summaryrefslogtreecommitdiffstats
path: root/drivers/block/drbd
Commit message (Collapse)AuthorAgeFilesLines
* BKL: remove extraneous #include <smp_lock.h>Arnd Bergmann2010-11-172-2/+0
| | | | | | | | | | The big kernel lock has been removed from all these files at some point, leaving only the #include. Remove this too as a cleanup. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Merge branch 'for-2.6.37/drivers' into for-linusJens Axboe2010-11-108-343/+201
|\ | | | | | | | | | | | | Conflicts: drivers/block/cciss.c Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
| * Merge branch 'for-jens' of git://git.drbd.org/linux-2.6-drbd into ↵Jens Axboe2010-10-238-343/+201
| |\ | | | | | | | | | for-2.6.37/drivers
| | * drbd: Removed checks for REQ_HARDBARRIER on incomming BIOsPhilipp Reisner2010-10-233-20/+0
| | | | | | | | | | | | | | | Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| | * drbd: REQ_HARDBARRIER -> REQ_FUA transition for meta data accessesPhilipp Reisner2010-10-233-20/+7
| | | | | | | | | | | | | | | Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| | * drbd: Removed the BIO_RW_BARRIER support form the receiver/epoch codePhilipp Reisner2010-10-236-219/+33
| | | | | | | | | | | | | | | Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| | * drbd: Silenced an assertPhilipp Reisner2010-10-221-1/+1
| | | | | | | | | | | | | | | | | | | | | That assertion's condition needed adjustment for today's semantics Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| | * drbd: rate limit an error messageLars Ellenberg2010-10-221-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | If we don't rate limit it, and you happen to log err level messages via serial console, an IO error on a disconnected Primary may cause serious unresponsiveness. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| | * drbd: fix a misleading printkLars Ellenberg2010-10-221-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | This codepath used to be called only for failed kmalloc GFP_ATOMIC, but is now also triggered by other things. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| | * drbd: fix potential data divergence after multiple failuresLars Ellenberg2010-10-223-11/+37
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we get an IO-error during an activity log transaction, if we failed to write the bitmap of the evicted extent, we must not write the transaction itself. If we failed to write the transaction, we must not even submit the corresponding bio, as its extent is not yet marked in the activity log. Otherwise, if this was a disconneted Primary (degraded cluster), which now lost its disk as well, and we later re-attach the same backend storage, we possibly "forget" to resync some parts of the disk that potentially have been changed. On the receiving side, when receiving from a peer with unhealthy disk, checking for pdsk == D_DISKLESS is not enough, we need to set out of sync and do AL transactions for everything pdsk < D_INCONSISTENT on the receiving side. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| | * drbd: fix potential deadlock on detachLars Ellenberg2010-10-224-63/+113
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we have contention in drbd_al_begin_iod (heavy randon IO), an administrative request to detach the disk may deadlock for similar reasons as the recently fixed deadlock if detaching because of IO-error. The approach taken here is to either go through the intermediate cleanup state D_FAILED, or first lock out application io, don't just go directly to D_DISKLESS. We need an additional state bit (WAS_IO_ERROR) to distinguish the -> D_FAILED because of IO-error from other failures. Sanitize D_ATTACHING -> D_FAILED to D_ATTACHING -> D_DISKLESS. If only attaching, ldev may be missing still, but would be referenced from within the after_state_ch for -> D_FAILED, potentially dereferencing a NULL pointer. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| | * drbd: tag a few error messages with "assert failed"Lars Ellenberg2010-10-221-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | If those messages ever get logged, clearly state that they are actually failed ASSERTS, so our regression tests can pick them up from the logs more easily. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| | * drbd: consolidate explicit drbd_md_sync into drbd_create_new_uuidLars Ellenberg2010-10-222-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | Every code path changing the current UUID needs to get it on stable storage anyways. Flush it to disk right there, remove the now obsolte explicit drbd_md_sync statements in the other code paths. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
