[prev in list] [next in list] [prev in thread] [next in thread] 

List:       squid-users
Subject:    [squid-users] Tweaking Squid for speed, not max requests
From:       Steve Snyder <swsnyder () home ! com>
Date:       2001-08-30 14:01:28
[Download RAW message or body]

There have been several threads on this list recently discussing the 
tweaking that is required for improving max requests/second in Squid.  How 
about raw performance? 

I administer a small LAN, running Squid v2.4S2 on a Linux (RedHat v7.1 /w 
v2.4.9 kernel) box.  The limited number of users I support will never choke 
Squid with too many requests/second.  That being the case, my emphasis is 
on performance, even at the expense of max requests.

I've already done the obvious: sufficient RAM, dual P3 CPUs, fast (single) 
SCSI disk, and ReiserFS ("noatime,notail") filesystem.  All my NICs are 
100Mbps, running at full-duplex.  I've configured Squid to use async-io.  
I'm using the default LRU replacement algorithm because I found that LFUDA 
didn't really provide any overall benefit (in Squid v2.3S4).

Many of the tweaks recommended seem to involve modifying operating system 
defaults (increasing max file descriptors, number of open ports, etc.).  
Are there similar parameters that can/should be tweaked for maximizing 
throughput from the cache to the users' machines?

Thanks.

[prev in list] [next in list] [prev in thread] [next in thread]