Skip to contentSkip to conversation

Different writeback timing since v5.14

DISCUSSION Richard Weinberger 2 participants 4 messages Mar 1, 2022 – Mar 2, 2022

Subsystems (3)
lore
Share & tools
lore

Richard Weinberger

author maintainer
#0 lore raw

Hi!

Rafał and I discovered that page writeback on UBIFS behaves different since v5.14. When a simple write, such as "echo foo > /mnt/ubibfs/bar.txt", happens it takes a few seconds until writeback calls ubifs_writepage().

Before commit ab19939a6a50 ("mm/page-writeback: Fix performance when BDI's share of ratio is 0.") it was 30 seconds (vm.dirty_expire_centisecs), after this change it happens after 5 seconds (vm.dirty_writeback_centisecs).

Is this expected?
Just want to make sure that the said commit didn't uncover an UBIFS issue.

Thanks,
//richard

reviewer
#1 lore raw

Hi!

Quoted 10 lines · Richard Weinberger

Rafał and I discovered that page writeback on UBIFS behaves different since v5.14. When a simple write, such as "echo foo > /mnt/ubibfs/bar.txt", happens it takes a few seconds until writeback calls ubifs_writepage().

Before commit ab19939a6a50 ("mm/page-writeback: Fix performance when BDI's share of ratio is 0.") it was 30 seconds (vm.dirty_expire_centisecs), after this change it happens after 5 seconds (vm.dirty_writeback_centisecs).

Is this expected?
Just want to make sure that the said commit didn't uncover an UBIFS issue.

Yes, I think it is expected. Likely the background threshold for UBIFS bdi is very small (probably UBIFS is not used much for writeback compared to other filesystems). Previously, we just used wb_stat() which returned 0 (PCP counter inexact value) and so background writeback didn't trigger. Now we use wb_stat_sum() when threshold is small, get exact value of dirty pages and decide to start background writeback.

The only thing is, whether it is really expected that the threshold for UBIFS bdi is so small. You can check the values in /sys/kernel/debug/bdi/<bdi>/stats.

Honza

Signature · 2 lines
Jan Kara <[email protected]>
SUSE Labs, CR
author maintainer
#2 lore raw

Jan,

----- Ursprüngliche Mail -----

Quoted 10 lines

Von: "Jan Kara" <[email protected]>

Quoted 2 lines

Is this expected?
Just want to make sure that the said commit didn't uncover an UBIFS issue.

Yes, I think it is expected. Likely the background threshold for UBIFS bdi is very small (probably UBIFS is not used much for writeback compared to other filesystems). Previously, we just used wb_stat() which returned 0 (PCP counter inexact value) and so background writeback didn't trigger. Now we use wb_stat_sum() when threshold is small, get exact value of dirty pages and decide to start background writeback.

Thanks for the prompt reply!

Quoted 3 lines

The only thing is, whether it is really expected that the threshold for UBIFS bdi is so small. You can check the values in /sys/kernel/debug/bdi/<bdi>/stats.

BdiDirtyThresh is indeed 0.

BdiWriteback:                0 kB
BdiReclaimable:              0 kB
BdiDirtyThresh:              0 kB
DirtyThresh:            772620 kB
BackgroundThresh:       385836 kB
BdiDirtied:                  0 kB
BdiWritten:                  0 kB
BdiWriteBandwidth:      102400 kBps
b_dirty:                     0
b_io:                        0
b_more_io:                   0
b_dirty_time:                0
bdi_list:                    1
state:                       1

Thanks,
//richard

reviewer
#3 lore raw
Quoted 22 lines · Richard Weinberger

Jan,

----- Ursprüngliche Mail -----

Quoted 10 lines

Von: "Jan Kara" <[email protected]>

Quoted 2 lines

Is this expected?
Just want to make sure that the said commit didn't uncover an UBIFS issue.

Yes, I think it is expected. Likely the background threshold for UBIFS bdi is very small (probably UBIFS is not used much for writeback compared to other filesystems). Previously, we just used wb_stat() which returned 0 (PCP counter inexact value) and so background writeback didn't trigger. Now we use wb_stat_sum() when threshold is small, get exact value of dirty pages and decide to start background writeback.

Thanks for the prompt reply!

Quoted 3 lines

The only thing is, whether it is really expected that the threshold for UBIFS bdi is so small. You can check the values in /sys/kernel/debug/bdi/<bdi>/stats.

BdiDirtyThresh is indeed 0.

Quoted 14 lines
BdiWriteback:                0 kB
BdiReclaimable:              0 kB
BdiDirtyThresh:              0 kB
DirtyThresh:            772620 kB
BackgroundThresh:       385836 kB
BdiDirtied:                  0 kB
BdiWritten:                  0 kB
BdiWriteBandwidth:      102400 kBps
b_dirty:                     0
b_io:                        0
b_more_io:                   0
b_dirty_time:                0
bdi_list:                    1
state:                       1

Yes, so this looks expected given the BDI wasn't active yet at all...

Honza

Signature · 2 lines
Jan Kara <[email protected]>
SUSE Labs, CR