Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 02 Jul 2013 09:00:21 -0700
From:      John Baldwin <jhb@FreeBSD.org>
To:        Julian Elischer <julian@freebsd.org>
Cc:        svn-src-head@freebsd.org, svn-src-all@freebsd.org, src-committers@freebsd.org
Subject:   Re: svn commit: r252346 - head/share/man/man9
Message-ID:  <51D2F915.2070303@FreeBSD.org>
In-Reply-To: <51CEE326.2010903@freebsd.org>
References:  <201306281633.r5SGXjFU017827@svn.freebsd.org> <51CEDE2B.60204@freebsd.org> <51CEE326.2010903@freebsd.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On 6/29/13 6:37 AM, Julian Elischer wrote:
> On 6/29/13 9:16 PM, Julian Elischer wrote:
>> thanks!
>>
>>
>>> -If the owner is not currently actually running then the spin step is
>>> skipped.
>>> +then a thread attempting to acquire the mutex will spin rather than
>>> yielding
>>> +the processor.
> Am I wrong in thinking that it will only spin for a short while,
> eventually yielding?
> 
> The original text said this but the new text implies it will spin forever.

It does not use a spin timeout.  I considered adding a separate note to
define adaptive spinning generically as it is used by multiple lock
types (mutexes, rwlocks, and sx locks).

-- 
John Baldwin



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?51D2F915.2070303>