Hi,
在 2023/09/26 21:12, Kirill Kirilenko 写道:
On 26.09.2023 06:28 +0300, Yu Kuai wrote:
I still don't quite understand what you mean 'kernel freeze', this patch
indeed fix a problem that diskcard bio is treated as normal write bio
and it's splitted.
Can you explain more by how do you judge 'kernel freeze'? In the
meantime dose 'iostat -dmx 1' shows that disk is idle and no dicard io
is handled?
I mean, keyboard and mouse stop working, screen stops updating,
sound card starts playing last audio buffer endlessly. At the same time,
the disk activity indicator goes off.
This means cpu is busy with something, in this case you must use top or
perf to figure out what all your cpus are doing, probably issue io and
handle io interrupt.
I've attached the last output of 'iostat -dmx 1'. My RAID1 LV is 'dm-4',
the underlying PVs are 'nvme0n1' and 'sda'. But the update interval
is 1 second, may be at the moment of freezing all discards have already
been completed.
iostat shows that disk is handling about 600 write, 1200 discard and 900
flush each second. I'm not sure what 'disk activity indicator goes off'
means, but your disk is really busy with handling all these io.
Thanks,
Kuai
