1. 28 May, 2014 1 commit
  2. 21 May, 2014 1 commit
  3. 21 Mar, 2014 1 commit
    • Mike Galbraith's avatar
      rt,blk,mq: Make blk_mq_cpu_notify_lock a raw spinlock · 55c816e3
      Mike Galbraith authored
      [  365.164040] BUG: sleeping function called from invalid context at kernel/rtmutex.c:674
      [  365.164041] in_atomic(): 1, irqs_disabled(): 1, pid: 26, name: migration/1
      [  365.164043] no locks held by migration/1/26.
      [  365.164044] irq event stamp: 6648
      [  365.164056] hardirqs last  enabled at (6647): [<ffffffff8153d377>] restore_args+0x0/0x30
      [  365.164062] hardirqs last disabled at (6648): [<ffffffff810ed98d>] multi_cpu_stop+0x9d/0x120
      [  365.164070] softirqs last  enabled at (0): [<ffffffff810543bc>] copy_process.part.28+0x6fc/0x1920
      [  365.164072] softirqs last disabled at (0): [<          (null)>]           (null)
      [  365.164076] CPU: 1 PID: 26 Comm: migration/1 Tainted: GF           N  3.12.12-rt19-0.gcb6c4a2-rt #3
      [  365.164078] Hardware name: QCI QSSC-S4R/QSSC-S4R, BIOS QSSC-S4R.QCI.01.00.S013.032920111005 03/29/2011
      [  365.164091]  0000000000000001 ffff880a42ea7c30 ffffffff815367e6 ffffffff81a086c0
      [  365.164099]  ffff880a42ea7c40 ffffffff8108919c ffff880a42ea7c60 ffffffff8153c24f
      [  365.164107]  ffff880a42ea91f0 00000000ffffffe1 ffff880a42ea7c88 ffffffff81297ec0
      [  365.164108] Call Trace:
      [  365.164119]  [<ffffffff810060b1>] try_stack_unwind+0x191/0x1a0
      [  365.164127]  [<ffffffff81004872>] dump_trace+0x92/0x360
      [  365.164133]  [<ffffffff81006108>] show_trace_log_lvl+0x48/0x60
      [  365.164138]  [<ffffffff81004c18>] show_stack_log_lvl+0xd8/0x1d0
      [  365.164143]  [<ffffffff81006160>] show_stack+0x20/0x50
      [  365.164153]  [<ffffffff815367e6>] dump_stack+0x54/0x9a
      [  365.164163]  [<ffffffff8108919c>] __might_sleep+0xfc/0x140
      [  365.164173]  [<ffffffff8153c24f>] rt_spin_lock+0x1f/0x70
      [  365.164182]  [<ffffffff81297ec0>] blk_mq_main_cpu_notify+0x20/0x70
      [  365.164191]  [<ffffffff81540a1c>] notifier_call_chain+0x4c/0x70
      [  365.164201]  [<ffffffff81083499>] __raw_notifier_call_chain+0x9/0x10
      [  365.164207]  [<ffffffff810567be>] cpu_notify+0x1e/0x40
      [  365.164217]  [<ffffffff81525da2>] take_cpu_down+0x22/0x40
      [  365.164223]  [<ffffffff810ed9c6>] multi_cpu_stop+0xd6/0x120
      [  365.164229]  [<ffffffff810edd97>] cpu_stopper_thread+0xd7/0x1e0
      [  365.164235]  [<ffffffff810863a3>] smpboot_thread_fn+0x203/0x380
      [  365.164241]  [<ffffffff8107cbf8>] kthread+0xc8/0xd0
      [  365.164250]  [<ffffffff8154440c>] ret_from_fork+0x7c/0xb0
      [  365.164429] smpboot: CPU 1 is now offline
      Signed-off-by: default avatarMike Galbraith <bitbucket@online.de>
      Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      55c816e3
  4. 03 Mar, 2014 1 commit
    • Mike Galbraith's avatar
      rt,blk,mq: Make blk_mq_cpu_notify_lock a raw spinlock · 2a26ebef
      Mike Galbraith authored
      [  365.164040] BUG: sleeping function called from invalid context at kernel/rtmutex.c:674
      [  365.164041] in_atomic(): 1, irqs_disabled(): 1, pid: 26, name: migration/1
      [  365.164043] no locks held by migration/1/26.
      [  365.164044] irq event stamp: 6648
      [  365.164056] hardirqs last  enabled at (6647): [<ffffffff8153d377>] restore_args+0x0/0x30
      [  365.164062] hardirqs last disabled at (6648): [<ffffffff810ed98d>] multi_cpu_stop+0x9d/0x120
      [  365.164070] softirqs last  enabled at (0): [<ffffffff810543bc>] copy_process.part.28+0x6fc/0x1920
      [  365.164072] softirqs last disabled at (0): [<          (null)>]           (null)
      [  365.164076] CPU: 1 PID: 26 Comm: migration/1 Tainted: GF           N  3.12.12-rt19-0.gcb6c4a2-rt #3
      [  365.164078] Hardware name: QCI QSSC-S4R/QSSC-S4R, BIOS QSSC-S4R.QCI.01.00.S013.032920111005 03/29/2011
      [  365.164091]  0000000000000001 ffff880a42ea7c30 ffffffff815367e6 ffffffff81a086c0
      [  365.164099]  ffff880a42ea7c40 ffffffff8108919c ffff880a42ea7c60 ffffffff8153c24f
      [  365.164107]  ffff880a42ea91f0 00000000ffffffe1 ffff880a42ea7c88 ffffffff81297ec0
      [  365.164108] Call Trace:
      [  365.164119]  [<ffffffff810060b1>] try_stack_unwind+0x191/0x1a0
      [  365.164127]  [<ffffffff81004872>] dump_trace+0x92/0x360
      [  365.164133]  [<ffffffff81006108>] show_trace_log_lvl+0x48/0x60
      [  365.164138]  [<ffffffff81004c18>] show_stack_log_lvl+0xd8/0x1d0
      [  365.164143]  [<ffffffff81006160>] show_stack+0x20/0x50
      [  365.164153]  [<ffffffff815367e6>] dump_stack+0x54/0x9a
      [  365.164163]  [<ffffffff8108919c>] __might_sleep+0xfc/0x140
      [  365.164173]  [<ffffffff8153c24f>] rt_spin_lock+0x1f/0x70
      [  365.164182]  [<ffffffff81297ec0>] blk_mq_main_cpu_notify+0x20/0x70
      [  365.164191]  [<ffffffff81540a1c>] notifier_call_chain+0x4c/0x70
      [  365.164201]  [<ffffffff81083499>] __raw_notifier_call_chain+0x9/0x10
      [  365.164207]  [<ffffffff810567be>] cpu_notify+0x1e/0x40
      [  365.164217]  [<ffffffff81525da2>] take_cpu_down+0x22/0x40
      [  365.164223]  [<ffffffff810ed9c6>] multi_cpu_stop+0xd6/0x120
      [  365.164229]  [<ffffffff810edd97>] cpu_stopper_thread+0xd7/0x1e0
      [  365.164235]  [<ffffffff810863a3>] smpboot_thread_fn+0x203/0x380
      [  365.164241]  [<ffffffff8107cbf8>] kthread+0xc8/0xd0
      [  365.164250]  [<ffffffff8154440c>] ret_from_fork+0x7c/0xb0
      [  365.164429] smpboot: CPU 1 is now offline
      Signed-off-by: default avatarMike Galbraith <bitbucket@online.de>
      Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      2a26ebef
  5. 28 Jan, 2014 1 commit
  6. 08 Jan, 2014 1 commit
  7. 14 Nov, 2013 1 commit
  8. 25 Oct, 2013 1 commit
    • Jens Axboe's avatar
      blk-mq: new multi-queue block IO queueing mechanism · 320ae51f
      Jens Axboe authored
      Linux currently has two models for block devices:
      
