Martin Schwenke c0939af571 LCP IP allocation algorithm - try harder to find a candidate source node ...

There's a bug in LCP2.  Selecting the node with the highest imbalance
doesn't always work.  Some nodes can have a high imbalance metric
because they have a lot of IPs.  However, these nodes can be part of a
group that is perfectly balanced.  Nodes in another group with less
IPs might actually be imbalanced.

Instead of just trying the source node with the highest imbalance this
tries them in descending order of imbalance until it finds one where
an IP can be moved to another node.

Signed-off-by: Martin Schwenke <martin@meltin.net>

(This used to be ctdb commit 574091d5aced5e87aefad52f8bc47aa75c25fbf6)

2011-11-02 10:17:00 +11:00

..

ctdb_banning.c

server/banning: also release all ips if we're banning ourself

2010-09-14 15:50:31 +10:00

ctdb_call.c

ReadOnly: fix bug writing incorrect amount of data in delegated record

2011-10-28 11:44:19 +11:00

ctdb_control.c

ReadOnly: add a new control to activate readonly lock capability for a database.

2011-09-01 11:08:18 +10:00

ctdb_daemon.c

ReadOnly: Check the readonly flag instead of whether the tdb pointer is NULL or not

2011-08-23 10:41:52 +10:00

ctdb_freeze.c

This needs more testing first

2011-03-21 14:25:53 +11:00

ctdb_keepalive.c

event: Update events to latest Samba version 0.9.8

2010-08-18 09:16:31 +09:30

ctdb_lockwait.c

LockWait congestion.

2011-01-24 12:21:58 +11:00

ctdb_logging.c

Logging: when we log stdout/stderr messages from eventscripts to the system log, prefix every line of output with the name of the eventscript.

2011-08-26 09:39:25 +10:00

ctdb_ltdb_server.c

Remove debug message

2011-10-24 12:21:55 +11:00

ctdb_monitor.c

remove a non-error logmessage about persistent databases being healthy, as expected

2011-08-04 13:49:48 +10:00

ctdb_persistent.c

persistent: add ctdb_persistent_finish_trans3_commits().

2011-02-24 10:35:26 +01:00

ctdb_recover.c

ReadOnly: revokechild_active is a list, not a context.

2011-09-13 18:47:18 +10:00

ctdb_recoverd.c

Merge branch 'master-readonly-records' into foo

2011-09-12 09:34:34 +10:00

ctdb_server.c

Create macros to update the statistics counters and use these macros

2010-09-29 12:14:24 +10:00

ctdb_serverids.c

merge from ronnie

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

ctdb_statistics.c

initialize the statistics to the current time, not start of epoch

2010-11-15 16:44:21 +11:00

ctdb_takeover.c

LCP IP allocation algorithm - try harder to find a candidate source node

2011-11-02 10:17:00 +11:00

ctdb_traverse.c

Add ctdb_fork(0 which will fork a child process and drop the real-time

2011-01-11 07:40:41 +11:00

ctdb_tunables.c

Add a tunable "AllowClientDBAttach" with default value 1.

2011-09-05 16:17:39 +10:00

ctdb_uptime.c

event: Update events to latest Samba version 0.9.8

2010-08-18 09:16:31 +09:30

ctdb_vacuum.c

Correction of spelling errors

2011-03-23 00:35:23 +01:00

ctdbd.c

Change the message when we start the daemon to "CTDB starting on node"

2011-08-04 13:49:30 +10:00

eventscript.c

Logging: when we log stdout/stderr messages from eventscripts to the system log, prefix every line of output with the name of the eventscript.

2011-08-26 09:39:25 +10:00