linux/mm/backing-dev.c, branch v3.9

bdi: allow block devices to say that they require stable page writes

2013-02-22T01:22:19Z

This patchset ("stable page writes, part 2") makes some key modifications to the original 'stable page writes' patchset. First, it provides creators (devices and filesystems) of a backing_dev_info a flag that declares whether or not it is necessary to ensure that page contents cannot change during writeout. It is no longer assumed that this is true of all devices (which was never true anyway). Second, the flag is used to relaxed the wait_on_page_writeback calls so that wait only occurs if the device needs it. Third, it fixes up the remaining disk-backed filesystems to use this improved conditional-wait logic to provide stable page writes on those filesystems. It is hoped that (for people not using checksumming devices, anyway) this patchset will give back unnecessary performance decreases since the original stable page write patchset went into 3.0. Sorry about not fixing it sooner. Complaints were registered by several people about the long write latencies introduced by the original stable page write patchset. Generally speaking, the kernel ought to allocate as little extra memory as possible to facilitate writeout, but for people who simply cannot wait, a second page stability strategy is (re)introduced: snapshotting page contents. The waiting behavior is still the default strategy; to enable page snapshotting, a superblock flag (MS_SNAP_STABLE) must be set. This flag is used to bandaid^Henable stable page writeback on ext3[1], and is not used anywhere else. Given that there are already a few storage devices and network FSes that have rolled their own page stability wait/page snapshot code, it would be nice to move towards consolidating all of these. It seems possible that iscsi and raid5 may wish to use the new stable page write support to enable zero-copy writeout. Thank you to Jan Kara for helping fix a couple more filesystems. Per Andrew Morton's request, here are the result of using dbench to measure latencies on ext2: 3.8.0-rc3: Operation Count AvgLat MaxLat ---------------------------------------- WriteX 109347 0.028 59.817 ReadX 347180 0.004 3.391 Flush 15514 29.828 287.283 Throughput 57.429 MB/sec 4 clients 4 procs max_latency=287.290 ms 3.8.0-rc3 + patches: WriteX 105556 0.029 4.273 ReadX 335004 0.005 4.112 Flush 14982 30.540 298.634 Throughput 55.4496 MB/sec 4 clients 4 procs max_latency=298.650 ms As you can see, for ext2 the maximum write latency decreases from ~60ms on a laptop hard disk to ~4ms. I'm not sure why the flush latencies increase, though I suspect that being able to dirty pages faster gives the flusher more work to do. On ext4, the average write latency decreases as well as all the maximum latencies: 3.8.0-rc3: WriteX 85624 0.152 33.078 ReadX 272090 0.010 61.210 Flush 12129 36.219 168.260 Throughput 44.8618 MB/sec 4 clients 4 procs max_latency=168.276 ms 3.8.0-rc3 + patches: WriteX 86082 0.141 30.928 ReadX 273358 0.010 36.124 Flush 12214 34.800 165.689 Throughput 44.9941 MB/sec 4 clients 4 procs max_latency=165.722 ms XFS seems to exhibit similar latency improvements as ext2: 3.8.0-rc3: WriteX 125739 0.028 104.343 ReadX 399070 0.005 4.115 Flush 17851 25.004 131.390 Throughput 66.0024 MB/sec 4 clients 4 procs max_latency=131.406 ms 3.8.0-rc3 + patches: WriteX 123529 0.028 6.299 ReadX 392434 0.005 4.287 Flush 17549 25.120 188.687 Throughput 64.9113 MB/sec 4 clients 4 procs max_latency=188.704 ms ...and btrfs, just to round things out, also shows some latency decreases: 3.8.0-rc3: WriteX 67122 0.083 82.355 ReadX 212719 0.005 2.828 Flush 9547 47.561 147.418 Throughput 35.3391 MB/sec 4 clients 4 procs max_latency=147.433 ms 3.8.0-rc3 + patches: WriteX 64898 0.101 71.631 ReadX 206673 0.005 7.123 Flush 9190 47.963 219.034 Throughput 34.0795 MB/sec 4 clients 4 procs max_latency=219.044 ms Before this patchset, all filesystems would block, regardless of whether or not it was necessary. ext3 would wait, but still generate occasional checksum errors. The network filesystems were left to do their own thing, so they'd wait too. After this patchset, all the disk filesystems except ext3 and btrfs will wait only if the hardware requires it. ext3 (if necessary) snapshots pages instead of blocking, and btrfs provides its own bdi so the mm will never wait. Network filesystems haven't been touched, so either they provide their own wait code, or they don't block at all. The blocking behavior is back to what it was before 3.0 if you don't have a disk requiring stable page writes. This patchset has been tested on 3.8.0-rc3 on x64 with ext3, ext4, and xfs. I've spot-checked 3.8.0-rc4 and seem to be getting the same results as -rc3. [1] The alternative fixes to ext3 include fixing the locking order and page bit handling like we did for ext4 (but then why not just use ext4?), or setting PG_writeback so early that ext3 becomes extremely slow. I tried that, but the number of write()s I could initiate dropped by nearly an order of magnitude. That was a bit much even for the author of the stable page series! :) This patch: Creates a per-backing-device flag that tracks whether or not pages must be held immutable during writeout. Eventually it will be used to waive wait_for_page_writeback() if nothing requires stable pages. Signed-off-by: Darrick J. Wong Reviewed-by: Jan Kara Cc: Adrian Hunter Cc: Andy Lutomirski Cc: Artem Bityutskiy Cc: Joel Becker Cc: Mark Fasheh Cc: Steven Whitehouse Cc: Jens Axboe Cc: Eric Van Hensbergen Cc: Ron Minnich Cc: Latchesar Ionkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

