Re: [PATCH 11/19] bcache: Subtract dirty sectors of thin flash from cache_sectors in calculating writeback rate

On 2017/7/13 下午12:12, Eric Wheeler wrote: > On Tue, 11 Jul 2017, tang.jun...@zte.com.cn wrote: > >>> Based on the above implementation, non-dirty space from flash only >>> bcache device will mislead writeback rate calculation too. So I suggest >>> to subtract all buckets size from all flash only

Re: [PATCH 12/19] bcache: update bucket_in_use periodically

On Tue, 11 Jul 2017, Coly Li wrote: > On 2017/7/11 下午1:39, tang.jun...@zte.com.cn wrote: > > Compared to bucket depletion, resulting in hanging dead, > > It is worthy to consumes a little time to update the bucket_in_use. > > If you have any better solution, please show to us, > > We should solve

Re: Re: [PATCH 11/19] bcache: Subtract dirty sectors of thin flash from cache_sectors in calculating writeback rate

On Tue, 11 Jul 2017, tang.jun...@zte.com.cn wrote: > > Based on the above implementation, non-dirty space from flash only > > bcache device will mislead writeback rate calculation too. So I suggest > > to subtract all buckets size from all flash only bcache devices. Then it > > might be something

Re: [PATCH 10/19] bcache: initialize stripe_sectors_dirty correctly for thin flash device

On Sun, 2 Jul 2017, Coly Li wrote: > On 2017/7/1 上午4:42, bca...@lists.ewheeler.net wrote: > > From: Tang Junhui > > > > Thin flash device does not initialize stripe_sectors_dirty correctly, this > > patch fixes this issue. > > Hi Junhui, > > Could you please explain

Re: [PATCH 04/19] bcache: fix wrong cache_misses statistics

On Sun, 2 Jul 2017, Coly Li wrote: > On 2017/7/1 上午4:42, bca...@lists.ewheeler.net wrote: > > From: Tang Junhui > > > > Some missed IOs are not counted into cache_misses, this patch fix this > > issue. > > Could you please explain more about, > - which kind of missed

Re: [PATCH] [PATCH v2] bcache: fix calling ida_simple_remove() with incorrect minor

Tang, Please resend. This patch seems to be malformed. -- Eric Wheeler On Thu, 6 Jul 2017, tang.jun...@zte.com.cn wrote: > From: Tang Junhui > > bcache called ida_simple_remove() with minor which have multiplied by > BCACHE_MINORS, it would cause minor wrong release

Re: [PATCH 2/2] md: raid1/raid10: initialize bvec table via bio_add_page()

On Thu, Jul 13 2017, Ming Lei wrote: > On Thu, Jul 13, 2017 at 10:01:33AM +1000, NeilBrown wrote: >> On Wed, Jul 12 2017, Ming Lei wrote: >> >> > We will support multipage bvec soon, so initialize bvec >> > table using the standardy way instead of writing the >> > talbe directly. Otherwise it

Re: [PATCH 1/2] md: remove 'idx' from 'struct resync_pages'

On Thu, Jul 13, 2017 at 09:58:41AM +1000, NeilBrown wrote: > On Wed, Jul 12 2017, Ming Lei wrote: > > > bio_add_page() won't fail for resync bio, and the page index for each > > bio is same, so remove it. > > > > More importantly the 'idx' of 'struct resync_pages' is initialized in > > mempool

Re: [PATCH 2/2] md: raid1/raid10: initialize bvec table via bio_add_page()

On Wed, Jul 12, 2017 at 02:16:08AM -0700, Christoph Hellwig wrote: > On Wed, Jul 12, 2017 at 04:29:12PM +0800, Ming Lei wrote: > > We will support multipage bvec soon, so initialize bvec > > table using the standardy way instead of writing the > > talbe directly. Otherwise it won't work any more

Re: [PATCH 2/2] md: raid1/raid10: initialize bvec table via bio_add_page()

On Thu, Jul 13, 2017 at 10:01:33AM +1000, NeilBrown wrote: > On Wed, Jul 12 2017, Ming Lei wrote: > > > We will support multipage bvec soon, so initialize bvec > > table using the standardy way instead of writing the > > talbe directly. Otherwise it won't work any more once > > multipage bvec is

Re: [PATCH v3 05/14] md: raid1: don't use bio's vec table to manage resync pages

On Wed, Jul 12, 2017 at 09:30:50AM -0700, Shaohua Li wrote: > On Wed, Jul 12, 2017 at 09:40:10AM +0800, Ming Lei wrote: > > On Tue, Jul 11, 2017 at 7:14 AM, NeilBrown wrote: > > > On Mon, Jul 10 2017, Shaohua Li wrote: > > > > > >> On Mon, Jul 10, 2017 at 03:25:41PM +0800, Ming

