My linode went belly up and consumed ~390% CPU for 12 straight hours, from approximately 11:55PM EST last night until 11:55AM EST today. I rebooted the crazy server as soon as I found out what happened, but here's my apology to anyone on fremont59 who may have experienced a degradation of performance due to this incident.

Regards,

Hybinet

Did it catch fire?

Sorry if I sound a noob but I don't understand...

Isn't the idea, and selling-point, of a Xen VPS is that processes that run amok on one VPS *won't* affect other VPSs on the same machine?

Well, yes. But if you are not using CPU then the other VPSs are free to take your share. His VPS running flat out for that long would have limited the burstability of the other nodes on the host.

Well by limit the burstability at worst your only talking about losing half the cpu.. since the cpu would just split its time between the two people needing it..

And that of course assumes your sharing the SAME 4 cpu's as the other.. etc etc etc

Edit: I should also point out, it wont/cant take away your share.. Your always garanteed a percentage of the CPU.. which you will always get when you NEED it, but this is farely small. but bare in mind one of the leverage points of VPS in general is being able to burst and use all the cpu's if you need them..

_________________
ServerAdmin - www.our-lan.com
"Diplomacy is the art of saying nice doggy whilst looking for a really big stick"
"In my experiece, any attempt to make any system idiot proof will only challenge God to make a better idiot"

Ahh ok guys thanks - yes I see what you both mean.

It's a limit on burstability that would be the potential issue, but that each VPS would still get it's guaranteed CPU time per normal.

Thanks for explaining that.