On Sat, Apr 09 2022 at 1:15P -0400,
Christoph Hellwig wrote:
> On Fri, Apr 08, 2022 at 11:42:51AM -0400, Mike Snitzer wrote:
> > I think we can achieve the goal of efficient cloning/remapping for
> > both usecases simply by splitting out the bio_set_dev() and leaving it
&g
On Thu, Mar 31 2022 at 5:15P -0400,
Christoph Hellwig wrote:
> On Wed, Mar 30, 2022 at 10:52:13PM -0700, Dennis Zhou wrote:
> > I took a quick look. It seems with the new interface,
> > bio_clone_blkg_association() is unnecessary given the correct
> > association should be derived from the
On Tue, Apr 05 2022 at 10:09P -0400,
Ming Lei wrote:
> On Mon, Apr 04, 2022 at 12:51:30PM -0400, Mike Snitzer wrote:
> > On Sun, Apr 03 2022 at 7:45P -0400,
> > Ming Lei wrote:
> >
> > > -EAGAIN still may return after io issue returns, and REQ_F_REISSUE is
>
On Fri, Apr 01 2022 at 6:07P -0400,
Michael Trimarchi wrote:
> The device driver can be deferrable and can be a race during
> the dm-init early. We need to wait all the probe are really finished
> in a loop as is done in do_mounts. This is was tested on kernel 5.4
> but code seems was not
> Current dm io polling may return -EAGAIN after bio submission is
> returned, also blk-throttle might trigger this situation too.
>
> Cc: Mike Snitzer
> Signed-off-by: Ming Lei
I first reverted commit 5291984004ed ("dm: fix bio polling to handle
possibile BLK_STS_AGAIN")
Hi Linus,
The following changes since commit 3f7282139fe1594be464b90141d56738e7a0ea8a:
Merge tag 'for-5.18/64bit-pi-2022-03-25' of git://git.kernel.dk/linux-block
(2022-03-26 12:01:35 -0700)
are available in the Git repository at:
On Sun, Mar 27 2022 at 1:37P -0400,
Xiaomeng Tong wrote:
> The bug is here:
> bypass_pg(m, pg, bypassed);
>
> The list iterator 'pg' will point to a bogus position containing
> HEAD if the list is empty or no element is found. This case must
> be checked before any use of the iterator,
Hey Tejun and Dennis,
I recently found that due to bio_set_dev()'s call to
bio_associate_blkg(), bio_set_dev() needs much more cpu than ideal;
especially when doing 4K IOs via io_uring's HIPRI bio-polling.
I'm very naive about blk-cgroups.. so I'm hopeful you or others can
help me cut through
the functionality tied to struct kiocb.
Signed-off-by: Mike Snitzer
[hch: refactored a bit]
Signed-off-by: Christoph Hellwig
---
block/bio.c | 86 ++-
block/blk.h | 3 +-
block/fops.c | 11 --
include/linux
on block accordingly.
Thanks,
Mike
v3: tweaked some code comments, refined patch headers and folded DM
patches so only one DM patch now.
v2: add REQ_ALLOC_CACHE and move use of bio_alloc_percpu_cache to
bio_alloc_bioset
Mike Snitzer (3):
block: allow using the per-cpu bio cache from
bio_clear_polled() to include/linux/bio.h to allow users
outside of block core.
Signed-off-by: Mike Snitzer
---
block/bio.c | 2 ++
block/blk.h | 6 --
include/linux/bio.h | 6 ++
3 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/block/bio.c b/block/bio.c
index
polling (REQ_POLLED) perf by
7 - 20% depending on the system.
Signed-off-by: Mike Snitzer
---
drivers/md/dm-table.c | 11 ---
drivers/md/dm.c | 8
drivers/md/dm.h | 4 ++--
3 files changed, 14 insertions(+), 9 deletions(-)
diff --git a/drivers/md/dm-table.c b
On Thu, Mar 24 2022 at 3:39P -0400,
Christoph Hellwig wrote:
> On Wed, Mar 23, 2022 at 03:45:20PM -0400, Mike Snitzer wrote:
> > I tried to address your review of the previous set. Patch 1 and 2 can
> > obviously be folded but I left them split out for review purposes.
