aboutsummaryrefslogtreecommitdiff
path: root/include/linux/raid
AgeCommit message (Collapse)Author
2008-07-23md: delay notification of 'active_idle' to the recovery threadDan Williams
sysfs_notify might sleep, so do not call it from md_safemode_timeout. Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2008-07-21md: Protect access to mddev->disks list using RCUNeilBrown
All modifications and most access to the mddev->disks list are made under the reconfig_mutex lock. However there are three places where the list is walked without any locking. If a reconfig happens at this time, havoc (and oops) can ensue. So use RCU to protect these accesses: - wrap them in rcu_read_{,un}lock() - use list_for_each_entry_rcu - add to the list with list_add_rcu - delete from the list with list_del_rcu - delay the 'free' with call_rcu rather than schedule_work Note that export_rdev did a list_del_init on this list. In almost all cases the entry was not in the list anymore so it was a no-op and so safe. It is no longer safe as after list_del_rcu we may not touch the list_head. An audit shows that export_rdev is called: - after unbind_rdev_from_array, in which case the delete has already been done, - after bind_rdev_to_array fails, in which case the delete isn't needed. - before the device has been put on a list at all (e.g. in add_new_disk where reading the superblock fails). - and in autorun devices after a failure when the device is on a different list. So remove the list_del_init call from export_rdev, and add it back immediately before the called to export_rdev for that last case. Note also that ->same_set is sometimes used for lists other than mddev->list (e.g. candidates). In these cases rcu is not needed. Signed-off-by: NeilBrown <neilb@suse.de>
2008-07-21md: only count actual openers as access which prevent a 'stop'NeilBrown
Open isn't the only thing that increments ->active. e.g. reading /proc/mdstat will increment it briefly. So to avoid false positives in testing for concurrent access, introduce a new counter that counts just the number of times the md device it open. Signed-off-by: NeilBrown <neilb@suse.de>
2008-07-21md: linear: Make array_size sector-based and rename it to array_sectors.Andre Noll
Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2008-07-21md: Make mddev->array_size sector-based.Andre Noll
This patch renames the array_size field of struct mddev_s to array_sectors and converts all instances to use units of 512 byte sectors instead of 1k blocks. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2008-07-11md: Remove some unused macros.Andre Noll
Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: Neil Brown <neilb@suse.de>
2008-07-11md: Turn rdev->sb_offset into a sector-based quantity.Andre Noll
Rename it to sb_start to make sure all users have been converted. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: Neil Brown <neilb@suse.de>
2008-06-30md: resolve external metadata handling deadlock in md_allow_writeDan Williams
md_allow_write() marks the metadata dirty while holding mddev->lock and then waits for the write to complete. For externally managed metadata this causes a deadlock as userspace needs to take the lock to communicate that the metadata update has completed. Change md_allow_write() in the 'external' case to start the 'mark active' operation and then return -EAGAIN. The expected side effects while waiting for userspace to write 'active' to 'array_state' are holding off reshape (code currently handles -ENOMEM), cause some 'stripe_cache_size' change requests to fail, cause some GET_BITMAP_FILE ioctl requests to fall back to GFP_NOIO, and cause updates to 'raid_disks' to fail. Except for 'stripe_cache_size' changes these failures can be mitigated by coordinating with mdmon. md_write_start() still prevents writes from occurring until the metadata handler has had a chance to take action as it unconditionally waits for MD_CHANGE_CLEAN to be cleared. [neilb@suse.de: return -EAGAIN, try GFP_NOIO] Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2008-06-28md: replace R5_WantPrexor with R5_WantDrain, add 'prexor' reconstruct_statesDan Williams
From: Dan Williams <dan.j.williams@intel.com> Currently ops_run_biodrain and other locations have extra logic to determine which blocks are processed in the prexor and non-prexor cases. This can be eliminated if handle_write_operations5 flags the blocks to be processed in all cases via R5_Wantdrain. The presence of the prexor operation is tracked in sh->reconstruct_state. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Neil Brown <neilb@suse.de>
