Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 30 Mar 2012 12:12:35 -0500
From:      Mark Felder <feld@feld.me>
To:        freebsd-hackers@freebsd.org, freebsd-questions@freebsd.org
Cc:        Joe Greco <jgreco@ns.sol.net>
Subject:   Re: Please help me diagnose this crazy VMWare/FreeBSD 8.x crash
Message-ID:  <op.wbzt29bs34t2sn@tech304>
In-Reply-To: <201203301653.q2UGrAEY098765@aurora.sol.net>
References:  <201203300027.q2U0RVZS085304@aurora.sol.net> <op.wbykhgrl34t2sn@cr48.lan> <201203301444.q2UEilmj097567@aurora.sol.net> <op.wbznjotd34t2sn@tech304> <201203301653.q2UGrAEY098765@aurora.sol.net>

next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 30 Mar 2012 11:53:10 -0500, Joe Greco <jgreco@ns.sol.net> wrote:

> On the same vmdk files?  "Deleting the VM" makes it sound like not.

Fresh new VMDK files every time, and always thick provisioned.

> None of the other VM's, even the VM's that had been abused in this
> horribly insensitive manner of being placed on intolerably slow iSCSI,
> developed this condition.

We've seen similar results. Baffling how VMs you know are worse off never  
develop this condition.

> There are dozens of other VM's running on these hosts, alongside the
> one that was exhibiting this behaviour.
> The VM continued to exhibit this behaviour even after having been moved
> onto a different ESXi platform and architecture (Opteron->Xeon).
> For the problem to "follow" the VM in this manner, and afflict *only*
> the one VM, strongly suggests that it is something that is contained
> within the VM files that constitute this VM.  That is consistent with
> the observation that the problem arose at a point where the VM is
> known to have had all those files moved from one location to a dodgy
> location.

We were hoping that was the explanation as well, but rebuilding the VM  
entirely from scratch on a new host and seeing the crash come back was a  
big blow to morale. :(

> That's why I believe the evidence points to corruption of some sort.
> Of course, your case makes this all interesting.

For the last year I've been convinced it's something hidden inside ESXi's  
I/O virtualization layer that happens to trigger on only certain VMs.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?op.wbzt29bs34t2sn>