* [dm-devel] [PATCH 0/3] block/dm: fix bio-based DM IO accounting
@ 2022-01-27 19:07 ` Mike Snitzer
0 siblings, 0 replies; 10+ messages in thread
From: Mike Snitzer @ 2022-01-27 19:07 UTC (permalink / raw)
To: axboe; +Cc: linux-block, dm-devel
Hi Jens,
Just over 3 years ago, with commit a1e1cb72d9649 ("dm: fix redundant
IO accounting for bios that need splitting") I focused too narrowly on
fixing the reported potential for redundant accounting for IO totals.
Which, at least mentally for me, papered over how inaccurate all other
bio-based DM's IO accounting is for bios that get split.
This set fixes things up properly by allowing DM to start IO
accounting _after_ IO is submitted and a split is occurred. The
proper start_time is still established (prior to submission), it is
passed in to a new __bio_start_io_acct(). This eliminates the need
for any DM hack to rewind block core's excessive accounting in the
face of a split bio recursing back to block core.
All said: If you'd provide your Acked-by(s) I'm happy to send this set
to Linus for v5.17-rc (and shepherd the changes into stable@ kernels).
Or you're welcome 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_start_io_acct() 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 | 27 ++++++++++++++++++++-------
drivers/md/dm.c | 20 +++-----------------
include/linux/blkdev.h | 1 +
3 files changed, 24 insertions(+), 24 deletions(-)
--
2.15.0
--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel
^ permalink raw reply [flat|nested] 10+ messages in thread* [PATCH 1/3] block: add __bio_start_io_acct() to control start_time
2022-01-27 19:07 ` [dm-devel] " Mike Snitzer
@ 2022-01-27 19:07 ` Mike Snitzer
-1 siblings, 0 replies; 10+ messages in thread
From: Mike Snitzer @ 2022-01-27 19:07 UTC (permalink / raw)
To: axboe; +Cc: dm-devel, linux-block
__bio_start_io_acct() 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 <snitzer@redhat.com>
---
block/blk-core.c | 27 ++++++++++++++++++++-------
include/linux/blkdev.h | 1 +
2 files changed, 21 insertions(+), 7 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 97f8bc8d3a79..18cd12fee67d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1060,21 +1060,30 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end)
}
}
-static unsigned long __part_start_io_acct(struct block_device *part,
- unsigned int sectors, unsigned int op)
+static void __part_start_io_acct(struct block_device *part, unsigned int sectors,
+ unsigned int op, unsigned long start_time)
{
const int sgrp = op_stat_group(op);
- unsigned long now = READ_ONCE(jiffies);
part_stat_lock();
- update_io_ticks(part, now, false);
+ update_io_ticks(part, start_time, false);
part_stat_inc(part, ios[sgrp]);
part_stat_add(part, sectors[sgrp], sectors);
part_stat_local_inc(part, in_flight[op_is_write(op)]);
part_stat_unlock();
+}
- return now;
+/**
+ * __bio_start_io_acct - start I/O accounting for bio based drivers
+ * @bio: bio to start account for
+ * @start_time: start time that should be passed back to bio_end_io_acct().
+ */
+void __bio_start_io_acct(struct bio *bio, unsigned long start_time)
+{
+ __part_start_io_acct(bio->bi_bdev, bio_sectors(bio),
+ bio_op(bio), start_time);
}
+EXPORT_SYMBOL_GPL(__bio_start_io_acct);
/**
* bio_start_io_acct - start I/O accounting for bio based drivers
@@ -1084,14 +1093,18 @@ static unsigned long __part_start_io_acct(struct block_device *part,
*/
unsigned long bio_start_io_acct(struct bio *bio)
{
- return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), bio_op(bio));
+ unsigned long now = READ_ONCE(jiffies);
+ __bio_start_io_acct(bio, now);
+ return now;
}
EXPORT_SYMBOL_GPL(bio_start_io_acct);
unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
unsigned int op)
{
- return __part_start_io_acct(disk->part0, sectors, op);
+ unsigned long now = READ_ONCE(jiffies);
+ __part_start_io_acct(disk->part0, sectors, op, now);
+ return now;
}
EXPORT_SYMBOL(disk_start_io_acct);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9c95df26fc26..ed3cd5f7f984 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1258,6 +1258,7 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
void disk_end_io_acct(struct gendisk *disk, unsigned int op,
unsigned long start_time);
+void __bio_start_io_acct(struct bio *bio, unsigned long start_time);
