linux-stable.git/fs/nfs/blocklayout, branch linux-3.3.y Linux kernel stable tree pnfsblock: alloc short extent before submit bio 2012-01-12T21:52:10+00:00 Peng Tao bergwolf@gmail.com 2012-01-12T15:18:46+00:00 7c5465d6ccd759caa959828e2add5603518dafc4 As discussed earlier, it is better for block client to allocate memory for tracking extents state before submitting bio. So the patch does it by allocating a short_extent for every INVALID extent touched by write pagelist and for every zeroing page we created, saving them in layout header. Then in end_io we can just use them to create commit list items and avoid memory allocation there. Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
As discussed earlier, it is better for block client to allocate memory for
tracking extents state before submitting bio. So the patch does it by allocating
a short_extent for every INVALID extent touched by write pagelist and for
every zeroing page we created, saving them in layout header. Then in end_io we
can just use them to create commit list items and avoid memory allocation there.

Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfsblock: remove rpc_call_ops from struct parallel_io 2012-01-12T21:52:10+00:00 Peng Tao bergwolf@gmail.com 2012-01-12T15:18:44+00:00 c0411a94a8f318379464e29dd81db806249dbca6 block layout can just make use of generic read/write_done. Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
block layout can just make use of generic read/write_done.

Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfsblock: move find lock page logic out of bl_write_pagelist 2012-01-12T21:52:10+00:00 Peng Tao bergwolf@gmail.com 2012-01-12T15:18:42+00:00 72c508879979522de347bcec706507e00d7c443d Also avoid unnecessary lock_page if page is handled by others. Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
Also avoid unnecessary lock_page if page is handled by others.

Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfsblock: cleanup bl_mark_sectors_init 2012-01-12T21:52:09+00:00 Peng Tao bergwolf@gmail.com 2012-01-12T15:18:40+00:00 60c52e3a72fda10e82f38b6f979956eb2dcb3d4e It does not need to manipulate on partial initialized blocks. Writeback code takes care of it. Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
It does not need to manipulate on partial initialized blocks.
Writeback code takes care of it.

Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfsblock: limit bio page count 2012-01-12T21:39:05+00:00 Peng Tao bergwolf@gmail.com 2012-01-12T15:18:48+00:00 74a6eeb44ca6174d9cc93b9b8b4d58211c57bc80 One bio can have at most BIO_MAX_PAGES pages. We should limit it bec otherwise bio_alloc will fail when there are many pages in one read/write_pagelist. Cc: <stable@vger.kernel.org> #3.1+ Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
One bio can have at most BIO_MAX_PAGES pages. We should limit it bec otherwise
bio_alloc will fail when there are many pages in one read/write_pagelist.

Cc: <stable@vger.kernel.org> #3.1+
Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfsblock: don't spinlock when freeing block_dev 2012-01-12T21:39:04+00:00 Peng Tao bergwolf@gmail.com 2012-01-12T15:18:47+00:00 93a3844ee0f843b05a1df4b52e1a19ff26b98d24 bl_free_block_dev() may sleep. We can not call it with spinlock held. Besides, there is no need to take bm_lock as we are last user freeing bm_devlist. Cc: <stable@vger.kernel.org> #3.1+ Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
bl_free_block_dev() may sleep. We can not call it with spinlock held.
Besides, there is no need to take bm_lock as we are last user freeing bm_devlist.

Cc: <stable@vger.kernel.org> #3.1+
Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfsblock: clean up _add_entry 2012-01-12T21:38:55+00:00 Peng Tao bergwolf@gmail.com 2012-01-12T15:18:45+00:00 57582b372f63d0f655b1a35b0d306d73d1a46775 It is wrong to kmalloc in _add_entry() as it is inside spinlock. memory should be already allocated _add_entry() is called. Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
It is wrong to kmalloc in _add_entry() as it is inside
spinlock. memory should be already allocated _add_entry() is called.

Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfsblock: set read/write tk_status to pnfs_error 2012-01-12T21:38:51+00:00 Peng Tao bergwolf@gmail.com 2012-01-12T15:18:43+00:00 82b906d6550ee5fe0d5553359b3c9692dd0aed31 To pass the IO status to upper layer. Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
To pass the IO status to upper layer.

Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfsblock: acquire im_lock in _preload_range 2012-01-12T21:38:49+00:00 Peng Tao bergwolf@gmail.com 2012-01-12T15:18:41+00:00 39e567ae36fe03c2b446e1b83ee3d39bea08f90b When calling _add_entry, we should take the im_lock to protect agains other modifiers. Cc: <stable@vger.kernel.org> #3.1+ Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
When calling _add_entry, we should take the im_lock to protect
agains other modifiers.

