2005-04-17 00:20:36 +02:00
|
|
|
#ifndef _RAID5_H
|
|
|
|
#define _RAID5_H
|
|
|
|
|
|
|
|
#include <linux/raid/xor.h>
|
2009-08-30 04:09:26 +02:00
|
|
|
#include <linux/dmaengine.h>
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
*
|
2011-07-26 03:34:20 +02:00
|
|
|
* Each stripe contains one buffer per device. Each buffer can be in
|
2005-04-17 00:20:36 +02:00
|
|
|
* one of a number of states stored in "flags". Changes between
|
2011-07-26 03:34:20 +02:00
|
|
|
* these states happen *almost* exclusively under the protection of the
|
|
|
|
* STRIPE_ACTIVE flag. Some very specific changes can happen in bi_end_io, and
|
|
|
|
* these are not protected by STRIPE_ACTIVE.
|
2005-04-17 00:20:36 +02:00
|
|
|
*
|
|
|
|
* The flag bits that are used to represent these states are:
|
|
|
|
* R5_UPTODATE and R5_LOCKED
|
|
|
|
*
|
|
|
|
* State Empty == !UPTODATE, !LOCK
|
|
|
|
* We have no data, and there is no active request
|
|
|
|
* State Want == !UPTODATE, LOCK
|
|
|
|
* A read request is being submitted for this block
|
|
|
|
* State Dirty == UPTODATE, LOCK
|
|
|
|
* Some new data is in this buffer, and it is being written out
|
|
|
|
* State Clean == UPTODATE, !LOCK
|
|
|
|
* We have valid data which is the same as on disc
|
|
|
|
*
|
|
|
|
* The possible state transitions are:
|
|
|
|
*
|
|
|
|
* Empty -> Want - on read or write to get old data for parity calc
|
|
|
|
* Empty -> Dirty - on compute_parity to satisfy write/sync request.(RECONSTRUCT_WRITE)
|
|
|
|
* Empty -> Clean - on compute_block when computing a block for failed drive
|
|
|
|
* Want -> Empty - on failed read
|
|
|
|
* Want -> Clean - on successful completion of read request
|
|
|
|
* Dirty -> Clean - on successful completion of write request
|
|
|
|
* Dirty -> Clean - on failed write
|
|
|
|
* Clean -> Dirty - on compute_parity to satisfy write/sync (RECONSTRUCT or RMW)
|
|
|
|
*
|
|
|
|
* The Want->Empty, Want->Clean, Dirty->Clean, transitions
|
|
|
|
* all happen in b_end_io at interrupt time.
|
|
|
|
* Each sets the Uptodate bit before releasing the Lock bit.
|
|
|
|
* This leaves one multi-stage transition:
|
|
|
|
* Want->Dirty->Clean
|
|
|
|
* This is safe because thinking that a Clean buffer is actually dirty
|
|
|
|
* will at worst delay some action, and the stripe will be scheduled
|
|
|
|
* for attention after the transition is complete.
|
|
|
|
*
|
|
|
|
* There is one possibility that is not covered by these states. That
|
|
|
|
* is if one drive has failed and there is a spare being rebuilt. We
|
|
|
|
* 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
|
|
|
|
* 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
|
|
|
|
* complete.
|
|
|
|
*
|
|
|
|
* Buffers for the md device that arrive via make_request are attached
|
|
|
|
* to the appropriate stripe in one of two lists linked on b_reqnext.
|
|
|
|
* One list (bh_read) for read requests, one (bh_write) for write.
|
|
|
|
* There should never be more than one buffer on the two lists
|
|
|
|
* together, but we are not guaranteed of that so we allow for more.
|
|
|
|
*
|
|
|
|
* If a buffer is on the read list when the associated cache buffer is
|
|
|
|
* Uptodate, the data is copied into the read buffer and it's b_end_io
|
|
|
|
* routine is called. This may happen in the end_request routine only
|
|
|
|
* if the buffer has just successfully been read. end_request should
|
|
|
|
* remove the buffers from the list and then set the Uptodate bit on
|
|
|
|
* the buffer. Other threads may do this only if they first check
|
|
|
|
* that the Uptodate bit is set. Once they have checked that they may
|
|
|
|
* take buffers off the read queue.
