|
From: | Shehjar Tikoo |
Subject: | Re: [Gluster-devel] Multiple NFS Servers (Gluster NFS in 3.x, unfsd, knfsd, etc.) |
Date: | Sat, 09 Jan 2010 16:47:06 +0530 |
User-agent: | Mozilla-Thunderbird 2.0.0.19 (X11/20090103) |
Martin Fick wrote:
--- On Thu, 1/7/10, Gordan Bobic <address@hidden> wrote:Shehjar Tikoo wrote:Gordan Bobic wrote:Martin Fick wrote:--- On Wed, 1/6/10, Gordan Bobic <address@hidden>wrote:I don't think it would be wasted if it includes NLM since unfsd does not do locking!It does not do decent security either. One of our goals is to implement kerberos5 based authentication. We also want to support NFS over RDMA and NFSACLs. For extending to these, unfsd code is highly limiting.So why exactly use NFS instead of GlusterFS with server-side brick assembly? What is the advantage? I cannot see one either in terms of performance or functionality. This is what I would be using if I could get that setup to work without bugginess (e.g. bug 186) and crashing (see other emails on this thread, will try to re-create and provide backtraces).The last time I evaluated GlusterFS, it did not support graceful server disconnection/rebooting (i.e. clients with open files will see errors instead of blocking). While it would be awesome of this were simply "fixed" at the GlusterFS level, if the NFS xlator provides this functionality it would be a big win. This feature is the single feature keeping me from using GlusterFS to this day. I look forward to either of theses solutions so thatI could use GlusterFS,
Yes. Gluster NFS server reboots work fine with the NFS xlator. The other aspect is the disconnections from and reboots of GlusterFS backends/replicas. That is handled by replicate and distribute self-heal but I havent yet come around to the cluster availability tests with NFS yet. Soon.. -Shehjar
-Martin_______________________________________________ Gluster-devel mailing list address@hidden http://lists.nongnu.org/mailman/listinfo/gluster-devel
[Prev in Thread] | Current Thread | [Next in Thread] |