Dual proc, dual core. Proc 0 = 90.72% avg Proc 1 = 50.18% avg Proc 2 = 49.49% avg Proc 4 = 49.74% avg
Total is 59.74% avg But it's been higher than that all the time I've been troubleshooting this problem. Kurt On Thu, Apr 8, 2010 at 15:12, Klint Price <[email protected]> wrote: > 90% utilization after downing two servers? Is that 90% on a single core, or > 90% total? > > How many other VMs do you have on the LUN(s) that are still powered on? Any > more than the two referenced below? > > What is the output / top CPU utilization pct for the processes found by > running: > > #top (from SSH) > > (exit with CTRL-C) > > > > -----Original Message----- > From: Kurt Buff [mailto:[email protected]] > Sent: Thursday, April 08, 2010 3:04 PM > To: NT System Admin Issues > Subject: Re: OTish: ESX 3.5 guest won't boot > > In line... > > On Thu, Apr 8, 2010 at 14:40, Klint Price <[email protected]> wrote: >> 1) I wouldn't expect a power on to work until you can get this command to >> work: >> >> vmkfstools -P /vmfs/volumes/esx2\:storage1/sus/sus.vmdk >> >> The host needs to be able to read from the disk. > > Reasonable. > >> 2) Do you have an additional non-production server on the same LUN that can >> be powered off, with an attempt to restart your current down server? Result? >> Will the 2nd non-production server power back on? > > Yes. It's acting in a similar way - I logged in, and it shut down > fine, but it won't power up now. Nor will a machine that I had powered > >> 3) All things DR considered, can you schedule a reboot tonight? If so, you >> may >> want to consider re-seating the HBA and drives, clear dust (which can cause >> cards >> to overheat), and reboot. > > Gotcha. > > One last thing for the moment: I've been looking at the performance > chart for this box, and see that CPU utilization is hovering around > 90%. I've got one VM that seems pretty far out of line from its normal > CPU utilization (our Win2k TS server), and another that's a bit higher > than normal (our Win2k3 file/print server). > > I'm thinking of kicking the one person using the TS server off and > rebooting, and seeing what that does to the situation, before downing > the other machine. > > Kurt > > ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ > ~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/> ~ > > > ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ > ~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/> ~ ~ Finally, powerful endpoint security that ISN'T a resource hog! ~ ~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/> ~
