summaryrefslogtreecommitdiffstats
AgeCommit message (Collapse)AuthorFilesLines
2011-03-21block: attempt to merge with existing requests on plug flushJens Axboe5-4/+59
One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized. Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging). This fixes a regression with multiple processes issuing IO that can be merged. Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing an accounting bug. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-19block: NULL dereference on error path in __blkdev_get()Dan Carpenter1-1/+1
"disk" is always NULL when we goto out. There was a check for this before, but it was removed in 69e02c59a7d9 "block: Don't check events while open is in progress". Signed-off-by: Dan Carpenter <error27@gmail.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@carl>
2011-03-17cfq-iosched: Don't update group weights when on service treeJustin TerAvest1-12/+41
Version 3 is updated to apply to for-2.6.39/core. For version 2, I took Vivek's advice and made sure we update the group weight from cfq_group_service_tree_add(). If a weight was updated while a group is on the service tree, the calculation for the total weight of the service tree can be adjusted improperly, which either leads to bad service tree weights, or potentially crashes (if total_weight becomes 0). This patch defers updates to the weight until a group is off the service tree. Signed-off-by: Justin TerAvest <teravest@google.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-17fs: assign sb->s_bdi to default_backing_dev_info if the bdi is going awayJens Axboe3-3/+5
We don't have proper reference counting for this yet, so we run into cases where the device is pulled and we OOPS on flushing the fs data. This happens even though the dirty inodes have already been migrated to the default_backing_dev_info. Reported-by: Torsten Hilbrich <torsten.hilbrich@secunet.com> Tested-by: Torsten Hilbrich <torsten.hilbrich@secunet.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-17block: Require subsystems to explicitly allocate bio_set integrity mempoolMartin K. Petersen11-22/+41
MD and DM create a new bio_set for every metadevice. Each bio_set has an integrity mempool attached regardless of whether the metadevice is capable of passing integrity metadata. This is a waste of memory. Instead we defer the allocation decision to MD and DM since we know at metadevice creation time whether integrity passthrough is needed or not. Automatic integrity mempool allocation can then be removed from bioset_create() and we make an explicit integrity allocation for the fs_bio_set. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Reported-by: Zdenek Kabelac <zkabelac@redhat.com> Acked-by: Mike Snitzer <snizer@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-17jbd2: finish conversion from WRITE_SYNC_PLUG to WRITE_SYNC and explicit pluggingJens Axboe1-10/+8
'write_op' was still used, even though it was always WRITE_SYNC now. Add plugging around the cases where it submits IO, and flush them before we end up waiting for that IO. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-17jbd: finish conversion from WRITE_SYNC_PLUG to WRITE_SYNC and explicit pluggingJens Axboe1-11/+11
'write_op' was still used, even though it was always WRITE_SYNC now. Add plugging around the cases where it submits IO, and flush them before we end up waiting for that IO. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-17fs: make fsync_buffers_list() plugJens Axboe1-0/+6
It used WRITE_SYNC_PLUG before and potentially submits a batch of IO, so lets enable plugging for this case. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-17mm: make generic_writepages() use pluggingShaohua Li1-1/+7
This recovers a performance regression caused by the removal of the per-device plugging. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-12blk-cgroup: Add unaccounted time to timeslice_used.Justin TerAvest4-14/+41
There are two kind of times that tasks are not charged for: the first seek and the extra time slice used over the allocated timeslice. Both of these exported as a new unaccounted_time stat. I think it would be good to have this reported in 'time' as well, but that is probably a separate discussion. Signed-off-by: Justin TerAvest <teravest@google.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-11block: fixup plugging stubs for !CONFIG_BLOCKJens Axboe1-3/+6
They used an older prototype, fix it up. Reported-by: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-11block: remove obsolete comments for blkdev_issue_zeroout.Tao Ma1-2/+0
barrier is already removed, so remove the obsolete comments in blkdev_issue_zeroout. Cc: Jens Axboe <jaxboe@fusionio.com> Signed-off-by: Tao Ma <boyu.mt@taobao.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-11blktrace: Use rq->cmd_flags directly in blk_add_trace_rq.Tao Ma1-11/+4
