Re: [Linux-cluster] R: nfs cluster, problem with delete file in the failover case

2015-07-08 Thread J. Bruce Fields
On Thu, May 21, 2015 at 09:05:36PM +0200, gianpietro.se...@unipd.it wrote: > > On Wed, May 13, 2015 at 07:38:03PM +, gianpietro sella wrote: > >> J. Bruce Fields fieldses.org> writes: > >> > >> > > >> > On Wed, May 13, 2015 at 01:06:17PM +0200, sella gianpietro wrote: > >> > > this is the inod

Re: [Linux-cluster] R: nfs cluster, problem with delete file in the failover case

2015-05-21 Thread gianpietro . sella
> On Wed, May 13, 2015 at 07:38:03PM +, gianpietro sella wrote: >> J. Bruce Fields fieldses.org> writes: >> >> > >> > On Wed, May 13, 2015 at 01:06:17PM +0200, sella gianpietro wrote: >> > > this is the inodes number in the exported folder of the volume >> > > in the server before write file i

Re: [Linux-cluster] R: nfs cluster, problem with delete file in the failover case

2015-05-21 Thread J. Bruce Fields
On Wed, May 13, 2015 at 07:38:03PM +, gianpietro sella wrote: > J. Bruce Fields fieldses.org> writes: > > > > > On Wed, May 13, 2015 at 01:06:17PM +0200, sella gianpietro wrote: > > > this is the inodes number in the exported folder of the volume > > > in the server before write file in the

Re: [Linux-cluster] R: nfs cluster, problem with delete file in the failover case

2015-05-13 Thread gianpietro sella
J. Bruce Fields fieldses.org> writes: > > On Wed, May 13, 2015 at 01:06:17PM +0200, sella gianpietro wrote: > > this is the inodes number in the exported folder of the volume > > in the server before write file in the client: > > > > [root cld-blu-13 nova]# du --inodes > > 2 . > > > >

Re: [Linux-cluster] R: nfs cluster, problem with delete file in the failover case

2015-05-13 Thread J. Bruce Fields
On Wed, May 13, 2015 at 01:06:17PM +0200, sella gianpietro wrote: > this is the inodes number in the exported folder of the volume > in the server before write file in the client: > > [root@cld-blu-13 nova]# du --inodes > 2 . > > this is the used block: > > [root@cld-blu-13 nova]# df -T >

Re: [Linux-cluster] R: nfs cluster, problem with delete file in the failover case

2015-05-13 Thread J. Bruce Fields
On Wed, May 13, 2015 at 11:38:51AM +, Cao, Vinh wrote: > Sounds like the process that has the file create while you are moving > it to another node still open. If I understand correctly, the filesystem is still unmountable. If a process held a file on the filesystem open, an unmount attempt w

Re: [Linux-cluster] R: nfs cluster, problem with delete file in the failover case

2015-05-13 Thread Cao, Vinh
Sounds like the process that has the file create while you are moving it to another node still open. Meaning you are deleting the file and doing failover at the same time. This has not things to do with your cluster setup. I believed , you can run lsof command on the system that you're seeing th