sin/samba-mirror
1
0
Fork 0
mirror of https://github.com/samba-team/samba.git synced 2025-02-28 01:58:17 +03:00
Code

ctdb-ipalloc: Use a cumulative timeout for takeover run stages

Browse Source 
RELEASE_IP sometimes times out because killing TCP connections can
take a long time.

The aim of the takeover timeout is actually to limit the total amount
of time for an IP takeover run.  So, calculate a combined timeout
offset once and use it for each of the RELEASE_IP, TAKEOVER_IP,
IPREALLOCATED stages.  This gives RELEASE_IP more time to kill TCP
connections but still limits the total time.

Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>
This commit is contained in:
Martin Schwenke 2016-05-27 15:22:27 +10:00 committed by Stefan Metzmacher
parent ff6a22757a
commit c40fc62642
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
ctdb/server/ctdb_takeover.c
View File

@ -1508,6 +1508,17 @@ int ctdb_takeover_run(struct ctdb_context *ctdb, struct ctdb_node_map_old *nodem
return -1;
}
/* Each of the later stages (RELEASE_IP, TAKEOVER_IP,
* IPREALLOCATED) notionally has a timeout of TakeoverTimeout
* seconds. However, RELEASE_IP can take longer due to TCP
* connection killing, so sometimes needs more time.
* Therefore, use a cumulative timeout of TakeoverTimeout * 3
* seconds across all 3 stages. No explicit expiry checks are
* needed before each stage because tevent is smart enough to
* fire the timeouts even if they are in the past. Initialise
* this here to cope with early jumps to IPREALLOCATED. */
timeout = timeval_current_ofs(3 * ctdb->tunable.takeover_timeout,0);
/*
* ip failover is completely disabled, just send out the
* ipreallocated event.
@ -1602,7 +1613,6 @@ int ctdb_takeover_run(struct ctdb_context *ctdb, struct ctdb_node_map_old *nodem
ip.pnn = tmp_ip->pnn;
ip.addr = tmp_ip->addr;
timeout = TAKEOVER_TIMEOUT();
data.dsize = sizeof(ip);
data.dptr = (uint8_t *)&ip;
state = ctdb_control_send(ctdb, nodemap->nodes[i].pnn,
@ -1645,7 +1655,6 @@ int ctdb_takeover_run(struct ctdb_context *ctdb, struct ctdb_node_map_old *nodem
ip.pnn = tmp_ip->pnn;
ip.addr = tmp_ip->addr;
timeout = TAKEOVER_TIMEOUT();
data.dsize = sizeof(ip);
data.dptr = (uint8_t *)&ip;
state = ctdb_control_send(ctdb, tmp_ip->pnn,
@ -1675,7 +1684,7 @@ ipreallocated:
*/
nodes = list_of_connected_nodes(ctdb, nodemap, tmp_ctx, true);
ret = ctdb_client_async_control(ctdb, CTDB_CONTROL_IPREALLOCATED,
nodes, 0, TAKEOVER_TIMEOUT(),
nodes, 0, timeout,
false, tdb_null,
NULL, takeover_run_fail_callback,
takeover_data);