2008-06-28md: replace STRIPE_OP_{BIODRAIN,PREXOR,POSTXOR} with 'reconstruct_states'Dan Williams
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>
2008-06-28md: replace STRIPE_OP_CHECK with 'check_states'Dan Williams
From: Dan Williams <dan.j.williams@intel.com> The STRIPE_OP_* flags record the state of stripe operations which are performed outside the stripe lock. Their use in indicating which operations need to be run is straightforward; however, interpolating what the next state of the stripe should be based on a given combination of these flags is not straightforward, and has led to bugs. An easier to read implementation with minimal degrees of freedom is needed. Towards this goal, this patch introduces explicit states to replace what was previously interpolated from the STRIPE_OP_* flags. For now this only converts the handle_parity_checks5 path, removing a user of the ops.{pending,ack,complete,count} fields of struct stripe_operations. This conversion also found a remaining issue with the current code. There is a small window for a drive to fail between when we schedule a repair and when the parity calculation for that repair completes. When this happens we will writeback to 'failed_num' when we really want to write back to 'pd_idx'. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Neil Brown <neilb@suse.de>
2008-06-28md: kill STRIPE_OP_IO flagDan Williams
From: Dan Williams <dan.j.williams@intel.com> The R5_Want{Read,Write} flags already gate i/o. So, this flag is superfluous and we can unconditionally call ops_run_io(). Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Neil Brown <neilb@suse.de>
2008-06-28md: kill STRIPE_OP_MOD_DMA in raid5 offloadDan Williams
From: Dan Williams <dan.j.williams@intel.com> This micro-optimization allowed the raid code to skip a re-read of the parity block after checking parity. It took advantage of the fact that xor-offload-engines have their own internal result buffer and can check parity without writing to memory. Remove it for the following reasons: 1/ It is a layering violation for MD to need to manage the DMA and non-DMA paths within async_xor_zero_sum 2/ Bad precedent to toggle the 'ops' flags outside the lock 3/ Hard to realize a performance gain as reads will not need an updated parity block and writes will dirty it anyways. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Neil Brown <neilb@suse.de>
2008-06-28Make sure all changes to md/dev-XX/state are notifiedNeil Brown
The important state change happens during an interrupt in md_error. So just set a flag there and call sysfs_notify later in process context. Signed-off-by: Neil Brown <neilb@suse.de>
2008-06-28Make sure all changes to md/sync_action are notified.Neil Brown
When the 'resync' thread starts or stops, when we explicitly set sync_action, or when we determine that there is definitely nothing to do, we notify sync_action. To stop "sync_action" from occasionally showing the wrong value, we introduce a new flags - MD_RECOVERY_RECOVER - to say that a recovery is probably needed or happening, and we make sure that we set MD_RECOVERY_RUNNING before clearing MD_RECOVERY_NEEDED. Signed-off-by: Neil Brown <neilb@suse.de>
2008-06-28Allow setting start point for requested check/repairNeil Brown
This makes it possible to just resync a small part of an array. e.g. if a drive reports that it has questionable sectors, a 'repair' of just the region covering those sectors will cause them to be read and, if there is an error, re-written with correct data. Signed-off-by: Neil Brown <neilb@suse.de>
2008-06-28Improve setting of "events_cleared" for write-intent bitmaps.Neil Brown
When an array is degraded, bits in the write-intent bitmap are not cleared, so that if the missing device is re-added, it can be synced by only updated those parts of the device that have changed since it was removed. The enable this a 'events_cleared' value is stored. It is the event counter for the array the last time that any bits were cleared. Sometimes - if a device disappears from an array while it is 'clean' - the events_cleared value gets updated incorrectly (there are subtle ordering issues between updateing events in the main metadata and the bitmap metadata) resulting in the missing device appearing to require a full resync when it is re-added. With this patch, we update events_cleared precisely when we are about to clear a bit in the bitmap. We record events_cleared when we clear the bit internally, and copy that to the superblock which is written out before the bit on storage. This makes it more "obviously correct". We also need to update events_cleared when the event_count is going backwards (as happens on a dirty->clean transition of a non-degraded array). Thanks to Mike Snitzer for identifying this problem and testing early "fixes". Cc: "Mike Snitzer" <snitzer@gmail.com> Signed-off-by: Neil Brown <neilb@suse.de>
