From fac4ab30f3076ba1147e652bd3ac8288d0d7f8b6 Mon Sep 17 00:00:00 2001 From: Jiffin Tony Thottan Date: Tue, 7 Apr 2015 13:56:16 +0530 Subject: doc : pNFS support for gluster volumes Change-Id: I910f8f786849b4ece3d3c258c2c52537edc173dd BUG: 1209380 Signed-off-by: Jiffin Tony Thottan Reviewed-on: http://review.gluster.org/10145 Reviewed-by: Kaleb KEITHLEY Reviewed-by: soumya k Reviewed-by: Humble Devassy Chirammal Tested-by: Humble Devassy Chirammal --- doc/features/mount_gluster_volume_using_pnfs.md | 56 +++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 doc/features/mount_gluster_volume_using_pnfs.md (limited to 'doc/features') diff --git a/doc/features/mount_gluster_volume_using_pnfs.md b/doc/features/mount_gluster_volume_using_pnfs.md new file mode 100644 index 0000000000..403f0c80e8 --- /dev/null +++ b/doc/features/mount_gluster_volume_using_pnfs.md @@ -0,0 +1,56 @@ +# How to export gluster volumes using pNFS? + +The Parallel Network File System (pNFS) is part of the NFS v4.1 protocol that +allows compute clients to access storage devices directly and in parallel. +The pNFS cluster consists of MDS(Meta-Data-Server) and DS (Data-Server). +The client sends all the read/write requests directly to DS and all other +operations are handle by the MDS. pNFS support is implemented as part of +glusterFS+NFS-ganesha integration. + +### 1.) Pre-requisites + + - Create a GlusterFS volume + + - Install nfs-ganesha (refer section 5) + + - Disable kernel-nfs, gluster-nfs services on the system using the following commands + - service nfs stop + - gluster vol set nfs.disable ON (Note: this command has to be repeated for all the volumes in the trusted-pool) + +### 2.) Configure nfs-ganesha for pNFS + + - Disable nfs-ganesha and tear down HA cluster via gluster cli (pNFS did not need to disturb HA setup) + - gluster features.ganesha disable + + - For the optimal working of pNFS, ganesha servers should run on every node in the trusted pool manually(refer section 5) + - *#ganesha.nfsd -f -L -N -d* + + - Check whether volume is exported via nfs-ganesha in all the nodes. + - *#showmount -e localhost* + +### 3.) Mount volume via pNFS + +Mount the volume using any nfs-ganesha server in the trusted pool.By default, nfs version 4.1 will use pNFS protocol for gluster volumes + - *#mount -t nfs4 -o minorversion=1 :/ * + +### 4.) Points to be noted + + - Current architecture supports only single MDS and mulitple DS. The server with which client mounts will act as MDS and all severs including MDS can act as DS. + + - If any of the DS goes down , then MDS will handle those I/O's. + + - Hereafter, all the subsequent nfs clients need to use same server for mounting that volume via pNFS. i.e more than one MDS for a volume is not prefered + + - pNFS support is only tested with distributed, replicated or distribute-replicate volumes + + - It is tested and verfied with RHEL 6.5 , fedora 20, fedora 21 nfs clients. It is always better to use latest nfs-clients + +### 5.) References + + - Setup and create glusterfs volumes : http://www.gluster.org/community/documentation/index.php/QuickStart + + - NFS-Ganesha wiki : https://github.com/nfs-ganesha/nfs-ganesha/wiki + + - For installing, running NFS-Ganesha and exporting a volume : + - read doc/features/glusterfs_nfs-ganesha_integration.md + - http://blog.gluster.org/2014/09/glusterfs-and-nfs-ganesha-integration/ -- cgit