Henrik Nordstrom wrote:
> Joe Cooper wrote:
>
>>I'll see if I have time to do more work on this before shipping out the
>>box (I have to ship it first thing tomorrow morning for it to arrive at
>>the event on time--and I have a ton of other preparation to do before I
>>can leave myself). I've got to get one complete PM-4 run in before
>>then, or Alex won't let me play when I get there.
>>
>
> A bit short of time to start discussing things like store selection..
> but good luck, and make it run!
Hehe... Yep. It only came about a couple of weeks ago that I would be
able to make it this time...so I wasn't expecting to have to do all this
in preparation. After thinking for a while about what kind of system to
take (a decision primarily based on what I have sitting on the bench at
this moment), and thinking about the kind of performance I could squeeze
out of it, I decided to try something a bit new (thus the ramdisk
stuff)...I was also going to pop in a second processor and run two Squid
processes, but found that two IDE disks just can't push enough data to
saturate even one fast processor (even with the help of a bunch of RAM).
I've banged on COSS a bit, and was spending some time seeing about
giving it a go, but found a couple of segfaults under Linux (which I
think Adrian has reproduced and is working on a fix for now). If he
gets them tracked down and killed by Monday or so, I'll try it for one
of my runs (I may only get two, since I have to fly out after
Wednesday). It would be nice to run something really new.
BTW-Henrik, I've been meaning to commend you and Adrian for the
aufs+storeio stuff. It overloads very gracefully, and without /too/
much of a hit to overall performance and hit ratio. I haven't been able
to crash the box because of load yet (and believe me I've tried). It's
definitely more relaxing to know that if I push it a little too hard it
won't fall down (2.2Stable5+async, while very zippy, had the annoying
habit of blowing up when pushed too hard).
-- Joe Cooper <joe@swelltech.com> http://www.swelltech.com Web Caching Appliances and SupportReceived on Fri Nov 09 2001 - 11:44:36 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:14:37 MST