unsigned long bio_start_io_acct(struct bio *bio);
void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
struct block_device *orig_bdev);
--
2.15.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [dm-devel] [PATCH 1/3] block: add __bio_start_io_acct() to control start_time
@ 2022-01-27 19:07 ` Mike Snitzer
0 siblings, 0 replies; 10+ messages in thread
From: Mike Snitzer @ 2022-01-27 19:07 UTC (permalink / raw)
To: axboe; +Cc: linux-block, dm-devel
__bio_start_io_acct() 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 <snitzer@redhat.com>
---
block/blk-core.c | 27 ++++++++++++++++++++-------
include/linux/blkdev.h | 1 +
2 files changed, 21 insertions(+), 7 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 97f8bc8d3a79..18cd12fee67d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1060,21 +1060,30 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end)
}
}
-static unsigned long __part_start_io_acct(struct block_device *part,
- unsigned int sectors, unsigned int op)
+static void __part_start_io_acct(struct block_device *part, unsigned int sectors,
+ unsigned int op, unsigned long start_time)
{
const int sgrp = op_stat_group(op);
- unsigned long now = READ_ONCE(jiffies);
part_stat_lock();
- update_io_ticks(part, now, false);
+ update_io_ticks(part, start_time, false);
part_stat_inc(part, ios[sgrp]);
part_stat_add(part, sectors[sgrp], sectors);
part_stat_local_inc(part, in_flight[op_is_write(op)]);
part_stat_unlock();
+}
- return now;
+/**
+ * __bio_start_io_acct - start I/O accounting for bio based drivers
+ * @bio: bio to start account for
+ * @start_time: start time that should be passed back to bio_end_io_acct().
+ */
+void __bio_start_io_acct(struct bio *bio, unsigned long start_time)
+{
+ __part_start_io_acct(bio->bi_bdev, bio_sectors(bio),
+ bio_op(bio), start_time);
}
+EXPORT_SYMBOL_GPL(__bio_start_io_acct);
/**
* bio_start_io_acct - start I/O accounting for bio based drivers
@@ -1084,14 +1093,18 @@ static unsigned long __part_start_io_acct(struct block_device *part,
*/
unsigned long bio_start_io_acct(struct bio *bio)
{
- return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), bio_op(bio));
+ unsigned long now = READ_ONCE(jiffies);
+ __bio_start_io_acct(bio, now);
+ return now;
}
EXPORT_SYMBOL_GPL(bio_start_io_acct);
unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
unsigned int op)
{
- return __part_start_io_acct(disk->part0, sectors, op);
+ unsigned long now = READ_ONCE(jiffies);
+ __part_start_io_acct(disk->part0, sectors, op, now);
+ return now;
}
EXPORT_SYMBOL(disk_start_io_acct);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9c95df26fc26..ed3cd5f7f984 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1258,6 +1258,7 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
void disk_end_io_acct(struct gendisk *disk, unsigned int op,
unsigned long start_time);
+void __bio_start_io_acct(struct bio *bio, unsigned long start_time);
unsigned long bio_start_io_acct(struct bio *bio);
void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
struct block_device *orig_bdev);
--
2.15.0
--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel
^ permalink raw reply related [flat|nested] 10+ messages in thread* Re: [dm-devel] [PATCH 1/3] block: add __bio_start_io_acct() to control start_time
2022-01-27 19:07 ` [dm-devel] " Mike Snitzer
@ 2022-01-27 20:01 ` Christoph Hellwig
-1 siblings, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2022-01-27 20:01 UTC (permalink / raw)
To: Mike Snitzer; +Cc: axboe, linux-block, dm-devel
> -static unsigned long __part_start_io_acct(struct block_device *part,
> - unsigned int sectors, unsigned int op)
> +static void __part_start_io_acct(struct block_device *part, unsigned int sectors,
> + unsigned int op, unsigned long start_time)
Please avoid the overly long line.
> +/**
> + * __bio_start_io_acct - start I/O accounting for bio based drivers
> + * @bio: bio to start account for
> + * @start_time: start time that should be passed back to bio_end_io_acct().
> + */
> +void __bio_start_io_acct(struct bio *bio, unsigned long start_time)
I'd name this something like bio_start_io_acct_time to be a little more
descriptive
> + unsigned long now = READ_ONCE(jiffies);
> + __bio_start_io_acct(bio, now);
> + return now;
Plase add an empty line after the variable declaration.