In blk_add_trace_rq, we only chose the minor 2 bits from request's cmd_flags and did some check for discard. so most of other flags(e.g, REQ_SYNC) are missing. For example, with a sync write after blkparse we get: 8,16 1 1 0.001776503 7509 A WS 1349632 + 1024 <- (8,17) 1347584 8,16 1 2 0.001776813 7509 Q WS 1349632 + 1024 [dd] 8,16 1 3 0.001780395 7509 G WS 1349632 + 1024 [dd] 8,16 1 5 0.001783186 7509 I W 1349632 + 1024 [dd] 8,16 1 11 0.001816987 7509 D W 1349632 + 1024 [dd] 8,16 0 2 0.006218192 0 C W 1349632 + 1024 [0] Since now we have integrated the flags of both bio and request, it is safe to pass rq->cmd_flags directly to __blk_add_trace. With this patch, after a sync write we get: 8,16 1 1 0.001776900 5425 A WS 1189888 + 1024 <- (8,17) 1187840 8,16 1 2 0.001777179 5425 Q WS 1189888 + 1024 [dd] 8,16 1 3 0.001780797 5425 G WS 1189888 + 1024 [dd] 8,16 1 5 0.001783402 5425 I WS 1189888 + 1024 [dd] 8,16 1 11 0.001817468 5425 D WS 1189888 + 1024 [dd] 8,16 0 2 0.005640709 0 C WS 1189888 + 1024 [0] Signed-off-by: Tao Ma <boyu.mt@taobao.com> Acked-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10Merge branch 'for-2.6.39/stack-plug' into for-2.6.39/coreJens Axboe137-1533/+606
Conflicts: block/blk-core.c block/blk-flush.c drivers/md/raid1.c drivers/md/raid10.c drivers/md/raid5.c fs/nilfs2/btnode.c fs/nilfs2/mdt.c Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10blk-throttle: Use blk_plug in throttle dispatchVivek Goyal1-0/+3
Use plug in throttle dispatch also as we are dispatching a bunch of bios in throttle context and some of them might merge. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10block: kill off REQ_UNPLUGJens Axboe24-75/+43
With the plugging now being explicitly controlled by the submitter, callers need not pass down unplugging hints to the block layer. If they want to unplug, it's because they manually plugged on their own - in which case, they should just unplug at will. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10aio: remove request submission batchingJens Axboe1-72/+3
This should be useless now that we have on-stack plugging. So lets just kill it. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10fs: make aio plugShaohua Li1-0/+4
Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10fs: make mpage read/write_pages() plugJens Axboe1-0/+8
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10read-ahead: use pluggingJens Axboe1-0/+6
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10fs: make generic file read/write functions plugJens Axboe1-0/+7
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10block: remove per-queue pluggingJens Axboe119-1269/+151
Code has been converted over to the new explicit on-stack plugging, and delay users have been converted to use the new API for that. So lets kill off the old plugging along with aops->sync_page(). Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10block: initial patch for on-stack per-task pluggingJens Axboe10-101/+344
This patch adds support for creating a queuing context outside of the queue itself. This enables us to batch up pieces of IO before grabbing the block device queue lock and submitting them to the IO scheduler. The context is created on the stack of the process and assigned in the task structure, so that we can auto-unplug it if we hit a schedule event. The current queue plugging happens implicitly if IO is submitted to an empty device, yet callers have to remember to unplug that IO when they are going to wait for it. This is an ugly API and has caused bugs in the past. Additionally, it requires hacks in the vm (->sync_page() callback) to handle that logic. By switching to an explicit plugging scheme we make the API a lot nicer and can get rid of the ->sync_page() hack in the vm. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10scsi: convert to blk_delay_queue()Jens Axboe1-25/+19
It was always abuse to reuse the plugging infrastructure for this, convert it to the (new) real API for delaying queueing a bit. A default delay of 3 msec is defined, to match the previous behaviour. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-10ide-cd: convert to blk_delay_queue() for a short pauseJens Axboe1-11/+2
It was always abuse to reuse the plugging infrastructure for this, convert it to the (new) real API for delaying queueing a bit. Signed-off-by: Jens Axboe <jaxboe@fusionio.com> Acked-by: David S. Miller <davem@davemloft.net>
2011-03-10block: add API for delaying work/request_fn a little bitJens Axboe2-0/+35
Currently we use plugging for that, but as plugging is going away, we need an alternative mechanism. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-09staging: Convert to bdops->check_events()Tejun Heo2-8/+14
Convert two staging drivers - blkvsc_drv and cyasblkdev_block - from ->media_changed() to ->check_events(). The former always indicated media changed while the latter always indicated media not changed. Not sure what the drivers are trying to achieve but keep the original behavior. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org>
2011-03-09pktcdvd: Convert to bdops->check_events()Tejun Heo1-4/+9