|
|
|
|
*
|
|
|
|
* When a buffer on the write list is committed for write it is copied
|
|
|
|
* into the cache buffer, which is then marked dirty, and moved onto a
|
|
|
|
* third list, the written list (bh_written). Once both the parity
|
|
|
|
* block and the cached buffer are successfully written, any buffer on
|
|
|
|
* a written list can be returned with b_end_io.
|
|
|
|
*
|
2011-07-26 03:34:20 +02:00
|
|
|
* The write list and read list both act as fifos. The read list,
|
|
|
|
* write list and written list are protected by the device_lock.
|
|
|
|
* The device_lock is only for list manipulations and will only be
|
|
|
|
* held for a very short time. It can be claimed from interrupts.
|
2005-04-17 00:20:36 +02:00
|
|
|
*
|
|
|
|
*
|
|
|
|
* Stripes in the stripe cache can be on one of two lists (or on
|
|
|
|
* neither). The "inactive_list" contains stripes which are not
|
|
|
|
* currently being used for any request. They can freely be reused
|
|
|
|
* for another stripe. The "handle_list" contains stripes that need
|
|
|
|
* to be handled in some way. Both of these are fifo queues. Each
|
|
|
|
* stripe is also (potentially) linked to a hash bucket in the hash
|
|
|
|
* table so that it can be found by sector number. Stripes that are
|
|
|
|
* not hashed must be on the inactive_list, and will normally be at
|
|
|
|
* the front. All stripes start life this way.
|
|
|
|
*
|
|
|
|
* The inactive_list, handle_list and hash bucket lists are all protected by the
|
|
|
|
* device_lock.
|
|
|
|
* - stripes have a reference counter. If count==0, they are on a list.
|
|
|
|
* - If a stripe might need handling, STRIPE_HANDLE is set.
|
|
|
|
* - When refcount reaches zero, then if STRIPE_HANDLE it is put on
|
|
|
|
* handle_list else inactive_list
|
|
|
|
*
|
|
|
|
* This, combined with the fact that STRIPE_HANDLE is only ever
|
|
|
|
* cleared while a stripe has a non-zero count means that if the
|
|
|
|
* refcount is 0 and STRIPE_HANDLE is set, then it is on the
|
|
|
|
* handle_list and if recount is 0 and STRIPE_HANDLE is not set, then
|
|
|
|
* the stripe is on inactive_list.
|
|
|
|
*
|
|
|
|
* The possible transitions are:
|
|
|
|
* activate an unhashed/inactive stripe (get_active_stripe())
|
|
|
|
* lockdev check-hash unlink-stripe cnt++ clean-stripe hash-stripe unlockdev
|
|
|
|
* activate a hashed, possibly active stripe (get_active_stripe())
|
|
|
|
* lockdev check-hash if(!cnt++)unlink-stripe unlockdev
|
|
|
|
* attach a request to an active stripe (add_stripe_bh())
|
|
|
|
* lockdev attach-buffer unlockdev
|
|
|
|
* handle a stripe (handle_stripe())
|
2011-07-26 03:34:20 +02:00
|
|
|
* setSTRIPE_ACTIVE, clrSTRIPE_HANDLE ...
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
* (lockdev check-buffers unlockdev) ..
|
|
|
|
* change-state ..
|
2011-07-26 03:34:20 +02:00
|
|
|
* record io/ops needed clearSTRIPE_ACTIVE schedule io/ops
|
2005-04-17 00:20:36 +02:00
|
|
|
* 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
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
* on a cached buffer, and plus one if the stripe is undergoing stripe
|
|
|
|
* operations.
|
|
|
|
*
|
2011-07-26 03:34:20 +02:00
|
|
|
* The stripe operations are:
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
* -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.
|
2005-04-17 00:20:36 +02:00
|
|
|
*/
|
|
|
|
|
2008-06-28 00:31:57 +02:00
|
|
|
/*
|
2011-07-26 03:34:20 +02:00
|
|
|
* Operations state - intermediate states that are visible outside of
|
|
|
|
* STRIPE_ACTIVE.