Re: [PATCH] bcache: only recovery I/O error for writethrough mode

On Wed, 12 Jul 2017, Coly Li wrote: > On 2017/7/12 上午10:01, tang.jun...@zte.com.cn wrote: > >>I meant "it is very necessary for data base applications which always > >>use *writeback* mode and not switch to other mode during all their > >>online time." ^_^ > > > > I know, it is necessary, but

Re: [PATCH 2/2] md: raid1/raid10: initialize bvec table via bio_add_page()

On Wed, Jul 12 2017, Ming Lei wrote: > We will support multipage bvec soon, so initialize bvec > table using the standardy way instead of writing the > talbe directly. Otherwise it won't work any more once > multipage bvec is enabled. > > Acked-by: Guoqing Jiang >

Re: [PATCH 1/2] md: remove 'idx' from 'struct resync_pages'

On Wed, Jul 12 2017, Ming Lei wrote: > bio_add_page() won't fail for resync bio, and the page index for each > bio is same, so remove it. > > More importantly the 'idx' of 'struct resync_pages' is initialized in > mempool allocator function, this way is wrong since mempool is only > responsible

Re: [PATCH] elevator: allow specifying elevator by config boot param for blk-mq devices

On 07/12/2017 12:57 PM, Alex Ivanov wrote: > It's now makes sense to use elevator boot argument when blk-mq is in use, > since there is now a bunch of schedulers for it (deadline, kyber, bfq, none). No, that boot option was a mistake, let's not propagate that to mq scheduling as well. -- Jens

Re: [PATCH V5 00/11] blktrace: output cgroup info

On 07/12/2017 12:49 PM, Shaohua Li wrote: > From: Shaohua Li > > Hi, > > Currently blktrace isn't cgroup aware. blktrace prints out task name of > current > context, but the task of current context isn't always in the cgroup where the > BIO comes from. We can't use task name to

[PATCH] elevator: allow specifying elevator by config boot param for blk-mq devices

It's now makes sense to use elevator boot argument when blk-mq is in use, since there is now a bunch of schedulers for it (deadline, kyber, bfq, none). Signed-off-by: Alex Ivanov --- block/elevator.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

[PATCH V5 04/11] kernfs: don't set dentry->d_fsdata

From: Shaohua Li When working on adding exportfs operations in kernfs, I found it's hard to initialize dentry->d_fsdata in the exportfs operations. Looks there is no way to do it without race condition. Look at the kernfs code closely, there is no point to set dentry->d_fsdata.

[PATCH V5 01/11] kernfs: use idr instead of ida to manage inode number

From: Shaohua Li kernfs uses ida to manage inode number. The problem is we can't get kernfs_node from inode number with ida. Switching to use idr, next patch will add an API to get kernfs_node from inode number. Acked-by: Tejun Heo Acked-by: Greg Kroah-Hartman

[PATCH V5 10/11] blktrace: add an option to allow displaying cgroup path

From: Shaohua Li By default we output cgroup id in blktrace. This adds an option to display cgroup path. Since get cgroup path is a relativly heavy operation, we don't enable it by default. with the option enabled, blktrace will output something like this: dd-1353 [007] d..2

[PATCH V5 02/11] kernfs: implement i_generation

From: Shaohua Li Set i_generation for kernfs inode. This is required to implement exportfs operations. The generation is 32-bit, so it's possible the generation wraps up and we find stale files. To reduce the posssibility, we don't reuse inode numer immediately. When the inode

[PATCH V5 06/11] kernfs: add exportfs operations

From: Shaohua Li Now we have the facilities to implement exportfs operations. The idea is cgroup can export the fhandle info to userspace, then userspace uses fhandle to find the cgroup name. Another example is userspace can get fhandle for a cgroup and BPF uses the fhandle to

[PATCH V5 09/11] block: always attach cgroup info into bio

From: Shaohua Li blkcg_bio_issue_check() already gets blkcg for a BIO. bio_associate_blkcg() uses a percpu refcounter, so it's a very cheap operation. There is no point we don't attach the cgroup info into bio at blkcg_bio_issue_check. This also makes blktrace outputs correct cgroup

[PATCH V5 05/11] kernfs: introduce kernfs_node_id

From: Shaohua Li inode number and generation can identify a kernfs node. We are going to export the identification by exportfs operations, so put ino and generation into a separate structure. It's convenient when later patches use the identification. Acked-by: Greg Kroah-Hartman

[PATCH V5 11/11] block: use standard blktrace API to output cgroup info for debug notes

From: Shaohua Li Currently cfq/bfq/blk-throttle output cgroup info in trace in their own way. Now we have standard blktrace API for this, so convert them to use it. Note, this changes the behavior a little bit. cgroup info isn't output by default, we only do this with 'blk_cgroup'

