This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: malloc cache/trace preview
- From: Szabolcs Nagy <szabolcs dot nagy at arm dot com>
- To: Florian Weimer <fweimer at redhat dot com>
- Cc: DJ Delorie <dj at redhat dot com>, <libc-alpha at sourceware dot org>, <nd at arm dot com>
- Date: Wed, 10 Feb 2016 13:26:54 +0000
- Subject: Re: malloc cache/trace preview
- Authentication-results: sourceware.org; auth=none
- Nodisclaimer: True
- References: <201602092251 dot u19MpO5s027665 at greed dot delorie dot com> <56BB2D1B dot 8000804 at arm dot com> <56BB31B7 dot 30203 at redhat dot com>
- Spamdiagnosticmetadata: NSPM
- Spamdiagnosticoutput: 1:23
On 10/02/16 12:48, Florian Weimer wrote:
> On 02/10/2016 01:29 PM, Szabolcs Nagy wrote:
>
>> i think the sbrk in the ctor of the trace tool is not ok,
>> if there are malloc calls using brk before that ctor.
>> (makes the malloc heap non-contiguous.)
>
> malloc has code to compensate for that. Does it work?
>
without looking into it, my guess is that the 'compensation'
has significant effect on malloc behaviour.
> We more or less have to support such use because we expose the sbrk
> interface. (Some mallocs complete avoid using sbrk by default.)
>
> Florian
>