Big thanks for your reply! > We see a very similar pattern on straight ufs disks on an > areca controller. Machine > console becomes totally unresponsive 30 or so seconds at a > time, so it maybe > something more intergral to device operation, buffercache or > something? In my case console is responsive, but there are delays when starting command due to disk busy. > The IO load on the machine is being generated by updating > rrds files in mrtg > for a few hundred switch ports and a few thousand servers. I'm noticing delays (lockups) even if system is idle. -- Alexander ZagrebinReceived on Fri Dec 18 2009 - 07:21:40 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:59 UTC