> -----Original Message----- > From: Liu Yuan [mailto:[email protected]] > Sent: Friday, March 02, 2012 7:07 PM > To: huxinwei > Cc: [email protected]; 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 -- sheepdog mailing list [email protected] http://lists.wpkg.org/mailman/listinfo/sheepdog
