 Sasha Levin
|
9b81c84235
block: don't access bio->bi_error after bio_put()
|
10 years ago |
 NeilBrown
|
49895bcc7e
md/raid5: don't let shrink_slab shrink too far.
|
10 years ago |
 Jens Axboe
|
b7c44ed9d2
block: manipulate bio->bi_flags through helpers
|
10 years ago |
 Christoph Hellwig
|
4246a0b63b
block: add a bi_error field to struct bio
|
10 years ago |
|
NeilBrown
|
e6030cb06c
md/raid5: clear R5_NeedReplace when no longer needed.
|
10 years ago |
|
NeilBrown
|
2d5b569b66
md/raid5: avoid races when changing cache size.
|
10 years ago |
 Shaohua Li
|
713bc5c2de
md/raid5: ignore released_stripes check
|
10 years ago |
 Yuanhan Liu
|
e9e4c377e2
md/raid5: per hash value and exclusive wait_for_stripe
|
10 years ago |
|
Yuanhan Liu
|
b1b4648648
md/raid5: split wait_for_stripe and introduce wait_for_quiescent
|
10 years ago |
 NeilBrown
|
ea358cd0d2
md: make sure MD_RECOVERY_DONE is clear before starting recovery/resync
|
10 years ago |
|
NeilBrown
|
626f2092c8
md/raid5: break stripe-batches when the array has failed.
|
10 years ago |
|
NeilBrown
|
787b76fa37
md/raid5: call break_stripe_batch_list from handle_stripe_clean_event
|
10 years ago |
|
NeilBrown
|
1b956f7a8f
md/raid5: be more selective about distributing flags across batch.
|
10 years ago |
|
NeilBrown
|
3960ce7961
md/raid5: add handle_flags arg to break_stripe_batch_list.
|
10 years ago |
|
NeilBrown
|
fb642b92c2
md/raid5: duplicate some more handle_stripe_clean_event code in break_stripe_batch_list
|
10 years ago |
|
NeilBrown
|
4e3d62ff49
md/raid5: remove condition test from check_break_stripe_batch_list.
|
10 years ago |
|
NeilBrown
|
b15a9dbdbf
md/raid5: Ensure a batch member is not handled prematurely.
|
10 years ago |
|
NeilBrown
|
d0852df543
md/raid5: close race between STRIPE_BIT_DELAY and batching.
|
10 years ago |
|
NeilBrown
|
2b6b245742
md/raid5: ensure whole batch is delayed for all required bitmap updates.
|
10 years ago |
 Shaohua Li
|
487696957e
raid5: fix broken async operation chain
|
10 years ago |
|
NeilBrown
|
bb27051f9f
md/raid5: fix handling of degraded stripes in batches.
|
10 years ago |
|
NeilBrown
|
738a273806
md/raid5: fix allocation of 'scribble' array.
|
10 years ago |
|
NeilBrown
|
6e9eac2dce
md/raid5: don't record new size if resize_stripes fails.
|
10 years ago |
|
NeilBrown
|
10d82c5f0d
md/raid5: avoid reading parity blocks for full-stripe write to degraded array
|
10 years ago |
|
NeilBrown
|
b0c783b323
md/raid5: more incorrect BUG_ON in handle_stripe_fill.
|
10 years ago |
|
NeilBrown
|
f18c1a35f6
md/raid5: new alloc_stripe() to allocate an initialize a stripe.
|
10 years ago |
 Eric Mei
|
9ffc8f7cb9
md/raid5: don't do chunk aligned read on degraded array.
|
10 years ago |
|
NeilBrown
|
edbe83ab4c
md/raid5: allow the stripe_cache to grow and shrink.
|
10 years ago |
|
NeilBrown
|
5423399a84
md/raid5: change ->inactive_blocked to a bit-flag.
|
10 years ago |
|
NeilBrown
|
486f0644c3
md/raid5: move max_nr_stripes management into grow_one_stripe and drop_one_stripe
|
10 years ago |
