[Gluster-users] 3.12, ganesha and storhaug

[Jim Kinney]

All,

I am upgrading the storage cluster from 3.8 to 3.10 or 3.12. I have
3.12 on the ovirt cluster. I would like to change the client connection
method to NFS/NFS-Ganesha as the FUSE method causes some issues with
heavy python users (mmap errors on file open for write).

I see that nfs-ganesha was dropped after 3.10 yet there is an updated
version in the 3.12 repo for CentOS 7 (which I am running).

It also seems apparent that storhaug is not ready for use.

Is it a likelyhood that nfs-ganesha will be reinstated as a supported
process for 3.12 in the near future? Or should I only upgrade to 3.10?
Or is it feasible to use the nfs-ganesha 2.5 release with gluster 3.12?
None of the official docs on howto (that I've found) give the method of
config/use that are clearly for the newest ganesha and gluster combo. 

Can the gnfs support multiple transport methods?

Granted, I have a conflicted need: the NFS is needed to resolve the
mmap issue (and hopefully do some speed up that the users see) but the
real high-speed need is possibly through pNFS clients to NFS-Ganesha
but those connections will be over infinniband so only TCP and no RDMA.
That drops my raw speed from 40Gbps to 10Gbps (connectx-2 gear). I can
run gnfs on RDMA (40Gbps!) but no NFSv4.1 for pNFS AND a manual mess
setting up HA for connections. The last connection fun is not all
clients connect over infinniband so I do have standard ethernet ports
as well (40Gbps feeding multiple switches for 10Gbps and 1Gbps).
-- 
James P. Kinney III

Every time you stop a school, you will have to build a jail. What you
gain at one end you lose at the other. It's like feeding a dog on his
own tail. It won't fatten the dog.
- Speech 11/23/1900 Mark Twain

http://heretothereideas.blogspot.com/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20180509/1abff6d1/attachment.html>