Starting new child in the syslog?

R

rugby

Member
Oct 24, 2009
138
0
16
We're having some performance issues with our PVE setup lately, specifically I/O spikes, and I see tons of these entries in the syslog. What is going on with all these child processes starting?


May 25 07:21:07 proxwww 28335 Starting new child 28335
May 25 07:21:30 proxwww 28358 Starting new child 28358
May 25 07:21:54 proxwww 28371 Starting new child 28371
May 25 07:22:03 proxwww 28379 Starting new child 28379
May 25 07:22:11 proxwww 28385 Starting new child 28385
May 25 07:22:17 proxwww 28389 Starting new child 28389

Here's the output for pveversion -v:

pm01:/etc# pveversion -v
pve-manager: 1.5-9 (pve-manager/1.5/4728)
running kernel: 2.6.32-1-pve
proxmox-ve-2.6.32: 1.5-4
pve-kernel-2.6.32-1-pve: 2.6.32-4
pve-kernel-2.6.24-9-pve: 2.6.24-18
pve-kernel-2.6.24-8-pve: 2.6.24-16
qemu-server: 1.1-14
pve-firmware: 1.0-5
libpve-storage-perl: 1.0-13
vncterm: 0.9-2
vzctl: 3.0.23-1pve11
vzdump: 1.2-5
vzprocps: 2.0.11-1dso2
vzquota: 3.0.11-1
pve-qemu-kvm: 0.12.4-1
ksm-control-daemon: 1.0-3
 
That didn't show anything useful. Any way to tell what's killing our I/O besides iotop?
 
any special reason why you do not run the latest kernel? (2.6.32-2-pve)
 
No, other than the fact that rebooting the box is a royal pain as it has 4 production email servers running on it. I *can* do it, but will tick of somebody.
 
Doing a bit more research it turns out the 3ware raid card was verifying itself. 8x2TB drives in RAID10 can take a long time. I turned the verification off and the IO delays have gone away. I'm going to test it over the next day and see if it stays low.
 
You must log in or register to reply here.
Top Bottom