* | | block: read i_size with i_size_read()Mike Snitzer2010-11-101-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Convert direct reads of an inode's i_size to using i_size_read(). i_size_{read,write} use a seqcount to protect reads from accessing incomple writes. Concurrent i_size_write()s require mutual exclussion to protect the seqcount that is used by i_size_{read,write}. But i_size_read() callers do not need to use additional locking. Signed-off-by: Mike Snitzer <snitzer@redhat.com> Acked-by: NeilBrown <neilb@suse.de> Acked-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
* | | drivers/block/drbd/drbd_main.c: fix error pathNicolas Kaiser2010-10-281-1/+1
|/ / | | | | | | | | | | | | | | | | | | | | Failure to create drbd_ee_mempool appears not to get checked. Looks like a copy-and-paste problem to me. Signed-off-by: Nicolas Kaiser <nikai@nikai.net> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
* | Merge branch 'for-2.6.37/barrier' of git://git.kernel.dk/linux-2.6-blockLinus Torvalds2010-10-222-3/+2
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'for-2.6.37/barrier' of git://git.kernel.dk/linux-2.6-block: (46 commits) xen-blkfront: disable barrier/flush write support Added blk-lib.c and blk-barrier.c was renamed to blk-flush.c block: remove BLKDEV_IFL_WAIT aic7xxx_old: removed unused 'req' variable block: remove the BH_Eopnotsupp flag block: remove the BLKDEV_IFL_BARRIER flag block: remove the WRITE_BARRIER flag swap: do not send discards as barriers fat: do not send discards as barriers ext4: do not send discards as barriers jbd2: replace barriers with explicit flush / FUA usage jbd2: Modify ASYNC_COMMIT code to not rely on queue draining on barrier jbd: replace barriers with explicit flush / FUA usage nilfs2: replace barriers with explicit flush / FUA usage reiserfs: replace barriers with explicit flush / FUA usage gfs2: replace barriers with explicit flush / FUA usage btrfs: replace barriers with explicit flush / FUA usage xfs: replace barriers with explicit flush / FUA usage block: pass gfp_mask and flags to sb_issue_discard dm: convey that all flushes are processed as empty ...
| * | block: remove BLKDEV_IFL_WAITChristoph Hellwig2010-09-162-3/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | All the blkdev_issue_* helpers can only sanely be used for synchronous caller. To issue cache flushes or barriers asynchronously the caller needs to set up a bio by itself with a completion callback to move the asynchronous state machine ahead. So drop the BLKDEV_IFL_WAIT flag that is always specified when calling blkdev_issue_* and also remove the now unused flags argument to blkdev_issue_flush and blkdev_issue_zeroout. For blkdev_issue_discard we need to keep it for the secure discard flag, which gains a more descriptive name and loses the bitops vs flag confusion. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
* | | Merge branch 'for-2.6.37/drivers' of git://git.kernel.dk/linux-2.6-blockLinus Torvalds2010-10-2210-888/+1733
|\ \ \ | | |/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'for-2.6.37/drivers' of git://git.kernel.dk/linux-2.6-block: (95 commits) cciss: fix PCI IDs for new Smart Array controllers drbd: add race-breaker to drbd_go_diskless drbd: use dynamic_dev_dbg to optionally log uuid changes dynamic_debug.h: Fix dynamic_dev_dbg() macro if CONFIG_DYNAMIC_DEBUG not set drbd: cleanup: change "<= 0" to "== 0" drbd: relax the grace period of the md_sync timer again drbd: add some more explicit drbd_md_sync drbd: drop wrong debug asserts, fix recently introduced race drbd: cleanup useless leftover warn/error printk's drbd: add explicit drbd_md_sync to drbd_resync_finished drbd: Do not log an ASSERT for P_OV_REQUEST packets while C_CONNECTED drbd: fix for possible deadlock on IO error during resync drbd: fix unlikely access after free and list corruption drbd: fix for spurious fullsync (uuids rotated too fast) drbd: allow for explicit resync-finished notifications drbd: preparation commit, using full state in receive_state() drbd: drbd_send_ack_dp must not rely on header information drbd: Fix regression in recv_bm_rle_bits (compressed bitmap) drbd: Fixed a stupid copy and paste error drbd: Allow larger values for c-fill-target. ... Fix up trivial conflict in drivers/block/ataflop.c due to BKL removal
