@christopher: I've mailed the maintainers.

@kent: Your setups looks okay. I have made a similar setup, and wasn't
able to reproduce the problem myself, even loading the exact database
dump. Even more, as the failing VM was a member of a two way mysql
master-master setup, we've installed a third machine, acting as a slave,
and this one runs just fine.

There must be something different to that specific VM, but I have no
idea what exactly it is. And while I can easily test the issue, and make
it crash within 10...15 minutes, it is never exactly at the same point,
so it isn't the exact content of the dump, generating a specific flush
to the disk with dataset xyz in it.

Additionally, I can tell you the iSCSI target is also a linux machine,
running debian squeeze, and LIO as iSCSI target. There is no
authentication, ACL is done with simple IP based restrictions. The
config of the VM is below:

kernel = "/boot/domU/xenu-linux-3.2-amd64"
ramdisk = "/boot/domU/xenu-initrd-3.2-amd64"
name = "crashing-db-host"
vif = [ 'mac=02:00:bc:5d:64:62,bridge=xenbr201' ]
disk = [ 'iscsi:storage:crashing-db-host:root,xvda1,w', 
'iscsi:local:crashing-db-host:swap,xvda2,w' ]
memory = 6144
maxmem = 16384
vcpus = 6
cpu_weight = 6144
extra = "4 mem=16384M xencons=hvc0 rootflags=uqnoenforce"
on_poweroff = 'destroy'
on_reboot   = 'restart'
on_crash    = 'restart'


The "iscsi" block device isn't really special, it just searches our storage 
systems for the correct iSCSI target, and takes the LVM volume from that 
system. Once it finds the correct volume, it just returns the exact LVM path, 
like you would use a phy:... with the path. 

The kernel used in the VM is vmlinuz-3.2.0-4-amd64, but we noticed this
doesn't make a difference.

-- 
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1331513

Title:
  14e4:165f tg3 eth1: transmit timed out, resetting on BCM5720

To manage notifications about this bug go to:
https://bugs.launchpad.net/dell-poweredge/+bug/1331513/+subscriptions

-- 
ubuntu-bugs mailing list
ubuntu-bugs@lists.ubuntu.com
https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs

Reply via email to