summaryrefslogtreecommitdiffstats
path: root/include/linux/raid
diff options
context:
space:
mode:
authorDan Williams <dan.j.williams@intel.com>2007-01-02 13:52:30 -0700
committerDan Williams <dan.j.williams@intel.com>2007-07-13 08:06:15 -0700
commit91c00924846a0034020451c280c76baa4299f9dc (patch)
tree7124ed6706937b793a10c37a861c5fc0f2e5b348 /include/linux/raid
parent45b4233caac05da0118b608a9fc2a40a9fc580cd (diff)
downloadop-kernel-dev-91c00924846a0034020451c280c76baa4299f9dc.zip
op-kernel-dev-91c00924846a0034020451c280c76baa4299f9dc.tar.gz
md: raid5_run_ops - run stripe operations outside sh->lock
When the raid acceleration work was proposed, Neil laid out the following attack plan: 1/ move the xor and copy operations outside spin_lock(&sh->lock) 2/ find/implement an asynchronous offload api The raid5_run_ops routine uses the asynchronous offload api (async_tx) and the stripe_operations member of a stripe_head to carry out xor+copy operations asynchronously, outside the lock. To perform operations outside the lock a new set of state flags is needed to track new requests, in-flight requests, and completed requests. In this new model handle_stripe is tasked with scanning the stripe_head for work, updating the stripe_operations structure, and finally dropping the lock and calling raid5_run_ops for processing. The following flags outline the requests that handle_stripe can make of raid5_run_ops: STRIPE_OP_BIOFILL - copy data into request buffers to satisfy a read request STRIPE_OP_COMPUTE_BLK - generate a missing block in the cache from the other blocks STRIPE_OP_PREXOR - subtract existing data as part of the read-modify-write process STRIPE_OP_BIODRAIN - copy data out of request buffers to satisfy a write request STRIPE_OP_POSTXOR - recalculate parity for new data that has entered the cache STRIPE_OP_CHECK - verify that the parity is correct STRIPE_OP_IO - submit i/o to the member disks (note this was already performed outside the stripe lock, but it made sense to add it as an operation type The flow is: 1/ handle_stripe sets STRIPE_OP_* in sh->ops.pending 2/ raid5_run_ops reads sh->ops.pending, sets sh->ops.ack, and submits the operation to the async_tx api 3/ async_tx triggers the completion callback routine to set sh->ops.complete and release the stripe 4/ handle_stripe runs again to finish the operation and optionally submit new operations that were previously blocked Note this patch just defines raid5_run_ops, subsequent commits (one per major operation type) modify handle_stripe to take advantage of this routine. Changelog: * removed ops_complete_biodrain in favor of ops_complete_postxor and ops_complete_write. * removed the raid5_run_ops workqueue * call bi_end_io for reads in ops_complete_biofill, saves a call to handle_stripe * explicitly handle the 2-disk raid5 case (xor becomes memcpy), Neil Brown * fix race between async engines and bi_end_io call for reads, Neil Brown * remove unnecessary spin_lock from ops_complete_biofill * remove test_and_set/test_and_clear BUG_ONs, Neil Brown * remove explicit interrupt handling for channel switching, this feature was absorbed (i.e. it is now implicit) by the async_tx api * use return_io in ops_complete_biofill Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-By: NeilBrown <neilb@suse.de>
Diffstat (limited to 'include/linux/raid')
-rw-r--r--include/linux/raid/raid5.h81
1 files changed, 78 insertions, 3 deletions
diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h
index b99d354..6fb9d94 100644
--- a/include/linux/raid/raid5.h
+++ b/include/linux/raid/raid5.h
@@ -116,13 +116,46 @@
* 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.
*/
struct stripe_head {
@@ -136,11 +169,26 @@ struct stripe_head {
spinlock_t lock;
int bm_seq; /* sequence number for bitmap flushes */
int disks; /* disks in stripe */
+ /* stripe_operations
+ * @pending - pending ops flags (set for request->issue->complete)
+ * @ack - submitted ops flags (set for issue->complete)
+ * @complete - completed ops flags (set for complete)
+ * @target - STRIPE_OP_COMPUTE_BLK target
+ * @count - raid5_runs_ops is set to run when this is non-zero
+ */
+ struct stripe_operations {
+ unsigned long pending;
+ unsigned long ack;
+ unsigned long complete;
+ int target;
+ int count;
+ 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 */
@@ -174,6 +222,15 @@ struct r6_state {
#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
*/
@@ -196,6 +253,24 @@ struct r6_state {
#define STRIPE_EXPAND_SOURCE 10
#define STRIPE_EXPAND_READY 11
/*
+ * Operations flags (in issue order)
+ */
+#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
+#define STRIPE_OP_IO 6
+
+/* modifiers to the base operations
+ * STRIPE_OP_MOD_REPAIR_PD - compute the parity block and write it back
+ * STRIPE_OP_MOD_DMA_CHECK - parity is not corrupted by the check
+ */
+#define STRIPE_OP_MOD_REPAIR_PD 7
+#define STRIPE_OP_MOD_DMA_CHECK 8
+
+/*
* Plugging:
*
* To improve write throughput, we need to delay the handling of some
OpenPOWER on IntegriCloud