| * | drbd: add race-breaker to drbd_go_disklessLars Ellenberg2010-10-151-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This adds a necessary race breaker to these commits: drbd: fix for possible deadlock on IO error during resync drbd: drop wrong debug asserts, fix recently introduced race What we do is get a refcount, check the state, then depending on the state and the requested minimum disk state, either hold it (success), or give it back immediately (failed "try lock"). Some code paths (flushing of drbd metadata) may still grab and hold a refcount even if we are D_FAILED (application IO won't). So even if we hit local_cnt == 0 once after being D_FAILED, we still need to wait for that again after we changed to D_DISKLESS. Once local_cnt reaches 0 while we are D_DISKLESS, we can be sure that no one will look at the protected members anymore, so only then is it safe to free them. We cannot easily convert to standard locking primitives here, as we want to be able to use it in atomic context (we always do a "try lock"), as well as hold references for a "long time" (from IO submission to completion callback). Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: use dynamic_dev_dbg to optionally log uuid changesLars Ellenberg2010-10-151-1/+31
| | | | | | | | | | | | | | | Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: cleanup: change "<= 0" to "== 0"Dan Carpenter2010-10-141-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | dt is unsigned so it's never less than zero. We are calculating the elapsed time, and that's never less than zero (unless there is a bug or we invent time travel). The comparison here is just to guard against divide by zero bugs. Signed-off-by: Dan Carpenter <error27@gmail.com> Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
| * | drbd: relax the grace period of the md_sync timer againLars Ellenberg2010-10-141-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Consolidate the ifdef's for the debug level, accidentally the used both DEBUG and DRBD_DEBUG_MD_SYNC. Default to off. For production, we can safely reduce the grace period for this timer again the the value we used to have. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: add some more explicit drbd_md_syncLars Ellenberg2010-10-141-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It sometimes may take a while for the after state change work to be scheduled, which does drbd_md_sync. At convenient places, we should do explicit drbd_md_sync to have the new state information on disk as soon as possible. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: drop wrong debug asserts, fix recently introduced raceLars Ellenberg2010-10-141-9/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | commit 2372c38caadeaebc68a5ee190782c2a0df01edc3 drbd: fix for possible deadlock on IO error during resync introduced a new ASSERT, which turns out to be wrong. Drop it. Also serialize the state change to D_DISKLESS with the after state change work of the -> D_FAILED transition, don't open a new race. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: cleanup useless leftover warn/error printk'sLars Ellenberg2010-10-142-6/+1
| | | | | | | | | | | | | | | Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: add explicit drbd_md_sync to drbd_resync_finishedLars Ellenberg2010-10-141-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | As we usually update the generation UUIDs here, we should explicitly sync them to disk. So far this has been done only implicitly by related code paths. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: Do not log an ASSERT for P_OV_REQUEST packets while C_CONNECTEDPhilipp Reisner2010-10-141-8/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This might happen if on the VERIFY_S node the disk gets dropped. Although this is an cluster wide state transition, the VERIFY_T node, updates it connection state first. Then the ack packet for the cluster wide state transition travels back, and the VERIFY_S node stops to produce the P_OV_REQUEST packets. There is absolutely nothing wrong with that. Further, do not log "Can not satisfy peer's..." on the VERIFY_S node in this case, but pretend that they had equal checksum. [Bugz 327] Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: fix for possible deadlock on IO error during resyncLars Ellenberg2010-10-142-22/+54
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Scenario: Something (say, flush-147:0) is in drbd_al_begin_io, holding a local_cnt, waiting for the resync to make progress. Disk fails, worker in after_state_ch does drbd_rs_cancel_all, then waits for local_cnt to drop to zero. flush-147:0 is woken by drbd_rs_cancel_all, needs to write an AL transaction, and queues that on the worker. Deadlock. Fix: do not wait in the worker, have put_ldev() trigger the state change D_FAILED -> D_DISKLESS when necessary. put_ldev() cannot do the state change directly, as it may or may not already hold various spinlocks. We queue a short work instead. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: fix unlikely access after free and list corruptionLars Ellenberg2010-10-142-0/+32
