summaryrefslogtreecommitdiffstats
path: root/sys/geom/raid3
Commit message (Expand)AuthorAgeFilesLines
* Sector size can not be greater than MAXPHYS. Since GRAID3 calculatesae2011-01-121-0/+4
* Move wakeup() out of mutex to reduce contention.mav2010-01-051-3/+3
* Slightly optimize XOR calculation.mav2010-01-051-24/+31
* As soon as geom_raid3 reports it's own stripe as sector size, report largestmav2009-12-241-0/+14
* Make graid3 fallback to malloc() when component request size is biggermav2009-12-212-9/+15
* Revert r190676,190677thompsa2009-04-101-1/+1
* Add a how argument to root_mount_hold() so it can be passed NOWAIT and be calledthompsa2009-04-031-1/+1
* Rename the kthread_xxx (e.g. kthread_create()) callsjulian2007-10-201-3/+3
* Commit 14/14 of sched_lock decomposition.jeff2007-06-051-2/+2
* Now, that we have gjournal in the tree add possibility to configurepjd2006-11-013-8/+49
* Change spaces to tabs where needed.pjd2006-11-012-24/+24
* Implement BIO_FLUSH handling by simply passing it down to the components.pjd2006-10-311-0/+47
* Guard against invalid metadata.pjd2006-10-101-0/+6
* One more white space fix.pjd2006-09-301-1/+1
* Remove trailing spaces.pjd2006-09-301-16/+16
* Small fixes after adding __printflike() to gctl_error().pjd2006-09-161-4/+4
* Fix synchronization in gmirror and graid3 which I broken. Synchronizationpjd2006-09-131-2/+5
* move created/detected/activated under debug level 1 to quiet the common case..jmg2006-09-091-5/+7
* Not only a request from us can be passed to g_{mirror,raid3}_worker()pjd2006-08-091-5/+11
* Commit the results of the typo hunt by Darren Pilgrim.yar2006-08-041-1/+1
* Don't use f-word in comments. We are gentlemans.pjd2006-08-011-1/+1
* Always allow to specify components with /dev/ prefix.pjd2006-07-131-0/+4
* Use proper defines instead of magic values.pjd2006-07-101-2/+2
* When kern.geom.raid3.use_malloc tunnable is set to 1, malloc(9) instead ofpjd2006-07-091-43/+88
* Remove bogus assertion.pjd2006-07-071-1/+0
* Allow to close access even if device is already destroyed.pjd2006-07-031-3/+5
* Use G_RAID3_FOREACH_SAFE_BIO() macro instead of G_RAID3_FOREACH_BIO() inpjd2006-05-041-6/+4
* We shouldn't lock the topology here - we will panic on assertion insidepjd2006-04-301-2/+0
* - Don't hold the device sx lock when going to sleep.pjd2006-04-281-6/+23
* - Remove dead code.pjd2006-04-281-9/+9
* Be sure to not destroy device twice. This is not possible in theory, butpjd2006-04-281-2/+13
* Fix storing offset of already synchronized data. Offset in entire array waspjd2006-04-181-3/+5
* Introduce and use delayed-destruction functionality from a pre-sync hook,pjd2006-04-103-55/+82
* Preserve previous behaviour of kern.geom.raid3.n{64,16,4}k tunables were 0pjd2006-03-281-1/+1
* Increase debug level for "Thread exiting." message. It's not that importantpjd2006-03-251-1/+1
* Update copyright for 2006.pjd2006-03-192-2/+2
* kern.geom.raid3.sync_requests=2 seems to be a better default - it stillpjd2006-03-191-3/+3
* Fix build on 64-bit platforms.ru2006-03-131-2/+2
* - Reimplement I/O data allocation to prevent deadlocks.pjd2006-03-133-352/+672
* When inserting a new component md_provsize metadata field wasn't set, whichpjd2006-03-101-0/+1
* Do not use bio structure after g_io_deliver(), it may not longer by valid.pjd2006-02-221-1/+1
* On component state change to ACTIVE don't forget to update metadata.pjd2006-02-121-3/+2
* Use time_uptime instead of time_second, as the latter may go backwards.pjd2006-02-121-4/+4
* Allow to set kern.geom.raid3.disconnect_on_failure from loader.conf.pjd2006-02-121-0/+2
* - Add kern.geom.raid3.disconnect_on_failure sysctl/tunnable (default to 1pjd2006-02-112-31/+76
* Correct typo. 'fbp' is NULL here so this will result in a panic.pjd2006-02-111-1/+1
* Mark array as CLEAN when there are no write requests inpjd2006-02-112-101/+53
* Remove trailing spaces.pjd2006-02-013-23/+23
* Fix typo which cased that 64kB elements limit was not set properly andpjd2006-01-301-1/+1
* Remove dead code.pjd2006-01-181-2/+0
OpenPOWER on IntegriCloud