From ba3ab3ca68caafb7700c4abae357b7fb7538df11 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Mon, 27 Jul 2020 09:13:37 -0400
Subject: [PATCH] fs: dlm: change handling of reconnects
This patch changes the handling of reconnects. At first we only close
the connection related to the communication failure. If we get a new
connection for an already existing connection we close the existing
connection and take the new one.
This patch improves significantly the stability of tcp connections while
running "tcpkill -9 -i $IFACE port 21064" while generating a lot of dlm
messages e.g. on a gfs2 mount with many files. My test setup shows that a
deadlock is "more" unlikely. Before this patch I wasn't able to get
not a deadlock after 5 seconds. After this patch my observation is
that it's more likely to survive after 5 seconds and more, but still a
deadlock occurs after certain time. My guess is that there are still
"segments" inside the tcp writequeue or retransmit queue which get dropped
when receiving a tcp reset [1]. Hard to reproduce because the right message
need to be inside these queues, which might even be in the 5 first seconds
with this patch.
[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/net/ipv4/tcp_input.c?h=v5.8-rc6#n4122
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
---
fs/dlm/lowcomms.c | 25 ++++++++++---------------
1 file changed, 10 insertions(+), 15 deletions(-)
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 9e6acbb47bb9a..289439fdca996 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -713,7 +713,7 @@ static int receive_from_sock(struct connection *con)
out_close:
mutex_unlock(&con->sock_mutex);
if (ret != -EAGAIN) {
- close_connection(con, true, true, false);
+ close_connection(con, false, true, false);
/* Reconnect when there is something to send */
}
/* Don't return success if we really got EOF */
@@ -804,21 +804,16 @@ static int accept_from_sock(struct connection *con)
INIT_WORK(&othercon->swork, process_send_sockets);
INIT_WORK(&othercon->rwork, process_recv_sockets);
set_bit(CF_IS_OTHERCON, &othercon->flags);
+ } else {
+ /* close other sock con if we have something new */
+ close_connection(othercon, false, true, false);
}
+
mutex_lock_nested(&othercon->sock_mutex, 2);
- if (!othercon->sock) {
- newcon->othercon = othercon;
- add_sock(newsock, othercon);
- addcon = othercon;
- mutex_unlock(&othercon->sock_mutex);
- }
- else {
- printk("Extra connection from node %d attempted\n", nodeid);
- result = -EAGAIN;
- mutex_unlock(&othercon->sock_mutex);
- mutex_unlock(&newcon->sock_mutex);
- goto accept_err;
- }
+ newcon->othercon = othercon;
+ add_sock(newsock, othercon);
+ addcon = othercon;
+ mutex_unlock(&othercon->sock_mutex);
}
else {
newcon->rx_action = receive_from_sock;
@@ -1415,7 +1410,7 @@ static void send_to_sock(struct connection *con)
send_error:
mutex_unlock(&con->sock_mutex);
- close_connection(con, true, false, true);
+ close_connection(con, false, false, true);
/* Requeue the send work. When the work daemon runs again, it will try
a new connection, then call this function again. */
queue_work(send_workqueue, &con->swork);
--
GitLab