[Lustre-discuss] lustre routing

Hi, I have a lustre configuration that works using following network IP 10.143.x.y netmask 255.255.0.0 I also have couple of login nodes that are in different network IP 10.142.10.z netmask 255.255.255.0 The OSS's and MGS/MDS has two NIC's each that are configured to work in both networks l

Re: [Lustre-discuss] Problems switching the OSS and getting Lustre to restart correctly.

Assuming [EMAIL PROTECTED] is the old OSS, the ptlrpc_expire_one_request()) @@@ timeout messages mean that the client / MDT was trying and failing to talk to the old server. You need to tell Lustre to regenerate the configuration logs using 'tunefs.lustre --writeconf

Re: [Lustre-discuss] Re: lustre and nfs

On Fri, 2007-08-03 at 18:00 +0100, Wojciech Turek wrote: > Hi, > > > I have exactly the same problem. I am looking for solution that let me > export lustre file system without having to specify fsid= in export > options. > I have found in bugzilla bug 10786 that apparently resolves that > problem

Re: [Lustre-discuss] Re: lustre and nfs

Hi, I have exactly the same problem. I am looking for solution that let me export lustre file system without having to specify fsid= in export options. I have found in bugzilla bug 10786 that apparently resolves that problem. Unfortunately I can't find if this patch is available for 1.6.0

Re: [Lustre-discuss] read-only mount

On Fri, Aug 03, 2007 at 10:36:05AM +0500, Mustafa A. Hashmi wrote: > Hi Papp: > > On 8/2/07, Papp Tamas <[EMAIL PROTECTED]> wrote: > > Dear Everybody, > > > > Is that normal, I cannot mount a ldiskfs formatted partition > > read-only? If yes, why? > > Indeed it is normal. Please see FAQ entry bel