linux-kernel - Re: single aio thread is migrated crazily by scheduler

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: <20191209165800.GB27229@linux.vnet.ibm.com>
Date:   Mon, 9 Dec 2019 22:28:00 +0530
From:   Srikar Dronamraju <srikar@...ux.vnet.ibm.com>
To:     Jens Axboe <axboe@...nel.dk>
Cc:     Boaz Harrosh <boaz@...xistor.com>, Phil Auld <pauld@...hat.com>,
        Ming Lei <ming.lei@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Dave Chinner <david@...morbit.com>,
        linux-block@...r.kernel.org, linux-fsdevel@...r.kernel.org,
        linux-xfs@...r.kernel.org, linux-kernel@...r.kernel.org,
        Jeff Moyer <jmoyer@...hat.com>,
        Dave Chinner <dchinner@...hat.com>,
        Eric Sandeen <sandeen@...hat.com>,
        Christoph Hellwig <hch@....de>, Ingo Molnar <mingo@...hat.com>,
        Tejun Heo <tj@...nel.org>,
        Vincent Guittot <vincent.guittot@...aro.org>
Subject: Re: single aio thread is migrated crazily by scheduler

* Jens Axboe <axboe@...nel.dk> [2019-11-21 09:19:29]:

> > 
> > I wish there was a flag to wake_up() or to the event object that says
> > to relinquish the remaning of the time-slice to the waiter on same
> > CPU, since I will be soon sleeping.
> 
> Isn't that basically what wake_up_sync() is?
> 

Workqueue don't seem to be using wait_queue_head which is needed when using
wake_up_sync and its related APIs.  Also wake_up_sync would work when the
waking task seems to hand off the CPU and goes to sleep/block. However here,
i.e in fsperf case atleast, the waking thread continues to run after it has
woken the per cpu workqueue.

-- 
Thanks and Regards
Srikar Dronamraju