|
2008-06-28 00:31:57 +02:00
|
|
|
* 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,
|
2009-07-14 22:40:19 +02:00
|
|
|
check_state_run, /* xor parity check */
|
|
|
|
check_state_run_q, /* q-parity check */
|
|
|
|
check_state_run_pq, /* pq dual parity check */
|
2008-06-28 00:31:57 +02:00
|
|
|
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,
|
2008-06-28 00:32:06 +02:00
|
|
|
reconstruct_state_prexor_drain_run, /* prexor-write */
|
2008-06-28 00:31:57 +02:00
|
|
|
reconstruct_state_drain_run, /* write */
|
|
|
|
reconstruct_state_run, /* expand */
|
2008-06-28 00:32:06 +02:00
|
|
|
reconstruct_state_prexor_drain_result,
|
2008-06-28 00:31:57 +02:00
|
|
|
reconstruct_state_drain_result,
|
|
|
|
reconstruct_state_result,
|
|
|
|
};
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
struct stripe_head {
|
2006-01-06 09:20:33 +01:00
|
|
|
struct hlist_node hash;
|
2009-03-31 05:39:38 +02:00
|
|
|
struct list_head lru; /* inactive_list or handle_list */
|
|
|
|
struct raid5_private_data *raid_conf;
|
2009-03-31 06:19:03 +02:00
|
|
|
short generation; /* increments with every
|
|
|
|
* reshape */
|
2009-03-31 05:39:38 +02:00
|
|
|
sector_t sector; /* sector of this row */
|
|
|
|
short pd_idx; /* parity disk index */
|
|
|
|
short qd_idx; /* 'Q' disk index for raid6 */
|
2009-03-31 05:39:38 +02:00
|
|
|
short ddf_layout;/* use DDF ordering to calculate Q */
|
2009-03-31 05:39:38 +02:00
|
|
|
unsigned long state; /* state flags */
|
|
|
|
atomic_t count; /* nr of active thread/requests */
|
2005-09-10 01:23:54 +02:00
|
|
|
int bm_seq; /* sequence number for bitmap flushes */
|
2009-03-31 05:39:38 +02:00
|
|
|
int disks; /* disks in stripe */
|
2008-06-28 00:31:57 +02:00
|
|
|
enum check_states check_state;
|
md: replace STRIPE_OP_{BIODRAIN,PREXOR,POSTXOR} with 'reconstruct_states'
From: Dan Williams <dan.j.williams@intel.com>
Track the state of reconstruct operations (recalculating the parity block
usually due to incoming writes, or as part of array expansion) Reduces the
scope of the STRIPE_OP_{BIODRAIN,PREXOR,POSTXOR} flags to only tracking whether
a reconstruct operation has been requested via the ops_request field of struct
stripe_head_state.
This is the final step in the removal of ops.{pending,ack,complete,count}, i.e.
the STRIPE_OP_{BIODRAIN,PREXOR,POSTXOR} flags only request an operation and do
not track the state of the operation.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Neil Brown <neilb@suse.de>
2008-06-28 00:32:05 +02:00
|
|
|
enum reconstruct_states reconstruct_state;
|
2009-10-16 07:25:22 +02:00
|
|
|
/**
|
|
|
|
* struct stripe_operations
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
* @target - STRIPE_OP_COMPUTE_BLK target
|
2009-10-16 07:25:22 +02:00
|
|
|
* @target2 - 2nd compute target in the raid6 case
|
|
|
|
* @zero_sum_result - P and Q verification flags
|
|
|
|
* @request - async service request flags for raid_run_ops
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
*/
|
|
|
|
struct stripe_operations {
|
2009-07-14 22:40:19 +02:00
|
|
|
int target, target2;
|
2009-08-30 04:09:26 +02:00
|
|
|
enum sum_check_flags zero_sum_result;
|
2009-10-16 07:25:22 +02:00
|
|
|
#ifdef CONFIG_MULTICORE_RAID456
|
|
|
|
unsigned long request;
|
|
|
|
wait_queue_head_t wait_for_ops;
|
|
|
|
#endif
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
} ops;
|
2005-04-17 00:20:36 +02:00
|
|
|
struct r5dev {
|
|
|
|
struct bio req;
|
|
|
|
struct bio_vec vec;
|
|
|
|
struct page *page;
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
struct bio *toread, *read, *towrite, *written;
|
2005-04-17 00:20:36 +02:00
|
|
|
sector_t sector; /* sector of this page */
|
|
|
|
unsigned long flags;
|
|
|
|
} dev[1]; /* allocated with extra space depending of RAID geometry */
|
|
|
|
};
|
2007-07-09 20:56:43 +02:00
|
|
|
|
|
|
|
/* stripe_head_state - collects and tracks the dynamic state of a stripe_head
|
2011-07-26 03:34:20 +02:00
|
|
|
* for handle_stripe.