> }
> EXPORT_SYMBOL_GPL(bio_start_io_acct);
>
> unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
> unsigned int op)
> {
> - return __part_start_io_acct(disk->part0, sectors, op);
> + unsigned long now = READ_ONCE(jiffies);
> + __part_start_io_acct(disk->part0, sectors, op, now);
> + return now;
I wonder if just returning the passed in time from __part_start_io_acct
wouldn't be a bit cleaner to avoid all the extra local variables.
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [dm-devel] [PATCH 1/3] block: add __bio_start_io_acct() to control start_time
@ 2022-01-27 20:01 ` Christoph Hellwig
0 siblings, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2022-01-27 20:01 UTC (permalink / raw)
To: Mike Snitzer; +Cc: axboe, linux-block, dm-devel
> -static unsigned long __part_start_io_acct(struct block_device *part,
> - unsigned int sectors, unsigned int op)
> +static void __part_start_io_acct(struct block_device *part, unsigned int sectors,
> + unsigned int op, unsigned long start_time)
Please avoid the overly long line.
> +/**
> + * __bio_start_io_acct - start I/O accounting for bio based drivers
> + * @bio: bio to start account for
> + * @start_time: start time that should be passed back to bio_end_io_acct().
> + */
> +void __bio_start_io_acct(struct bio *bio, unsigned long start_time)
I'd name this something like bio_start_io_acct_time to be a little more
descriptive
> + unsigned long now = READ_ONCE(jiffies);
> + __bio_start_io_acct(bio, now);
> + return now;
Plase add an empty line after the variable declaration.
> }
> EXPORT_SYMBOL_GPL(bio_start_io_acct);
>
> unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
> unsigned int op)
> {
> - return __part_start_io_acct(disk->part0, sectors, op);
> + unsigned long now = READ_ONCE(jiffies);
> + __part_start_io_acct(disk->part0, sectors, op, now);
> + return now;
I wonder if just returning the passed in time from __part_start_io_acct
wouldn't be a bit cleaner to avoid all the extra local variables.
--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH 2/3] dm: revert partial fix for redundant bio-based IO accounting
2022-01-27 19:07 ` [dm-devel] " Mike Snitzer
@ 2022-01-27 19:07 ` Mike Snitzer
-1 siblings, 0 replies; 10+ messages in thread
From: Mike Snitzer @ 2022-01-27 19:07 UTC (permalink / raw)
To: axboe; +Cc: dm-devel, linux-block
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: stable@vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
drivers/md/dm.c | 15 ---------------
1 file changed, 15 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c0ae8087c602..9849114b3c08 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1442,9 +1442,6 @@ static void init_clone_info(struct clone_info *ci, struct mapped_device *md,
ci->sector = bio->bi_iter.bi_sector;
}
-#define __dm_part_stat_sub(part, field, subnd) \
- (part_stat_get(part, field) -= (subnd))
-
/*
* Entry point to split a bio into clones and submit them to the targets.
*/
@@ -1480,18 +1477,6 @@ static void __split_and_process_bio(struct mapped_device *md,
GFP_NOIO, &md->queue->bio_split);
ci.io->orig_bio = b;
- /*
- * Adjust IO stats for each split, otherwise upon queue
- * reentry there will be redundant IO accounting.
- * NOTE: this is a stop-gap fix, a proper fix involves
- * significant refactoring of DM core's bio splitting
- * (by eliminating DM's splitting and just using bio_split)
- */
- part_stat_lock();
- __dm_part_stat_sub(dm_disk(md)->part0,
- sectors[op_stat_group(bio_op(bio))], ci.sector_count);
- part_stat_unlock();
-
bio_chain(b, bio);
trace_block_split(b, bio->bi_iter.bi_sector);
submit_bio_noacct(bio);
--
2.15.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [dm-devel] [PATCH 2/3] dm: revert partial fix for redundant bio-based IO accounting
@ 2022-01-27 19:07 ` Mike Snitzer
0 siblings, 0 replies; 10+ messages in thread
From: Mike Snitzer @ 2022-01-27 19:07 UTC (permalink / raw)
To: axboe; +Cc: linux-block, dm-devel
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: stable@vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
drivers/md/dm.c | 15 ---------------
1 file changed, 15 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c0ae8087c602..9849114b3c08 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1442,9 +1442,6 @@ static void init_clone_info(struct clone_info *ci, struct mapped_device *md,
ci->sector = bio->bi_iter.bi_sector;
}
-#define __dm_part_stat_sub(part, field, subnd) \
- (part_stat_get(part, field) -= (subnd))
-
/*
* Entry point to split a bio into clones and submit them to the targets.