      - The classic request_fn based approach, where drivers use struct
        request units for IO. The block layer provides various helper
        functionalities to let drivers share code, things like tag
        management, timeout handling, queueing, etc.
      
      - The "stacked" approach, where a driver squeezes in between the
        block layer and IO submitter. Since this bypasses the IO stack,
        driver generally have to manage everything themselves.
      
      With drivers being written for new high IOPS devices, the classic
      request_fn based driver doesn't work well enough. The design dates
      back to when both SMP and high IOPS was rare. It has problems with
      scaling to bigger machines, and runs into scaling issues even on
      smaller machines when you have IOPS in the hundreds of thousands
      per device.
      
      The stacked approach is then most often selected as the model
      for the driver. But this means that everybody has to re-invent
      everything, and along with that we get all the problems again
      that the shared approach solved.
      
      This commit introduces blk-mq, block multi queue support. The
      design is centered around per-cpu queues for queueing IO, which
      then funnel down into x number of hardware submission queues.
      We might have a 1:1 mapping between the two, or it might be
      an N:M mapping. That all depends on what the hardware supports.
      
      blk-mq provides various helper functions, which include:
      
      - Scalable support for request tagging. Most devices need to
        be able to uniquely identify a request both in the driver and
        to the hardware. The tagging uses per-cpu caches for freed
        tags, to enable cache hot reuse.
      
      - Timeout handling without tracking request on a per-device
        basis. Basically the driver should be able to get a notification,
        if a request happens to fail.
      
      - Optional support for non 1:1 mappings between issue and
        submission queues. blk-mq can redirect IO completions to the
        desired location.
      
      - Support for per-request payloads. Drivers almost always need
        to associate a request structure with some driver private
        command structure. Drivers can tell blk-mq this at init time,
        and then any request handed to the driver will have the
        required size of memory associated with it.
      
      - Support for merging of IO, and plugging. The stacked model
        gets neither of these. Even for high IOPS devices, merging
        sequential IO reduces per-command overhead and thus
        increases bandwidth.
      
      For now, this is provided as a potential 3rd queueing model, with
      the hope being that, as it matures, it can replace both the classic
      and stacked model. That would get us back to having just 1 real
      model for block devices, leaving the stacked approach to dm/md
      devices (as it was originally intended).
      
      Contributions in this patch from the following people:
      
      Shaohua Li <shli@fusionio.com>
      Alexander Gordeev <agordeev@redhat.com>
      Christoph Hellwig <hch@infradead.org>
      Mike Christie <michaelc@cs.wisc.edu>
      Matias Bjorling <m@bjorling.me>
      Jeff Moyer <jmoyer@redhat.com>
      Acked-by: default avatarChristoph Hellwig <hch@lst.de>
      Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
      320ae51f