Re: [dm-devel] why does __split_and_process_bio use bio_clone_bioset?

2018-06-14 Thread NeilBrown
On Thu, Jun 14 2018, Mike Snitzer wrote: > On Thu, Jun 14 2018 at 2:12P -0400, > Mike Snitzer wrote: > >> On Thu, Jun 14 2018 at 4:19am -0400, >> Christoph Hellwig wrote: >> >> > Hi Neil, >> > >> > In commit 18a25da8 ("dm: ensure bio submission follows a depth-first >> > tree walk") you've a

Re: [dm-devel] why does __split_and_process_bio use bio_clone_bioset?

2018-06-14 Thread Mike Snitzer
On Thu, Jun 14 2018 at 2:12P -0400, Mike Snitzer wrote: > On Thu, Jun 14 2018 at 4:19am -0400, > Christoph Hellwig wrote: > > > Hi Neil, > > > > In commit 18a25da8 ("dm: ensure bio submission follows a depth-first > > tree walk") you've added a call to bio_clone_bioset to > > __split_and_pro

Re: [dm-devel] dm bufio: Reduce dm_bufio_lock contention

2018-06-14 Thread Mikulas Patocka
On Thu, 14 Jun 2018, Michal Hocko wrote: > On Thu 14-06-18 15:18:58, jing xia wrote: > [...] > > PID: 22920 TASK: ffc0120f1a00 CPU: 1 COMMAND: "kworker/u8:2" > > #0 [ffc0282af3d0] __switch_to at ff8008085e48 > > #1 [ffc0282af3f0] __schedule at ff8008850cc8 > > #2 [fff

Re: [dm-devel] why does __split_and_process_bio use bio_clone_bioset?

2018-06-14 Thread Mike Snitzer
On Thu, Jun 14 2018 at 4:19am -0400, Christoph Hellwig wrote: > Hi Neil, > > In commit 18a25da8 ("dm: ensure bio submission follows a depth-first > tree walk") you've added a call to bio_clone_bioset to > __split_and_process_bio. Unlike all other bio splitting code this > actually allocates a

Re: [dm-devel] [bug report] dm verity: add support for forward error correction

2018-06-14 Thread Sami Tolvanen
On Thu, Jun 14, 2018 at 7:33 AM Dan Carpenter wrote: > Apparently, if the read is a blocking read then new_read() returns NULL. It looks like new_read can return NULL only if it's called with NF_GET or NF_PREFETCH. dm_bufio_read calls it with NF_READ, which means it shouldn't return NULL. Someone

[dm-devel] [bug report] dm verity: add support for forward error correction

2018-06-14 Thread Dan Carpenter
Hello Sami Tolvanen, The patch a739ff3f543a: "dm verity: add support for forward error correction" from Dec 3, 2015, leads to the following static checker warning: drivers/md/dm-verity-fec.c:147 fec_decode_bufs() warn: 'par' can also be NULL drivers/md/dm-verity-fec.c 128 sta

[dm-devel] why does __split_and_process_bio use bio_clone_bioset?

2018-06-14 Thread Christoph Hellwig
Hi Neil, In commit 18a25da8 ("dm: ensure bio submission follows a depth-first tree walk") you've added a call to bio_clone_bioset to __split_and_process_bio. Unlike all other bio splitting code this actually allocates a new bio_vec array instead of just splitting the bio and the iterator. I can'

Re: [dm-devel] dm bufio: Reduce dm_bufio_lock contention

2018-06-14 Thread jing xia
Thanks for your comment. On Wed, Jun 13, 2018 at 10:02 PM, Mikulas Patocka wrote: > > > On Tue, 12 Jun 2018, Mike Snitzer wrote: > >> On Tue, Jun 12 2018 at 4:03am -0400, >> Jing Xia wrote: >> >> > Performance test in android reports that the phone sometimes gets >> > hanged and shows black scr

Re: [dm-devel] dm bufio: Reduce dm_bufio_lock contention

2018-06-14 Thread jing xia
Thank for your comment,I appreciate it. On Wed, Jun 13, 2018 at 5:20 AM, Mike Snitzer wrote: > On Tue, Jun 12 2018 at 4:03am -0400, > Jing Xia wrote: > >> Performance test in android reports that the phone sometimes gets >> hanged and shows black screen for about several minutes.The sysdump sho

Re: [dm-devel] dm bufio: Reduce dm_bufio_lock contention

2018-06-14 Thread Michal Hocko
On Thu 14-06-18 15:18:58, jing xia wrote: [...] > PID: 22920 TASK: ffc0120f1a00 CPU: 1 COMMAND: "kworker/u8:2" > #0 [ffc0282af3d0] __switch_to at ff8008085e48 > #1 [ffc0282af3f0] __schedule at ff8008850cc8 > #2 [ffc0282af450] schedule at ff8008850f4c > #3 [ff