Correct, yes, good, no. When a public webserver is running above 100% it doesn't take much to send it into downward spiral with runaway load. The server stops serving but the number of requests keep coming, and so the load increases and increases. It can take hours to recover. We have this problem a lot and have to look at splitting up the server's load to cope. If you are running a lot of databased sites and are seeing loads often above 100%, you need to increase your capacity or you will have reliability problems. Our biggest problem is over-active spiders who want to load pages as fast as you can serve them.
-----Original Message----- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On Behalf Of dogface Sent: Friday, October 11, 2002 3:33 PM To: [EMAIL PROTECTED] Subject: Re: uptime 2:27pm up 6 days, 6:27, 3 users, load average: 1.54, 2.67, 2.44 at peak hours it can go up to 8.** ...can this be correct? eric -- every passing minute is another chance to turn it all around -- Dear God, I didn't think orange went with purple until I saw the sunset you made on Tuesday. That was Cool! Eugene -- 3rd Grader ----- Original Message ----- From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Friday, October 11, 2002 2:04 PM Subject: [RHL] Re: uptime On Fri, Oct 11, 2002 at 01:44:55PM -0500, scott.list wrote: > Hi guys: > > can someone explain the what the load averages numbers mean for the > uptime command > > i.e. 1:42pm up 4:31, 1 user, load average: 1.28, 1.09, 1.06 > > I know what the three are, but what does 1.28 mean? 1.28% of 100% > load, 128% of max? What DOES the 1.28 reflect? FDrom the man page: uptime gives a one line display of the following information. The current time, how long the system has been running, how many users are currently logged on, and the system load averages for the past 1, 5, and 15 minutes. so from your output you had a utilization of 128% for the past 1 minute, 109 % for the last five, abd 106 % for the last 15 minutes. Congratulations. You're getting more out of your system then you should be able to. :-) hmmm - maybe this calculation sould use some refinenet. (Or Scott needs to tell us how to configure our systems! ) -- Jeff Kinz, Director, Emergent Research, Hudson, MA. "[EMAIL PROTECTED]" "[EMAIL PROTECTED]" copyright 2002. Use is restricted. Any use is an acceptance of the offer at http://users.rcn.com/jkinz/policy.html. (o- -o) //\ eLviintuaxbilse /\\ V_/_ _\_V -- redhat-list mailing list unsubscribe mailto:[EMAIL PROTECTED]?subject=unsubscribe https://listman.redhat.com/mailman/listinfo/redhat-list -- redhat-list mailing list unsubscribe mailto:[EMAIL PROTECTED]?subject=unsubscribe https://listman.redhat.com/mailman/listinfo/redhat-list -- redhat-list mailing list unsubscribe mailto:[EMAIL PROTECTED]?subject=unsubscribe https://listman.redhat.com/mailman/listinfo/redhat-list