2008-05-24md: restart recovery cleanly after device failure.NeilBrown
When we get any IO error during a recovery (rebuilding a spare), we abort the recovery and restart it. For RAID6 (and multi-drive RAID1) it may not be best to restart at the beginning: when multiple failures can be tolerated, the recovery may be able to continue and re-doing all that has already been done doesn't make sense. We already have the infrastructure to record where a recovery is up to and restart from there, but it is not being used properly. This is because: - We sometimes abort with MD_RECOVERY_ERR rather than just MD_RECOVERY_INTR, which causes the recovery not be be checkpointed. - We remove spares and then re-added them which loses important state information. The distinction between MD_RECOVERY_ERR and MD_RECOVERY_INTR really isn't needed. If there is an error, the relevant drive will be marked as Faulty, and that is enough to ensure correct handling of the error. So we first remove MD_RECOVERY_ERR, changing some of the uses of it to MD_RECOVERY_INTR. Then we cause the attempt to remove a non-faulty device from an array to fail (unless recovery is impossible as the array is too degraded). Then when remove_and_add_spares attempts to remove the devices on which recovery can continue, it will fail, they will remain in place, and recovery will continue on them as desired. Issue: If we are halfway through rebuilding a spare and another drive fails, and a new spare is immediately available, do we want to: 1/ complete the current rebuild, then go back and rebuild the new spare or 2/ restart the rebuild from the start and rebuild both devices in parallel. Both options can be argued for. The code currently takes option 2 as a/ this requires least code change b/ this results in a minimally-degraded array in minimal time. Cc: "Eivind Sarto" <ivan@kasenna.com> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-24md: allow parallel resync of md-devices.Bernd Schubert
In some configurations, a raid6 resync can be limited by CPU speed (Calculating P and Q and moving data) rather than by device speed. In these cases there is nothing to be gained byt serialising resync of arrays that share a device, and doing the resync in parallel can provide benefit. So add a sysfs tunable to flag an array as being allowed to resync in parallel with other arrays that use (a different part of) the same device. Signed-off-by: Bernd Schubert <bs@q-leap.de> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-24md: kill file_path wrapperChristoph Hellwig
Kill the trivial and rather pointless file_path wrapper around d_path. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-24md: proper extern for mdp_majorAdrian Bunk
This patch adds a proper extern for mdp_major in include/linux/raid/md.h Signed-off-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-30md: support blocking writes to an array on device failureDan Williams
Allows a userspace metadata handler to take action upon detecting a device failure. Based on an original patch by Neil Brown. Changes: -added blocked_wait waitqueue to rdev -don't qualify Blocked with Faulty always let userspace block writes -added md_wait_for_blocked_rdev to wait for the block device to be clear, if userspace misses the notification another one is sent every 5 seconds -set MD_RECOVERY_NEEDED after clearing "blocked" -kill DoBlock flag, just test mddev->external Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28md: introduce get_priority_stripe() to improve raid456 write performanceDan Williams
Improve write performance by preventing the delayed_list from dumping all its stripes onto the handle_list in one shot. Delayed stripes are now further delayed by being held on the 'hold_list'. The 'hold_list' is bypassed when: * a STRIPE_IO_STARTED stripe is found at the head of 'handle_list' * 'handle_list' is empty and i/o is being done to satisfy full stripe-width write requests * 'bypass_count' is less than 'bypass_threshold'. By default the threshold is 1, i.e. every other stripe handled is a preread stripe provided the top two conditions are false. Benchmark data: System: 2x Xeon 5150, 4x SATA, mem=1GB Baseline: 2.6.24-rc7 Configuration: mdadm --create /dev/md0 /dev/sd[b-e] -n 4 -l 5 --assume-clean Test1: dd if=/dev/zero of=/dev/md0 bs=1024k count=2048 * patched: +33% (stripe_cache_size = 256), +25% (stripe_cache_size = 512) Test2: tiobench --size 2048 --numruns 5 --block 4096 --block 131072 (XFS) * patched: +13% * patched + preread_bypass_threshold = 0: +37% Changes since v1: * reduce bypass_threshold from (chunk_size / sectors_per_chunk) to (1) and make it configurable. This defaults to fairness and modest performance gains out of the box. Changes since v2: * [neilb@suse.de]: kill STRIPE_PRIO_HI and preread_needed as they are not necessary, the important change was clearing STRIPE_DELAYED in add_stripe_bio and this has been moved out to make_request for the hang fix. * [neilb@suse.de]: simplify get_priority_stripe * [dan.j.williams@intel.com]: reset the bypass_count when ->hold_list is sampled empty (+11%) * [dan.j.williams@intel.com]: decrement the bypass_count at the detection of stripes being naturally promoted off of hold_list +2%. Note, resetting bypass_count instead of decrementing on these events yields +4% but that is probably too aggressive. Changes since v3: * cosmetic fixups Tested-by: James W. Laferriere <babydr@baby-dragons.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-18include: Remove unnecessary inclusions of asm/semaphore.hMatthew Wilcox
None of these files use any of the functionality promised by asm/semaphore.h. It's possible that they (or some user of them) rely on it dragging in some unrelated header file, but I can't build all these files, so we'll have to fix any build failures as they come up. Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
2008-03-04md: clean up irregularity with raid autodetectNeilBrown
When a raid1 array is stopped, all components currently get added to the list for auto-detection. However we should really only add components that were found by autodetection in the first place. So add a flag to record that information, and use it. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-03-04md: reduce CPU wastage on idle md array with a write-intent bitmapNeilBrown
On an md array with a write-intent bitmap, a thread wakes up every few seconds and scans the bitmap looking for work to do. If the array is idle, there will be no work to do, but a lot of scanning is done to discover this. So cache the fact that the bitmap is completely clean, and avoid scanning the whole bitmap when the cache is known to be clean. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-06md: change ITERATE_RDEV_GENERIC to rdev_for_each_list, and remove ↵NeilBrown
ITERATE_RDEV_PENDING. Finish ITERATE_ to for_each conversion. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-06md: change ITERATE_RDEV to rdev_for_eachNeilBrown
As this is more in line with common practice in the kernel. Also swap the args around to be more like list_for_each. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-06md: allow devices to be shared between md arraysNeilBrown
Currently, a given device is "claimed" by a particular array so that it cannot be used by other arrays. This is not ideal for DDF and other metadata schemes which have their own partitioning concept. So for externally managed metadata, just claim the device for md in general, require that "offset" and "size" are set properly for each device, and make sure that if a device is included in different arrays then the active sections do not overlap. This involves adding another flag to the rdev which makes it awkward to set "->flags = 0" to clear certain flags. So now clear flags explicitly by name when we want to clear things. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-06md: allow a maximum extent to be set for resyncingNeilBrown
This allows userspace to control resync/reshape progress and synchronise it with other activities, such as shared access in a SAN, or backing up critical sections during a tricky reshape. Writing a number of sectors (which must be a multiple of the chunk size if such is meaningful) causes a resync to pause when it gets to that point. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-06md: support 'external' metadata for md arraysNeilBrown
- Add a state flag 'external' to indicate that the metadata is managed externally (by user-space) so important changes need to be left of user-space to handle. Alternates are non-persistant ('none') where there is no stable metadata - after the array is stopped there is no record of it's status - and internal which can be version 0.90 or version 1.x These are selected by writing to the 'metadata' attribute. - move the updating of superblocks (sync_sbs) to after we have checked if there are any superblocks or not. - New array state 'write_pending'. This means that the metadata records the array as 'clean', but a write has been requested, so the metadata has to be updated to record a 'dirty' array before the write can continue. This change is reported to md by writing 'active' to the array_state attribute. - tidy up marking of sb_dirty: - don't set sb_dirty when resync finishes as md_check_recovery calls md_update_sb when the sync thread finishes anyway. - Don't set sb_dirty in multipath_run as the array might not be dirty. - don't mark superblock dirty when switching to 'clean' if there is no internal superblock (if external, userspace can choose to update the superblock whenever it chooses to). Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-06md: Update md bitmap during resync.NeilBrown
Currently an md array with a write-intent bitmap does not updated that bitmap to reflect successful partial resync. Rather the entire bitmap is updated when the resync completes. This is because there is no guarentee that resync requests will complete in order, and tracking each request individually is unnecessarily burdensome. However there is value in regularly updating the bitmap, so add code to periodically pause while all pending sync requests complete, then update the bitmap. Doing this only every few seconds (the same as the bitmap update time) does not notciably affect resync performance. [snitzer@gmail.com: export bitmap_cond_end_sync] Signed-off-by: Neil Brown <neilb@suse.de> Cc: "Mike Snitzer" <snitzer@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17bitmap.h: remove dead artifactsAdrian Bunk
bitmap_active() no longer exists and BITMAP_ACTIVE is no longer used. Signed-off-by: Adrian Bunk <bunk@kernel.org> Cc: Neil Brown <neilb@suse.de> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-24[BLOCK] Get rid of request_queue_t typedefJens Axboe
Some of the code has been gradually transitioned to using the proper struct request_queue, but there's lots left. So do a full sweet of the kernel and get rid of this typedef and replace its uses with the proper type. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-07-17md: change bitmap_unplug and others to void functionsNeilBrown
bitmap_unplug only ever returns 0, so it may as well be void. Two callers try to print a message if it returns non-zero, but that message is already printed by bitmap_file_kick. write_page returns an error which is not consistently checked. It always causes BITMAP_WRITE_ERROR to be set on an error, and that can more conveniently be checked. When the return of write_page is checked, an error causes bitmap_file_kick to be called - so move that call into write_page - and protect against recursive calls into bitmap_file_kick. bitmap_update_sb returns an error that is never checked. So make these 'void' and be consistent about checking the bit. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17md: improve the is_mddev_idle test fixNeilBrown
Don't use 'unsigned' variable to track sync vs non-sync IO, as the only thing we want to do with them is a signed comparison, and fix up the comment which had become quite wrong. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-13md: handle_stripe5 - add request/completion logic for async read opsDan Williams
When a read bio is attached to the stripe and the corresponding block is marked R5_UPTODATE, then a read (biofill) operation is scheduled to copy the data from the stripe cache to the bio buffer. handle_stripe flags the blocks to be operated on with the R5_Wantfill flag. If new read requests arrive while raid5_run_ops is running they will not be handled until handle_stripe is scheduled to run again. Changelog: * cleanup to_read and to_fill accounting * do not fail reads that have reached the cache Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-By: NeilBrown <neilb@suse.de>
2007-07-13md: handle_stripe5 - add request/completion logic for async compute opsDan Williams
handle_stripe will compute a block when a backing disk has failed, or when it determines it can save a disk read by computing the block from all the other up-to-date blocks. Previously a block would be computed under the lock and subsequent logic in handle_stripe could use the newly up-to-date block. With the raid5_run_ops implementation the compute operation is carried out a later time outside the lock. To preserve the old functionality we take advantage of the dependency chain feature of async_tx to flag the block as R5_Wantcompute and then let other parts of handle_stripe operate on the block as if it were up-to-date. raid5_run_ops guarantees that the block will be ready before it is used in another operation. However, this only works in cases where the compute and the dependent operation are scheduled at the same time. If a previous call to handle_stripe sets the R5_Wantcompute flag there is no facility to pass the async_tx dependency chain across successive calls to raid5_run_ops. The req_compute variable protects against this case. Changelog: * remove the req_compute BUG_ON Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-By: NeilBrown <neilb@suse.de>
