summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* dlm_load: lvb bitsHEADmasterDavid Teigland2012-11-161-0/+55
|
* sanlvm: updateDavid Teigland2012-08-311-147/+378
|
* sanlvm: updateDavid Teigland2012-08-291-65/+206
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_seq: updateDavid Teigland2012-08-291-10/+166
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* sanlvm: updateDavid Teigland2012-08-281-42/+155
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* sanlvm: add scriptDavid Teigland2012-08-241-0/+390
|
* dlm_load: use QUECVTDavid Teigland2012-04-091-6/+18
| | | | | | add QUECVT command and random load option Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_master: time opsDavid Teigland2012-02-141-1/+17
|
* dlm_master: more locksDavid Teigland2012-01-241-18/+41
|
* dlm_master: new testDavid Teigland2012-01-201-0/+353
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_load: user command inputDavid Teigland2011-11-161-156/+300
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_seq: add iterations optionDavid Teigland2011-10-031-16/+33
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* manyfilep/manyfiles: add new testsDavid Teigland2011-07-132-0/+68
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_seq: add new testDavid Teigland2011-07-131-0/+306
| | | | | | | | | measure time to: acquire locks on resources 1-N convert the locks (with -c) unlock the locks (with -u) Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_load: sleep optionsDavid Teigland2011-07-131-6/+22
|
* dlm_kill: fix sleepsDavid Teigland2010-11-042-2/+2
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_kill: dlm_lock releaseDavid Teigland2010-11-041-0/+19
| | | | | | to forcibly clear default lockspace Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_kill: updatesDavid Teigland2010-11-043-17/+89
| | | | | | better emulate target application Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_kill: add dlm_lock_alt testDavid Teigland2010-10-293-11/+322
| | | | | | | | dlm_lock_alt is like dlm_lock_loop, but it enforces a back-and-forth pattern (using a separate dlm lock), ensuring that each node gets the EX in turn after a kill. Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_kill: new testDavid Teigland2010-10-274-0/+353
| | | | | | | | | | | | (dlm_lockspace keeps lockspace around during loop test) node1: dlm_lockspace node2: dlm_lockspace (multiple instances of loop test can be run per node) node1: dlm_lock_loop node2: dlm_lock_loop Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_klock: ifdef RHEL5David Teigland2010-10-221-0/+12
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_klock: miscDavid Teigland2010-07-302-16/+5
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_klock: new testDavid Teigland2010-07-294-0/+384
| | | | | | kernel module that acquires dlm locks Signed-off-by: David Teigland <teigland@redhat.com>
* lock_load: miscDavid Teigland2010-07-272-12/+42
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* alternate-lvb: copy overDavid Teigland2010-04-131-0/+179
| | | | | | from cluster git tree Signed-off-by: David Teigland <teigland@redhat.com>
* dlm_load: handle EBUSY after cancelDavid Teigland2010-04-091-0/+40
| | | | | | | Nothing we can do to be certain we won't get EBUSY after cancel sometimes, so don't make it an error. Signed-off-by: David Teigland <teigland@redhat.com>
* add new dlm and fs testsDavid Teigland2010-04-064-0/+1422
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: define MAX_NODES 8, 16, 32, 64David Teigland2009-11-201-17/+21
| | | | | | can build cpgx to support any of them Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: support up to 16 nodesDavid Teigland2009-08-041-23/+51
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: let events wrap around event bufferDavid Teigland2009-07-231-28/+29
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: fix sync_fromDavid Teigland2009-07-131-1/+23
| | | | | | when that node dies; add todo comments Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: add commentDavid Teigland2009-07-131-0/+3
| | | | | | note to stop using join/leave lists Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: fix syncDavid Teigland2009-07-131-22/+45
| | | | | | | the synced_nodes and sync_from weren't accounting for nodes that had been removed. Problems here found by Honza. Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: fix & vs &&David Teigland2009-06-261-1/+7
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: write debug buffer to stderr on errorDavid Teigland2009-06-121-2/+12
| | | | | | | | If an error occurs with debug/event output is disabled (-D0 -H0), then print the buffer of debug/event output to stderr before exit(1). The buffer is still written to /var/log/cluster/cpgx_debug.txt. Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: add -n option to set nameDavid Teigland2009-06-111-17/+26
| | | | | | of the cpg Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: version 1.2-gitDavid Teigland2009-06-091-1/+1
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: version 1.2David Teigland2009-06-092-2/+5
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: add -w optionDavid Teigland2009-06-091-1/+5
| | | | | | wait this many seconds between kill/restart Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: version 1.1-gitDavid Teigland2009-06-091-1/+1
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: munge makefileDavid Teigland2009-06-091-2/+2
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: version 1.1David Teigland2009-06-092-2/+5
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: munge restart messagesDavid Teigland2009-06-091-13/+16
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: improve optionsDavid Teigland2009-06-081-11/+17
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: option to just run iptablesDavid Teigland2009-06-051-2/+28
| | | | | | | | it can just be convenient -IA runs the iptables -A command -ID runs the iptables -D command Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: use iptables to kill nodesDavid Teigland2009-06-041-9/+34
| | | | | | | stop traffic with iptables prior to killing the corosync process; I think this tends to look more like a real node failure Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: improve killing and restartingDavid Teigland2009-06-031-9/+44
| | | | | | | of corosync or aisexec, and optionally by starting exec directly instead of via cman_tool Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: version 1.0-gitDavid Teigland2009-06-031-1/+1
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: build stuffDavid Teigland2009-06-032-1/+4
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
* cpgx: build stuffDavid Teigland2009-06-034-31/+40
| | | | Signed-off-by: David Teigland <teigland@redhat.com>
generated by cgit (git 2.34.1) at 2024-04-25 15:56:38 +0000