linux-kernel - Re: [RFC PATCH v2 6/6] sched/fair: Implement starvation monitor

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

Message-ID: <20200807150635.GU42956@localhost.localdomain>
Date:   Fri, 7 Aug 2020 17:06:35 +0200
From:   Juri Lelli <juri.lelli@...hat.com>
To:     peterz@...radead.org
Cc:     luca abeni <luca.abeni@...tannapisa.it>, mingo@...hat.com,
        rostedt@...dmis.org, tglx@...utronix.de,
        linux-kernel@...r.kernel.org, tommaso.cucinotta@...tannapisa.it,
        alessio.balsini@...il.com, bristot@...hat.com,
        dietmar.eggemann@....com, linux-rt-users@...r.kernel.org,
        mtosatti@...hat.com, williams@...hat.com,
        valentin.schneider@....com
Subject: Re: [RFC PATCH v2 6/6] sched/fair: Implement starvation monitor

On 07/08/20 16:13, peterz@...radead.org wrote:
> On Fri, Aug 07, 2020 at 03:43:53PM +0200, Juri Lelli wrote:
> 
> > Right, but I fear we won't be able to keep current behavior for wakeups:
> > RT with highest prio always gets scheduled right away?
> 
> If you consider RT throttling, that's already not the case. We can
> consider this fair server to be just another way to implement that.
> 
> At some point, we'll have have to preempt higher priority tasks, that's
> the entire point of the thing after all.
> 

Ah, indeed. But I was thinking we might try to do a little "better" wrt
to RT Throttling while we are at it. :-)

This proposal has the potential to be more flexible and to kick in only
when really needed.