|
2007-07-09 20:56:43 +02:00
|
|
|
*/
|
|
|
|
struct stripe_head_state {
|
|
|
|
int syncing, expanding, expanded;
|
|
|
|
int locked, uptodate, to_read, to_write, failed, written;
|
2007-01-02 21:52:31 +01:00
|
|
|
int to_fill, compute, req_compute, non_overwrite;
|
2011-07-26 03:35:19 +02:00
|
|
|
int failed_num[2];
|
|
|
|
int p_failed, q_failed;
|
2011-07-26 03:35:20 +02:00
|
|
|
int dec_preread_active;
|
|
|
|
unsigned long ops_request;
|
|
|
|
|
|
|
|
struct bio *return_bi;
|
|
|
|
mdk_rdev_t *blocked_rdev;
|
2011-07-28 03:39:22 +02:00
|
|
|
int handle_bad_blocks;
|
2007-07-09 20:56:43 +02:00
|
|
|
};
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/* Flags */
|
|
|
|
#define R5_UPTODATE 0 /* page contains current data */
|
|
|
|
#define R5_LOCKED 1 /* IO has been submitted on "req" */
|
|
|
|
#define R5_OVERWRITE 2 /* towrite covers whole page */
|
|
|
|
/* and some that are internal to handle_stripe */
|
|
|
|
#define R5_Insync 3 /* rdev && rdev->in_sync at start */
|
|
|
|
#define R5_Wantread 4 /* want to schedule a read */
|
|
|
|
#define R5_Wantwrite 5
|
|
|
|
#define R5_Overlap 7 /* There is a pending overlapping request on this block */
|
2005-11-09 06:39:22 +01:00
|
|
|
#define R5_ReadError 8 /* seen a read error here recently */
|
|
|
|
#define R5_ReWrite 9 /* have tried to over-write the readerror */
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2006-03-27 11:18:09 +02:00
|
|
|
#define R5_Expanded 10 /* This block now has post-expand data */
|
2011-07-28 03:39:22 +02:00
|
|
|
#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_Wantdrain 13 /* dev->towrite needs to be drained */
|
|
|
|
#define R5_WantFUA 14 /* Write should be FUA */
|
|
|
|
#define R5_WriteError 15 /* got a write error - need to record it */
|
2011-07-28 03:39:23 +02:00
|
|
|
#define R5_MadeGood 16 /* A bad block has been fixed by writing to it*/
|
2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* Write method
|
|
|
|
*/
|
|
|
|
#define RECONSTRUCT_WRITE 1
|
|
|
|
#define READ_MODIFY_WRITE 2
|
|
|
|
/* not a write method, but a compute_parity mode */
|
|
|
|
#define CHECK_PARITY 3
|
2009-03-31 06:09:39 +02:00
|
|
|
/* Additional compute_parity mode -- updates the parity w/o LOCKING */
|
|
|
|
#define UPDATE_PARITY 4
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Stripe state
|
|
|
|
*/
|
2011-07-26 03:19:49 +02:00
|
|
|
enum {
|
2011-07-26 03:34:20 +02:00
|
|
|
STRIPE_ACTIVE,
|
2011-07-26 03:19:49 +02:00
|
|
|
STRIPE_HANDLE,
|
|
|
|
STRIPE_SYNC_REQUESTED,
|
|
|
|
STRIPE_SYNCING,
|
|
|
|
STRIPE_INSYNC,
|
|
|
|
STRIPE_PREREAD_ACTIVE,
|
|
|
|
STRIPE_DELAYED,
|
|
|
|
STRIPE_DEGRADED,
|
|
|
|
STRIPE_BIT_DELAY,
|
|
|
|
STRIPE_EXPANDING,
|
|
|
|
STRIPE_EXPAND_SOURCE,
|
|
|
|
STRIPE_EXPAND_READY,
|
|
|
|
STRIPE_IO_STARTED, /* do not count towards 'bypass_count' */
|
|
|
|
STRIPE_FULL_WRITE, /* all blocks are set to be overwritten */
|
|
|
|
STRIPE_BIOFILL_RUN,
|
|
|
|
STRIPE_COMPUTE_RUN,
|
|
|
|
STRIPE_OPS_REQ_PENDING,
|
|
|
|
};
|
2009-10-16 07:25:22 +02:00
|
|
|
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
/*
|
2008-06-28 00:31:57 +02:00
|
|
|
* Operation request flags
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
*/
|
|
|
|
#define STRIPE_OP_BIOFILL 0
|
|
|
|
#define STRIPE_OP_COMPUTE_BLK 1
|
|
|
|
#define STRIPE_OP_PREXOR 2
|
|
|
|
#define STRIPE_OP_BIODRAIN 3
|
2009-07-14 22:40:19 +02:00
|
|
|
#define STRIPE_OP_RECONSTRUCT 4
|
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>
2007-01-02 21:52:30 +01:00
|
|
|
#define STRIPE_OP_CHECK 5
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* Plugging:
|
|
|
|
*
|
|
|
|
* To improve write throughput, we need to delay the handling of some
|
|
|
|
* stripes until there has been a chance that several write requests
|
|
|
|
* for the one stripe have all been collected.