Cc: <stable@vger.kernel.org> #3.1+
Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfsblock: fix writeback deadlock 2011-10-18T16:08:15+00:00 Peng Tao bergwolf@gmail.com 2011-09-23T01:50:17+00:00 7542274519b3ba87555410c66e8356ac1e3bc9b3 We should check if the sector is already initialized before trying to grab the page from page cache. Otherwise when two pages of the same block are written back by two threads each calling from writepage_locked, it can cause deadlock like bellow. [ 1080.972099] INFO: task kswapd0:25 blocked for more than 120 seconds. [ 1080.972377] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 1080.972812] kswapd0 D ffff88000c4926c0 0 25 2 0x00000000 [ 1080.972816] ffff88000df276b0 0000000000000046 ffff88000df27640 ffffffff81013ba7 [ 1080.972821] ffff88000c492310 ffff88000df27fd8 ffff88000df27fd8 00000000001d3440 [ 1080.972824] ffff88000c378000 ffff88000c492310 ffff8800175d3d40 ffff880017fc75a8 [ 1080.972828] Call Trace: [ 1080.972860] [<ffffffff81013ba7>] ? read_tsc+0x9/0x19 [ 1080.972877] [<ffffffff810e0b23>] ? lock_page+0x2b/0x2b [ 1080.972899] [<ffffffff81475a1d>] io_schedule+0x63/0x7e [ 1080.972902] [<ffffffff810e0b31>] sleep_on_page+0xe/0x12 [ 1080.972905] [<ffffffff81475fe8>] __wait_on_bit_lock+0x46/0x8f [ 1080.972916] [<ffffffff810822d7>] ? lock_release_holdtime.part.7+0x6b/0x72 [ 1080.972919] [<ffffffff810e0af6>] __lock_page+0x66/0x68 [ 1080.972928] [<ffffffff81072705>] ? autoremove_wake_function+0x3d/0x3d [ 1080.972932] [<ffffffff810e0b1f>] lock_page+0x27/0x2b [ 1080.972934] [<ffffffff810e0bcf>] find_lock_page+0x34/0x57 [ 1080.972937] [<ffffffff810e1738>] find_or_create_page+0x34/0x8a [ 1080.972947] [<ffffffffa034245b>] bl_write_pagelist+0x205/0x6da [blocklayoutdriver] [ 1080.972951] [<ffffffffa034145d>] ? bl_free_lseg+0x38/0x38 [blocklayoutdriver] [ 1080.972995] [<ffffffffa02e27b9>] ? nfs_write_rpcsetup+0x118/0x123 [nfs] [ 1080.973033] [<ffffffffa030246b>] pnfs_generic_pg_writepages+0x10b/0x1f4 [nfs] [ 1080.973089] [<ffffffffa02deaae>] nfs_pageio_doio+0x1a/0x43 [nfs] [ 1080.973098] [<ffffffffa02df035>] nfs_pageio_complete+0x16/0x2d [nfs] [ 1080.973108] [<ffffffffa02e2d8f>] nfs_writepage_locked+0xa0/0xbf [nfs] [ 1080.973119] [<ffffffffa02e36a1>] nfs_writepage+0x16/0x2b [nfs] [ 1080.973122] [<ffffffff810e8762>] ? clear_page_dirty_for_io+0x87/0x9a [ 1080.973133] [<ffffffff810efc5b>] shrink_page_list+0x39b/0x6c8 [ 1080.973139] [<ffffffff810f03bb>] shrink_inactive_list+0x22c/0x39e [ 1080.973144] [<ffffffff810822d7>] ? lock_release_holdtime.part.7+0x6b/0x72 [ 1080.973148] [<ffffffff810f0c33>] shrink_zone+0x445/0x588 [ 1080.973152] [<ffffffff810f1a11>] balance_pgdat+0x2c2/0x56b [ 1080.973170] [<ffffffff81254208>] ? __bitmap_weight+0x34/0x80 [ 1080.973175] [<ffffffff810f1f78>] kswapd+0x2be/0x2fa [ 1080.973179] [<ffffffff810726c8>] ? __init_waitqueue_head+0x4b/0x4b [ 1080.973183] [<ffffffff810f1cba>] ? balance_pgdat+0x56b/0x56b [ 1080.973187] [<ffffffff81071f69>] kthread+0xa8/0xb0 [ 1080.973200] [<ffffffff814806b4>] kernel_thread_helper+0x4/0x10 [ 1080.973205] [<ffffffff81071ec1>] ? __init_kthread_worker+0x5a/0x5a [ 1080.973210] [<ffffffff814806b0>] ? gs_change+0x13/0x13 [ 1080.973213] no locks held by kswapd0/25. Signed-off-by: Peng Tao <peng_tao@emc.com> Signed-off-by: Jim Rees <rees@umich.edu> Cc: stable@kernel.org [3.0] Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> 
We should check if the sector is already initialized before
trying to grab the page from page cache. Otherwise when two
pages of the same block are written back by two threads each
calling from writepage_locked, it can cause deadlock like bellow.