*/
@@ -1480,18 +1477,6 @@ static void __split_and_process_bio(struct mapped_device *md,
GFP_NOIO, &md->queue->bio_split);
ci.io->orig_bio = b;
- /*
- * Adjust IO stats for each split, otherwise upon queue
- * reentry there will be redundant IO accounting.
- * NOTE: this is a stop-gap fix, a proper fix involves
- * significant refactoring of DM core's bio splitting
- * (by eliminating DM's splitting and just using bio_split)
- */
- part_stat_lock();
- __dm_part_stat_sub(dm_disk(md)->part0,
- sectors[op_stat_group(bio_op(bio))], ci.sector_count);
- part_stat_unlock();
-
bio_chain(b, bio);
trace_block_split(b, bio->bi_iter.bi_sector);
submit_bio_noacct(bio);
--
2.15.0
--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH 3/3] dm: properly fix redundant bio-based IO accounting
2022-01-27 19:07 ` [dm-devel] " Mike Snitzer
@ 2022-01-27 19:07 ` Mike Snitzer
-1 siblings, 0 replies; 10+ messages in thread
From: Mike Snitzer @ 2022-01-27 19:07 UTC (permalink / raw)
To: axboe; +Cc: dm-devel, linux-block
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().
This approach avoids the need to mess around with any of the
individual IO stats in response to a bio_split() that follows bio
submission.
Reported-by: Bud Brown <bubrown@redhat.com>
Cc: stable@vger.kernel.org
Depends-on: e8d7405fccc6 ("block: add __bio_start_io_acct() to control start_time")
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
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 9849114b3c08..144436301a57 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -489,7 +489,7 @@ static void start_io_acct(struct dm_io *io)
struct mapped_device *md = io->md;
struct bio *bio = io->orig_bio;
- io->start_time = bio_start_io_acct(bio);
+ __bio_start_io_acct(bio, io->start_time);
if (unlikely(dm_stats_used(&md->stats)))
dm_stats_account_io(&md->stats, bio_data_dir(bio),
bio->bi_iter.bi_sector, bio_sectors(bio),
@@ -535,7 +535,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
io->md = md;
spin_lock_init(&io->endio_lock);
- start_io_acct(io);
+ io->start_time = READ_ONCE(jiffies);
return io;
}
@@ -1482,6 +1482,7 @@ static void __split_and_process_bio(struct mapped_device *md,
submit_bio_noacct(bio);
}
}
+ start_io_acct(ci.io);
/* drop the extra reference count */
dm_io_dec_pending(ci.io, errno_to_blk_status(error));
--
2.15.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [dm-devel] [PATCH 3/3] dm: properly fix redundant bio-based IO accounting
@ 2022-01-27 19:07 ` Mike Snitzer
0 siblings, 0 replies; 10+ messages in thread
From: Mike Snitzer @ 2022-01-27 19:07 UTC (permalink / raw)
To: axboe; +Cc: linux-block, dm-devel
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().
This approach avoids the need to mess around with any of the
individual IO stats in response to a bio_split() that follows bio
submission.
Reported-by: Bud Brown <bubrown@redhat.com>
Cc: stable@vger.kernel.org
Depends-on: e8d7405fccc6 ("block: add __bio_start_io_acct() to control start_time")
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
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 9849114b3c08..144436301a57 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -489,7 +489,7 @@ static void start_io_acct(struct dm_io *io)
struct mapped_device *md = io->md;
struct bio *bio = io->orig_bio;
- io->start_time = bio_start_io_acct(bio);
+ __bio_start_io_acct(bio, io->start_time);
if (unlikely(dm_stats_used(&md->stats)))
dm_stats_account_io(&md->stats, bio_data_dir(bio),
bio->bi_iter.bi_sector, bio_sectors(bio),
@@ -535,7 +535,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
io->md = md;
spin_lock_init(&io->endio_lock);
- start_io_acct(io);
+ io->start_time = READ_ONCE(jiffies);
return io;
}
@@ -1482,6 +1482,7 @@ static void __split_and_process_bio(struct mapped_device *md,
submit_bio_noacct(bio);
}
}
+ start_io_acct(ci.io);
/* drop the extra reference count */
dm_io_dec_pending(ci.io, errno_to_blk_status(error));
--
2.15.0
--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel
^ permalink raw reply related [flat|nested] 10+ messages in thread