linux-kernel - Re: [PATCH RFC] Documentation: Add document for false sharing

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]

Message-ID: <d0032404-e627-2d51-9c7b-42f5cdf29929@infradead.org>
Date:   Thu, 23 Mar 2023 21:30:14 -0700
From:   Randy Dunlap <rdunlap@...radead.org>
To:     Feng Tang <feng.tang@...el.com>
Cc:     Jonathan Corbet <corbet@....net>, linux-doc@...r.kernel.org,
        linux-kernel@...r.kernel.org,
        Arnaldo Carvalho de Melo <acme@...hat.com>,
        Joe Mario <jmario@...hat.com>, Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Eric Dumazet <edumazet@...gle.com>,
        Shakeel Butt <shakeelb@...gle.com>, dave.hansen@...el.com,
        ying.huang@...el.com, tim.c.chen@...el.com, andi.kleen@...el.com
Subject: Re: [PATCH RFC] Documentation: Add document for false sharing

Hi--

On 3/23/23 20:03, Feng Tang wrote:
> Hi Randy,
> 
> Thank you for the thorough reviews!
> 
> On Thu, Mar 23, 2023 at 09:49:02AM -0700, Randy Dunlap wrote:
>> Hi,
>>
>> Lots of good/interesting info here.
>>
>> On 3/23/23 01:26, Feng Tang wrote:
>>> From: "Tang, Feng" <feng.tang@...el.com>


>>> +
>>> +'refcount' is modified frequently, but 'name' is set once at object
>>> +creation time and is never modified.  When many CPUs access 'foo' at
>>> +the same time, and 'refcount' is only bumped by one CPU frequently,
>>> +while 'name' is read by all other CPUs, which have to reload the whole
>>> +cache line over and over, even though the 'name' is never changed.
>>
>> That last "sentence" is not a sentence.
> 
> How about:
> 
> "
> When many CPUs access 'foo' at the same time, with 'refcount' being only
> bumped by one CPU frequently and 'name' being read by other CPUs, all
> those reading CPUs have to reload the whole cache line over and over
> due to the 'sharing', even though 'name' is never changed.
> "
> ?

Yes, that's good. Thanks.

-- 
~Randy