|
|
|
|
* In particular, any write request that would require pre-reading
|
|
|
|
* is put on a "delayed" queue until there are no stripes currently
|
|
|
|
* in a pre-read phase. Further, if the "delayed" queue is empty when
|
|
|
|
* a stripe is put on it then we "plug" the queue and do not process it
|
|
|
|
* until an unplug call is made. (the unplug_io_fn() is called).
|
|
|
|
*
|
|
|
|
* When preread is initiated on a stripe, we set PREREAD_ACTIVE and add
|
|
|
|
* it to the count of prereading stripes.
|
|
|
|
* When write is initiated, or the stripe refcnt == 0 (just in case) we
|
|
|
|
* clear the PREREAD_ACTIVE flag and decrement the count
|
2006-10-03 10:15:45 +02:00
|
|
|
* Whenever the 'handle' queue is empty and the device is not plugged, we
|
|
|
|
* move any strips from delayed to handle and clear the DELAYED flag and set
|
|
|
|
* PREREAD_ACTIVE.
|
2005-04-17 00:20:36 +02:00
|
|
|
* In stripe_handle, if we find pre-reading is necessary, we do it if
|
|
|
|
* PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue.
|
2011-07-26 03:34:20 +02:00
|
|
|
* HANDLE gets cleared if stripe_handle leaves nothing locked.
|
2005-04-17 00:20:36 +02:00
|
|
|
*/
|
2009-03-31 05:27:03 +02:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
struct disk_info {
|
|
|
|
mdk_rdev_t *rdev;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct raid5_private_data {
|
2006-01-06 09:20:33 +01:00
|
|
|
struct hlist_head *stripe_hashtbl;
|
2005-04-17 00:20:36 +02:00
|
|
|
mddev_t *mddev;
|
|
|
|
struct disk_info *spare;
|
2009-06-18 00:45:55 +02:00
|
|
|
int chunk_sectors;
|
|
|
|
int level, algorithm;
|
2006-06-26 09:27:38 +02:00
|
|
|
int max_degraded;
|
2006-10-03 10:15:47 +02:00
|
|
|
int raid_disks;
|
2005-04-17 00:20:36 +02:00
|
|
|
int max_nr_stripes;
|
|
|
|
|
2009-03-31 06:16:46 +02:00
|
|
|
/* reshape_progress is the leading edge of a 'reshape'
|
|
|
|
* It has value MaxSector when no reshape is happening
|
|
|
|
* If delta_disks < 0, it is the last sector we started work on,
|
|
|
|
* else is it the next sector to work on.
|
|
|
|
*/
|
|
|
|
sector_t reshape_progress;
|
|
|
|
/* reshape_safe is the trailing edge of a reshape. We know that
|
|
|
|
* before (or after) this address, all reshape has completed.