>
On Wed, Mar 23 2022 at 6:57P -0400,
kernel test robot wrote:
> tree:
> https://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm.git
> dm-5.19
> head: 7f8ac95a6464b895e3d2b6175f7ee64a4c10fcfe
> commit: 7f8ac95a6464b895e3d2b6175f7ee64a4c10fcfe [132/132] dm: push error
>
ev
dm: stop using bdevname
Colin Ian King (1):
dm cache policy smq: make static read-only array table const
Jordy Zomer (1):
dm ioctl: prevent potential spectre v1 gadget
Kirill Tkhai (1):
dm: fix use-after-free in dm_cleanup_zoned_dev()
Mike Snitzer (33):
dm:
Also change dm_io_complete() to use bio_clear_polled() so that it
properly clears all associated bio state (REQ_POLLED, BIO_PERCPU_CACHE,
etc).
This commit improves DM's hipri bio polling (REQ_POLLED) perf by ~7%.
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 6 +++---
1 file changed, 3
participation in a specific alloc cache (BIO_PERCPU_CACHE).
Otherwise an upper layer's bioset may not have an alloc cache, in which
case the bio issued to underlying device(s) wouldn't reflect that
allocating from an alloc cache warranted (if possible).
Signed-off-by: Mike Snitzer
---
block/bio.c
A bioset's percpu cache may have broader utility in the future but for
now constrain it to being tightly coupled to QUEUE_FLAG_POLL.
Signed-off-by: Mike Snitzer
---
drivers/md/dm-table.c | 11 ---
drivers/md/dm.c | 6 +++---
drivers/md/dm.h | 4 ++--
3 files changed, 13
ove bio_clear_polled() to include/linux/bio.h to allow users outside
of block core.
Signed-off-by: Mike Snitzer
---
block/bio.c | 56 +
block/blk.h | 7 ---
include/linux/bio.h | 7 +++
3 files changed, 42 insertions(+), 28 deleti
to
bio_alloc_bioset
Mike Snitzer (4):
block: allow BIOSET_PERCPU_CACHE use from bio_alloc_clone
block: allow BIOSET_PERCPU_CACHE use from bio_alloc_bioset
dm: enable BIOSET_PERCPU_CACHE for dm_io bioset
dm: conditionally enable BIOSET_PERCPU_CACHE for bio-based dm_io bioset
block/bio.c
On Tue, Mar 22 2022 at 3:54P -0400,
Christoph Hellwig wrote:
> On Tue, Mar 22, 2022 at 03:49:25PM -0400, Mike Snitzer wrote:
> > - bio = bio_alloc_bioset(bdev, 0, bio_src->bi_opf, gfp, bs);
> > + if (bs->cache && bio_src->bi_opf & REQ_POLLED)
> >
in
process context.
This change improves DM's hipri bio polling performance by ~7%.
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a2e80c376827..06f3720a190b 100644
--- a/drivers
, this series builds on linux-dm.git's "dm-5.18" branch, and the
commits in this series are available in linux-dm.git's "dm-5.19"
branch).
Thanks,
Mike
Mike Snitzer (3):
block: allow BIOSET_PERCPU_CACHE use from bio_alloc_clone
dm: enable BIOSET_PERCPU_CACHE for dm_io bioset
dm:
There is no point establishing the bioset percpu cache if request_queue
won't have QUEUE_FLAG_POLL.
Signed-off-by: Mike Snitzer
---
drivers/md/dm-table.c | 11 ---
drivers/md/dm.c | 6 +++---
drivers/md/dm.h | 4 ++--
3 files changed, 13 insertions(+), 8 deletions(-)
diff
nux/bio.h to allow users outside
of block core.
Signed-off-by: Mike Snitzer
---
block/bio.c | 56 +
block/blk.h | 7 ---
include/linux/bio.h | 7 +++
3 files changed, 42 insertions(+), 28 deletions(-)
diff --git a/bl
which is retrieved via bio->bi_bio_drv_data; call
dm_io_dec_pending() after the target io is done in .poll_bio()
5) enable QUEUE_FLAG_POLL if all underlying queues enable QUEUE_FLAG_POLL,
which is based on Jeffle's previous patch.
