[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <74067d6f-45f8-3c08-1829-828a1aebddee@huawei.com>
Date: Mon, 18 Jan 2021 16:51:03 +0800
From: Chao Yu <yuchao0@...wei.com>
To: Daeho Jeong <daeho43@...il.com>, <linux-kernel@...r.kernel.org>,
<linux-f2fs-devel@...ts.sourceforge.net>, <kernel-team@...roid.com>
CC: Sungjong Seo <sj1557.seo@...sung.com>,
Daeho Jeong <daehojeong@...gle.com>
Subject: Re: [f2fs-dev] [PATCH v3 1/2] f2fs: introduce checkpoint=merge mount
option
On 2021/1/16 9:00, Daeho Jeong wrote:
> From: Daeho Jeong <daehojeong@...gle.com>
>
> We've added a new mount option "checkpoint=merge", which creates a
> kernel daemon and makes it to merge concurrent checkpoint requests as
> much as possible to eliminate redundant checkpoint issues. Plus, we
> can eliminate the sluggish issue caused by slow checkpoint operation
> when the checkpoint is done in a process context in a cgroup having
> low i/o budget and cpu shares, and The below verification result
> explains this.
Could you please summary and add below info into commit message and f2fs.rst?
"Actually, the default I/O priority of kernel thread is "4". So, we're
going to raise this
priority by one, because we want to give one higher priority for
checkpointing thread
than other normal threads. This is the same way to give a I/O priority
to the jbd2 journaling
thread of ext4 filesystem."
Otherwise this patch looks good to me.
Thanks,
Powered by blists - more mailing lists