[PATCH V5 00/11] blktrace: output cgroup info

From: Shaohua Li Hi, Currently blktrace isn't cgroup aware. blktrace prints out task name of current context, but the task of current context isn't always in the cgroup where the BIO comes from. We can't use task name to find out IO cgroup. For example, Writeback BIOs always comes

[PATCH 1/2] block: delete bio_uninit in blockdev

From: Shaohua Li This is to partially revert commit 9ae3b3f52c62 (block: provide bio_uninit() free freeing integrity/task associations). With commit b222dd2 (block: call bio_uninit in bio_endio) and 7c20f11(bio-integrity: stop abusing bi_end_io), integrity/cgroup info is freed in

[PATCH 2/2] block: delete bio_uninit

From: Shaohua Li bio_uninit only calls bio_disassociate_task now. It's meaningless to have a wrap. Cc: Christoph Hellwig Signed-off-by: Shaohua Li --- block/bio.c | 11 +++ 1 file changed, 3 insertions(+), 8 deletions(-) diff --git

Re: [PATCH] blk-mq-debugfs: add mapping show for hw queue to cpu

On Wed, Jul 12, 2017 at 10:57:37AM -0600, Jens Axboe wrote: > On 07/12/2017 10:54 AM, weiping zhang wrote: > > A mapping show as following: > > > > hctxcpus > > hctx0 0 1 > > hctx1 2 > > hctx2 3 > > hctx3 4 5 > >

Re: linux-next scsi-mq hang in suspend-resume

ests as a > testlist. I'm assuming that it creates the correct amount or pattern > of actions to the device. The testlist consists of the following > lines: > > igt@gem_exec_gttfill@basic > igt@gem_exec_suspend@basic-s3 > > Kernel option scsi_mod.use_blk_mq=0 hides th

Re: [PATCH v3 05/14] md: raid1: don't use bio's vec table to manage resync pages

On Wed, Jul 12, 2017 at 09:40:10AM +0800, Ming Lei wrote: > On Tue, Jul 11, 2017 at 7:14 AM, NeilBrown wrote: > > On Mon, Jul 10 2017, Shaohua Li wrote: > > > >> On Mon, Jul 10, 2017 at 03:25:41PM +0800, Ming Lei wrote: > >>> On Mon, Jul 10, 2017 at 02:38:19PM +1000, NeilBrown

Re: [PATCH V2] block: call bio_uninit in bio_endio

On Wed, Jul 12, 2017 at 09:25:17AM +0200, Christoph Hellwig wrote: > On Mon, Jul 10, 2017 at 11:40:17AM -0700, Shaohua Li wrote: > > bio_free isn't a good place to free cgroup info. There are a > > lot of cases bio is allocated in special way (for example, in stack) and > > never gets called by

Re: [PATCH 4/6] blk-mq: use EWMA to estimate congestion threshold

On Wed, 2017-07-12 at 10:30 +0800, Ming Lei wrote: > On Tue, Jul 11, 2017 at 12:25:16PM -0600, Jens Axboe wrote: > > What happens with fluid congestion boundaries, with shared tags? > > The approach in this patch should work, but the threshold may not > be accurate in this way, one simple method

Re: [PATCH 2/6] SCSI: use blk_mq_run_hw_queues() in scsi_kick_queue()

On Wed, 2017-07-12 at 11:15 +0800, Ming Lei wrote: > On Tue, Jul 11, 2017 at 07:57:53PM +, Bart Van Assche wrote: > > On Wed, 2017-07-12 at 02:20 +0800, Ming Lei wrote: > > > Now SCSI won't stop queue, and not necessary to use > > > blk_mq_start_hw_queues(), so switch to blk_mq_run_hw_queues()

linux-next scsi-mq hang in suspend-resume

lines: igt@gem_exec_gttfill@basic igt@gem_exec_suspend@basic-s3 Kernel option scsi_mod.use_blk_mq=0 hides the issue on testhosts. Configuration option was copied over on testhosts and 20170712 was re- tested, that's why today looks so much greener. More information including traces and reproduction

Re: [PATCH] block, bfq: dispatch request to prevent queue stalling after the request completion

> Il giorno 12 lug 2017, alle ore 16:22, Jens Axboe ha > scritto: > > On 07/12/2017 03:41 AM, Paolo Valente wrote: >> >>> Il giorno 11 lug 2017, alle ore 15:58, Hou Tao ha >>> scritto: >>> >>> There are mq devices (eg., virtio-blk, nbd and loopback)

Re: [PATCH] block, bfq: dispatch request to prevent queue stalling after the request completion

