diff options
Diffstat (limited to 'drivers/md/raid5.h')
| -rw-r--r-- | drivers/md/raid5.h | 61 |
1 files changed, 54 insertions, 7 deletions
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 8d8e13934a4..bc72cd4be5f 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -49,7 +49,7 @@ * can't distinguish between a clean block that has been generated * from parity calculations, and a clean block that has been * successfully written to the spare ( or to parity when resyncing). - * To distingush these states we have a stripe bit STRIPE_INSYNC that + * To distinguish these states we have a stripe bit STRIPE_INSYNC that * is set whenever a write is scheduled to the spare, or to the parity * disc if there is no spare. A sync request clears this bit, and * when we find it set with no buffers locked, we know the sync is @@ -197,6 +197,7 @@ enum reconstruct_states { struct stripe_head { struct hlist_node hash; struct list_head lru; /* inactive_list or handle_list */ + struct llist_node release_list; struct r5conf *raid_conf; short generation; /* increments with every * reshape */ @@ -204,12 +205,16 @@ struct stripe_head { short pd_idx; /* parity disk index */ short qd_idx; /* 'Q' disk index for raid6 */ short ddf_layout;/* use DDF ordering to calculate Q */ + short hash_lock_index; unsigned long state; /* state flags */ atomic_t count; /* nr of active thread/requests */ int bm_seq; /* sequence number for bitmap flushes */ int disks; /* disks in stripe */ enum check_states check_state; enum reconstruct_states reconstruct_state; + spinlock_t stripe_lock; + int cpu; + struct r5worker_group *group; /** * struct stripe_operations * @target - STRIPE_OP_COMPUTE_BLK target @@ -220,10 +225,6 @@ struct stripe_head { struct stripe_operations { int target, target2; enum sum_check_flags zero_sum_result; - #ifdef CONFIG_MULTICORE_RAID456 - unsigned long request; - wait_queue_head_t wait_for_ops; - #endif } ops; struct r5dev { /* rreq and rvec are used for the replacement device when @@ -231,7 +232,7 @@ struct stripe_head { */ struct bio req, rreq; struct bio_vec vec, rvec; - struct page *page; + struct page *page, *orig_page; struct bio *toread, *read, *towrite, *written; sector_t sector; /* sector of this page */ unsigned long flags; @@ -273,6 +274,7 @@ enum r5dev_flags { R5_Wantwrite, R5_Overlap, /* There is a pending overlapping request * on this block */ + R5_ReadNoMerge, /* prevent bio from merging in block-layer */ R5_ReadError, /* seen a read error here recently */ R5_ReWrite, /* have tried to over-write the readerror */ @@ -285,6 +287,7 @@ enum r5dev_flags { */ R5_Wantdrain, /* dev->towrite needs to be drained */ R5_WantFUA, /* Write should be FUA */ + R5_SyncIO, /* The IO is sync */ R5_WriteError, /* got a write error - need to record it */ R5_MadeGood, /* A bad block has been fixed by writing to it */ R5_ReadRepl, /* Will/did read from replacement rather than orig */ @@ -295,6 +298,8 @@ enum r5dev_flags { R5_WantReplace, /* We need to update the replacement, we have read * data in, and now is a good time to write it out. */ + R5_Discard, /* Discard the stripe */ + R5_SkipCopy, /* Don't copy data from bio to stripe cache */ }; /* @@ -306,6 +311,7 @@ enum { STRIPE_SYNC_REQUESTED, STRIPE_SYNCING, STRIPE_INSYNC, + STRIPE_REPLACED, STRIPE_PREREAD_ACTIVE, STRIPE_DELAYED, STRIPE_DEGRADED, @@ -318,6 +324,9 @@ enum { STRIPE_BIOFILL_RUN, STRIPE_COMPUTE_RUN, STRIPE_OPS_REQ_PENDING, + STRIPE_ON_UNPLUG_LIST, + STRIPE_DISCARD, + STRIPE_ON_RELEASE_LIST, }; /* @@ -360,8 +369,32 @@ struct disk_info { struct md_rdev *rdev, *replacement; }; +/* NOTE NR_STRIPE_HASH_LOCKS must remain below 64. + * This is because we sometimes take all the spinlocks + * and creating that much locking depth can cause + * problems. + */ +#define NR_STRIPE_HASH_LOCKS 8 +#define STRIPE_HASH_LOCKS_MASK (NR_STRIPE_HASH_LOCKS - 1) + +struct r5worker { + struct work_struct work; + struct r5worker_group *group; + struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS]; + bool working; +}; + +struct r5worker_group { + struct list_head handle_list; + struct r5conf *conf; + struct r5worker *workers; + int stripes_cnt; +}; + struct r5conf { struct hlist_head *stripe_hashtbl; + /* only protect corresponding hash list and inactive_list */ + spinlock_t hash_locks[NR_STRIPE_HASH_LOCKS]; struct mddev *mddev; int chunk_sectors; int level, algorithm; @@ -383,8 +416,15 @@ struct r5conf { int prev_chunk_sectors; int prev_algo; short generation; /* increments with every reshape */ + seqcount_t gen_lock; /* lock against generation changes */ unsigned long reshape_checkpoint; /* Time we last updated * metadata */ + long long min_offset_diff; /* minimum difference between + * data_offset and + * new_data_offset across all + * devices. May be negative, + * but is closest to zero. + */ struct list_head handle_list; /* stripes needing handling */ struct list_head hold_list; /* preread ready stripes */ @@ -397,6 +437,7 @@ struct r5conf { atomic_t pending_full_writes; /* full write backlog */ int bypass_count; /* bypassed prereads */ int bypass_threshold; /* preread nice */ + int skip_copy; /* Don't copy data from bio to stripe cache */ struct list_head *last_hold; /* detect hold_list promotions */ atomic_t reshape_stripes; /* stripes with pending writes for reshape */ @@ -435,7 +476,9 @@ struct r5conf { * Free stripes pool */ atomic_t active_stripes; - struct list_head inactive_list; + struct list_head inactive_list[NR_STRIPE_HASH_LOCKS]; + atomic_t empty_inactive_list_nr; + 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, @@ -449,6 +492,10 @@ struct r5conf { * the new thread here until we fully activate the array. */ struct md_thread *thread; + struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS]; + struct r5worker_group *worker_groups; + int group_cnt; + int worker_cnt_per_group; }; /* |