Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 2 Dec 2010 13:14:20 -0800
From:      Artem Belevich <fbsdlist@src.cx>
To:        Andrew Duane <aduane@juniper.net>
Cc:        "freebsd-hackers@freebsd.org" <freebsd-hackers@freebsd.org>
Subject:   Re: Question about process rlimits
Message-ID:  <AANLkTi=g_wCn2UK8afB0srfM%2B_y8gNLCKQKDRxrNUdSg@mail.gmail.com>
In-Reply-To: <AC6674AB7BC78549BB231821ABF7A9AE907A1E0703@EMBX01-WF.jnpr.net>
References:  <AC6674AB7BC78549BB231821ABF7A9AE907A1E0703@EMBX01-WF.jnpr.net>

next in thread | previous in thread | raw e-mail | index | archive | help
Hi,

On Thu, Dec 2, 2010 at 12:51 PM, Andrew Duane <aduane@juniper.net> wrote:
>
> I've been poking at some bugs we have around pushing user memory to/past =
the limits of our box, and decided to try seeing what happens on a stock Fr=
eeBSD system (7.1 in this case).
>
> Basically I have a program that mallocs big memory chunks and zeros them =
to consume both physical and virtual memory. I had expected the program to =
stop malloc'ing when brk() reaches the process' RLIMIT_DATA (512MB cur and =
max). It didn't. It happily malloc'd many gigabytes of memory until I stopp=
ed it.
>
> On our 6.2 based product boxes, RLIMIT_DATA correctly stops the malloc fr=
om continuing, just like the manuals say.
>
> Am I missing something?

Perhaps that malloc has two ways of grabbing memory from system --
sbrk() and mmap() and they are subject to different limits. I believe
these days malloc is allowed to use both but prefers mmap which would
explain why RLIMIT_DATA didn't have much effect.

Try forcing malloc to use sbrk only via MALLOC_OPTIONS=3DDm (not sure if
that's correct way to specify my intent, though).

--Artem



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTi=g_wCn2UK8afB0srfM%2B_y8gNLCKQKDRxrNUdSg>