Signed-off-by: Ming Lei
Signed-off-by: Mike Snitzer
---
driv
Hi,
I've rebased Ming's latest [1] ontop of dm-5.18 [2] (which is based on
for-5.18/block). End result available in dm-5.18-biopoll branch [3]
These changes add bio polling support to DM. Tested with linear and
striped DM targets.
IOPS improvement was ~5% on my baremetal system with a single
: Ming Lei
Signed-off-by: Mike Snitzer
---
block/blk-core.c | 14 +-
block/genhd.c | 4
include/linux/blkdev.h | 2 ++
3 files changed, 15 insertions(+), 5 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 94bf37f8e61d..ce08f0aa9dfc 100644
--- a
On Mon, Mar 07 2022 at 11:48P -0500,
Christoph Hellwig wrote:
> On Mon, Mar 07, 2022 at 11:45:53AM -0500, Mike Snitzer wrote:
> > Should those go through block too? Or is there no plan to remove
> > bdevname()?
>
> My preference would be: do the full bio_devname removal
On Mon, Mar 07 2022 at 8:42P -0500,
Jens Axboe wrote:
> On Fri, 4 Mar 2022 19:00:55 +0100, Christoph Hellwig wrote:
> > this series removes the bio_devname helper and just switches all users
> > to use the %pg format string directly.
> >
> > Diffstat
> > block/bio.c |6
On Fri, Mar 04 2022 at 8:43P -0500,
Ming Lei wrote:
> On Fri, Mar 04, 2022 at 04:26:21PM -0500, Mike Snitzer wrote:
> > Hi,
> >
> > I've rebased Ming's latest [1] ontop of dm-5.18 [2] (which is based on
> > for-5.18/block). End result available i
Hi,
I've rebased Ming's latest [1] ontop of dm-5.18 [2] (which is based on
for-5.18/block). End result available in dm-5.18-biopoll branch [3]
These changes add bio polling support to DM. Tested with linear and
striped DM targets.
IOPS improvement was ~5% on my baremetal system with a single
which is retrieved via bio->bi_bio_drv_data; call
dm_io_dec_pending() after the target io is done in .poll_bio()
5) enable QUEUE_FLAG_POLL if all underlying queues enable QUEUE_FLAG_POLL,
which is based on Jeffle's previous patch.
Signed-off-by: Ming Lei
Signed-off-by: Mike Snitzer
---
drivers/md/
From: Ming Lei
Prepare for supporting IO polling for bio-based driver.
Add ->poll_bio callback so that bio-based driver can provide their own
logic for polling bio.
Also fix ->submit_bio_bio typo in comment block above
__submit_bio_noacct.
Signed-off-by: Ming Lei
Signed-off-by: Mike S
On Fri, Mar 04 2022 at 4:39P -0500,
Jens Axboe wrote:
> On 3/4/22 2:26 PM, Mike Snitzer wrote:
> > diff --git a/block/blk-core.c b/block/blk-core.c
> > index 94bf37f8e61d..e739c6264331 100644
> > --- a/block/blk-core.c
> > +++ b/block/blk-core.c
> > @@ -985,10 +
From: Ming Lei
Prepare for supporting IO polling for bio based driver.
Add ->poll_bio callback so that bio driver can provide their own logic
for polling bio.
Signed-off-by: Ming Lei
Signed-off-by: Mike Snitzer
---
block/blk-core.c | 12 +---
block/genhd.c |
Hi,
I've rebased Ming's latest [1] ontop of dm-5.18 [2] (which is based on
for-5.18/block). End result available in dm-5.18-biopoll branch [3]
These changes add bio polling support to DM. Tested with linear and
striped DM targets.
IOPS improvement was ~5% on my baremetal system with a single
which is retrieved via bio->bi_bio_drv_data; call
dm_io_dec_pending() after the target io is done in .poll_bio()
5) enable QUEUE_FLAG_POLL if all underlying queues enable QUEUE_FLAG_POLL,
which is based on Jeffle's previous patch.
