diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-24 09:28:01 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-24 09:28:01 -0700 |
commit | 474095e46cd14421821da3201a9fd6a4c070996b (patch) | |
tree | 7203d36f53c376a96099ed0310787b1fb0c4f7a5 /drivers/md/raid5.h | |
parent | d56a669ca59c37ed0a7282a251b2f2f22533343a (diff) | |
parent | 9ffc8f7cb9647b13dfe4d1ad0d5e1427bb8b46d6 (diff) |
Merge tag 'md/4.1' of git://neil.brown.name/md
Pull md updates from Neil Brown:
"More updates that usual this time. A few have performance impacts
which hould mostly be positive, but RAID5 (in particular) can be very
work-load ensitive... We'll have to wait and see.
Highlights:
- "experimental" code for managing md/raid1 across a cluster using
DLM. Code is not ready for general use and triggers a WARNING if
used. However it is looking good and mostly done and having in
mainline will help co-ordinate development.
- RAID5/6 can now batch multiple (4K wide) stripe_heads so as to
handle a full (chunk wide) stripe as a single unit.
- RAID6 can now perform read-modify-write cycles which should help
performance on larger arrays: 6 or more devices.
- RAID5/6 stripe cache now grows and shrinks dynamically. The value
set is used as a minimum.
- Resync is now allowed to go a little faster than the 'mininum' when
there is competing IO. How much faster depends on the speed of the
devices, so the effective minimum should scale with device speed to
some extent"
* tag 'md/4.1' of git://neil.brown.name/md: (58 commits)
md/raid5: don't do chunk aligned read on degraded array.
md/raid5: allow the stripe_cache to grow and shrink.
md/raid5: change ->inactive_blocked to a bit-flag.
md/raid5: move max_nr_stripes management into grow_one_stripe and drop_one_stripe
md/raid5: pass gfp_t arg to grow_one_stripe()
md/raid5: introduce configuration option rmw_level
md/raid5: activate raid6 rmw feature
md/raid6 algorithms: xor_syndrome() for SSE2
md/raid6 algorithms: xor_syndrome() for generic int
md/raid6 algorithms: improve test program
md/raid6 algorithms: delta syndrome functions
raid5: handle expansion/resync case with stripe batching
raid5: handle io error of batch list
RAID5: batch adjacent full stripe write
raid5: track overwrite disk count
raid5: add a new flag to track if a stripe can be batched
raid5: use flex_array for scribble data
md raid0: access mddev->queue (request queue member) conditionally because it is not set when accessed from dm-raid
md: allow resync to go faster when there is competing IO.
md: remove 'go_faster' option from ->sync_request()
...
Diffstat (limited to 'drivers/md/raid5.h')
-rw-r--r-- | drivers/md/raid5.h | 59 |
1 files changed, 50 insertions, 9 deletions
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 983e18a83db1..7dc0dd86074b 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -210,11 +210,19 @@ struct stripe_head { atomic_t count; /* nr of active thread/requests */ int bm_seq; /* sequence number for bitmap flushes */ int disks; /* disks in stripe */ + int overwrite_disks; /* total overwrite disks in stripe, + * this is only checked when stripe + * has STRIPE_BATCH_READY + */ enum check_states check_state; enum reconstruct_states reconstruct_state; spinlock_t stripe_lock; int cpu; struct r5worker_group *group; + + struct stripe_head *batch_head; /* protected by stripe lock */ + spinlock_t batch_lock; /* only header's lock is useful */ + struct list_head batch_list; /* protected by head's batch lock*/ /** * struct stripe_operations * @target - STRIPE_OP_COMPUTE_BLK target @@ -327,8 +335,15 @@ enum { STRIPE_ON_UNPLUG_LIST, STRIPE_DISCARD, STRIPE_ON_RELEASE_LIST, + STRIPE_BATCH_READY, + STRIPE_BATCH_ERR, }; +#define STRIPE_EXPAND_SYNC_FLAG \ + ((1 << STRIPE_EXPAND_SOURCE) |\ + (1 << STRIPE_EXPAND_READY) |\ + (1 << STRIPE_EXPANDING) |\ + (1 << STRIPE_SYNC_REQUESTED)) /* * Operation request flags */ @@ -340,6 +355,24 @@ enum { STRIPE_OP_RECONSTRUCT, STRIPE_OP_CHECK, }; + +/* + * RAID parity calculation preferences + */ +enum { + PARITY_DISABLE_RMW = 0, + PARITY_ENABLE_RMW, + PARITY_PREFER_RMW, +}; + +/* + * Pages requested from set_syndrome_sources() + */ +enum { + SYNDROME_SRC_ALL, + SYNDROME_SRC_WANT_DRAIN, + SYNDROME_SRC_WRITTEN, +}; /* * Plugging: * @@ -396,10 +429,11 @@ struct r5conf { spinlock_t hash_locks[NR_STRIPE_HASH_LOCKS]; struct mddev *mddev; int chunk_sectors; - int level, algorithm; + int level, algorithm, rmw_level; int max_degraded; int raid_disks; int max_nr_stripes; + int min_nr_stripes; /* reshape_progress is the leading edge of a 'reshape' * It has value MaxSector when no reshape is happening @@ -458,15 +492,11 @@ struct r5conf { /* per cpu variables */ struct raid5_percpu { struct page *spare_page; /* Used when checking P/Q in raid6 */ - void *scribble; /* space for constructing buffer + struct flex_array *scribble; /* space for constructing buffer * lists and performing address * conversions */ } __percpu *percpu; - size_t scribble_len; /* size of scribble region must be - * associated with conf to handle - * cpu hotplug while reshaping - */ #ifdef CONFIG_HOTPLUG_CPU struct notifier_block cpu_notify; #endif @@ -480,9 +510,19 @@ struct r5conf { struct llist_head released_stripes; wait_queue_head_t wait_for_stripe; wait_queue_head_t wait_for_overlap; - int inactive_blocked; /* release of inactive stripes blocked, - * waiting for 25% to be free - */ + unsigned long cache_state; +#define R5_INACTIVE_BLOCKED 1 /* release of inactive stripes blocked, + * waiting for 25% to be free + */ +#define R5_ALLOC_MORE 2 /* It might help to allocate another + * stripe. + */ +#define R5_DID_ALLOC 4 /* A stripe was allocated, don't allocate + * more until at least one has been + * released. This avoids flooding + * the cache. + */ + struct shrinker shrinker; int pool_size; /* number of disks in stripeheads in pool */ spinlock_t device_lock; struct disk_info *disks; @@ -497,6 +537,7 @@ struct r5conf { int worker_cnt_per_group; }; + /* * Our supported algorithms */ |