Andrew Tridgell 59b6a9a9e6 fixed problem with looping ctdb recoveries ...

After a node failure, GPFS can get into a state where non-blocking
fcntl() locks can take a long time. This means to the ctdb set_recmode
test timing out, which leads to a recovery failure, and a new
recovery. The recovery loop can last a long time.

The fix is to consider a fcntl timeout as a success of this test. The
test is to see that we can't lock the shared reclock file, so a
timeout is fine for a success.

(This used to be ctdb commit 6579a6a2a7161214adedf0f67dce62f4a4ad1afe)

2008-11-21 10:24:13 +11:00

..

ctdb_call.c

fix a memory leak

2008-03-25 11:11:13 +11:00

ctdb_control.c

reqrite the handling of flag updates across the cluster to eliminate a

2008-11-20 12:43:18 +11:00

ctdb_daemon.c

reqrite the handling of flag updates across the cluster to eliminate a

2008-11-20 12:43:18 +11:00

ctdb_freeze.c

proper waitpid() fix.

2008-07-09 14:02:54 +10:00

ctdb_keepalive.c

Keepalive packets were only sent every KeepaliveInterval if the socket

2008-11-20 13:35:08 +11:00

ctdb_lockwait.c

add control and logging of very high latencies.

2008-10-30 12:49:53 +11:00

ctdb_logging.c

specify a "script log level" on the commandline to set under which log

2008-10-17 07:56:12 +11:00

ctdb_ltdb_server.c

make sure we honor the TDB_NOSYNC flag from clients in the server

2008-07-30 19:58:49 +10:00

ctdb_monitor.c

reqrite the handling of flag updates across the cluster to eliminate a

2008-11-20 12:43:18 +11:00

ctdb_persistent.c

add control and logging of very high latencies.

2008-10-30 12:49:53 +11:00

ctdb_recover.c

fixed problem with looping ctdb recoveries

2008-11-21 10:24:13 +11:00

ctdb_recoverd.c

reqrite the handling of flag updates across the cluster to eliminate a

2008-11-20 12:43:18 +11:00

ctdb_server.c

from Michael Adams : allow #-style comments in the nodes and public

2008-10-07 19:25:10 +11:00

ctdb_serverids.c

merge from ronnie

2008-02-04 20:07:15 +11:00

ctdb_takeover.c

add a context and a timed event so that once we have been in recovery

2008-10-22 11:04:41 +11:00

ctdb_traverse.c

change how we filter out "empty" records in the traversecode

2008-07-16 12:23:18 +10:00

ctdb_tunables.c

add control and logging of very high latencies.

2008-10-30 12:49:53 +11:00

ctdb_uptime.c

track both when we last started and ended a recovery.

2008-07-02 13:55:59 +10:00

ctdbd.c

dont override/change CTDB_BASE if it is already set by the shell

2008-11-20 16:39:56 +11:00

eventscript.c

add a context and a timed event so that once we have been in recovery

2008-10-22 11:04:41 +11:00