[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <ZiB_2ryBOxq2_IyG@slm.duckdns.org>
Date: Wed, 17 Apr 2024 16:05:14 -1000
From: Tejun Heo <tj@...nel.org>
To: Yu Kuai <yukuai1@...weicloud.com>
Cc: axboe@...nel.dk, chenhuacai@...nel.org, josef@...icpanda.com,
jhs@...atatu.com, svenjoac@....de, raven@...maw.net,
pctammela@...atatu.com, qde@...cy.de, zhaotianrui@...ngson.cn,
linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
loongarch@...ts.linux.dev, cgroups@...r.kernel.org,
yi.zhang@...wei.com, yangerkun@...wei.com,
"yukuai (C)" <yukuai3@...wei.com>
Subject: Re: [PATCH RFC v2 5/6] blk-throttle: support to destroy throtl_data
when blk-throttle is disabled
Hello,
On Wed, Apr 17, 2024 at 09:39:43AM +0800, Yu Kuai wrote:
..
> I guess I'll do lazy init first, and then modularization for rq_qos,
> and leave blk-throtl there for now. Perhaps add a new throtl model in
> iocost can replace blk-throtl in the future.
That sounds like a plan.
> BTW, currently during test of iocost, I found that iocost can already
> achieve that, for example, by following configure:
>
> echo "$dev enable=1 min=100 max=100" > qos
> echo "$dev wbps=4096 wseqiops=1 wrandiops=1" > model
>
> In the test, I found that wbps and iops is actually limited to the
> set value.
Yeah, it shouldn't be too difficult to add .max support to iocost so that
you can say something like "this cgroup subtree can't use more than 60% of
available capacity". That'd be really cool to have.
Thanks.
--
tejun
Powered by blists - more mailing lists