I am dealing with a server that should handle traffic from a few hundred automatic agents accessing it on more or less regular basis. While we were at around 200 agaents the system worked fine. Now that we are at nearly 400 agents.
The load average that used to be at 0.6 now is 1.2-1.9 most of the time. The CPU states also show very high % for both user and system time. One of the things which is not clear to me is that it seems there is a total lack of connection between the average load and the CPU states. Could someone explain why that would be ? Basically there are only two things on this server Apache/mod_perl and MySQL. At the current state I am not sure what to do or what to measure. Any ideas ? A snapshot of top looks like this: 10:50am up 59 days, 18:47, 3 users, load average: 1.25, 1.17, 1.27 125 processes: 124 sleeping, 1 running, 0 zombie, 0 stopped CPU0 states: 17.0% user, 21.0% system, 0.0% nice, 60.0% idle CPU1 states: 27.0% user, 11.0% system, 0.0% nice, 60.0% idle Mem: 2579260K av, 2518756K used, 60504K free, 0K shrd, 76608K buff Swap: 522072K av, 0K used, 522072K free 2109908K cached Some more details: Linux foo 2.4.20-28.7bigmem #1 SMP Thu Dec 18 11:04:21 EST 2003 i686 unknown mysql Ver 11.15 Distrib 3.23.41, for redhat-linux-gnu (i386) Apache/1.3.27 (Unix) (Red-Hat/Linux) mod_ssl/2.8.7 OpenSSL/0.9.6b mod_perl/1.26 Gabor ================================================================= To unsubscribe, send mail to [EMAIL PROTECTED] with the word "unsubscribe" in the message body, e.g., run the command echo unsubscribe | mail [EMAIL PROTECTED]