Signed-off-by: Ming Lei
Signed-off-by: Mike Snitzer
---
drivers/md/
On Mon, Feb 28 2022 at 7:58P -0500,
Ming Lei wrote:
> On Mon, Feb 28, 2022 at 11:27:44AM -0500, Mike Snitzer wrote:
> >
> > Hey Ming,
> >
> > I'd like us to follow-through with adding bio-based polling support.
> > Kind of strange none of us that were sent
On Wed, Jun 23 2021 at 3:40P -0400,
Ming Lei wrote:
> Hello Guys,
>
> Based on Christoph's bio based polling model[1], implement DM bio polling
> with one very simple approach.
>
> Patch 1 adds helper of blk_queue_poll().
>
> Patch 2 adds .bio_poll() callback to block_device_operations, so
s
discards. The thin-pool controls the allocation of underlying storage.
So all said:
Nacked-by: Mike Snitzer
--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel
On Thu, Feb 17, 2022 at 5:49 AM Damien Le Moal
wrote:
>
> On 2/17/22 19:13, Kirill Tkhai wrote:
> >
> > dm_cleanup_zoned_dev() uses queue, so it must be called
> > before blk_cleanup_disk() starts its killing:
> >
> > blk_cleanup_disk->blk_cleanup_queue()->kobject_put()->blk_release_queue()->
> >
On Wed, Feb 02 2022 at 9:42P -0500,
Christoph Hellwig wrote:
> Withmy block hat on: nak to this. No block driver has any business at
> all rejecting "too many openers". In fact any opener but the first of
> a partition is already not counted as an opener, and I plan to complete
> hide the
On Wed, Feb 09 2022 at 4:37P -0500,
Zhang Yi wrote:
> We found a NULL pointer dereference problem when using dm-mpath target.
> The problem is if we submit IO between loading and binding the table,
> we could neither get a valid dm_target nor a valid dm table when
> submitting request in
On Mon, Feb 14 2022 at 2:59P -0500,
Nitesh Shetty wrote:
> Before enabling copy for dm target, check if underlying devices and
> dm target support copy. Avoid split happening inside dm target.
> Fail early if the request needs split, currently splitting copy
> request is not supported.
>
>
On Mon, Feb 21 2022 at 5:36P -0500,
Faqiang Zhu wrote:
> Hi Christoph,
>
>
>
> Recently when I use kernel5.15 with android, an issue related to bow_target
> is found with below log:
>
>
>
> [8.935429][T1] kobject_add_internal failed for bow (error: -2
> parent: (null))
>
>
>
On Wed, Feb 09 2022 at 3:28P -0500,
Christoph Hellwig wrote:
> There are no more end-users of REQ_OP_WRITE_SAME left, so we can start
> deleting it.
>
> Signed-off-by: Christoph Hellwig
Thanks.
Reviewed-by: Mike Snitzer
--
dm-devel mailing list
dm-devel@redh
he ufs
> driver more easily. And while I touched this code I also ended up
> cleaning up various loose ends.
All look good to me, thanks, for series:
Reviewed-by: Mike Snitzer
--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel
On Mon, Feb 14 2022 at 9:02P -0500,
Christoph Hellwig wrote:
> On Fri, Feb 11, 2022 at 04:40:53PM -0500, Mike Snitzer wrote:
> > DM needs the ability to account a clone bio's IO to the original
> > block_device. So add @orig_bdev argument to bio_start_io_acct_time.
Fold __clone_and_map_data_bio into its only caller.
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 30 --
1 file changed, 8 insertions(+), 22 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 2cecb8832936
Rename __split_and_process_bio to dm_split_and_process_bio.
Rename __split_and_process_non_flush to __split_and_process_bio.
Also fix a stale comment and whitespace.
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 22 +++---
1 file changed, 11
Signed-off-by: Mike Snitzer
---
drivers/md/dm-delay.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 59e51d285b0e..9a51bf51a859 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -72,7 +72,7 @@ static
Suggested-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 27 +--
1 file changed, 13 insertions(+), 14 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 2461df65e2fe..20c7b1b4d1f7 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
nly started once.