On 07/12/2017 03:41 AM, Paolo Valente wrote: > >> Il giorno 11 lug 2017, alle ore 15:58, Hou Tao ha >> scritto: >> >> There are mq devices (eg., virtio-blk, nbd and loopback) which don't >> invoke blk_mq_run_hw_queues() after the completion of a request. >> If bfq is enabled

Re: Lots of new warnings with gcc-7.1.1

On Wed, Jul 12, 2017 at 3:10 PM, Greg Kroah-Hartman wrote: > On Tue, Jul 11, 2017 at 03:35:15PM -0700, Linus Torvalds wrote: >> [ Very random list of maintainers and mailing lists, at least >> partially by number of warnings generated by gcc-7.1.1 that is then >>

Re: Lots of new warnings with gcc-7.1.1

On Wed, Jul 12, 2017 at 5:41 AM, Linus Torvalds wrote: > > We also have about a bazillion > > warning: ‘*’ in boolean context, suggest ‘&&’ instead > > warnings in drivers/ata/libata-core.c, all due to a single macro that > uses a pattern that gcc-7.1.1 doesn't

Re: Lots of new warnings with gcc-7.1.1

Em Tue, 11 Jul 2017 15:35:15 -0700 Linus Torvalds escreveu: > [ Very random list of maintainers and mailing lists, at least > partially by number of warnings generated by gcc-7.1.1 that is then > correlated with the get_maintainers script ] Under drivers/media, I

Re: [PATCH] block, bfq: dispatch request to prevent queue stalling after the request completion

On 2017/7/12 17:41, Paolo Valente wrote: > >> Il giorno 11 lug 2017, alle ore 15:58, Hou Tao ha >> scritto: >> >> There are mq devices (eg., virtio-blk, nbd and loopback) which don't >> invoke blk_mq_run_hw_queues() after the completion of a request. >> If bfq is enabled

Re: [PATCH] block, bfq: dispatch request to prevent queue stalling after the request completion

> Il giorno 11 lug 2017, alle ore 15:58, Hou Tao ha > scritto: > > There are mq devices (eg., virtio-blk, nbd and loopback) which don't > invoke blk_mq_run_hw_queues() after the completion of a request. > If bfq is enabled on these devices and the slice_idle attribute or >

Re: [PATCH 09/19 v2] bcache: update bio->bi_opf bypass/writeback REQ_ flag hints

On 2017/7/11 上午11:48, Coly Li wrote: > On 2017/7/6 下午11:24, Christoph Hellwig wrote: >> On Thu, Jul 06, 2017 at 03:35:48PM +0800, Coly Li wrote: >>> Then gfs2 breaks the above rule ? in gfs2_metapath_ra() and >>> gfs2_dir_readahead(), only REQ_META is used in submit_bh(). It seems an >>> extra

Re: [PATCH 2/2] md: raid1/raid10: initialize bvec table via bio_add_page()

On Wed, Jul 12, 2017 at 04:29:12PM +0800, Ming Lei wrote: > We will support multipage bvec soon, so initialize bvec > table using the standardy way instead of writing the > talbe directly. Otherwise it won't work any more once > multipage bvec is enabled. It seems to me like these callsites also

Re: [PATCH] block, bfq: fix typos in comments about B-WF2Q+ algorithm

> Il giorno 12 lug 2017, alle ore 09:25, Hou Tao ha > scritto: > > The start time of eligible entity should be less than or equal to > the current virtual time, and the entity in idle tree has a finish > time being greater than the current virtual time. > Thanks for

[PATCH 2/2] md: raid1/raid10: initialize bvec table via bio_add_page()

We will support multipage bvec soon, so initialize bvec table using the standardy way instead of writing the talbe directly. Otherwise it won't work any more once multipage bvec is enabled. Acked-by: Guoqing Jiang Signed-off-by: Ming Lei ---

[PATCH 1/2] md: remove 'idx' from 'struct resync_pages'

bio_add_page() won't fail for resync bio, and the page index for each bio is same, so remove it. More importantly the 'idx' of 'struct resync_pages' is initialized in mempool allocator function, this way is wrong since mempool is only responsible for allocation, we can't use that for

Re: [PATCH V2] block: call bio_uninit in bio_endio

On Mon, Jul 10, 2017 at 11:40:17AM -0700, Shaohua Li wrote: > bio_free isn't a good place to free cgroup info. There are a > lot of cases bio is allocated in special way (for example, in stack) and > never gets called by bio_put hence bio_free, we are leaking memory. This > patch moves the free to

[PATCH] block, bfq: fix typos in comments about B-WF2Q+ algorithm

The start time of eligible entity should be less than or equal to the current virtual time, and the entity in idle tree has a finish time being greater than the current virtual time. Signed-off-by: Hou Tao --- block/bfq-iosched.h | 2 +- block/bfq-wf2q.c| 2 +- 2 files