summaryrefslogtreecommitdiffstats
path: root/ctdb
Commit message (Expand)AuthorAgeFilesLines
...
* recoverd: Log more information when interfaces changeMartin Schwenke2013-08-221-2/+15
* traverse: Log when database traverse is startedAmitay Isaacs2013-08-221-0/+2
* ctdbd: Finish eventscript callback processing before debugging hung scriptAmitay Isaacs2013-08-221-26/+47
* ctdbd: Make sure call data is freed if doing an early returnAmitay Isaacs2013-08-221-2/+10
* common/io: Limit the queue buffer size for fair scheduling via teventAmitay Isaacs2013-08-221-12/+31
* Revert "common/io: Keep queue buffer size multiple of 4K"Amitay Isaacs2013-08-221-22/+6
* Revert "LACOUNT: Add back lacount mechanism to defer migrating a fetched/rea...Amitay Isaacs2013-08-226-29/+13
* ctdbd: Print a log message when a key becomes hotAmitay Isaacs2013-08-221-0/+2
* ctdbd: For volatile databases, write an empty record with rsn=0 only on dmasterAmitay Isaacs2013-08-221-1/+3
* tools/ctdb: Fix message in showban when node is bannedMartin Schwenke2013-08-211-1/+2
* tools/ctdb: Reimplement ban/unban using update_flags_wait_and_ipreallocate()Martin Schwenke2013-08-211-61/+18
* tools/ctdb: Factor out common pattern used in disable/enable/stop/continueMartin Schwenke2013-08-211-119/+76
* tools/ctdb: Factor, simplify and improve robustness of ipreallocate codeMartin Schwenke2013-08-211-45/+32
* tools/ctdb: Use ctdb_get_pnn() to get PNN of the current nodeMartin Schwenke2013-08-211-29/+5
* util: In passing the code, fix a space vs. tab in set_close_on_exec().Michael Adam2013-08-191-1/+1
* server: standardize formatting of comment block for ctdb_reply_dmaster() whil...Michael Adam2013-08-191-6/+6
* server: fix wording and punctuation in comment block for ctdb_reply_dmaster().Michael Adam2013-08-191-2/+2
* recoverd: Improve log message when nodes disagree on recmasterAmitay Isaacs2013-08-141-1/+1
* common: Null terminate process name string so valgrind doesn't complainAmitay Isaacs2013-08-141-0/+1
* vacuuming: Fix vacuuming bug where requests keep bouncing between nodes (part 2)Amitay Isaacs2013-08-141-20/+20
* vacuuming: Fix vacuuming bug where requests keep bouncing between nodes (part 1)Amitay Isaacs2013-08-141-1/+1
* db_wrap: Make sure tdb messages are logged correctlyAmitay Isaacs2013-08-141-0/+1
* eventscripts: Become unhealthy faster on nfsd failureMartin Schwenke2013-08-144-15/+5
* tools/ctdb: Increase default control timeout to 10 secondsMartin Schwenke2013-08-141-1/+1
* eventscripts: Improve message logged when a counter hits a limitMartin Schwenke2013-08-141-1/+1
* eventscripts: Print a message when waiting for TCP connections to be killedMartin Schwenke2013-08-142-1/+7
* eventscripts: New configuration variable $CTDB_RPCINFO_LOCALHOSTMartin Schwenke2013-08-142-1/+8
* eventscripts: Add modulo (%) operator to ctdb_check_counter()Martin Schwenke2013-08-142-8/+23
* eventscripts: Separate out RPC service restart codeMartin Schwenke2013-08-143-51/+60
* tests/eventscripts: Override background_with_logging(), just prepend "&"Martin Schwenke2013-08-146-31/+34
* eventscripts: Remove support for RPC service 'q' and 's' restart flagsMartin Schwenke2013-08-145-10/+6
* eventscripts: When restarting the nfslock service only show output of startMartin Schwenke2013-08-141-2/+2
* tests/simple: Unreachable node test should wait for recovery to completeMartin Schwenke2013-08-141-0/+2
* tests/simple: Fix the missing IP testMartin Schwenke2013-08-141-6/+8
* recoverd: Use TDB_INCOMPATIBLE_HASH when creating volatile databasesAmitay Isaacs2013-08-141-1/+7
* Revert "recoverd: Use correct tdb flags when creating missing databases"Amitay Isaacs2013-08-143-10/+8
* common/io: Keep queue buffer size multiple of 4KAmitay Isaacs2013-08-091-6/+22
* packaging: Allow setting custom release number in RPM spec fileMartin Schwenke2013-08-094-8/+16
* ctdbd: When a record is made sticky, log only onceAmitay Isaacs2013-08-091-2/+3
* ctdbd: Improve high hopcount log messages when request is redirectedAmitay Isaacs2013-08-091-5/+5
* scripts: Do not run ctdb tool commands when debugging hung "init" eventMartin Schwenke2013-08-091-2/+6
* ctdbd: Avoid leaking file descriptor if talloc failsAmitay Isaacs2013-08-091-1/+4
* eventscript: Wait for debug hung script to finish or timeout before continuingAmitay Isaacs2013-08-091-13/+59
* eventscripts: Use configured RECLOCK file instead of asking CTDBAmitay Isaacs2013-08-091-7/+5
* locking: Do not create multiple lock processes for the same keyAmitay Isaacs2013-08-091-6/+15
* locking: Move function find_lock_context() before ctdb_lock_schedule()Amitay Isaacs2013-08-091-53/+53
* ctdbd: Print set db sticky message after it's setAmitay Isaacs2013-08-011-3/+2
* tests: Add a test program to hold a lock on a databaseAmitay Isaacs2013-08-012-1/+47
* recoverd: Use correct tdb flags when creating missing databasesAmitay Isaacs2013-08-013-8/+10
* client: Always use jenkins hash when attaching volatile databasesAmitay Isaacs2013-08-011-0/+8