From 9848b6ddd8c92305252f94592c5e278574e7a6ac Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Thu, 20 Dec 2018 17:23:41 +0100 Subject: [PATCH] drbd: skip spurious timeout (ping-timeo) when failing promote If you try to promote a Secondary while connected to a Primary and allow-two-primaries is NOT set, we will wait for "ping-timeout" to give this node a chance to detect a dead primary, in case the cluster manager noticed faster than we did. But if we then are *still* connected to a Primary, we fail (after an additional timeout of ping-timout). This change skips the spurious second timeout. Most people won't notice really, since "ping-timeout" by default is half a second. But in some installations, ping-timeout may be 10 or 20 seconds or more, and spuriously delaying the error return becomes annoying. Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_nl.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 8291588..bfe1b00 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -697,14 +697,15 @@ drbd_set_role(struct drbd_device *const device, enum drbd_role new_role, int for if (rv == SS_TWO_PRIMARIES) { /* Maybe the peer is detected as dead very soon... retry at most once more in this case. */ - int timeo; - rcu_read_lock(); - nc = rcu_dereference(connection->net_conf); - timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1; - rcu_read_unlock(); - schedule_timeout_interruptible(timeo); - if (try < max_tries) + if (try < max_tries) { + int timeo; try = max_tries - 1; + rcu_read_lock(); + nc = rcu_dereference(connection->net_conf); + timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1; + rcu_read_unlock(); + schedule_timeout_interruptible(timeo); + } continue; } if (rv < SS_SUCCESS) { -- 2.7.4