Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 16 Jan 2014 11:20:23 +0400
From:      Alexander <ags18@yandex.ru>
To:        "freebsd-ports@freebsd.org" <freebsd-ports@freebsd.org>
Cc:        "stable@freebsd.org" <stable@freebsd.org>
Subject:   Re: SCHED_ULE bug (was Re: cpuminer mines only on one core regardless of "--threads" option)
Message-ID:  <37721389856823@web8h.yandex.ru>
In-Reply-To: <113571389724340@web5g.yandex.ru>
References:  <399751389704518@web9j.yandex.ru> <52D541E7.3040305@gmail.com> <5101389708996@web13m.yandex.ru> <52D55B24.8080102@freebsd.org> <CAFt_eMr18eog8VNZS=MkmJwuubYD%2BNTxGJLpOOqt0GcO-Xsfnw@mail.gmail.com> <113571389724340@web5g.yandex.ru>

next in thread | previous in thread | raw e-mail | index | archive | help


14.01.2014, 22:32, "Alexander" <ags18@yandex.ru>:
> 14.01.2014, 20:14, "Subbsd" <subbsd@gmail.com>:
>
>> šOn Tue, Jan 14, 2014 at 7:43 PM, Andrey Chernov <ache@freebsd.org> wrote:
>>> ššOn 14.01.2014 17:01, Alexander wrote:
>>>> ššon Freebsd 9.2 x64 on 5 different PCs I installed net-p2p/cpuminer
>>>> ššfrom ports and by "pkg install" - result is the same - minerd mines
>>>> ššonly on one core regardless of "--threads" option.
>>> šš...
>>>> šš# top -P
>>>> ššCPU 0: š0.0% user, š0.0% nice, š0.0% system, š0.0% interrupt, š100% idle
>>>> ššCPU 1: š0.0% user, š0.0% nice, š0.0% system, š0.0% interrupt, š100% idle
>>>> ššCPU 2: š0.0% user, š0.0% nice, š0.0% system, š0.0% interrupt, š100% idle
>>>> ššCPU 3: š0.0% user, š100% nice, š0.0% system, š0.0% interrupt, š0.0% idle
>>> ššThis is SCHED_ULE bug, I see _all_ processes (not minerd only in
>>> ššparticular) stuck to the last CPU too (top's 'C' column is equal to the
>>> ššlast CPU and never changes), latest -stable i386. It disappears for me
>>> ššswitching to SCHED_4BSD.
>>>
>
> reboot didn't help (try on 3 different PCs)
> I'll try switching to SCHED_4BSD tomorrow š(thanks Andrey Chernov)
>

I sad wrong.
minerd was started from cron after reboot immediately and broke SMP, so when I disable minerd from cron and reboot - SMP works fine.
I think Andrey Chernov said here the reason http://www.freebsd.org/cgi/query-pr.cgi?pr=kern/163585#reply3
So this bug is alive - on 9.1 and 9.2 x64 releases.
I didn't try SCHED_4BSD yet, cause don't wont to use not-generic kernel because of mining only, but for interest I'll try it on one machine on this weekends.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?37721389856823>