From: Rumen G. Bogdanovski <[EMAIL PROTECTED]>
This patch makes the master daemon to sync the connection when it is about
to close. This makes the connections on the backup to close or timeout
according their state. Before the sync was performed only if the
connection is in ESTABLISHED state which always made the connections to
timeout in the hard coded 3 minutes. However the Andy Gospodarek's patch
([IPVS]: use proper timeout instead of fixed value) effectively did nothing
more than increasing this to 15 minutes (Established state timeout). So
this patch makes use of proper timeout since it syncs the connections on
status changes to FIN_WAIT (2min timeout) and CLOSE (10sec timeout).
However if the backup misses CLOSE hopefully it did not miss FIN_WAIT.
Otherwise we will just have to wait for the ESTABLISHED state timeout. As
it is without this patch. This way the number of the hanging connections
on the backup is kept to minimum. And very few of them will be left to
timeout with a long timeout.
This is important if we want to make use of the fix for the real server
overcommit on master/backup fail-over.
Regards,
Rumen Bogdanovski
Signed-off-by: Rumen G. Bogdanovski <[EMAIL PROTECTED]>
Signed-off-by: Simon Horman <[EMAIL PROTECTED]>
---
Thu, 01 Nov 2007 18:25:10 +0900, Horms
* Redifed for net-2.6
* Ran through scripts/checkpatch.pl and fixed up everything
that it complains about except the use of volatile, as
its in keeping with other fields in the structure.
If its wrong, lets fix them all together.
WARNING: Use of volatile is usually wrong: see
Documentation/volatile-considered-harmful.txt
#49: FILE: include/net/ip_vs.h:523:
+ volatile __u16 old_state; /* old state, to be used for
Index: net-2.6/include/net/ip_vs.h
===================================================================
--- net-2.6.orig/include/net/ip_vs.h 2007-11-01 18:17:55.000000000 +0900
+++ net-2.6/include/net/ip_vs.h 2007-11-01 18:21:02.000000000 +0900
@@ -520,6 +520,10 @@ struct ip_vs_conn {
spinlock_t lock; /* lock for state transition */
volatile __u16 flags; /* status flags */
volatile __u16 state; /* state info */
+ volatile __u16 old_state; /* old state, to be used for
+ * state transition triggerd
+ * synchronization
+ */
/* Control members */
struct ip_vs_conn *control; /* Master control connection */
Index: net-2.6/net/ipv4/ipvs/ip_vs_core.c
===================================================================
--- net-2.6.orig/net/ipv4/ipvs/ip_vs_core.c 2007-11-01 18:17:55.000000000
+0900
+++ net-2.6/net/ipv4/ipvs/ip_vs_core.c 2007-11-01 18:18:23.000000000 +0900
@@ -979,15 +979,23 @@ ip_vs_in(unsigned int hooknum, struct sk
ret = NF_ACCEPT;
}
- /* increase its packet counter and check if it is needed
- to be synchronized */
+ /* Increase its packet counter and check if it is needed
+ * to be synchronized
+ *
+ * Sync connection if it is about to close to
+ * encorage the standby servers to update the connections timeout
+ */
atomic_inc(&cp->in_pkts);
if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
- (cp->protocol != IPPROTO_TCP ||
- cp->state == IP_VS_TCP_S_ESTABLISHED) &&
- (atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1]
- == sysctl_ip_vs_sync_threshold[0]))
+ (((cp->protocol != IPPROTO_TCP ||
+ cp->state == IP_VS_TCP_S_ESTABLISHED) &&
+ (atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1]
+ == sysctl_ip_vs_sync_threshold[0])) ||
+ ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) &&
+ ((cp->state == IP_VS_TCP_S_FIN_WAIT) ||
+ (cp->state == IP_VS_TCP_S_CLOSE)))))
ip_vs_sync_conn(cp);
+ cp->old_state = cp->state;
ip_vs_conn_put(cp);
return ret;
Index: net-2.6/net/ipv4/ipvs/ip_vs_sync.c
===================================================================
--- net-2.6.orig/net/ipv4/ipvs/ip_vs_sync.c 2007-11-01 18:17:55.000000000
+0900
+++ net-2.6/net/ipv4/ipvs/ip_vs_sync.c 2007-11-01 18:20:30.000000000 +0900
@@ -332,7 +332,7 @@ static void ip_vs_process_message(const
s->daddr, s->dport,
flags, dest);
if (dest)
- atomic_dec(&dest->refcnt);
+ ip_vs_dest_get(dest);
if (!cp) {
IP_VS_ERR("ip_vs_conn_new failed\n");
return;
@@ -343,10 +343,9 @@ static void ip_vs_process_message(const
if (!dest) {
/* it is an unbound entry created by
* synchronization */
- cp->state = ntohs(s->state);
cp->flags = flags | IP_VS_CONN_F_HASHED;
} else
- atomic_dec(&dest->refcnt);
+ ip_vs_dest_put(dest);
} /* Note that we don't touch its state and flags
if it is a normal entry. */
@@ -358,6 +357,7 @@ static void ip_vs_process_message(const
p += SIMPLE_CONN_SIZE;
atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
+ cp->state = ntohs(s->state);
pp = ip_vs_proto_get(s->protocol);
cp->timeout = pp->timeout_table[cp->state];
ip_vs_conn_put(cp);
--
Horms
H: http://www.vergenet.net/~horms/
W: http://www.valinux.co.jp/en/
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