Revert "bdi: add a user-tunable cpu_list for the bdi flusher threads"

2012-12-17T19:29:09Z

This reverts commit 8fa72d234da9b6b473bbb1f74d533663e4996e6b. People disagree about how this should be done, so let's revert this for now so that nobody starts using the new tuning interface. Tejun is thinking about a more generic interface for thread pool affinity. Requested-by: Tejun Heo Acked-by: Jeff Moyer Acked-by: Jens Axboe Signed-off-by: Linus Torvalds

bdi: add a user-tunable cpu_list for the bdi flusher threads

2012-12-05T19:17:21Z

In realtime environments, it may be desirable to keep the per-bdi flusher threads from running on certain cpus. This patch adds a cpu_list file to /sys/class/bdi/* to enable this. The default is to tie the flusher threads to the same numa node as the backing device (though I could be convinced to make it a mask of all cpus to avoid a change in behaviour). Thanks to Jeremy Eder for the original idea. Signed-off-by: Jeff Moyer Signed-off-by: Jens Axboe

backing-dev: use kstrto* in preference to simple_strtoul

2012-08-25T08:58:14Z

Fix checkpatch warnings: WARNING: consider using kstrto* in preference to simple_strtoul for the below sys entry parsers: /sys/block//bdi/read_ahead_kb /sys/block//bdi/max_ratio /sys/block//bdi/min_ratio Signed-off-by: Namjae Jeon Signed-off-by: Vivek Trivedi

vfs: kill write_super and sync_supers

2012-08-03T21:24:44Z

Finally we can kill the 'sync_supers' kernel thread along with the '->write_super()' superblock operation because all the users are gone. Now every file-system is supposed to self-manage own superblock and its dirty state. The nice thing about killing this thread is that it improves power management. Indeed, 'sync_supers' is a source of monotonic system wake-ups - it woke up every 5 seconds no matter what - even if there were no dirty superblocks and even if there were no file-systems using this service (e.g., btrfs and journalled ext4 do not need it). So it was wasting power most of the time. And because the thread was in the core of the kernel, all systems had to have it. So I am quite happy to make it go away. Interestingly, this thread is a left-over from the pdflush kernel thread which was a self-forking kernel thread responsible for all the write-back in old Linux kernels. It was turned into per-block device BDI threads, and 'sync_supers' was a left-over. Thus, R.I.P, pdflush as well. Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro

mm: prepare for removal of obsolete /proc/sys/vm/nr_pdflush_threads

2012-08-01T01:42:40Z

Since per-BDI flusher threads were introduced in 2.6, the pdflush mechanism is not used any more. But the old interface exported through /proc/sys/vm/nr_pdflush_threads still exists and is obviously useless. For back-compatibility, printk warning information and return 2 to notify the users that the interface is removed. Signed-off-by: Wanpeng Li Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

block: Convert BDI proportion calculations to flexible proportions

2012-06-08T23:37:56Z

Convert calculations of proportion of writeback each bdi does to new flexible proportion code. That allows us to use aging period of fixed wallclock time which gives better proportion estimates given the hugely varying throughput of different devices. Acked-by: Peter Zijlstra Signed-off-by: Jan Kara Signed-off-by: Fengguang Wu

backing-dev: fix wakeup timer races with bdi_unregister()

2012-02-01T08:52:49Z

While 7a401a972df8e18 ("backing-dev: ensure wakeup_timer is deleted") addressed the problem of the bdi being freed with a queued wakeup timer, there are other races that could happen if the wakeup timer expires after/during bdi_unregister(), before bdi_destroy() is called. wakeup_timer_fn() could attempt to wakeup a task which has already has been freed, or could access a NULL bdi->dev via the wake_forker_thread tracepoint. Cc: Cc: Jens Axboe Reported-by: Chanho Min Reviewed-by: Namjae Jeon Signed-off-by: Rabin Vincent Signed-off-by: Wu Fengguang

freezer: implement and use kthread_freezable_should_stop()

