> Date: Fri, 27 Feb 1998 00:56:46 -0800 (PST)
> From: Dean Gaudet <dgaudet-list-linux-kernel@arctic.org>
>
> No joke, the system had over 350Mb cached, it was definately not
> touching disk while accessing this directory. If it were touching
> disk I bet interactive performance would have been better.
>
> 2.0.x or 2.1.x, this is very important. The dcache in 2.0.x performs
> several orders of magnitude worse than in the 2.1.x kernel. Also, you
> could have long buffer cache hash chains, so experimenting with
> increasing the size of the buffer cache hash table would be
> interesting.
for some odd reason, when i first booted 2.1.45 (i read beforehand about a
new dcache implementation in it), it seemed to *seriously* fly.
unfortunately, it was shown to cause fs corruption.. is there anybody else
who had really good performance with 2.1.45? anyone get a corrupted fs?
anyone know if we can work the cache from 2.1.45 into the next devel, and
fix the corruption problem? or is this asking too much? :)
_ _ __ __ _ _ _
| / |/ /_ __/ /_____ | Nuke Skyjumper |
| / / // / '_/ -_) | "Master of the Farce" |
|_ /_/|_/\_,_/_/\_\\__/ _|_ nuke@bayside.net _|
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu