Pretty incredible load on a Quickweb VPS...

96mb

And it is not running Unix Bench whatsoever, just a Wordpress installation with Nginx. idk, I would expect something like this to happen on a really oversold VPS provider, but not on Quickweb Xen VPS.

uptime 09:06:02 up 21:05, 1 user, load average: 21.75, 20.84, 14.76

uptime 09:08:20 up 21:07, 1 user, load average: 21.39, 20.75, 15.53

uptime 09:11:20 up 21:10, 1 user, load average: 21.53, 21.08, 16.57

cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU E5620 @ 2.40GHz stepping : 2 cpu MHz : 2400.130 cache size : 12288 KB fdiv_bug : no hlt_bug : no f00f_bug : no coma_bug : no fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu de tsc msr pae cx8 sep cmov pat clflush mmx fxsr sse sse2 ss ht nx constant_tsc aperfmperf pni ssse3 sse4_1 sse4_2 popcnt hypervisor ida arat bogomips : 4800.26 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management:

processor : 1 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU E5620 @ 2.40GHz stepping : 2 cpu MHz : 2400.130 cache size : 12288 KB fdiv_bug : no hlt_bug : no f00f_bug : no coma_bug : no fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu de tsc msr pae cx8 sep cmov pat clflush mmx fxsr sse sse2 ss ht nx constant_tsc aperfmperf pni ssse3 sse4_1 sse4_2 popcnt hypervisor ida arat bogomips : 4800.26 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: `

Jack

@96mb it might be an abuser on the node?

sonic

http://www.96mb.com/ This website is offline

No cached version is available

budingyun

We can see the load if other person abusing the processor? :o

KuJoe

If it's a Xen VPS then there's a good chance the abuse is IO related since Xen does a pretty good job balancing CPU load (it does a good job balancing IO load also but at those levels Disk IO tends to be the culprit unless somebody is running a fork bomb or something).

96mb

The problem is, this has been going around for quite a while, every time they have promised me I won't see it again.

However, they at least still reply my tickets, which is a good sign

96mb

@sonic said: No cached version is available

I doubt any one could still get Nginx to run when the load is this high, let alone MySQL.

HC_Ro

There is a provider here that has that kind of load almost constantly. I have moved a few clients and every time the nodes are like 25.

Asim

@96mb you still use one of these? I cancelled it long ago http://www.asim.pk/my-virtual-private-servers-vps/

I do admit the support is fast; even if sometimes you feel that they did not read your ticket before replying a canned or a totally unrelated reply (the staff members, of course)

AnthonySmith

@96mb it is possible they have lost a drive and are resyncing the raid at the same time as heavy disk use by other VM's

I have also seen this happen on XEN PV if a few people try to run e.g. centos 6 64bit or similar with 128mb ram and the VPS just hangs during boot and for some reason eats 5k+ Disk I/O requests every few seconds.

Gary

@budingyun said: We can see the load if other person abusing the processor? :o

If they're thrashing the disk, for example, and then you try to do the same (not uncommon while benchmarking, really) then your iowait will be high, and so will your load. Load isn't entirely to do with CPU usage.

JoeMerit

Sounds like its time to switch providers!

Gary

Well it could've been just after midnight for a few of the containers, doing automated backups or whatever. A few of those going and hammering hdd and cpu can drive up the load. I wouldn't say that a one-off load of 20 is anything to worry about. If it happens regularly, maybe.

What happens during benchmarking and during normal use of a VPS are very different usage scenarios.

tommy

the load just like my old vps on infinitie. fresh install load above 20, asking support and they said something wrong with my script ;) few minute later I cancel my vps and moving

Corey

They probably tell you it won't happen again because they remove the abuser only to find someone else abusing it later?

Asim

@96mb is the issue resolved?

96mb

@Asim said: is the issue resolved?

Yes, kernel panic, same as the past few times...and again, I think I was promised something along the line that nothing like this will happen again.

This actually reminded me of one of the LEA's post, I think he had the same issue with LEB as well when it was hosted on Quickweb.