2007-07-13md: raid5_run_ops - run stripe operations outside sh->lockDan Williams
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>
2007-07-13raid5: refactor handle_stripe5 and handle_stripe6 (v3)Dan Williams
handle_stripe5 and handle_stripe6 have very deep logic paths handling the various states of a stripe_head. By introducing the 'stripe_head_state' and 'r6_state' objects, large portions of the logic can be moved to sub-routines. 'struct stripe_head_state' consumes all of the automatic variables that previously stood alone in handle_stripe5,6. 'struct r6_state' contains the handle_stripe6 specific variables like p_failed and q_failed. One of the nice side effects of the 'stripe_head_state' change is that it allows for further reductions in code duplication between raid5 and raid6. The following new routines are shared between raid5 and raid6: handle_completed_write_requests handle_requests_to_failed_array handle_stripe_expansion Changes: * v2: fixed 'conf->raid_disk-1' for the raid6 'handle_stripe_expansion' path * v3: removed the unused 'dirty' field from struct stripe_head_state * v3: coalesced open coded bi_end_io routines into return_io() Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-By: NeilBrown <neilb@suse.de>
2007-07-13async_tx: add the async_tx apiDan Williams
The async_tx api provides methods for describing a chain of asynchronous bulk memory transfers/transforms with support for inter-transactional dependencies. It is implemented as a dmaengine client that smooths over the details of different hardware offload engine implementations. Code that is written to the api can optimize for asynchronous operation and the api will fit the chain of operations to the available offload resources. I imagine that any piece of ADMA hardware would register with the 'async_*' subsystem, and a call to async_X would be routed as appropriate, or be run in-line. - Neil Brown async_tx exploits the capabilities of struct dma_async_tx_descriptor to provide an api of the following general format: struct dma_async_tx_descriptor * async_<operation>(..., struct dma_async_tx_descriptor *depend_tx, dma_async_tx_callback cb_fn, void *cb_param) { struct dma_chan *chan = async_tx_find_channel(depend_tx, <operation>); struct dma_device *device = chan ? chan->device : NULL; int int_en = cb_fn ? 1 : 0; struct dma_async_tx_descriptor *tx = device ? device->device_prep_dma_<operation>(chan, len, int_en) : NULL; if (tx) { /* run <operation> asynchronously */ ... tx->tx_set_dest(addr, tx, index); ... tx->tx_set_src(addr, tx, index); ... async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param); } else { /* run <operation> synchronously */ ... <operation> ... async_tx_sync_epilog(flags, depend_tx, cb_fn, cb_param); } return tx; } async_tx_find_channel() returns a capable channel from its pool. The channel pool is organized as a per-cpu array of channel pointers. The async_tx_rebalance() routine is tasked with managing these arrays. In the uniprocessor case async_tx_rebalance() tries to spread responsibility evenly over channels of similar capabilities. For example if there are two copy+xor channels, one will handle copy operations and the other will handle xor. In the SMP case async_tx_rebalance() attempts to spread the operations evenly over the cpus, e.g. cpu0 gets copy channel0 and xor channel0 while cpu1 gets copy channel 1 and xor channel 1. When a dependency is specified async_tx_find_channel defaults to keeping the operation on the same channel. A xor->copy->xor chain will stay on one channel if it supports both operation types, otherwise the transaction will transition between a copy and a xor resource. Currently the raid5 implementation in the MD raid456 driver has been converted to the async_tx api. A driver for the offload engines on the Intel Xscale series of I/O processors, iop-adma, is provided in a later commit. With the iop-adma driver and async_tx, raid456 is able to offload copy, xor, and xor-zero-sum operations to hardware engines. On iop342 tiobench showed higher throughput for sequential writes (20 - 