* attach a request to an active stripe (add_stripe_bh())
* lockdev attach-buffer unlockdev
* handle a stripe (handle_stripe())
- * lockstripe clrSTRIPE_HANDLE ... (lockdev check-buffers unlockdev) .. change-state .. record io needed unlockstripe schedule io
+ * lockstripe clrSTRIPE_HANDLE ...
+ * (lockdev check-buffers unlockdev) ..
+ * change-state ..
+ * record io/ops needed unlockstripe schedule io/ops
* release an active stripe (release_stripe())
* lockdev if (!--cnt) { if STRIPE_HANDLE, add to handle_list else add to inactive-list } unlockdev
*
* The refcount counts each thread that have activated the stripe,
* plus raid5d if it is handling it, plus one for each active request
- * on a cached buffer.
+ * on a cached buffer, and plus one if the stripe is undergoing stripe
+ * operations.
+ *
+ * Stripe operations are performed outside the stripe lock,
+ * the stripe operations are:
+ * -copying data between the stripe cache and user application buffers
+ * -computing blocks to save a disk access, or to recover a missing block
+ * -updating the parity on a write operation (reconstruct write and
+ * read-modify-write)
+ * -checking parity correctness
+ * -running i/o to disk
+ * These operations are carried out by raid5_run_ops which uses the async_tx
+ * api to (optionally) offload operations to dedicated hardware engines.
+ * When requesting an operation handle_stripe sets the pending bit for the
+ * operation and increments the count. raid5_run_ops is then run whenever
+ * the count is non-zero.
+ * There are some critical dependencies between the operations that prevent some
+ * from being requested while another is in flight.
+ * 1/ Parity check operations destroy the in cache version of the parity block,
+ * so we prevent parity dependent operations like writes and compute_blocks
+ * from starting while a check is in progress. Some dma engines can perform
+ * the check without damaging the parity block, in these cases the parity
+ * block is re-marked up to date (assuming the check was successful) and is
+ * not re-read from disk.
+ * 2/ When a write operation is requested we immediately lock the affected
+ * blocks, and mark them as not up to date. This causes new read requests
+ * to be held off, as well as parity checks and compute block operations.
+ * 3/ Once a compute block operation has been requested handle_stripe treats
+ * that block as if it is up to date. raid5_run_ops guaruntees that any
+ * operation that is dependent on the compute block result is initiated after
+ * the compute block completes.
+ */
+
+/*
+ * Operations state - intermediate states that are visible outside of sh->lock
+ * In general _idle indicates nothing is running, _run indicates a data
+ * processing operation is active, and _result means the data processing result
+ * is stable and can be acted upon. For simple operations like biofill and
+ * compute that only have an _idle and _run state they are indicated with
+ * sh->state flags (STRIPE_BIOFILL_RUN and STRIPE_COMPUTE_RUN)
+ */
+/**
+ * enum check_states - handles syncing / repairing a stripe
+ * @check_state_idle - check operations are quiesced
+ * @check_state_run - check operation is running
+ * @check_state_result - set outside lock when check result is valid
+ * @check_state_compute_run - check failed and we are repairing
+ * @check_state_compute_result - set outside lock when compute result is valid
*/
+enum check_states {
+ check_state_idle = 0,
+ check_state_run, /* parity check */
+ check_state_check_result,
+ check_state_compute_run, /* parity repair */
+ check_state_compute_result,
+};
+
+/**
+ * enum reconstruct_states - handles writing or expanding a stripe
+ */
+enum reconstruct_states {
+ reconstruct_state_idle = 0,
+ reconstruct_state_drain_run, /* write */
+ reconstruct_state_run, /* expand */
+ reconstruct_state_drain_result,
+ reconstruct_state_result,
+};
struct stripe_head {
struct hlist_node hash;
spinlock_t lock;
int bm_seq; /* sequence number for bitmap flushes */
int disks; /* disks in stripe */
+ enum check_states check_state;
+ enum reconstruct_states reconstruct_state;
+ /* stripe_operations
+ * @target - STRIPE_OP_COMPUTE_BLK target
+ */
+ struct stripe_operations {
+ int target;
+ u32 zero_sum_result;
+ } ops;
struct r5dev {
struct bio req;
struct bio_vec vec;
struct page *page;
- struct bio *toread, *towrite, *written;
+ struct bio *toread, *read, *towrite, *written;
sector_t sector; /* sector of this page */
unsigned long flags;
} dev[1]; /* allocated with extra space depending of RAID geometry */
};
+
+/* stripe_head_state - collects and tracks the dynamic state of a stripe_head
+ * for handle_stripe. It is only valid under spin_lock(sh->lock);
+ */
+struct stripe_head_state {
+ int syncing, expanding, expanded;
+ int locked, uptodate, to_read, to_write, failed, written;
+ int to_fill, compute, req_compute, non_overwrite;
+ int failed_num;
+ unsigned long ops_request;
+};
+
+/* r6_state - extra state data only relevant to r6 */
+struct r6_state {
+ int p_failed, q_failed, qd_idx, failed_num[2];
+};
+
/* Flags */
#define R5_UPTODATE 0 /* page contains current data */
#define R5_LOCKED 1 /* IO has been submitted on "req" */
#define R5_ReWrite 9 /* have tried to over-write the readerror */
#define R5_Expanded 10 /* This block now has post-expand data */
+#define R5_Wantcompute 11 /* compute_block in progress treat as
+ * uptodate
+ */
+#define R5_Wantfill 12 /* dev->toread contains a bio that needs
+ * filling
+ */
+#define R5_Wantprexor 13 /* distinguish blocks ready for rmw from
+ * other "towrites"
+ */
/*
* Write method
*/
#define STRIPE_EXPANDING 9
#define STRIPE_EXPAND_SOURCE 10
#define STRIPE_EXPAND_READY 11
+#define STRIPE_IO_STARTED 12 /* do not count towards 'bypass_count' */
+#define STRIPE_FULL_WRITE 13 /* all blocks are set to be overwritten */
+#define STRIPE_BIOFILL_RUN 14
+#define STRIPE_COMPUTE_RUN 15
+/*
+ * Operation request flags
+ */
+#define STRIPE_OP_BIOFILL 0
+#define STRIPE_OP_COMPUTE_BLK 1
+#define STRIPE_OP_PREXOR 2
+#define STRIPE_OP_BIODRAIN 3
+#define STRIPE_OP_POSTXOR 4
+#define STRIPE_OP_CHECK 5
+
/*
* Plugging:
*
int previous_raid_disks;
struct list_head handle_list; /* stripes needing handling */
+ struct list_head hold_list; /* preread ready stripes */
struct list_head delayed_list; /* stripes that have plugged requests */
struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */
+ struct bio *retry_read_aligned; /* currently retrying aligned bios */
+ struct bio *retry_read_aligned_list; /* aligned bios retry list */
atomic_t preread_active_stripes; /* stripes with scheduled io */
+ atomic_t active_aligned_reads;
+ atomic_t pending_full_writes; /* full write backlog */
+ int bypass_count; /* bypassed prereads */
+ int bypass_threshold; /* preread nice */
+ struct list_head *last_hold; /* detect hold_list promotions */
atomic_t reshape_stripes; /* stripes with pending writes for reshape */
/* unfortunately we need two cache names as we temporarily have