MIME-Version: 1.0
References: <20211214031553.16435-1-yajun.deng@linux.dev> <CAPhsuW5X+zewpKoJLjMMGOUeSiJ1EYqD+0i1bA8y7SFtJLkMeg@mail.gmail.com>
 <0d07e13a5454dfb03b22e5223d101a1b@linux.dev> <CAPhsuW6T_nqqfOtj_dVn9KV+iUbki2X3WU3pxfo25Ewj3i5ZjA@mail.gmail.com>
 <3ed867e06f7f9bb9d89beaafc50905c8@linux.dev> <CAPhsuW63KawpM0vBPo9gXjgELKMtUtsL0M4DkbwWZTkub2ZDSw@mail.gmail.com>
In-Reply-To: <CAPhsuW63KawpM0vBPo9gXjgELKMtUtsL0M4DkbwWZTkub2ZDSw@mail.gmail.com>
From:   Daniel Vacek <neelx.g@gmail.com>
Date:   Fri, 17 Dec 2021 22:51:38 +0100
Message-ID: <CAA7rmPGOL0vGg_6xxyTx5fNHP75ZYYXukF737ycqyLgmYpqoVA@mail.gmail.com>
Subject: Re: [PATCH] lib/raid6: fix abnormally high latency
To:     Song Liu <song@kernel.org>
Cc:     Yajun Deng <yajun.deng@linux.dev>, stockhausen@collogia.de,
        open list <linux-kernel@vger.kernel.org>,
        linux-rt-users <linux-rt-users@vger.kernel.org>,
        linux-raid <linux-raid@vger.kernel.org>, masahiroy@kernel.org,
        williams@redhat.com
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Thu, Dec 16, 2021 at 1:19 PM Song Liu <song@kernel.org> wrote:
> I think allowing preempt may still affect the speed comparison. But
> such discrepancy
> should be acceptable. I will apply this to md-next.

No, please. This could eventually result with people starting to
report 'sometimes the storage does not perform' or 'random high CPU
usage on some boots' kind of issues.

We should not touch this. See my other email with detailed explanation.

--nX

> Thanks,
> Song