30% improvement) and sequential reads to a degraded array (40 - 55% improvement). For the other cases performance was roughly equal, +/- a few percentage points. On a x86-smp platform the performance of the async_tx implementation (in synchronous mode) was also +/- a few percentage points of the original implementation. According to 'top' on iop342 CPU utilization drops from ~50% to ~15% during a 'resync' while the speed according to /proc/mdstat doubles from ~25 MB/s to ~50 MB/s. The tiobench command line used for testing was: tiobench --size 2048 --block 4096 --block 131072 --dir /mnt/raid --numruns 5 * iop342 had 1GB of memory available Details: * if CONFIG_DMA_ENGINE=n the asynchronous path is compiled away by making async_tx_find_channel a static inline routine that always returns NULL * when a callback is specified for a given transaction an interrupt will fire at operation completion time and the callback will occur in a tasklet. if the the channel does not support interrupts then a live polling wait will be performed * the api is written as a dmaengine client that requests all available channels * In support of dependencies the api implicitly schedules channel-switch interrupts. The interrupt triggers the cleanup tasklet which causes pending operations to be scheduled on the next channel * Xor engines treat an xor destination address differently than a software xor routine. To the software routine the destination address is an implied source, whereas engines treat it as a write-only destination. This patch modifies the xor_blocks routine to take a an explicit destination address to mirror the hardware. Changelog: * fixed a leftover debug print * don't allow callbacks in async_interrupt_cond * fixed xor_block changes * fixed usage of ASYNC_TX_XOR_DROP_DEST * drop dma mapping methods, suggested by Chris Leech * printk warning fixups from Andrew Morton * don't use inline in C files, Adrian Bunk * select the API when MD is enabled * BUG_ON xor source counts <= 1 * implicitly handle hardware concerns like channel switching and interrupts, Neil Brown * remove the per operation type list, and distribute operation capabilities evenly amongst the available channels * simplify async_tx_find_channel to optimize the fast path * introduce the channel_table_initialized flag to prevent early calls to the api * reorganize the code to mimic crypto * include mm.h as not all archs include it in dma-mapping.h * make the Kconfig options non-user visible, Adrian Bunk * move async_tx under crypto since it is meant as 'core' functionality, and the two may share algorithms in the future * move large inline functions into c files * checkpatch.pl fixes * gpl v2 only correction Cc: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-By: NeilBrown <neilb@suse.de>
2007-07-13xor: make 'xor_blocks' a library routine for use with async_txDan Williams
The async_tx api tries to use a dma engine for an operation, but will fall back to an optimized software routine otherwise. Xor support is implemented using the raid5 xor routines. For organizational purposes this routine is moved to a common area. The following fixes are also made: * rename xor_block => xor_blocks, suggested by Adrian Bunk * ensure that xor.o initializes before md.o in the built-in case * checkpatch.pl fixes * mark calibrate_xor_blocks __init, Adrian Bunk Cc: Adrian Bunk <bunk@stusta.de> Cc: NeilBrown <neilb@suse.de> Cc: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2007-05-23md: don't write more than is required of the last page of a bitmapNeilBrown
It is possible that real data or metadata follows the bitmap without full page alignment. So limit the last write to be only the required number of bytes, rounded up to the hard sector size of the device. Signed-off-by: Neil Brown <neilb@suse.de> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09Revert "md: improve partition detection in md array"Linus Torvalds
This reverts commit 5b479c91da90eef605f851508744bfe8269591a0. Quoth Neil Brown: "It causes an oops when auto-detecting raid arrays, and it doesn't seem easy to fix. The array may not be 'open' when do_md_run is called, so bdev->bd_disk might be NULL, so bd_set_size can oops. This whole approach of opening an md device before it has been assembled just seems to get more and more painful. I think I'm going to have to come up with something clever to provide both backward comparability with usage expectation, and sane integration into the rest of the kernel." Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09md: improve partition detection in md arrayNeilBrown
