd/drbd_state.c Philipp Reisner
2014-07-01 16:16 ` [PATCH 12/20] block: Convert last uses of __FUNCTION__ to __func__ Philipp Reisner
2014-07-01 16:16 ` Philipp Reisner [this message]
2014-07-01 16:16 ` [PATCH 14/20] drbd: clear CRASHED_PRIMARY only after successful resync Philipp Reisner
2014-07-01 16:16 ` [PATCH 15/20] drbd: cosmetic: change all printk(level, ...) to pr_<level>(...) Philipp Reisner
2014-07-01 16:30 ` Joe Perches
2014-07-02 9:58 ` [Drbd-dev] " Philipp Reisner
2014-07-01 16:16 ` [PATCH 16/20] drbd: drbd_rs_number_requests: fix unit mismatch in comparison Philipp Reisner
2014-07-01 16:16 ` [PATCH 17/20] drbd: add drbd_queue_work_if_unqueued helper Philipp Reisner
2014-07-01 16:16 ` [PATCH 18/20] drbd: drop drbd_md_flush Philipp Reisner
2014-07-01 16:16 ` [PATCH 19/20] drbd: consistently use list_add_tail for peer_request tracking Philipp Reisner
2014-07-01 16:16 ` [PATCH 20/20] drbd: also keep track of trim -> zero-out fallback peer_requests Philipp Reisner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1404231410-29852-14-git-send-email-philipp.reisner@linbit.com \
--to=philipp.reisner@linbit.com \
--cc=axboe@kernel.dk \
--cc=drbd-dev@lists.linbit.com \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®