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Various cleanup paths have been incomplete, for the very unlikely case that we cannot allocate enough bios from process context when submitting on behalf of the peer or resync process. Never observed. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: fix for spurious fullsync (uuids rotated too fast)Lars Ellenberg2010-10-142-11/+36
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If it was an "empty" resync, the SyncSource may have already "finished" the resync and rotated the UUIDs, before noticing the connection loss (and generating a new uuid, if Primary, rotating again), while the SyncTarget did not change its uuids at all, or only got to the previous sync-uuid. This would then again lead to a full sync on next handshake (see also Bug #251). Fix: Use explicit resync finished notification even for empty resyncs, do not finish an empty resync implicitly on the SyncSource. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: allow for explicit resync-finished notificationsLars Ellenberg2010-10-141-0/+34
| | | | | | | | | | | | | | | | | | | | | | | | Preparation patch so more drbd_send_state() usage on the peer will not confuse drbd in receive_state(). Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: preparation commit, using full state in receive_state()Lars Ellenberg2010-10-141-21/+18
| | | | | | | | | | | | | | | | | | | | | | | | no functional change, just using full state instead of just the .conn part of it for comparisons. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: drbd_send_ack_dp must not rely on header informationLars Ellenberg2010-10-143-8/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | drbd commit 17c854fea474a5eb3cfa12e4fb019e46debbc4ec drbd: receiving of big packets, for payloads between 64kByte and 4GByte introduced a new on-the-wire packet header format. We must no longer assume either format, but use the result of whatever drbd_recv_header has decoded. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: Fix regression in recv_bm_rle_bits (compressed bitmap)Lars Ellenberg2010-10-141-12/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We used to be16_to_cpu the length field in our received packet header. drbd commit 17c854fea474a5eb3cfa12e4fb019e46debbc4ec drbd: receiving of big packets, for payloads between 64kByte and 4GByte changed this, but forgot to adjust a few places where we relied on h->length being in native byte order. This broke the receiving side of the RLE compressed bitmap exchange. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: Fixed a stupid copy and paste errorPhilipp Reisner2010-10-141-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | This caused rs_planed to be not in sync with the content of the fifo. That in turn could cause that the resync comes to a complete halt. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: Allow larger values for c-fill-target.Philipp Reisner2010-10-141-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | Connections through a compressing proxy might have more bits on the fly. 500MByte instead of 50MByte Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: fix possible access after freeLars Ellenberg2010-10-141-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we release the page pointed to by md_io_tmpp, we need to zero out the pointer, too, as that may be used later to decide whether we need to allocate a new page again. Impact: a previously freed page may be used and clobbered. Depending on what that particular page is being used for meanwhile, this may result in silent data corruption of completely unrelated things. Only of concern on devices with logical_block_size != 512 byte, if you re-attach after becoming diskless once. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: protocol compatibility for maximum packet sizesLars Ellenberg2010-10-142-3/+17
| | | | | | | | | | | | | | | | | | | | | Two missing corner cases to the "maximum packet size" handshake. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: Track the reasons to suspend IO in dedicated state bitsPhilipp Reisner2010-10-146-27/+52
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There are three ways to get IO suspended: * Loss of any access to data * Fence-peer-handler running * User requested to suspend IO Track those in different bits, so that one condition clearing its state bit does not interfere with the other two conditions. Only when the user resumes IO he overrules all three bits. The fact is hidden from the user, he sees only a single suspend bit. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: DIV_ROUND_UP not needed hereLars Ellenberg2010-10-141-1/+1
| | | | | | | | | | | | | | | Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: Fixed compatibility with protocol versions smaller than 95Philipp Reisner2010-10-141-2/+3
| | | | | | | | | | | | | | | | | | | | | Forgot to consider the max size for the resync requests. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: fix for spurious full sync (becoming sync target looked like invalidate)Lars Ellenberg2010-10-141-2/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If a synctarget lost connection while being WFSyncUUID, due to "state sanitizing", the attempted state change to SyncTarget looked like an "invalidate" to after_state_ch() later, thus caused a full sync on next handshake (Bug #318). drbd0: PingAck did not arrive in time. drbd0: peer( Primary -> Unknown ) conn( WFSyncUUID -> NetworkFailure ) pdsk( UpToDate -> DUnknown ) from : { cs:NetworkFailure ro:Secondary/Unknown ds:UpToDate/DUnknown r--- } to : { cs:SyncTarget ro:Secondary/Unknown ds:Inconsistent/DUnknown r--- } after sanizising, resulted in state: { cs:NetworkFailure ro:Secondary/Unknown ds:Inconsistent/DUnknown r--- } drbd0: disk( UpToDate -> Inconsistent ) Fix: don't mask state transition errors in "sanitizing", so the requested state change to SyncTarget fails, instead of being implicitly "remaped" to invalidate. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: cosmetic, don't report resync for online-verifyLars Ellenberg2010-10-141-5/+7
| | | | | | | | | | | | | | | Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: fix spurious protocol errorLars Ellenberg2010-10-141-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | If we cannot satisfy a request (because our disk just broke), we still need to drain the payload. Or we'll get a protocol error when interpreting the payload as DRBD packet header. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: fix potential kernel BUG (NULL deref)Lars Ellenberg2010-10-142-6/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | BUG trace would look like: lc_find drbd_rs_complete_io got_OVResult drbd_asender Could be triggered by explicit, or IO-error policy based, detach during online-verify. We may only dereference mdev->resync, if we first get_ldev(), as the disk may break any time, causing mdev->resync to disappear once all ldev references have been returned. Already in flight online-verify requests or replies may still come in, which we then need to ignore. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: don't count sendpage()d pages only referenced by tcp as in useLars Ellenberg2010-10-144-12/+27
| | | | | | | | | | | | | | | Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: Adding support for BIO/Request flags: REQ_FUA, REQ_FLUSH and REQ_DISCARDPhilipp Reisner2010-10-143-22/+34
| | | | | | | | | | | | | | | Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: drbd_md_sync before calling user space helpersLars Ellenberg2010-10-141-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | Just in case we have some pending meta data changes to sync, do it before we call our userland helper, as that may take some time, or even cause a hard reboot. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: fix race on meta-data update, addendumLars Ellenberg2010-10-142-5/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | addendum to baa33ae4eaa4477b60af7c434c0ddd1d182c1ae7 The race: drbd_md_sync() if (!test_and_clear_bit(MD_DIRTY, &mdev->flags)) return; ==> RACE with drbd_md_mark_dirty() rearming the timer. del_timer(&mdev->md_sync_timer); Fixed by moving the del_timer before the test_and_clear_bit. Additionally only rearm the timer in drbd_md_mark_dirty, if MD_DIRTY was not already set, reduce the grace period from five to one second, and add an ifdef'ed debuging aid to find code paths missing an explicit drbd_md_sync, if any, as those are the only relevant ones for this race. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
| * | drbd: Removed a race that could cause unexpected execution of ↵Philipp Reisner2010-10-144-30/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | w_make_resync_request() The actual race happened int the drbd_start_resync() function. Where drbd_resync_finished() -> __drbd_set_state() set STOP_SYNC_TIMER and armed the timer. If the timer fired before execution reaches the mod_timer statement at the end of drbd_start_resync() the latter would cause an unexpected call to w_make_resync_request(). Removed the STOP_SYNC_TIMER bit, and base it on the connection state. The STOP_SYNC_TIMER bit probably originates probably the time before the state engine. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
OpenPOWER on IntegriCloud