md currently uses ->media_changed to make sure rescan_partitions is call on md array after they are assembled. However that doesn't happen until the array is opened, which is later than some people would like. So use blkdev_ioctl to do the rescan immediately that the array has been assembled. This means we can remove all the ->change infrastructure as it was only used to trigger a partition rescan. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-04-04[PATCH] md: avoid a deadlock when removing a device from an md array via sysfsNeilBrown
A device can be removed from an md array via e.g. echo remove > /sys/block/md3/md/dev-sde/state This will try to remove the 'dev-sde' subtree which will deadlock since commit e7b0d26a86943370c04d6833c6edba2a72a6e240 With this patch we run the kobject_del via schedule_work so as to avoid the deadlock. Cc: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-09[PATCH] md: avoid possible BUG_ON in md bitmap handlingNeil Brown
md/bitmap tracks how many active write requests are pending on blocks associated with each bit in the bitmap, so that it knows when it can clear the bit (when count hits zero). The counter has 14 bits of space, so if there are ever more than 16383, we cannot cope. Currently the code just calles BUG_ON as "all" drivers have request queue limits much smaller than this. However is seems that some don't. Apparently some multipath configurations can allow more than 16383 concurrent write requests. So, in this unlikely situation, instead of calling BUG_ON we now wait for the count to drop down a bit. This requires a new wait_queue_head, some waiting code, and a wakeup call. Tested by limiting the counter to 20 instead of 16383 (writes go a lot slower in that case...). Signed-off-by: Neil Brown <neilb@suse.de> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-01-26[PATCH] md: fix potential memalloc deadlock in mdNeilBrown
If a GFP_KERNEL allocation is attempted in md while the mddev_lock is held, it is possible for a deadlock to eventuate. This happens if the array was marked 'clean', and the memalloc triggers a write-out to the md device. For the writeout to succeed, the array must be marked 'dirty', and that requires getting the mddev_lock. So, before attempting a GFP_KERNEL allocation while holding the lock, make sure the array is marked 'dirty' (unless it is currently read-only). Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2006-12-10[PATCH] md: allow reads that have bypassed the cache to be retried on failureRaz Ben-Jehuda(caro)
If a bypass-the-cache read fails, we simply try again through the cache. If it fails again it will trigger normal recovery precedures. update 1: From: NeilBrown <neilb@suse.de> 1/ chunk_aligned_read and retry_aligned_read assume that data_disks == raid_disks - 1 which is not true for raid6. So when an aligned read request bypasses the cache, we can get the wrong data. 2/ The cloned bio is being used-after-free in raid5_align_endio (to test BIO_UPTODATE). 3/ We forgot to add rdev->data_offset when submitting a bio for aligned-read 4/ clone_bio calls blk_recount_segments and then we change bi_bdev, so we need to invalidate the segment counts. 5/ We don't de-reference the rdev when the read completes. This means we need to record the rdev to so it is still available in the end_io routine. Fortunately bi_next in the original bio is unused at this point so we can stuff it in there. 6/ We leak a cloned bio if the target rdev is not usable. From: NeilBrown <neilb@suse.de> update 2: 1/ When aligned requests fail (read error) they need to be retried via the normal method (stripe cache). As we cannot be sure that we can process a single read in one go (we may not be able to allocate all the stripes needed) we store a bio-being-retried and a list of bioes-that-still-need-to-be-retried. When find a bio that needs to be retried, we should add it to the list, not to single-bio... 2/ We were never incrementing 'scnt' when resubmitting failed aligned requests. [akpm@osdl.org: build fix] Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07[PATCH] slab: remove kmem_cache_tChristoph Lameter
Replace all uses of kmem_cache_t with struct kmem_cache. The patch was generated using the following script: #!/bin/sh # # Replace one string by another in all the kernel sources. # set -e for file in `find * -name "*.c" -o -name "*.h"|xargs grep -l $1`; do quilt add $file sed -e "1,\$s/$1/$2/g" $file >/tmp/$$ mv /tmp/$$ $file quilt refresh done The script was run like this sh replace kmem_cache_t "struct kmem_cache" Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>