Have you considered using NAPI(Linux)/polling(FreeBSD)?
Although it can increase response times a little, but helps freeing the
machine from the interrupt load.
On 05/03/07 20:48, Steve Grimm wrote:
At peak times we see about 35-40% utilization (that’s across all 4
CPUs.) But as you say, that number will vary dramatically depending on
how you use it. The biggest single user of CPU time isn’t actually
memcached per se; it’s interrupt handling for all the incoming packets.
-Steve
On 5/3/07 11:41 AM, "Jerry Maldonado" <[EMAIL PROTECTED]>
wrote:
With the configuration you noted below, what is your CPU
utilization. We are implementing memcached in our environment and
I am trying to get a feel for what we will need for production. I
realize that it all depends on how we are using it, but I am
interested to see what it is based on your configuration.
Thanks,
Jerry
-----Original Message-----
*From:* [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED]
<mailto:[EMAIL PROTECTED]>*On Behalf Of
*Steve Grimm
*Sent:* Thursday, May 03, 2007 11:33 AM
*To:* Sam Lavery; [email protected]
*Subject:* Re: Largest production memcached install?
No clue if we’re the largest installation, but Facebook has
roughly 200 dedicated memcached servers in its production
environment, plus a small number of others for development and so
on. A few of those 200 are hot spares. They are all 16GB 4-core
AMD64 boxes, just because that’s where the price/performance sweet
spot is for us right now (though it looks like 32GB boxes are
getting more economical lately, so I suspect we’ll roll out some
of those this year.)
We have a home-built management and monitoring system that keeps
track of all our servers, both memcached and other custom backend
stuff. Some of our other backend services are written
memcached-style with fully interchangeable instances; for such
services, the monitoring system knows how to take a hot spare and
swap it into place when a live server has a failure. When one of
our memcached servers dies, a replacement is always up and running
in under a minute.
All our services use a unified database-backed configuration
scheme which has a Web front-end we use for manual operations like
adding servers to handle increased load. Unfortunately that
management and configuration system is highly tailored to our
particular environment, but I expect you could accomplish
something similar on the monitoring side using Nagios or another
such app.
All that said, I agree with the earlier comment on this list:
start small to get some experience running memcached in a
production environment. It’s easy enough to expand later once you
have appropriate expertise and code in place to make things run
smoothly.
-Steve
On 5/3/07 8:06 AM, "Sam Lavery" <[EMAIL PROTECTED]> wrote:
Does anyone know what the largest installation of memcached
currently is? I'm considering putting it on 100+
machines(solaris/mod_perl), and would love to hear any tips
people have for managing a group of that size(and larger).
Additionally, are there any particular patches I should try
out for this specific platform?
Thanks in advance,
Sam
--
Attila Nagy e-mail: [EMAIL PROTECTED]
Free Software Network (FSN.HU) phone: +3630 306 6758
http://www.fsn.hu/