Suggested-by: Mikulas Patocka
Signed-off-by: Mike Snitzer
---
drivers/md/dm-core.h | 1 +
drivers/md/dm.c | 59 ---
include/linux/device-mapper.h | 7 +
include/uapi/linux/dm-ioctl.h | 4 +--
4 files changed,
sector
cursor, in __send_duplicate_bios().
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 11 ++-
1 file changed, 2 insertions(+), 9 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 137e578785f6..164cccf59297 100644
--- a/drivers/md/dm.c
+++ b/dr
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index bd07ccadbf01..137e578785f6 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -539,7 +539,7 @@ static
Error path code (for handling DM_MAPIO_REQUEUE and DM_MAPIO_KILL) is
effectively identical.
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 18 ++
1 file changed, 6 insertions(+), 12 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
/archives/dm-devel/2022-February/msg00193.html
Christoph, I addressed all your feedback from v1 and added the
Reviewed-by:s you provided. Thanks for your review.
Patch 10 now isolates the block changes like you asked.
All further review of this v2 patchset is welcomed.
Mike
Mike Snitzer (14
Signed-off-by: Mike Snitzer
---
drivers/md/dm-crypt.c | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index a5006cb6ee8a..337517cb4e90 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1855,7 +1855,7
Move kicking of the suspend queue to dm_io_dec_pending (the only
caller) since end_io_acct will soon only be called if IO accounting
was started.
Also, some comment tweaks and removal of local variables.
No functional change.
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
The flush_bio in question was just initialized to be empty, so there
is no way bio_has_data() will return true. So remove stale BUG_ON().
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/md/dm.c b/drivers
to blkdev.h and have it call
bio_start_io_acct_remapped.
Signed-off-by: Mike Snitzer
---
block/blk-core.c | 24
drivers/md/dm.c| 3 ++-
include/linux/blkdev.h | 16 ++--
3 files changed, 24 insertions(+), 19 deletions(-)
diff --git a/block/blk-core.c b
Prep for being able to defer trace_block_bio_remap() until when the
bio is remapped and submitted by the DM target.
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
---
drivers/md/dm-core.h | 1 +
drivers/md/dm.c | 7 ---
2 files changed, 5 insertions(+), 3 deletions
Remove needless branching and indentation. Leaves code to catch
malformed op_is_zone_mgmt bios (they shouldn't have a payload).
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 54 --
1 file changed, 28
On Fri, Feb 11 2022 at 10:01P -0500,
Mikulas Patocka wrote:
> Exactly the same sector number and length must be passed to both calls of
> dm_stats_account_io, otherwise its per-zone in_flight counters go out of
> sync. This patch fixes it.
>
> Signed-off-by: Mikulas Patocka
>
> ---
>
On Fri, Feb 11 2022 at 10:03P -0500,
Mikulas Patocka wrote:
> If a bio was split to multiple targets, only one target's sub-range was
> counted. This patch changes it so that all the targets' ranges are
> counted.
>
> Note that calls to bio_start_io_acct_remapped and bio_end_io_acct must
>
Remove needless branching. Leaves code to catch malformed
op_is_zone_mgmt bios (they shouldn't have a payload).
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 51 ++-
1 file changed, 26 insertions(+), 25 deletions(-)
diff --git a/drivers/md
sector
cursor, in __send_duplicate_bios().
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 11 ++-
1 file changed, 2 insertions(+), 9 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f091bbf8a8dc..5950d518e544 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1176,12 +1176,6 @
Fold __clone_and_map_data_bio into its only caller.
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 30 --
1 file changed, 8 insertions(+), 22 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 2cecb8832936..2f1942b61d48 100644
--- a/drivers/md/dm.c
Signed-off-by: Mike Snitzer
---
drivers/md/dm-delay.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 59e51d285b0e..8235927a3912 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -72,7 +72,7 @@ static void
Rename __split_and_process_bio to dm_split_and_process_bio.
