Changes in sysfs-class-bdi

eba39236 - mm: document /sys/class/bdi//min_ratio_fine knob

Sat, 19 Nov 2022 00:52:15 +0000

mm: document /sys/class/bdi//min_ratio_fine knobThis documents the new /sys/class/bdi//max_ratio_fine knob.[akpm@linux-foundation.org: fix htmldocs warnings]Link: https://lkml.kernel.org/r/20221119005215.3052436-21-shr@devkernel.ioSigned-off-by: Stefan Roesch Cc: Chris Mason Cc: Jens Axboe Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

54790f30 - mm: document /sys/class/bdi//max_ratio_fine knob

Sat, 19 Nov 2022 00:52:12 +0000

mm: document /sys/class/bdi//max_ratio_fine knobThis documents the new /sys/class/bdi//max_ratio_fine knob.[akpm@linux-foundation.org: fix htmldocs warnings]Link: https://lkml.kernel.org/r/20221119005215.3052436-18-shr@devkernel.ioSigned-off-by: Stefan Roesch Cc: Chris Mason Cc: Jens Axboe Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

9c832a8d - mm: document /sys/class/bdi//min_bytes knob

Sat, 19 Nov 2022 00:52:09 +0000

mm: document /sys/class/bdi//min_bytes knobThis documents the new /sys/class/bdi//min_bytes knob.[akpm@linux-foundation.org: fix htmldocs warnings]Link: https://lkml.kernel.org/r/20221119005215.3052436-15-shr@devkernel.ioSigned-off-by: Stefan Roesch Cc: Chris Mason Cc: Jens Axboe Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

c354d926 - mm: document /sys/class/bdi//max_bytes knob

Sat, 19 Nov 2022 00:52:04 +0000

mm: document /sys/class/bdi//max_bytes knobThis documents the new /sys/class/bdi//max_bytes knob.Link: https://lkml.kernel.org/r/20221119005215.3052436-10-shr@devkernel.ioSigned-off-by: Stefan Roesch Cc: Chris Mason Cc: Jens Axboe Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

16b837eb - mm: document /sys/class/bdi//strict_limit knob

Sat, 19 Nov 2022 00:51:58 +0000

mm: document /sys/class/bdi//strict_limit knobThis documents the new /sys/class/bdi//strict_limit knob.Link: https://lkml.kernel.org/r/20221119005215.3052436-4-shr@devkernel.ioSigned-off-by: Stefan Roesch Cc: Chris Mason Cc: Jens Axboe Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

8a609589 - ABI: sysfs-class-bdi: use What: to describe each property

Mon, 27 Sep 2021 13:59:44 +0000

ABI: sysfs-class-bdi: use What: to describe each propertyInstead of listing all bdi entries inside the description, addone entry for each, just like the remaining ABI files.That allows get_abi.pl script to properly parse it.Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/77e5904dfd275ed2670cd13779e5ef1da96e355c.1632750608.git.mchehab+huawei@kernel.orgSigned-off-by: Greg Kroah-Hartman List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

54a19b4d - docs: ABI: cleanup several ABI documents

Fri, 30 Oct 2020 07:40:50 +0000

docs: ABI: cleanup several ABI documentsThere are some ABI documents that, while they don't generateany warnings, they have issues when parsed by get_abi.pl scripton its output result.Address them, in order to provide a clean output.Reviewed-by: Tom Rix # for fpga-managerReviewed-By: Kajol Jain # for sysfs-bus-event_source-devices-hv_gpci and sysfs-bus-event_source-devices-hv_24x7Acked-by: Jonathan Cameron #for IIOAcked-by: Oded Gabbay # for HabanalabsAcked-by: Vaibhav Jain # for sysfs-bus-papr-pmemAcked-by: Cezary Rojewski # for catptAcked-by: Suzuki K Poulose Acked-by: Ilya Dryomov # for rbdAcked-by: Jonathan Corbet Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/5bc78e5b68ed1e9e39135173857cb2e753be868f.1604042072.git.mchehab+huawei@kernel.orgSigned-off-by: Greg Kroah-Hartman List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