Convert from ->media_changed() to ->check_events(). pktcdvd needs to forward all event related operations to the underlying device. Forward ->check_events() instead of ->media_changed() and inherit disk->[async_]events. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Peter Osterlund <petero2@telia.com>
2011-03-09umem: Drop dummy ->media_changed()Tejun Heo1-10/+0
umem doesn't implement media changed detection and there's no need to implement dummy callback anymore. Remove it. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org>
2011-03-09s390/tape_block: Convert to bdops->check_events()Tejun Heo1-5/+6
Convert from ->media_changed() to ->check_events(). s390/tape_block buffers media changed state and clears it on revalidation. It will behave correctly with kernel event polling. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
2011-03-09i2o_block: Convert to bdops->check_events()Tejun Heo1-4/+7
Convert from ->media_changed() to ->check_events(). i2o_block buffers media changed state and clears it after reporting. It will behave correctly with kernel event polling. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com>
2011-03-09xsysace: Convert to bdops->check_events()Tejun Heo1-4/+5
Convert from ->media_changed() to ->check_events(). xsysace buffers media changed state and clears it on revalidation. It will behave correctly with kernel event polling. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Grant Likely <grant.likely@secretlab.ca> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org>
2011-03-09ub: Convert to bdops->check_events()Tejun Heo1-4/+6
Convert from ->media_changed() to ->check_events(). ub buffers media changed state and clears it on revalidation. It will behave correctly with kernel event polling. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Pete Zaitcev <zaitcev@redhat.com>
2011-03-09swim[3]: Convert to bdops->check_events()Tejun Heo2-7/+12
Convert from ->media_changed() to ->check_events(). Both swim and swim3 buffer media changed state and clear it on revalidation. They will behave correctly with kernel event polling. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Laurent Vivier <laurent@lvivier.info> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-03-09dac960: Convert to bdops->check_events()Tejun Heo1-3/+5
Convert from ->media_changed() to ->check_events(). DAC960 media change notification seems to be one way (once set, never cleared) and will generate spurious events when polled once the condition triggers. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org>
2011-03-09paride: Convert to bdops->check_events()Tejun Heo3-14/+21
Convert paride drivers from ->media_changed() to ->check_events(). pcd and pd buffer and clear events after reporting; however, pf unconditionally reports MEDIA_CHANGE and will generate spurious events when polled. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Tim Waugh <tim@cyberelk.net>
2011-03-09gdrom,viocd: Convert to bdops->check_events()Tejun Heo2-13/+20
Convert gdrom and viocd from ->media_changed() to ->check_events(). It's unclear how the conditions are cleared and it's possible that it may generate spurious events when polled. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org>
2011-03-09floppy,{ami|ata}flop: Convert to bdops->check_events()Tejun Heo3-14/+19
Convert the floppy drivers from ->media_changed() to ->check_events(). Both floppy and ataflop buffer media changed state bit and clear them on revalidation and will behave correctly with kernel event polling. I can't tell how amiflop clears its event and it's possible that it may generate spurious events when polled. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org>
2011-03-09ide: Convert to bdops->check_events()Tejun Heo4-15/+20
Convert ->media_changed() to the new ->check_events() method. The conversion is mostly mechanical. The only notable change is that cdrom now doesn't generate any event if @slot_nr isn't CDSL_CURRENT. It used to return -EINVAL which would be treated as media changed. As media changer isn't supported anyway, this doesn't make any difference. This makes ide emit the standard disk events and allows kernel event polling. Currently, only MEDIA_CHANGE event is implemented. Adding support for EJECT_REQUEST shouldn't be difficult; however, given that ide driver is already deprecated, it probably is best to leave it alone. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: linux-ide@vger.kernel.org
2011-03-09block: Don't check events while open is in progressTejun Heo1-7/+10
Not all block drivers clear events immediately after reporting. Some do so in ->revalidate_disk() or other steps during ->open(). There is a slim chance event poll may happen between the clearing event check from check_disk_change() and the actual clearing of the events which would result in spurious events. Block event checks while block device open is in progress. There is no need to kick explicit event check afterwards as events are always checked during open. -v2: The original patch could have called disk_unblock_events() with an already released or %NULL @disk causing oops. Fixed by making sure references are put after disk_unblock_events() is called. It also makes the error path of __blkdev_get() a bit simpler. This problem was reported by Jens. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org>
