slowness on Host 45
I'll immediately check vmstat, top, and my iotokens and all is good. My CPU usage is 98% idle, I have 399900+ iotokens available… but si and so from vmstat are going nuts. Also I notice the load will reach upwards of 7 before calming down again.
Also, is the load computed for the entire host or just my linode?
3 Replies
Rebooting my Linode does not seem to have any effect. Today it took 22 minutes for Linode to reboot. Also I am unable to connect via LISH at host45.linode.com. I get an immediate close connection response.
Not sure if it is related, but I have noticed the following errors in my logs:
Jun 3 06:30:15 www kernel: _allocpages: 0-order allocation failed (gfp=0xf0/0)
May 26 10:15:12 www kernel: _allocpages: 0-order allocation failed (gfp=0x1d2/0)
May 26 10:45:13 www kernel: _allocpages: 0-order allocation failed (gfp=0x1d2/0)
May 26 10:45:13 www kernel: _allocpages: 0-order allocation failed (gfp=0x1d2/0)
I tried to get to lish but kept getting the following error message:
sshexchangeidentification: Connection closed by remote host
I then went to the web and executed a Shutdown job. It took over a half hour for that job to finish. Then the Boot job took over a half hour to complete. The jobs kept in the "waiting for host" state.
After my linode booted it still remained very slow and the host load was 5+.
Note that I still can't get to lish even after rebooting my linode. Now I get a password prompt but then it just hangs.
@drware:
Not sure if it is related, but I have noticed the following errors in my logs:
Jun 3 06:30:15 www kernel: _allocpages: 0-order allocation failed (gfp=0xf0/0)
May 26 10:15:12 www kernel: _allocpages: 0-order allocation failed (gfp=0x1d2/0)
May 26 10:45:13 www kernel: _allocpages: 0-order allocation failed (gfp=0x1d2/0)
May 26 10:45:13 www kernel: _allocpages: 0-order allocation failed (gfp=0x1d2/0)
This means your Linode ran out of both RAM and swap and further attempts to allocate memory failed.