Re: [RFC v1 2/2] mm: SLUB Freelist randomization

From	Joonsoo Kim <js1304@gmail.com>
Newsgroups	linux.kernel
Subject	Re: [RFC v1 2/2] mm: SLUB Freelist randomization
Date	2016-05-20 04:20 +0200
Message-ID	<rAIcF-83P-1@gated-at.bofh.it> (permalink)
References	(3 earlier) <rAexY-5ID-23@gated-at.bofh.it> <rAf0Z-67j-5@gated-at.bofh.it> <rAfaG-6av-17@gated-at.bofh.it> <rAlzr-1So-5@gated-at.bofh.it> <rACJX-4xR-7@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

2016-05-20 5:20 GMT+09:00 Thomas Garnier <thgarnie@google.com>:
> I ran the test given by Joonsoo and it gave me these minimum cycles
> per size across 20 usage:

I can't understand what you did here. Maybe, it's due to my poor Engling.
Please explain more. You did single thread test? Why minimum cycles
rather than average?

> size,before,after
> 8,63.00,64.50 (102.38%)
> 16,64.50,65.00 (100.78%)
> 32,65.00,65.00 (100.00%)
> 64,66.00,65.00 (98.48%)
> 128,66.00,65.00 (98.48%)
> 256,64.00,64.00 (100.00%)
> 512,65.00,66.00 (101.54%)
> 1024,68.00,64.00 (94.12%)
> 2048,66.00,65.00 (98.48%)
> 4096,66.00,66.00 (100.00%)

It looks like performance of all size classes are the same?

> I assume the difference is bigger if you don't have RDRAND support.

What does RDRAND means? Kconfig? How can I check if I have RDRAND?

> Christoph, Joonsoo: Do you think it would be valuable to add a CONFIG
> to disable additional randomization per new page? It will remove
> additional entropy but increase performance for machines without arch
> specific randomization instructions.

I don't think that it deserve another CONFIG. If performance is a matter,
I think that removing additional entropy is better until it is proved that
entropy is a problem.

Thanks.

Thread

[RFC v1 2/2] mm: SLUB Freelist randomization Thomas Garnier <thgarnie@google.com> - 2016-05-18 20:00 +0200
  Re: [RFC v1 2/2] mm: SLUB Freelist randomization Christoph Lameter <cl@linux.com> - 2016-05-18 20:30 +0200
    Re: [RFC v1 2/2] mm: SLUB Freelist randomization Thomas Garnier <thgarnie@google.com> - 2016-05-18 20:40 +0200
      Re: [RFC v1 2/2] mm: SLUB Freelist randomization Christoph Lameter <cl@linux.com> - 2016-05-18 21:10 +0200
        Re: [RFC v1 2/2] mm: SLUB Freelist randomization Thomas Garnier <thgarnie@google.com> - 2016-05-18 21:20 +0200
          Re: [RFC v1 2/2] mm: SLUB Freelist randomization Joonsoo Kim <iamjoonsoo.kim@lge.com> - 2016-05-19 04:10 +0200
            Re: [RFC v1 2/2] mm: SLUB Freelist randomization Thomas Garnier <thgarnie@google.com> - 2016-05-19 22:30 +0200
              Re: [RFC v1 2/2] mm: SLUB Freelist randomization Joonsoo Kim <js1304@gmail.com> - 2016-05-20 04:20 +0200
                Re: [RFC v1 2/2] mm: SLUB Freelist randomization Thomas Garnier <thgarnie@google.com> - 2016-05-20 18:30 +0200
                Re: [RFC v1 2/2] mm: SLUB Freelist randomization Joonsoo Kim <iamjoonsoo.kim@lge.com> - 2016-05-24 07:20 +0200

csiph-web