linux - Linux Kernel (branches are rebased on master from time to time)

Age	Commit message (Expand)	Author	Files	Lines
2012-08-02	Merge tag 'md-3.6' of git://neil.brown.name/md	Linus Torvalds	1	-16/+91
2012-08-02	raid5: raid5d handle stripe in batch way	Shaohua Li	1	-13/+32
2012-08-02	raid5: make_request use batch stripe release	Shaohua Li	1	-3/+59
2012-08-01	Merge branch 'for-3.6/drivers' of git://git.kernel.dk/linux-block	Linus Torvalds	1	-3/+2
2012-07-31	md: remove plug_cnt feature of plugging.	NeilBrown	1	-3/+2
2012-07-31	md/raid5: For odirect-write performance, do not set STRIPE_PREREAD_ACTIVE.	majianpeng	1	-1/+1
2012-07-31	raid5: Add R5_ReadNoMerge flag which prevent bio from merging at block layer	majianpeng	1	-2/+12
2012-07-19	raid5: add a per-stripe lock	Shaohua Li	1	-16/+19
2012-07-19	raid5: remove unnecessary bitmap write optimization	Shaohua Li	1	-12/+9
2012-07-19	raid5: lockless access raid5 overrided bi_phys_segments	Shaohua Li	1	-30/+32
2012-07-19	raid5: reduce chance release_stripe() taking device_lock	Shaohua Li	1	-34/+41
2012-07-03	md: fix up plugging (again).	NeilBrown	1	-5/+1
2012-07-03	raid5: delayed stripe fix	Shaohua Li	1	-1/+3
2012-07-03	md/raid456: When read error cannot be recovered, record bad block	majianpeng	1	-4/+11
2012-07-03	md: make 'name' arg to md_register_thread non-optional.	NeilBrown	1	-1/+3
2012-07-03	md/raid5: fix refcount problem when blocked_rdev is set.	NeilBrown	1	-2/+12
2012-07-03	md/raid5: In ops_run_io, inc nr_pending before calling md_wait_for_blocked_rdev	majianpeng	1	-0/+6
2012-07-03	md/raid5: Do not add data_offset before call to is_badblock	majianpeng	1	-2/+3
2012-07-03	md/raid5: prefer replacing failed devices over want-replacement devices.	NeilBrown	1	-5/+8
2012-05-22	md/raid5: improve removal of extra devices after reshape.	NeilBrown	1	-5/+5
2012-05-22	md/raid5: Allow reshape while a bitmap is present.	NeilBrown	1	-3/+3
2012-05-22	md: allow array to be resized while bitmap is present.	NeilBrown	1	-4/+10
2012-05-22	raid5: support sync request	Shaohua Li	1	-2/+10
2012-05-22	raid5: remove unused variables	Shaohua Li	1	-4/+0
2012-05-21	md/raid5: allow for change in data_offset while managing a reshape.	NeilBrown	1	-33/+76
2012-05-21	md/raid5: Use correct data_offset for all IO.	NeilBrown	1	-13/+59
2012-05-21	md: add possibility to change data-offset for devices.	NeilBrown	1	-3/+7
2012-05-21	md: allow a reshape operation to be reversed.	NeilBrown	1	-11/+12
2012-04-03	md/raid5: Fix a bug about judging if the operation is syncing or replacing	majianpeng	1	-1/+3
2012-04-03	md/raid5: fix handling of bad blocks during recovery.	NeilBrown	1	-26/+29
2012-03-19	md: tidy up rdev_for_each usage.	NeilBrown	1	-4/+4
2012-03-19	md: allow re-add to failed arrays.	NeilBrown	1	-1/+1
2012-03-13	md/raid5: use atomic_dec_return() instead of atomic_dec() and atomic_read().	majianpeng	1	-4/+3
2012-03-13	md/raid5: removed unused 'added_devices' variable.	NeilBrown	1	-5/+2
2012-03-13	md/raid5: make sure reshape_position is cleared on error path.	NeilBrown	1	-0/+1
2011-12-23	md/raid5: Mark device want_replacement when we see a write error.	NeilBrown	1	-0/+3
2011-12-23	md/raid5: If there is a spare and a want_replacement device, start replacement.	NeilBrown	1	-2/+14
2011-12-23	md/raid5: recognise replacements when assembling array.	NeilBrown	1	-6/+31
2011-12-23	md/raid5: handle activation of replacement device when recovery completes.	NeilBrown	1	-7/+62
2011-12-23	md/raid5: detect and handle replacements during recovery.	NeilBrown	1	-29/+94
2011-12-23	md/raid5: writes should get directed to replacement as well as original.	NeilBrown	1	-23/+96
2011-12-23	md/raid5: allow removal for failed replacement devices.	NeilBrown	1	-26/+32
2011-12-23	md/raid5: preferentially read from replacement device if possible.	NeilBrown	1	-15/+54
2011-12-23	md/raid5: remove redundant bio initialisations.	NeilBrown	1	-8/+1
2011-12-23	md/raid5: allow each slot to have an extra replacement device	NeilBrown	1	-2/+13
2011-12-23	md: change hot_remove_disk to take an rdev rather than a number.	NeilBrown	1	-5/+5
2011-12-23	md/raid5: be more thorough in calculating 'degraded' value.	NeilBrown	1	-30/+33
2011-12-23	md/raid5: ensure correct assessment of drives during degraded reshape.	NeilBrown	1	-4/+10
2011-12-09	md: raid5 crash during degradation	Adam Kwolek	1	-2/+2
2011-12-08	md/raid5: never wait for bad-block acks on failed device.	NeilBrown	1	-1/+3