summaryrefslogtreecommitdiffstats
path: root/drivers/block
diff options
context:
space:
mode:
authorLars Ellenberg <lars.ellenberg@linbit.com>2011-03-09 22:44:55 +0100
committerPhilipp Reisner <philipp.reisner@linbit.com>2011-05-24 10:03:30 +0200
commitf36af18c7b4ea1ba333c09b606bb4a7e5af66b4d (patch)
tree6983acfaa859fee028b2927f8f520a27e1785c4d /drivers/block
parent53ea433145d9a56c7ad5e69f21f5662053e00e84 (diff)
downloadop-kernel-dev-f36af18c7b4ea1ba333c09b606bb4a7e5af66b4d.zip
op-kernel-dev-f36af18c7b4ea1ba333c09b606bb4a7e5af66b4d.tar.gz
drbd: fix disconnect/reconnect loop, if ping-timeout == ping-int
If there is no replication traffic within the idle timeout (ping-int seconds), DRBD will send a P_PING, and adjust the timeout to ping-timeout. If there is no P_PING_ACK received within this ping-timeout, DRBD finally drops the connection, and tries to re-establish it. To decide which timeout was active, we compared the current timeout with the ping-timeout, and dropped the connection, if that was the case. By default, ping-int is 10 seconds, ping-timeout is 500 ms. Unfortunately, if you configure ping-timeout to be the same as ping-int, expiry of the idle-timeout had been mistaken for a missing ping ack, and caused an immediate reconnection attempt. Fix: Allow both timeouts to be equal, use a local variable to store which timeout is active. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Diffstat (limited to 'drivers/block')
-rw-r--r--drivers/block/drbd/drbd_receiver.c10
1 files changed, 8 insertions, 2 deletions
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index fd26666..0b17d42 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -4554,6 +4554,7 @@ int drbd_asender(struct drbd_thread *thi)
int received = 0;
int expect = sizeof(struct p_header80);
int empty;
+ int ping_timeout_active = 0;
sprintf(current->comm, "drbd%d_asender", mdev_to_minor(mdev));
@@ -4566,6 +4567,7 @@ int drbd_asender(struct drbd_thread *thi)
ERR_IF(!drbd_send_ping(mdev)) goto reconnect;
mdev->meta.socket->sk->sk_rcvtimeo =
mdev->net_conf->ping_timeo*HZ/10;
+ ping_timeout_active = 1;
}
/* conditionally cork;
@@ -4620,8 +4622,7 @@ int drbd_asender(struct drbd_thread *thi)
dev_err(DEV, "meta connection shut down by peer.\n");
goto reconnect;
} else if (rv == -EAGAIN) {
- if (mdev->meta.socket->sk->sk_rcvtimeo ==
- mdev->net_conf->ping_timeo*HZ/10) {
+ if (ping_timeout_active) {
dev_err(DEV, "PingAck did not arrive in time.\n");
goto reconnect;
}
@@ -4660,6 +4661,11 @@ int drbd_asender(struct drbd_thread *thi)
if (!cmd->process(mdev, h))
goto reconnect;
+ /* the idle_timeout (ping-int)
+ * has been restored in got_PingAck() */
+ if (cmd == get_asender_cmd(P_PING_ACK))
+ ping_timeout_active = 0;
+
buf = h;
received = 0;
expect = sizeof(struct p_header80);
OpenPOWER on IntegriCloud