linux-kernel - RE: [PATCH] sched/topology: fix the issue groups don't span domain->span for NUMA diameter

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:   Wed, 03 Feb 2021 11:42:15 +0000
From:   Valentin Schneider <valentin.schneider@....com>
To:     "Song Bao Hua \(Barry Song\)" <song.bao.hua@...ilicon.com>,
        "vincent.guittot\@linaro.org" <vincent.guittot@...aro.org>,
        "mgorman\@suse.de" <mgorman@...e.de>,
        "mingo\@kernel.org" <mingo@...nel.org>,
        "peterz\@infradead.org" <peterz@...radead.org>,
        "dietmar.eggemann\@arm.com" <dietmar.eggemann@....com>,
        "morten.rasmussen\@arm.com" <morten.rasmussen@....com>,
        "linux-kernel\@vger.kernel.org" <linux-kernel@...r.kernel.org>
Cc:     "linuxarm\@openeuler.org" <linuxarm@...neuler.org>,
        "xuwei \(O\)" <xuwei5@...wei.com>,
        "Liguozhu \(Kenneth\)" <liguozhu@...ilicon.com>,
        "tiantao \(H\)" <tiantao6@...ilicon.com>,
        wanghuiqiang <wanghuiqiang@...wei.com>,
        "Zengtao \(B\)" <prime.zeng@...ilicon.com>,
        Jonathan Cameron <jonathan.cameron@...wei.com>,
        "guodong.xu\@linaro.org" <guodong.xu@...aro.org>,
        Meelis Roos <mroos@...ux.ee>
Subject: RE: [PATCH] sched/topology: fix the issue groups don't span domain->span for NUMA diameter > 2

On 03/02/21 10:23, Song Bao Hua (Barry Song) wrote:
>> -----Original Message-----
>> From: Valentin Schneider [mailto:valentin.schneider@....com]
>> Thoughts?
>
> I guess the original purpose of overlapping groups is creating as few groups
> as possible. If we totally remove overlapping groups, it seems we will create
> much more groups?
> For example, while node0 begins to build sched_domain for distance 20, it will
> add node2, since the distance between node2 and node3 is 15, so while node2 is
> added, node3 is also added as node2's lower domain has covered node3. So we need
> two groups only for node0's sched_domain of distance level 20.
> +-------+                  +--------+
>  |       |      15          |        |
>  |  node0+----------------+ | node1  |
>  |       |                  |        |
>  +----+--+                XXX--------+
>       |                 XXX
>       |                XX
> 20    |         15   XX
>       |            XXX
>       |       X XXX
>  +----+----XXX               +-------+
>  |         |     15          |  node3|
>  | node2   +-----------------+       |
>  |         |                 +-------+
>  +---------+
>
> If we remove overlapping group, we will add a group for node2, another
> group for node3. Then we get three groups.
>
> I am not sure if it is always positive for performance.
>

Neither am I! At the same time our strategy for generating groups is pretty
much flawed for anything with distance > 2, so I'd like to have a saner
setup that doesn't involve fixing groups "after the fact".

I have a sort-of-working hack, I'll make this into a patch and toss it out
for discussion.