Re: [RFC] [PATCH 0/5 V2] Huge page backed user-space stacks

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: Andrew Morton <akpm@...>
Cc: Mel Gorman <mel@...>, <linuxppc-dev@...>, <libhugetlbfs-devel@...>, <linux-kernel@...>, <linux-mm@...>
Date: Wednesday, August 6, 2008 - 2:49 pm

Andrew Morton <akpm@linux-foundation.org> writes:


The catch with 2MB pages on x86 is that x86 CPUs generally have
much less 2MB TLB entries than 4K entries. So if you're unlucky
and access a lot of mappings you might actually thrash more with
them. That is why they are not necessarily an universal win.

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

Messages in current thread:
Re: [RFC] [PATCH 0/5 V2] Huge page backed user-space stacks, Andi Kleen, (Wed Aug 6, 2:49 pm)
Re: [RFC] [PATCH 0/5 V2] Huge page backed user-space stacks, Michael Ellerman, (Thu Jul 31, 10:32 am)
Re: [RFC] [PATCH 0/5 V2] Huge page backed user-space stacks, Christoph Lameter, (Wed Jul 30, 3:40 pm)
[PATCH 4/5 V2] Build hugetlb backed process stacks, Eric Munson, (Mon Jul 28, 3:17 pm)
Re: [PATCH 4/5 V2] Build hugetlb backed process stacks, Dave Hansen, (Mon Jul 28, 4:37 pm)