7d311cda - bdi: allow block devices to say that they require stable page writes

Fri, 22 Feb 2013 00:42:48 +0000

bdi: allow block devices to say that they require stable page writesThis patchset ("stable page writes, part 2") makes some keymodifications to the original 'stable page writes' patchset. First, itprovides creators (devices and filesystems) of a backing_dev_info a flagthat declares whether or not it is necessary to ensure that pagecontents cannot change during writeout. It is no longer assumed thatthis is true of all devices (which was never true anyway). Second, theflag is used to relaxed the wait_on_page_writeback calls so that waitonly occurs if the device needs it. Third, it fixes up the remainingdisk-backed filesystems to use this improved conditional-wait logic toprovide 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 theoriginal stable page write patchset went into 3.0. Sorry about notfixing it sooner.Complaints were registered by several people about the long writelatencies introduced by the original stable page write patchset.Generally speaking, the kernel ought to allocate as little extra memoryas possible to facilitate writeout, but for people who simply cannotwait, a second page stability strategy is (re)introduced: snapshottingpage contents. The waiting behavior is still the default strategy; toenable page snapshotting, a superblock flag (MS_SNAP_STABLE) must beset. This flag is used to bandaid^Henable stable page writeback onext3[1], and is not used anywhere else.Given that there are already a few storage devices and network FSes thathave rolled their own page stability wait/page snapshot code, it wouldbe nice to move towards consolidating all of these. It seems possiblethat iscsi and raid5 may wish to use the new stable page write supportto 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 measurelatencies 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 ms3.8.0-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 msAs you can see, for ext2 the maximum write latency decreases from ~60mson a laptop hard disk to ~4ms. I'm not sure why the flush latenciesincrease, though I suspect that being able to dirty pages faster givesthe flusher more work to do.On ext4, the average write latency decreases as well as all the maximumlatencies: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 ms3.8.0-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 msXFS 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 ms3.8.0-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 latencydecreases: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 ms3.8.0-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 msBefore this patchset, all filesystems would block, regardless of whetheror not it was necessary. ext3 would wait, but still generate occasionalchecksum errors. The network filesystems were left to do their ownthing, so they'd wait too.After this patchset, all the disk filesystems except ext3 and btrfs willwait only if the hardware requires it. ext3 (if necessary) snapshotspages instead of blocking, and btrfs provides its own bdi so the mm willnever wait. Network filesystems haven't been touched, so either theyprovide their own wait code, or they don't block at all. The blockingbehavior is back to what it was before 3.0 if you don't have a diskrequiring stable page writes.This patchset has been tested on 3.8.0-rc3 on x64 with ext3, ext4, andxfs. I've spot-checked 3.8.0-rc4 and seem to be getting the sameresults as -rc3.[1] The alternative fixes to ext3 include fixing the locking order andpage bit handling like we did for ext4 (but then why not just useext4?), or setting PG_writeback so early that ext3 becomes extremelyslow. I tried that, but the number of write()s I could initiate droppedby nearly an order of magnitude. That was a bit much even for theauthor of the stable page series! :)This patch:Creates a per-backing-device flag that tracks whether or not pages mustbe held immutable during writeout. Eventually it will be used to waivewait_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 List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

03fb0bce - fuse: fix bdi naming conflict

Fri, 23 May 2008 20:04:19 +0000

fuse: fix bdi naming conflictFuse allocates a separate bdi for each filesystem, and registers themin sysfs with "MAJOR:MINOR" of sb->s_dev (st_dev). This works fine foranon devices normally used by fuse, but can conflict with an alreadyregistered BDI for "fuseblk" filesystems, where sb->s_dev represents areal block device. In particularl this happens if a non-partitioneddevice is being mounted.Fix by registering with a different name for "fuseblk" filesystems.Thanks to Ioan Ionita for the bug report.Signed-off-by: Miklos Szeredi Reported-by: Ioan Ionita Tested-by: Ioan Ionita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

76f1418b - mm: bdi: move statistics to debugfs

Wed, 30 Apr 2008 07:54:36 +0000

mm: bdi: move statistics to debugfsMove BDI statistics to debugfs: /sys/kernel/debug/bdi//statsUse postcore_initcall() to initialize the sysfs class and debugfs,because debugfs is initialized in core_initcall().Update descriptions in ABI documentation.Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

a42dde04 - mm: bdi: allow setting a maximum for the bdi dirty limit

Wed, 30 Apr 2008 07:54:36 +0000

mm: bdi: allow setting a maximum for the bdi dirty limitAdd "max_ratio" to /sys/class/bdi. This indicates the maximum percentage ofthe global dirty threshold allocated to this bdi.[mszeredi@suse.cz] - fix parsing in max_ratio_store(). - export bdi_set_max_ratio() to modules - limit bdi_dirty with bdi->max_ratio - document new sysfs attributeSigned-off-by: Peter Zijlstra Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

189d3c4a - mm: bdi: allow setting a minimum for the bdi dirty limit

Wed, 30 Apr 2008 07:54:35 +0000

mm: bdi: allow setting a minimum for the bdi dirty limitUnder normal circumstances each device is given a part of the total write-backcache that relates to its current avg writeout speed in relation to the otherdevices.min_ratio - allows one to assign a minimum portion of the write-back cache toa particular device. This is useful in situations where you might want toprovide a minimum QoS. (One request for this feature came from flash basedstorage people who wanted to avoid writing out at all costs - they of courseneeded some pdflush hacks as well)max_ratio - allows one to assign a maximum portion of the dirty limit to aparticular device. This is useful in situations where you want to avoid onedevice taking all or most of the write-back cache. Eg. an NFS mount that isprone to get stuck, or a FUSE mount which you don't trust to play fair.Add "min_ratio" to /sys/class/bdi. This indicates the minimum percentage ofthe global dirty threshold allocated to this bdi.[mszeredi@suse.cz] - fix parsing in min_ratio_store() - document new sysfs attributeSigned-off-by: Peter Zijlstra Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi

cf0ca9fe - mm: bdi: export BDI attributes in sysfs

Wed, 30 Apr 2008 07:54:32 +0000

mm: bdi: export BDI attributes in sysfsProvide a place in sysfs (/sys/class/bdi) for the backing_dev_info object.This allows us to see and set the various BDI specific variables.In particular this properly exposes the read-ahead window for all relevantusers and /sys/block//queue/read_ahead_kb should be deprecated.With patient help from Kay Sievers and Greg KH[mszeredi@suse.cz] - split off NFS and FUSE changes into separate patches - document new sysfs attributes under Documentation/ABI - do bdi_class_init as a core_initcall, otherwise the "default" BDI won't be initialized - remove bdi_init_fmt macro, it's not used very much[akpm@linux-foundation.org: fix ia64 warning]Signed-off-by: Peter Zijlstra Cc: Kay Sievers Acked-by: Greg KH Cc: Trond Myklebust Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-class-bdi