Rename __split_and_process_non_flush to __split_and_process_bio.
Also fix a stale comment and whitespace.
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 22 +++---
1 file changed, 11 insertions(+), 11 deletions
Prep for being able to defer trace_block_bio_remap() until when the
bio is remapped and submitted by the DM target.
Signed-off-by: Mike Snitzer
---
drivers/md/dm-core.h | 1 +
drivers/md/dm.c | 7 ---
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/md/dm-core.h b
Don't use jiffies as a glorified bool because jiffies can/will
rollover to 0.
Also use xchg(), instead of spin_lock_irq{save,restore} and
smp_load_acquire/smp_store_release, to avoid performance impact of
disabling and enabling interrupts.
Suggested-by: Mikulas Patocka
Signed-off-by: Mike
Signed-off-by: Mike Snitzer
---
drivers/md/dm-crypt.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index a5006cb6ee8a..9ea197de08c2 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1855,7 +1855,7
additional processing of each bio in
conjunction with their DM_MAPIO_SUBMITTED return from their map
function.
Signed-off-by: Mike Snitzer
---
drivers/md/dm-core.h | 1 +
drivers/md/dm.c | 93 +++
include/linux/device-mapper.h | 7
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1985fc3f2a95..f091bbf8a8dc 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -539,7 +539,7 @@ static struct dm_io *alloc_io(struct
to blkdev.h and have it call
bio_start_io_acct_remapped.
Improve DM to no longer need to play games with swizzling a clone
bio's bi_bdev (in dm_submit_bio_remap) and remove DM's
clone_and_start_io_acct() interface.
Signed-off-by: Mike Snitzer
---
block/blk-core.c | 24
The flush_bio in question was just initialized to be empty, so there
is no way bio_has_data() will retrun true. So remove stale BUG_ON().
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index cc014e56252e
.
Some comment tweaks and removal of local variables. No functional
change.
Signed-off-by: Mike Snitzer
---
drivers/md/dm-core.h | 2 +-
drivers/md/dm.c | 32 ++--
2 files changed, 15 insertions(+), 19 deletions(-)
diff --git a/drivers/md/dm-core.h b/drivers/md/dm
Error path code (for handling DM_MAPIO_REQUEUE and DM_MAPIO_KILL) is
effectively identical.
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 18 ++
1 file changed, 6 insertions(+), 12 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 56734aae718d..cc014e56252e
little
indication that anything is happening. Given dm-crypt's cpu intensive
nature it takes time to complete IO but unless you look at the
underlying devices' iostats you wouldn't see it occurring.
Mike
Mike Snitzer (14):
dm: rename split functions
dm: fold __clone_and_map_data_bio
id10.c | 16 +--
> drivers/md/raid5.c |4
> fs/btrfs/extent_io.c |4
> include/linux/bio.h |6 -
> 22 files changed, 183 insertions(+), 239 deletions(-)
>
Looks good, for all:
Reviewed-by: Mike Snitzer
I
On Wed, Feb 02 2022 at 11:01P -0500,
Christoph Hellwig wrote:
> Return the clone bio embedded into the tio as that is what the callers
> actually want. Similar for the free side.
>
> Signed-off-by: Christoph Hellwig
Small nit, subject has typo: s/retun/return/
--
dm-devel mailing list
se, thanks.
Mike
v4: added Christoph's Reviewed-bys. Removed READ_ONCE from patch 3
v3: fix patch 3 to call bio_start_io_acct_time
v2: made block changes suggested by Christoph
Mike Snitzer (3):
block: add bio_start_io_acct_time() to control start_time
dm: revert partial fix for redundant bio-base
Reverts a1e1cb72d9649 ("dm: fix redundant IO accounting for bios that
need splitting") because it was too narrow in scope (only addressed
redundant 'sectors[]' accounting and not ios, nsecs[], etc).
