Re: tbench regression - Why process scheduler has impact on tbench and why small per-cpu slab (SLUB) cache creates the scenario?

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

On Tue, 11 Sep 2007, Nick Piggin wrote:


Its not? I have had Intel test this thoroughly and they assured me that it 
is up to SLAB. This particular case is an synthetic tests for a PAGE_SIZE 
alloc and SLUB was not optimized for that case because PAGE_SIZEd 
allocations should be handled by the page allocators. Quicklists were 
introduced for the explicit purpose to get these messy page sized cases 
out of the slab allocators.


Ok so you are for pushing in the page allocator pass through patch from mm 
into rc6? Isnt it a bit late for such a change? I would think that 2.6.24
is early enough.
-
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Re: tbench regression - Why process scheduler has impact o ..., Christoph Lameter, (Tue Sep 4, 11:58 pm)
Re: tbench regression - Why process scheduler has impact o ..., Christoph Lameter, (Wed Sep 5, 12:07 am)
Re: tbench regression - Why process scheduler has impact o ..., Christoph Lameter, (Mon Sep 10, 12:07 pm)
Re: tbench regression - Why process scheduler has impact o ..., Christoph Lameter, (Tue Sep 11, 1:19 pm)
Re: tbench regression - Why process scheduler has impact o ..., Siddha, Suresh B, (Wed Sep 12, 11:04 pm)
Re: tbench regression - Why process scheduler has impact o ..., Christoph Lameter, (Thu Sep 13, 11:03 am)
Re: tbench regression - Why process scheduler has impact o ..., Siddha, Suresh B, (Fri Sep 14, 12:15 pm)
Re: tbench regression - Why process scheduler has impact o ..., Christoph Lameter, (Fri Sep 14, 12:51 pm)
Re: tbench regression - Why process scheduler has impact o ..., Christoph Lameter, (Thu Sep 20, 10:53 am)