Thanks for your answer, it's sendmail which is waiting disk and forks himself... strange because i don't use sendmail, even if it was default activated -- Best regards,
Loïc BLOT, Engineering UNIX Systems, Security and Networks http://www.unix-experience.fr Le jeudi 03 janvier 2013 à 15:38 +0100, Peter Hessler a écrit : > On 2013 Jan 03 (Thu) at 14:49:35 +0100 (+0100), Loïc Blot wrote: > :Hello, > :Since this morning is get a high uptime value for server load, but the > :server does nothing. It's our CARP backup gateway for our clients, and > :it stays in backup mode since few month. > : > :The CPU does nothing special, the gateway is waiting failover, the > :memory isn't used (3G/16G Ram), and disk IO are normal. > : > > Not true. > > > :Here is my systat output: > : > : > :++++++++++++++++++++++++ > : 1 users Load 21.49 21.47 21.21 Thu Jan 3 > :14:45:36 2013 > : > : memory totals (in KB) PAGING SWAPPING > :Interrupts > : real virtual free in out in out 2595 > :total > :Active 1987252 1987252 13376804 ops 398 > :clock > :All 2862376 2862376 30156692 pages 1714 > :ipi > : > :acpi0 > :Proc:r d s w Csw Trp Sys Int Sof Flt forks 408 > :mfi0 > : 23 11 2993 116 4839 481 251 80 fkppw 26 > > ^^ > You have 23 processes waiting on disk IO. This is what is causing the > load. > > > > :em0 > : fksvm 49 > :em1 > : 0.2%Int 1.4%Sys 0.2%Usr 0.0%Nic 98.2%Idle pwait > :ehci0 > :| | | | | | | | | | | relck > :ehci1 > := rlkok > :ahci0 > : noram > :Namei Sys-cache Proc-cache No-cache 3 ndcpy > : Calls hits % hits % miss % fltcp > : 7722 6252 81 1157 15 5 zfod > : cow > :Disks sd0 cd0 135326 fmin > :seeks 180434 ftarg > :xfers 407 itarg > :speed 11M 4 wired > : sec 1.0 pdfre > : pdscn > : pzidle > : 17 kmapent > : > : 162 > :IPKTS > : 56 > :OPKTS > :+++++++++++++++++++++++ > : > :Do you have any idea why uptime usage is so high ? > : > :Thanks for advance > : > :-- > :Best regards, > : > : > :Lo??c BLOT, Engineering > :UNIX Systems, Security and Networks > :http://www.unix-experience.fr > :