lkml.org 
[lkml]   [2013]   [Dec]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [PATCH v7 1/4] qrwlock: A queue read/write lock implementation
Date
Peter Zijlstra <peterz@infradead.org> writes:

> On Wed, Dec 18, 2013 at 11:38:29AM -0800, Andi Kleen wrote:
>> (maybe it would be time to get rid of the patchable LOCK though?)
>
> With the argument that Intel simply doesn't ship UP chips anymore, with
> the exception of quark which should probably run custom UP kernels due
> to size constraints anyway?

That, and:

- Anything with a single core only has very fast LOCK
- LOCK generally became much faster everywhere.
- The original reason was for single cpu VM guests, but even those
should increasingly have at least two VCPUs.

-Andi

--
ak@linux.intel.com -- Speaking for myself only


\
 
 \ /
  Last update: 2013-12-18 21:41    [W:0.096 / U:3.700 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site