OpenVZ Forum


Home » General » Support » High I/O in 028stab112 VZ kernels
High I/O in 028stab112 VZ kernels [message #51475] Mon, 23 June 2014 08:29 Go to next message
ccto is currently offline  ccto
Messages: 57
Registered: October 2005
Member
From: 180.92.180*
Hello OpenVZ developer,

Under the kernel 2.6.18-371.6.1.el5.028stab112.3, when we transfer large files (the weekly full backup), the load average grow exponentially.

We used mdadm to form 2 RAID
/dev/md0 = /boot (consists of /dev/sda1 and /dev/sdb1)
/dev/md1 = LVM for / , /vz , /tmp , and swap (consists of /dev/sda2 and /dev/sdb2)
/dev/sdc1 = /backup

We run - tar czf /backup/<VEID>.tar.gz /vz/private/VEID/ - on weekly basis ,
and use rsync over ssh to sync the tar.gz files to remote server.

During the rsync process, the load average grows from around 1 - 3 to over 200 (the OpenVZ server is very busy, not so responsive)
The transfer speed is around 400Mbps.

If we limit the rsync speed to around 100Mbps, the load average is OK.

In the past, it does not have such phenomenon.

It happens in both OpenVZ CentOS 5 x86 and x64 servers.

We already use a separate disk to store the backup files to prevent I/O congestion during tar or rsync process.

Is there any issue in the CPU scheduler or I/O priority?

It seems it does not happen in CentOS 6 series (e.g. 2.6.32-042stab090.3) kernel.

Please kindly have a look.

Thank you very much for your kind attention.

Regards
George

[Updated on: Mon, 23 June 2014 08:33]

Report message to a moderator

Re: High I/O in 028stab112 VZ kernels [message #51482 is a reply to message #51475] Tue, 24 June 2014 19:29 Go to previous messageGo to next message
devonblzx is currently offline  devonblzx
Messages: 127
Registered: December 2006
Senior Member
From: *dhcp.bycy.mi.charter.com
Just my two cents, but since OpenVZ is more of a development platform and a smaller team, they probably take more consideration into 2.6.32 than 2.6.18. This will be the same once they start releasing RHEL7 kernels. 2.6.32 will be lower priority and 3.10 will start receiving the primary attention.

In other words, you may wish to start updating your systems or switch to paid support / Parallels which probably would offer you much better support for more "legacy" systems.


http://static.openvz.org/userbars/openvz-user-2.png
ByteOnSite President
Re: High I/O in 028stab112 VZ kernels [message #51610 is a reply to message #51475] Tue, 19 August 2014 21:16 Go to previous message
seanfulton is currently offline  seanfulton
Messages: 102
Registered: May 2007
Senior Member
From: *dyn.optonline.net
We had similar problems with the RHEL5 kernels and I think it went back to a kernel bug that sat around for two years until Red Hat just closed it for inactivity.

RHEL6 has no such problems!

sean
Previous Topic: Debian 6 online live migration fails( Error: can't open file /dev/ptyp0 )
Next Topic: Install DADHI in OpenVZ container
Goto Forum:
  


Current Time: Thu Dec 12 04:02:14 GMT 2019