Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1554155

Re: [PATCH] mm: support __GFP_REPEAT in kvmalloc_node

From Michal Hocko <mhocko@kernel.org>
Newsgroups linux.kernel
Subject Re: [PATCH] mm: support __GFP_REPEAT in kvmalloc_node
Date 2017-01-09 10:00 +0100
Message-ID <sXDY6-1SO-5@gated-at.bofh.it> (permalink)
References <sVb0e-7pH-41@gated-at.bofh.it> <sVYki-8gW-33@gated-at.bofh.it> <sWBEZ-1NR-1@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On Fri 06-01-17 13:09:36, Vlastimil Babka wrote:
> On 01/04/2017 07:12 PM, Michal Hocko wrote:
> > While checking opencoded users I've encountered that vhost code would
> > really like to use kvmalloc with __GFP_REPEAT [1] so the following patch
> > adds support for __GFP_REPEAT and converts both vhost users.
> > 
> > So currently I am sitting on 3 patches. I will wait for more feedback -
> > especially about potential split ups or cleanups few more days and then
> > repost the whole series.
> > 
> > [1] http://lkml.kernel.org/r/20170104150800.GO25453@dhcp22.suse.cz
> > ---
> > From 0b92e4d2e040524b878d4e7b9ee88fbad5284b33 Mon Sep 17 00:00:00 2001
> > From: Michal Hocko <mhocko@suse.com>
> > Date: Wed, 4 Jan 2017 18:01:39 +0100
> > Subject: [PATCH] mm: support __GFP_REPEAT in kvmalloc_node
> > 
> > vhost code uses __GFP_REPEAT when allocating vhost_virtqueue resp.
> > vhost_vsock because it would really like to prefer kmalloc to the
> > vmalloc fallback - see 23cc5a991c7a ("vhost-net: extend device
> > allocation to vmalloc") for more context. Michael Tsirkin has also
> > noted:
> > "
> > __GFP_REPEAT overhead is during allocation time.  Using vmalloc means all
> > accesses are slowed down.  Allocation is not on data path, accesses are.
> > "
> > 
> > Let's teach kvmalloc_node to handle __GFP_REPEAT properly. There are two
> > things to be careful about. First we should prevent from the OOM killer
> > and so have to involve __GFP_NORETRY by default and secondly override
> > __GFP_REPEAT for !costly order requests as the __GFP_REPEAT is ignored
> > for !costly orders.
> > 
> > This patch shouldn't introduce any functional change.
> 
> Which is because the converted usages are always used for costly order,
> right.

I have overlooked this remark previously. You are right. And I've
updated the documentation and also the inline comment to be more
explicit about this. We do not have a good way to support __GFP_REPEAT
for !costly orders currently unfortunatelly. Maybe I should revive my
__GFP_RETRY_MAYFAIL patch, this would be another user (outside of xfs
which already wants something like that for KM_MAYFAIL.
-- 
Michal Hocko
SUSE Labs

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread


Thread

[PATCH] mm: support __GFP_REPEAT in kvmalloc_node Michal Hocko <mhocko@kernel.org> - 2017-01-04 19:20 +0100
  Re: [PATCH] mm: support __GFP_REPEAT in kvmalloc_node Vlastimil Babka <vbabka@suse.cz> - 2017-01-06 13:20 +0100
    Re: [PATCH] mm: support __GFP_REPEAT in kvmalloc_node Michal Hocko <mhocko@kernel.org> - 2017-01-06 13:40 +0100
    Re: [PATCH] mm: support __GFP_REPEAT in kvmalloc_node Michal Hocko <mhocko@kernel.org> - 2017-01-09 10:00 +0100

csiph-web