linux-kernel - Re: [PATCH v3] softlockup: remove hung_task_check

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]

Date:	Fri, 23 Jan 2009 11:04:39 +0100
From:	Frédéric Weisbecker <fweisbec@...il.com>
To:	Ingo Molnar <mingo@...e.hu>
Cc:	Mandeep Baines <msb@...gle.com>, linux-kernel@...r.kernel.org,
	rientjes@...gle.com, mbligh@...gle.com, thockin@...gle.com
Subject: Re: [PATCH v3] softlockup: remove hung_task_check_count

2009/1/23 Ingo Molnar <mingo@...e.hu>:
>
> * Mandeep Baines <msb@...gle.com> wrote:
>
>> On Thu, Jan 22, 2009 at 11:55 AM, Mandeep Singh Baines <msb@...gle.com> wrote:
>> >
>> > The unlock and lock could be removed and only compiled in if PREEMPT.
>> > If the number of tasks isn't bound, the lock might be held too long.
>> >
>>
>> This is incorrect. The adding the lock and unlock will not make the
>> system more pre-emptive. To be more pre-emptive you'd want to check
>> need_resched() as often as possible.
>>
>> > It would be kinda funny if hung_task caused a softlockup.
>> >
>>
>> Again. This is incorrect. Rescheduling if need_resched() will prevent
>> softlockup.
>>
>> Not sure what I was thinking this morning;)
>>
>> However, I am happy with the patch. To give writers a chance, the lock
>> should held for bounded time. Holding the lock in khungtask (which is
>> running at low scheduler priority) could potentially be delaying
>> important work. The longer the lock is held, the bigger the priority
>> inversion problem.
>
> not sure i like the whole idea of removing the max iterations check. In
> theory if there's a _ton_ of tasks, we could spend a lot of time looping
> there. So it always looked prudent to limit it somewhat.
>
>        Ingo
>

Which means we can loose several of them. Would it hurt to iterate as
much as possible along the task list,
keeping some care about writers starvation and latency?
BTW I thought about the slow work framework, but I can't retrieve
it....  But this thread has already a slow priority.

Would it be interesting to provide a way for rwlocks to know if there
is writer waiting for the lock?
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/