2011-03-09block: Don't check events on close unless it was blockedTejun Heo1-4/+2
The block event mechanism currently always checks events when the device is being closed regardless of the open mode. The intention was to allow detection of EJECT_REQUEST when a device is closed whether disk event polling is enabled or not. This is unnecessary as, for devices of interest, events are checked from either userland or kernel and in the former case ->check_events() is performed on open of each poll attempt anyway. Furthermore, this unconditional event check on close makes the code susceptible to event loop if the block driver doesn't clear reported events correctly - an event triggers userland to open and close the device which in turn causes another event, rinse and repeat. Check events on close only if it was blocked by excl write open. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org>
2011-03-09block: Don't implicitly trigger event check on disk_unblock_events()Tejun Heo2-1/+2
Currently, disk_unblock_events() implicitly kick event check if the block count reaches zero. This behavior is not described in the comment and hinders with future changes. Make the unblocker explicitly check events by calling disk_check_events() as necessary. This patch doesn't cause any behavior difference. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Kay Sievers <kay.sievers@vrfy.org>
2011-03-08blk-cgroup: Lower minimum weight from 100 to 10.Justin TerAvest2-2/+2
We've found that we still get good, useful isolation at weights this low. I'd like to adjust the minimum so that any other changes can take these values into account. Signed-off-by: Justin TerAvest <teravest@google.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-08block: biovec_slab vs. CONFIG_BLK_DEV_INTEGRITYMartin K. Petersen2-4/+1
The block integrity subsystem no longer uses the bio_vec slabs so this code can safely be compiled in. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-07blk-throttle: Some cleanups and race fixes in limit update codeVivek Goyal1-56/+40
When throttle group limits are updated through cgroups, a thread is woken up to process these updates. While reviewing that code, oleg noted couple of race conditions existed in the code and he also suggested that code can be simplified. This patch fixes the races simplifies the code based on Oleg's suggestions: - Use xchg(). - Introduced a common function throtl_update_blkio_group_common() which is shared now by all iops/bps update functions. Reviewed-by: Oleg Nesterov <oleg@redhat.com> Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Fixed a merge issue, throtl_schedule_delayed_work() takes throtl_data as the argument now, not the queue. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-07blk-throttle: process limit change only through one functionVivek Goyal1-7/+1
With the help of cgroup interface one can go and upate the bps/iops limits of existing group. Once the limits are udpated, a thread is woken up to see if some blocked group needs recalculation based on new limits and needs to be requeued. There was also a piece of code where I was checking for group limit update when a fresh bio comes in. This patch gets rid of that piece of code and keeps processing the limit change at one place throtl_process_limit_change(). It just keeps the code simple and easy to understand. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-07Merge branch 'block-for-2.6.39-core' of ↵Jens Axboe209-734/+1841
ssh://master.kernel.org/pub/scm/linux/kernel/git/tj/misc into for-2.6.39/core
2011-03-07cfq-iosched: Fix update_vdisktime logicGui Jianfeng1-4/+2
The update_vdisktime logic is broken since commit b54ce60eb7f61f8e314b8b241b0469eda3bb1d42, st->min_vdisktime never makes a progress. Fix it. Thanks Vivek for pointing it out. Signed-off-by: Gui Jianfeng <guijianfen@cn.fujitsu.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-07cfq-iosched: give busy sync queue no dispatch limitShaohua Li1-2/+24
If there are a sync and an async queue and the sync queue's think time is small, we can ignore the sync queue's dispatch quantum. Because the sync queue will always preempt the async queue, we don't need to care about async's latency. This can fix a performance regression of aiostress test, which is introduced by commit f8ae6e3eb825. The issue should exist even without the commit, but the commit amplifies the impact. The initial post does the same optimization for RT queue too, but since I have no real workload for it, Vivek suggests to drop it. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-07cfq-iosched: fix race in cfq_set_request()Jens Axboe1-2/+1
We need to hold the queue lock over the reference increment, it's not atomic anymore. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-15 06:10:32 +0000