Cc: sta...@vger.kernel.org
Signed-off-by: Mike Snitzer
---
drivers/md
-by: Bud Brown
Reviewed-by: Christoph Hellwig
Cc: sta...@vger.kernel.org
Depends-on: 1073e8492f88 ("block: add bio_start_io_acct_time() to control
start_time")
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers
bio_start_io_acct_time() interface is like bio_start_io_acct() that
allows start_time to be passed in. This gives drivers the ability to
defer starting accounting until after IO is issued (but possibily not
entirely due to bio splitting).
Reviewed-by: Christoph Hellwig
Signed-off-by: Mike
On Fri, Jan 28 2022 at 1:13P -0500,
Christoph Hellwig wrote:
> On Thu, Jan 27, 2022 at 11:17:51PM -0500, Mike Snitzer wrote:
> > + __part_start_io_acct(bio->bi_bdev, bio_sectors(bio),
> > +bio_op(bio), start_time);
> > }
> > +EXPORT_SYM
-by: Bud Brown
Cc: sta...@vger.kernel.org
Depends-on: f9893e1da2e3 ("block: add bio_start_io_acct_time() to control
start_time")
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 98
Reverts a1e1cb72d9649 ("dm: fix redundant IO accounting for bios that
need splitting") because it was too narrow in scope (only addressed
redundant 'sectors[]' accounting and not ios, nsecs[], etc).
Cc: sta...@vger.kernel.org
Signed-off-by: Mike Snitzer
---
drivers/md
bio_start_io_acct_time() interface is like bio_start_io_acct() that
allows start_time to be passed in. This gives drivers the ability to
defer starting accounting until after IO is issued (but possibily not
entirely due to bio splitting).
Signed-off-by: Mike Snitzer
---
block/blk-core.c
e
v2: made block changes suggested by Christoph
Mike Snitzer (3):
block: add bio_start_io_acct_time() to control start_time
dm: revert partial fix for redundant bio-based IO accounting
dm: properly fix redundant bio-based IO accounting
block/blk-core.c | 25 +++--
On Thu, Jan 27 2022 at 5:56P -0500,
Mike Snitzer wrote:
> Record the start_time for a bio but defer the starting block core's IO
> accounting until after IO is submitted using bio_start_io_acct_time().
>
> This approach avoids the need to mess around with any of the
> indi
Reverts a1e1cb72d9649 ("dm: fix redundant IO accounting for bios that
need splitting") because it was too narrow in scope (only addressed
redundant 'sectors[]' accounting and not ios, nsecs[], etc).
Cc: sta...@vger.kernel.org
Signed-off-by: Mike Snitzer
---
drivers/md
-by: Bud Brown
Cc: sta...@vger.kernel.org
Depends-on: f9893e1da2e3 ("block: add bio_start_io_acct_time() to control
start_time")
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 98
bio_start_io_acct_time() interface is like bio_start_io_acct() that
allows start_time to be passed in. This gives drivers the ability to
defer starting accounting until after IO is issued (but possibily not
entirely due to bio splitting).
Signed-off-by: Mike Snitzer
---
block/blk-core.c
ges suggested by Christoph
Mike Snitzer (3):
block: add bio_start_io_acct_time() to control start_time
dm: revert partial fix for redundant bio-based IO accounting
dm: properly fix redundant bio-based IO accounting
block/blk-core.c | 25 +++--
drivers/md/dm.
Reverts a1e1cb72d9649 ("dm: fix redundant IO accounting for bios that
need splitting") because it was too narrow in scope (only addressed
redundant 'sectors[]' accounting and not ios, nsecs[], etc).
Cc: sta...@vger.kernel.org
Signed-off-by: Mike Snitzer
---
drivers/md
Brown
Cc: sta...@vger.kernel.org
Depends-on: e8d7405fccc6 ("block: add __bio_start_io_acct() to control
start_time")
Signed-off-by: Mike Snitzer
---
drivers/md/dm.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 98
to pickup this set to send along (I'd obviously
still do any stable@ backports). NOTE: the 3rd patch references the
linux-dm.git commit id for the 1st patch.. so that'll require tweaking
no matter who sends the changes to Linus.
Please advise, thanks.
Mike
Mike Snitzer (3):
block: add __bio_sta
401 - 500 of 2007 matches
Mail list logo
