Date: Mon, 5 Apr 1999 08:15:21 -0700 (PDT) From: Tom <tom@uniserve.com> To: Brad Knowles <blk@skynet.be> Cc: Mike Tancsa <mike@sentex.net>, doka@triton.kiev.sovam.com, freebsd-stable@FreeBSD.ORG Subject: Re: benchmark program Message-ID: <Pine.BSF.4.02A.9904050812500.9618-100000@shell.uniserve.ca> In-Reply-To: <19990405163628.014925@relay.skynet.be>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 5 Apr 1999, Brad Knowles wrote: > I'm curious. I looked at bonnie, and it creates a huge file (with > (2**31)-1 problems), which it then reads and re-writes with multiple > child processes (unless I misunderstand the man page). What (2**31) -1) problem? > However, this exercises the buffer cache but does not exercise the Since the file is large, the cache is not useful. > creation of lots of small files, directories and subdirectories, etc... > (e.g., the kind of traffic that one might see with a heavily loaded news > server), and this misses much of the potential performance enhancements > of "soft updates", etc.... Yes, bonnie is situated towards testing raw io performance. > I'm wondering if anyone has heard of any benchmark programs that are > more oriented towards some sort of simulation of a heavily loaded news > server, or the kind of load you might see with a heavily loaded anonymous > ftp server (both during the mirror updates and during heavy reader load)? > Are any of these benchmarks portable to other platforms? Well, it shouldn't be hard to create one. Tom To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.02A.9904050812500.9618-100000>