From 60bf8bf8815e6adea4c1d0423578c3b8000e2ec8 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Fri, 4 Mar 2011 12:24:28 -0800 Subject: libceph: fix msgr backoff With commit f363e45f we replaced a bunch of hacky workqueue mutual exclusion logic with the WQ_NON_REENTRANT flag. One pieces of fallout is that the exponential backoff breaks in certain cases: * con_work attempts to connect. * we get an immediate failure, and the socket state change handler queues immediate work. * con_work calls con_fault, we decide to back off, but can't queue delayed work. In this case, we add a BACKOFF bit to make con_work reschedule delayed work next time it runs (which should be immediately). Signed-off-by: Sage Weil --- include/linux/ceph/messenger.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c3011beac30d..eb31e108a64d 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -123,6 +123,7 @@ struct ceph_msg_pos { #define SOCK_CLOSED 11 /* socket state changed to closed */ #define OPENING 13 /* open connection w/ (possibly new) peer */ #define DEAD 14 /* dead, about to kfree */ +#define BACKOFF 15 /* * A single connection with another host. -- cgit v1.2.3 From e76661d0a59e53e5cc4dccbe4b755d1dc8a968ec Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Thu, 3 Mar 2011 10:10:15 -0800 Subject: libceph: fix msgr keepalive flag There was some broken keepalive code using a dead variable. Shift to using the proper bit flag. Signed-off-by: Sage Weil --- include/linux/ceph/messenger.h | 1 - net/ceph/messenger.c | 9 ++++----- 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index eb31e108a64d..31d91a64838b 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -161,7 +161,6 @@ struct ceph_connection { struct list_head out_queue; struct list_head out_sent; /* sending or sent but unacked */ u64 out_seq; /* last message queued for send */ - bool out_keepalive_pending; u64 in_seq, in_seq_acked; /* last message received, acked */ diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 46fbc422ba74..3252ea974e8f 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -336,7 +336,6 @@ static void reset_connection(struct ceph_connection *con) ceph_msg_put(con->out_msg); con->out_msg = NULL; } - con->out_keepalive_pending = false; con->in_seq = 0; con->in_seq_acked = 0; } @@ -2019,10 +2018,10 @@ static void ceph_fault(struct ceph_connection *con) /* Requeue anything that hasn't been acked */ list_splice_init(&con->out_sent, &con->out_queue); - /* If there are no messages in the queue, place the connection - * in a STANDBY state (i.e., don't try to reconnect just yet). */ - if (list_empty(&con->out_queue) && !con->out_keepalive_pending) { - dout("fault setting STANDBY\n"); + /* If there are no messages queued or keepalive pending, place + * the connection in a STANDBY state */ + if (list_empty(&con->out_queue) && + !test_bit(KEEPALIVE_PENDING, &con->state)) { set_bit(STANDBY, &con->state); } else { /* retry after a delay. */ -- cgit v1.2.3