[LWN Logo]

Date:	Fri, 4 Dec 1998 15:07:07 GMT
From:	"Stephen C. Tweedie" <sct@redhat.com>
To:	Tigran Aivazian <tigran@aivazian.demon.co.uk>
Subject: SAR (was Re: disks stats through /proc)

Hi,

On Thu, 3 Dec 1998 13:39:42 +0000 (GMT), Tigran Aivazian
<tigran@aivazian.demon.co.uk> said:

> IMHO, this should be done on a fine-grained (partition level) rather than
> coarse (drive) level. There is enough information in
> ll_rw_blk.c/add_request() to do it now but, of course, kernel_stat
> structure will have to be seriously modified.

> There is something frustrating about the quality and speed of Linux
> development. I.e. the quality is too high and the speed is too high,
> in other words, I can implement this disk stat feature, but I bet
> someone else has already done it and is just about to release his
> patch to Linus soon...

Yep, done that. :)

I have patches for 2.0.34/35 and 2.1.125 already working, outputing
both per-partition and per-spindle access stats via /proc/partitions.
A "sard" front-end gives human-readable output.  (It is modeled on the
output of the SVR4 "sar -d" output.)

Currently you get average %utilisation; average request queue length;
number of K transfered plus number of distinct IOs for reads, writes
and combined; and average request service time for each disk and each
partition. 

Look for

	ftp://ftp.uk.linux.org:/pub/linux/sct/fs/sard-0.2.tar.gz

for the patches and sard source code.  The plan is to integrate this
into 2.3 once we have got a more sensible kdev_t in the kernel.

--Stephen

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/