Date: Sat, 11 Nov 2000 17:10:33 -0600 From: Dan Nelson <dnelson@emsphone.com> To: Mitch Collinsworth <mitch@ccmr.cornell.edu> Cc: Doug Barton <DougB@FreeBSD.ORG>, freebsd-questions@FreeBSD.ORG, Mitch Collinsworth <mitch@mercury.ccmr.cornell.edu> Subject: Re: Linux malloc better on FreeBSD than FreeBSD malloc? Message-ID: <20001111171033.A21628@dan.emsphone.com> In-Reply-To: <20001111164754.A9356@dan.emsphone.com>; from "Dan Nelson" on Sat Nov 11 16:47:54 GMT 2000 References: <3A0DC4EC.509A982C@FreeBSD.org> <Pine.LNX.4.10.10011111736170.16421-100000@dragon.ccmr.cornell.edu> <20001111164754.A9356@dan.emsphone.com>
next in thread | previous in thread | raw e-mail | index | archive | help
In the last episode (Nov 11), Dan Nelson said: > In the last episode (Nov 11), Mitch Collinsworth said: > > Well I did include the version, but you clipped it from the text > > you included in your message: > > > > > The system the tests are being run on is a 900 MHz Xeon running > > > FreeBSD 4.1-R with 1 GB RAM and 18 GB swap: > > > > I have not yet done any special kernel tuning but I'll try some of > > the options suggested. None of this explains however, why the > > Linux binary running on FreeBSD was able to do what the FreeBSD > > binary could not. That was my first question. > > The "datasize" limits only apply to memory allocated via sbrk(). If > Linux's glibc allocator mmaps /dev/zero for new pages, I don't think > resource limits apply. You might want to try installing the "libdlmalloc" port, linking with that, and re-running your FreeBSD test; dlmalloc implements mmap()-based allocation for large requests. -- Dan Nelson dnelson@emsphone.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20001111171033.A21628>