[Sheepdog] panic in get_nth_node

[huxinwei]

> -----Original Message-----
> From: Liu Yuan [mailto:namei.unix at gmail.com]
> Sent: Friday, March 02, 2012 7:07 PM
> To: huxinwei
> Cc: sheepdog at lists.wpkg.org; Liu Jiang
> Subject: Re: [Sheepdog] panic in get_nth_node
> 
> On 03/02/2012 09:47 AM, huxinwei wrote:
> 
> > et's say we have 2 nodes, running 3 sheep instance
> >
> > Node1 # sheep /home/sheep1 -p 7000
> > Node2 # sheep /home/sheep1 -p 7000
> > Node2 # sheep /home/sheep2 -p 7001
> >
> > Node1 # collie cluster format -c 2 # farm or simple doesn't matter here
> > Node1 # collie vdi create ss1 1G
> > ... Keep ss1 busy writing ...
> > Then kill sheep2 on node2, will almost surely panic sheep1 on node2 too.
> 
> Hi,
> 
> I cannot reproduce the issue.
> 
> I do:
> 
> Node1 # sheep /home/sheep1 -p 7000
> Node2 # sheep /home/sheep1 -p 7000
> Node2 # sheep /home/sheep2 -p 7001
> 
> Node1 # collie cluster format -c 2
> Node1 # collie vdi create test 1G
> 
> ... in a Linux Guest test, I run the command 'dd if=/dev/vda
> of=/dev/zero' in a loop...
> 
> Then killed sheep2 on node2, nothing panic or error happened, guest was
> still responsive.

Interesting. I'm testing in an VMware only environment.
Will try to redo the test on bare metal later, and come back to this then.

FYI

> Thanks,
> Yuan