 [ 1080.972099] INFO: task kswapd0:25 blocked for more than 120 seconds.
 [ 1080.972377] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
 [ 1080.972812] kswapd0         D ffff88000c4926c0     0    25      2 0x00000000
 [ 1080.972816]  ffff88000df276b0 0000000000000046 ffff88000df27640 ffffffff81013ba7
 [ 1080.972821]  ffff88000c492310 ffff88000df27fd8 ffff88000df27fd8 00000000001d3440
 [ 1080.972824]  ffff88000c378000 ffff88000c492310 ffff8800175d3d40 ffff880017fc75a8
 [ 1080.972828] Call Trace:
 [ 1080.972860]  [<ffffffff81013ba7>] ? read_tsc+0x9/0x19
 [ 1080.972877]  [<ffffffff810e0b23>] ? lock_page+0x2b/0x2b
 [ 1080.972899]  [<ffffffff81475a1d>] io_schedule+0x63/0x7e
 [ 1080.972902]  [<ffffffff810e0b31>] sleep_on_page+0xe/0x12
 [ 1080.972905]  [<ffffffff81475fe8>] __wait_on_bit_lock+0x46/0x8f
 [ 1080.972916]  [<ffffffff810822d7>] ? lock_release_holdtime.part.7+0x6b/0x72
 [ 1080.972919]  [<ffffffff810e0af6>] __lock_page+0x66/0x68
 [ 1080.972928]  [<ffffffff81072705>] ? autoremove_wake_function+0x3d/0x3d
 [ 1080.972932]  [<ffffffff810e0b1f>] lock_page+0x27/0x2b
 [ 1080.972934]  [<ffffffff810e0bcf>] find_lock_page+0x34/0x57
 [ 1080.972937]  [<ffffffff810e1738>] find_or_create_page+0x34/0x8a
 [ 1080.972947]  [<ffffffffa034245b>] bl_write_pagelist+0x205/0x6da [blocklayoutdriver]
 [ 1080.972951]  [<ffffffffa034145d>] ? bl_free_lseg+0x38/0x38 [blocklayoutdriver]
 [ 1080.972995]  [<ffffffffa02e27b9>] ? nfs_write_rpcsetup+0x118/0x123 [nfs]
 [ 1080.973033]  [<ffffffffa030246b>] pnfs_generic_pg_writepages+0x10b/0x1f4 [nfs]
 [ 1080.973089]  [<ffffffffa02deaae>] nfs_pageio_doio+0x1a/0x43 [nfs]
 [ 1080.973098]  [<ffffffffa02df035>] nfs_pageio_complete+0x16/0x2d [nfs]
 [ 1080.973108]  [<ffffffffa02e2d8f>] nfs_writepage_locked+0xa0/0xbf [nfs]
 [ 1080.973119]  [<ffffffffa02e36a1>] nfs_writepage+0x16/0x2b [nfs]
 [ 1080.973122]  [<ffffffff810e8762>] ? clear_page_dirty_for_io+0x87/0x9a
 [ 1080.973133]  [<ffffffff810efc5b>] shrink_page_list+0x39b/0x6c8
 [ 1080.973139]  [<ffffffff810f03bb>] shrink_inactive_list+0x22c/0x39e
 [ 1080.973144]  [<ffffffff810822d7>] ? lock_release_holdtime.part.7+0x6b/0x72
 [ 1080.973148]  [<ffffffff810f0c33>] shrink_zone+0x445/0x588
 [ 1080.973152]  [<ffffffff810f1a11>] balance_pgdat+0x2c2/0x56b
 [ 1080.973170]  [<ffffffff81254208>] ? __bitmap_weight+0x34/0x80
 [ 1080.973175]  [<ffffffff810f1f78>] kswapd+0x2be/0x2fa
 [ 1080.973179]  [<ffffffff810726c8>] ? __init_waitqueue_head+0x4b/0x4b
 [ 1080.973183]  [<ffffffff810f1cba>] ? balance_pgdat+0x56b/0x56b
 [ 1080.973187]  [<ffffffff81071f69>] kthread+0xa8/0xb0
 [ 1080.973200]  [<ffffffff814806b4>] kernel_thread_helper+0x4/0x10
 [ 1080.973205]  [<ffffffff81071ec1>] ? __init_kthread_worker+0x5a/0x5a
 [ 1080.973210]  [<ffffffff814806b0>] ? gs_change+0x13/0x13
 [ 1080.973213] no locks held by kswapd0/25.

Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Jim Rees <rees@umich.edu>
Cc: stable@kernel.org [3.0]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>