2011-11-21T20:32:23Z

Writeback and thinkpad_acpi have been using thaw_process() to prevent deadlock between the freezer and kthread_stop(); unfortunately, this is inherently racy - nothing prevents freezing from happening between thaw_process() and kthread_stop(). This patch implements kthread_freezable_should_stop() which enters refrigerator if necessary but is guaranteed to return if kthread_stop() is invoked. Both thaw_process() users are converted to use the new function. Note that this deadlock condition exists for many of freezable kthreads. They need to be converted to use the new should_stop or freezable workqueue. Tested with synthetic test case. Signed-off-by: Tejun Heo Acked-by: Henrique de Moraes Holschuh Cc: Jens Axboe Cc: Oleg Nesterov

backing-dev: ensure wakeup_timer is deleted

2011-11-11T12:29:04Z

bdi_prune_sb() in bdi_unregister() attempts to removes the bdi links from all super_blocks and then del_timer_sync() the writeback timer. However, this can race with __mark_inode_dirty(), leading to bdi_wakeup_thread_delayed() rearming the writeback timer on the bdi we're unregistering, after we've called del_timer_sync(). This can end up with the bdi being freed with an active timer inside it, as in the case of the following dump after the removal of an SD card. Fix this by redoing the del_timer_sync() in bdi_destory(). ------------[ cut here ]------------ WARNING: at /home/rabin/kernel/arm/lib/debugobjects.c:262 debug_print_object+0x9c/0xc8() ODEBUG: free active (active state 0) object type: timer_list hint: wakeup_timer_fn+0x0/0x180 Modules linked in: Backtrace: [] (dump_backtrace+0x0/0x110) from [] (dump_stack+0x18/0x1c) r6:c02bc638 r5:00000106 r4:c79f5d18 r3:00000000 [] (dump_stack+0x0/0x1c) from [] (warn_slowpath_common+0x54/0x6c) [] (warn_slowpath_common+0x0/0x6c) from [] (warn_slowpath_fmt+0x38/0x40) r8:20000013 r7:c780c6f0 r6:c031613c r5:c780c6f0 r4:c02b1b29 r3:00000009 [] (warn_slowpath_fmt+0x0/0x40) from [] (debug_print_object+0x9c/0xc8) r3:c02b1b29 r2:c02bc662 [] (debug_print_object+0x0/0xc8) from [] (debug_check_no_obj_freed+0xac/0x1dc) r6:c7964000 r5:00000001 r4:c7964000 [] (debug_check_no_obj_freed+0x0/0x1dc) from [] (kmem_cache_free+0x88/0x1f8) [] (kmem_cache_free+0x0/0x1f8) from [] (blk_release_queue+0x70/0x78) [] (blk_release_queue+0x0/0x78) from [] (kobject_release+0x70/0x84) r5:c79641f0 r4:c796420c [] (kobject_release+0x0/0x84) from [] (kref_put+0x68/0x80) r7:00000083 r6:c74083d0 r5:c015289c r4:c796420c [] (kref_put+0x0/0x80) from [] (kobject_put+0x48/0x5c) r5:c79643b4 r4:c79641f0 [] (kobject_put+0x0/0x5c) from [] (blk_cleanup_queue+0x68/0x74) r4:c7964000 [] (blk_cleanup_queue+0x0/0x74) from [] (mmc_blk_put+0x78/0xe8) r5:00000000 r4:c794c400 [] (mmc_blk_put+0x0/0xe8) from [] (mmc_blk_release+0x24/0x38) r5:c794c400 r4:c0322824 [] (mmc_blk_release+0x0/0x38) from [] (__blkdev_put+0xe8/0x170) r5:c78d5e00 r4:c74083c0 [] (__blkdev_put+0x0/0x170) from [] (blkdev_put+0x11c/0x12c) r8:c79f5f70 r7:00000001 r6:c74083d0 r5:00000083 r4:c74083c0 r3:00000000 [] (blkdev_put+0x0/0x12c) from [] (kill_block_super+0x60/0x6c) r7:c7942300 r6:c79f4000 r5:00000083 r4:c74083c0 [] (kill_block_super+0x0/0x6c) from [] (deactivate_locked_super+0x44/0x70) r6:c79f4000 r5:c031af64 r4:c794dc00 r3:c00b06c4 [] (deactivate_locked_super+0x0/0x70) from [] (deactivate_super+0x6c/0x70) r5:c794dc00 r4:c794dc00 [] (deactivate_super+0x0/0x70) from [] (mntput_no_expire+0x188/0x194) r5:c794dc00 r4:c7942300 [] (mntput_no_expire+0x0/0x194) from [] (sys_umount+0x2e4/0x310) r6:c7942300 r5:00000000 r4:00000000 r3:00000000 [] (sys_umount+0x0/0x310) from [] (ret_fast_syscall+0x0/0x30) ---[ end trace e5c83c92ada51c76 ]--- Cc: stable@kernel.org Signed-off-by: Rabin Vincent Signed-off-by: Linus Walleij Signed-off-by: Jens Axboe