[prev in list] [next in list] [prev in thread] [next in thread] 

List:       ast-users
Subject:    Re: [ast-users] [patch] vmalloc |mmap(MAP_ANON)| fixes for fragmentation issues (on Solaris) ... / w
From:       Glenn Fowler <glenn.s.fowler () gmail ! com>
Date:       2013-12-10 8:21:45
Message-ID: CAK449vDxbMjx7j3uvT2556Y1q_kKkp+XxW5nZd9So-SnA=gJFA () mail ! gmail ! com
[Download RAW message or body]

[Attachment #2 (multipart/alternative)]


On Mon, Dec 9, 2013 at 5:21 PM, Roland Mainz <roland.mainz@nrubsig.org>wrote:

> On Mon, Dec 9, 2013 at 11:08 PM, Glenn Fowler <glenn.s.fowler@gmail.com>
> wrote:
> > On Mon, Dec 9, 2013 at 4:53 PM, Roland Mainz <roland.mainz@nrubsig.org>
> > wrote:
> [snip]
> >> 4. The patch removes one unneccesary |memset(p, 0, size)| which was
> >> touching pages and therefore allocating them
> >
> > if that memset(0) is in vmopen() then im not sure its unnecessary
> >
> > run these tests to check your patch with different sizes and with/without
> > the memset(0)
> >
> > bin/package use
> > cd builtin
> > nmake test
>
> Seems to be no problem... and neither valgrind nor Rational Purify
> complained. I think the issue is that a memory page obtained via
> |mmap(MAP_ANON)| is zero'ed by the system on the first
> read/write/execute access.
>

it consistently chokes for getmem=safe
memset(0) is required but only the head part to cover the 2 small vmalloc
structs

[Attachment #5 (text/html)]

<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On Mon, Dec 9, 2013 \
at 5:21 PM, Roland Mainz <span dir="ltr">&lt;<a \
href="mailto:roland.mainz@nrubsig.org" \
target="_blank">roland.mainz@nrubsig.org</a>&gt;</span> wrote:<br> <blockquote \
class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc \
solid;padding-left:1ex"><div class="im">On Mon, Dec 9, 2013 at 11:08 PM, Glenn Fowler \
&lt;<a href="mailto:glenn.s.fowler@gmail.com">glenn.s.fowler@gmail.com</a>&gt; \
wrote:<br>

&gt; On Mon, Dec 9, 2013 at 4:53 PM, Roland Mainz &lt;<a \
href="mailto:roland.mainz@nrubsig.org">roland.mainz@nrubsig.org</a>&gt;<br> &gt; \
wrote:<br> </div>[snip]<br>
<div class="im">&gt;&gt; 4. The patch removes one unneccesary |memset(p, 0, size)| \
which was<br> &gt;&gt; touching pages and therefore allocating them<br>
&gt;<br>
</div><div class="im">&gt; if that memset(0) is in vmopen() then im not sure its \
unnecessary<br> &gt;<br>
&gt; run these tests to check your patch with different sizes and with/without<br>
&gt; the memset(0)<br>
&gt;<br>
&gt; bin/package use<br>
&gt; cd builtin<br>
&gt; nmake test<br>
<br>
</div>Seems to be no problem... and neither valgrind nor Rational Purify<br>
complained. I think the issue is that a memory page obtained via<br>
> mmap(MAP_ANON)| is zero&#39;ed by the system on the first<br>
read/write/execute access.<br></blockquote><div><br></div><div>it consistently chokes \
for getmem=safe</div><div>memset(0) is required but only the head part to cover the 2 \
small vmalloc structs</div><div> </div></div></div> </div>



_______________________________________________
ast-users mailing list
ast-users@lists.research.att.com
http://lists.research.att.com/mailman/listinfo/ast-users


[prev in list] [next in list] [prev in thread] [next in thread]