[DLM] fix softlockup in dlm_recv

This patch stops the dlm_recv workqueue from busy-waiting when a node
disconnects. This can cause soft lockup errors on debug systems and bad
performance generally.

Signed-Off-By: Patrick Caulfield <pcaulfie@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
This commit is contained in:
Patrick Caulfield 2007-02-01 16:46:33 +00:00 committed by Steven Whitehouse
parent 62a0f62369
commit a34fbc6363

View file

@ -2,7 +2,7 @@
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
** Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@ -109,7 +109,6 @@ struct connection {
struct page *rx_page;
struct cbuf cb;
int retries;
atomic_t waiting_requests;
#define MAX_CONNECT_RETRIES 3
struct connection *othercon;
struct work_struct rwork; /* Receive workqueue */
@ -278,8 +277,11 @@ static int receive_from_sock(struct connection *con)
mutex_lock(&con->sock_mutex);
if (con->sock == NULL)
goto out;
if (con->sock == NULL) {
ret = -EAGAIN;
goto out_close;
}
if (con->rx_page == NULL) {
/*
* This doesn't need to be atomic, but I think it should
@ -352,7 +354,6 @@ static int receive_from_sock(struct connection *con)
con->rx_page = NULL;
}
out:
if (call_again_soon)
goto out_resched;
mutex_unlock(&con->sock_mutex);
@ -370,6 +371,9 @@ out_close:
close_connection(con, false);
/* Reconnect when there is something to send */
}
/* Don't return success if we really got EOF */
if (ret == 0)
ret = -EAGAIN;
return ret;
}
@ -847,7 +851,6 @@ int dlm_lowcomms_close(int nodeid)
if (con) {
clean_one_writequeue(con);
close_connection(con, true);
atomic_set(&con->waiting_requests, 0);
}
return 0;