|
|
|
|
*/
|
|
|
|
sector_t reshape_safe;
|
2006-03-27 11:18:08 +02:00
|
|
|
int previous_raid_disks;
|
2009-06-18 00:45:55 +02:00
|
|
|
int prev_chunk_sectors;
|
|
|
|
int prev_algo;
|
2009-03-31 06:19:03 +02:00
|
|
|
short generation; /* increments with every reshape */
|
2009-03-31 06:28:40 +02:00
|
|
|
unsigned long reshape_checkpoint; /* Time we last updated
|
|
|
|
* metadata */
|
2006-03-27 11:18:08 +02:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
struct list_head handle_list; /* stripes needing handling */
|
2008-04-28 11:15:53 +02:00
|
|
|
struct list_head hold_list; /* preread ready stripes */
|
2005-04-17 00:20:36 +02:00
|
|
|
struct list_head delayed_list; /* stripes that have plugged requests */
|
2005-09-10 01:23:54 +02:00
|
|
|
struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */
|
2006-12-10 11:20:47 +01:00
|
|
|
struct bio *retry_read_aligned; /* currently retrying aligned bios */
|
|
|
|
struct bio *retry_read_aligned_list; /* aligned bios retry list */
|
2005-04-17 00:20:36 +02:00
|
|
|
atomic_t preread_active_stripes; /* stripes with scheduled io */
|
2006-12-10 11:20:47 +01:00
|
|
|
atomic_t active_aligned_reads;
|
2008-04-28 11:15:53 +02:00
|
|
|
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 */
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2006-03-27 11:18:11 +02:00
|
|
|
atomic_t reshape_stripes; /* stripes with pending writes for reshape */
|
2006-03-27 11:18:07 +02:00
|
|
|
/* unfortunately we need two cache names as we temporarily have
|
|
|
|
* two caches.
|
|
|
|
*/
|
|
|
|
int active_name;
|
2010-06-01 11:37:25 +02:00
|
|
|
char cache_name[2][32];
|
2006-12-07 05:33:20 +01:00
|
|
|
struct kmem_cache *slab_cache; /* for allocating stripes */
|
2005-09-10 01:23:54 +02:00
|
|
|
|
|
|
|
int seq_flush, seq_write;
|
|
|
|
int quiesce;
|
|
|
|
|
|
|
|
int fullsync; /* set to 1 if a full sync is needed,
|
|
|
|
* (fresh device added).
|
|
|
|
* Cleared when a sync completes.
|
|
|
|
*/
|
2011-07-28 03:39:22 +02:00
|
|
|
int recovery_disabled;
|
2009-07-14 20:48:22 +02:00
|
|
|
/* per cpu variables */
|
|
|
|
struct raid5_percpu {
|
|
|
|
struct page *spare_page; /* Used when checking P/Q in raid6 */
|
2009-07-14 20:50:52 +02:00
|
|
|
void *scribble; /* space for constructing buffer
|
|
|
|
* lists and performing address
|
|
|
|
* conversions
|
|
|
|
*/
|
2010-02-02 06:39:15 +01:00
|
|
|
} __percpu *percpu;
|
2009-07-14 20:50:52 +02:00
|
|
|
size_t scribble_len; /* size of scribble region must be
|
|
|
|
* associated with conf to handle
|
|
|
|
* cpu hotplug while reshaping
|
|
|
|
*/
|
2009-07-14 20:48:22 +02:00
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
struct notifier_block cpu_notify;
|
|
|
|
#endif
|
2006-01-06 09:20:17 +01:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* Free stripes pool
|
|
|
|
*/
|
|
|
|
atomic_t active_stripes;
|
|
|
|
struct list_head inactive_list;
|
|
|
|
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
|
2006-03-27 11:18:07 +02:00
|
|
|
*/
|
|
|
|
int pool_size; /* number of disks in stripeheads in pool */
|
2005-04-17 00:20:36 +02:00
|
|
|
spinlock_t device_lock;
|
2006-03-27 11:18:06 +02:00
|
|
|
struct disk_info *disks;
|
2009-03-31 05:39:39 +02:00
|
|
|
|
|
|
|
/* When taking over an array from a different personality, we store
|
|
|
|
* the new thread here until we fully activate the array.
|
|
|
|
*/
|
|
|
|
struct mdk_thread_s *thread;
|
2005-04-17 00:20:36 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
typedef struct raid5_private_data raid5_conf_t;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Our supported algorithms
|
|
|
|
*/
|
2009-03-31 05:39:38 +02:00
|
|
|
#define ALGORITHM_LEFT_ASYMMETRIC 0 /* Rotating Parity N with Data Restart */
|
|
|
|
#define ALGORITHM_RIGHT_ASYMMETRIC 1 /* Rotating Parity 0 with Data Restart */
|
|
|
|
#define ALGORITHM_LEFT_SYMMETRIC 2 /* Rotating Parity N with Data Continuation */
|
|
|
|
#define ALGORITHM_RIGHT_SYMMETRIC 3 /* Rotating Parity 0 with Data Continuation */
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2009-03-31 05:39:38 +02:00
|
|
|
/* Define non-rotating (raid4) algorithms. These allow
|
|
|
|
* conversion of raid4 to raid5.
|
|
|
|
*/
|
|
|
|
#define ALGORITHM_PARITY_0 4 /* P or P,Q are initial devices */
|
|
|
|
#define ALGORITHM_PARITY_N 5 /* P or P,Q are final devices. */
|
|
|
|
|
|
|
|
/* DDF RAID6 layouts differ from md/raid6 layouts in two ways.
|
|
|
|
* Firstly, the exact positioning of the parity block is slightly
|
|
|
|
* different between the 'LEFT_*' modes of md and the "_N_*" modes
|
|
|
|
* of DDF.
|
|
|
|
* Secondly, or order of datablocks over which the Q syndrome is computed
|
|
|
|
* is different.
|
|
|
|
* Consequently we have different layouts for DDF/raid6 than md/raid6.
|
|
|
|
* These layouts are from the DDFv1.2 spec.
|
|
|
|
* Interestingly DDFv1.2-Errata-A does not specify N_CONTINUE but
|
|
|
|
* leaves RLQ=3 as 'Vendor Specific'
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define ALGORITHM_ROTATING_ZERO_RESTART 8 /* DDF PRL=6 RLQ=1 */
|
|
|
|
#define ALGORITHM_ROTATING_N_RESTART 9 /* DDF PRL=6 RLQ=2 */
|
|
|
|
#define ALGORITHM_ROTATING_N_CONTINUE 10 /*DDF PRL=6 RLQ=3 */
|
|
|
|
|
|
|
|
|
|
|
|
/* For every RAID5 algorithm we define a RAID6 algorithm
|
|
|
|
* with exactly the same layout for data and parity, and
|
|
|
|
* with the Q block always on the last device (N-1).
|
|
|
|
* This allows trivial conversion from RAID5 to RAID6
|
|
|
|
*/
|
|
|
|
#define ALGORITHM_LEFT_ASYMMETRIC_6 16
|
|
|
|
#define ALGORITHM_RIGHT_ASYMMETRIC_6 17
|
|
|
|
#define ALGORITHM_LEFT_SYMMETRIC_6 18
|
|
|
|
#define ALGORITHM_RIGHT_SYMMETRIC_6 19
|
|
|
|
#define ALGORITHM_PARITY_0_6 20
|
|
|
|
#define ALGORITHM_PARITY_N_6 ALGORITHM_PARITY_N
|
|
|
|
|
|
|
|
static inline int algorithm_valid_raid5(int layout)
|
|
|
|
{
|
|
|
|
return (layout >= 0) &&
|
|
|
|
(layout <= 5);
|
|
|
|
}
|
|
|
|
static inline int algorithm_valid_raid6(int layout)
|
|
|
|
{
|
|
|
|
return (layout >= 0 && layout <= 5)
|
|
|
|
||
|
2009-10-16 07:27:34 +02:00
|
|
|
(layout >= 8 && layout <= 10)
|
2009-03-31 05:39:38 +02:00
|
|
|
||
|
|
|
|
(layout >= 16 && layout <= 20);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int algorithm_is_DDF(int layout)
|
|
|
|
{
|
|
|
|
return layout >= 8 && layout <= 10;
|
|
|
|
}
|
2010-07-26 03:57:07 +02:00
|
|
|
|
|
|
|
extern int md_raid5_congested(mddev_t *mddev, int bits);
|
2011-03-10 08:52:07 +01:00
|
|
|
extern void md_raid5_kick_device(raid5_conf_t *conf);
|
2010-06-01 11:37:24 +02:00
|
|
|
extern int raid5_set_cache_size(mddev_t *mddev, int size);
|
2005-04-17 00:20:36 +02:00
|
|
|
#endif
|