Hi, I guess some good advice is "pre-mature optimization is the root of all evil". Use the Gluster defaults for your replica volumes, then, when you inevitably have performance issues, identify bottlenecks logically and iteratively: - Raw RAID read/write speeds - Raw network read/write speeds ie, make sure your hardware/network can keep up before trying to "fix" GlusterFS. We use GlusterFS for home directories on a compute cluster with 10-20 concurrent users (~100 total users), and I mandate that users do write-heavy jobs to compute-node local storage. It's a bit different use case than yours, but hopefully useful insight. For the record, we're using 10Gbe over copper. Other than that, the Red Hat storage guide recommends hardware RAID6 and XFS (rather than ext4). Cheers, Alan On 08/01/2014 10:02 AM, Bruno MACADRÉ wrote: > Hi all, > > I'm currently doing a Fileserver between 2 nodes, I use GlusterFS in > replicate mode between them to keep data in sync. > > This fileserver is planned to be used by about 200 > users/workstations simultaneously for homes and other shares so my > questions are : > > * What's the best mount type (GlusterFS or NFS) for performances > and/or stability ? > * I see around the Web a lot of tuning (all and nothing), is > there a tuning concept according to the final use and the hardware of > the servers ? > * Is there some caveat to avoid ? > > Thanks by advance for any answers > Regards, > Bruno. > -- Alan Orth alan.orth@xxxxxxxxx http://alaninkenya.org http://mjanja.co.ke "I have always wished for my computer to be as easy to use as my telephone; my wish has come true because I can no longer figure out how to use my telephone." -Bjarne Stroustrup, inventor of C++ GPG public key ID: 0x8cb0d0acb5cd81ec209c6cdfbd1a0e09c2f836c0
Attachment:
signature.asc
Description: OpenPGP digital signature
_______________________________________________ Gluster-users mailing list Gluster-users@xxxxxxxxxxx http://supercolony.gluster.org/mailman/listinfo/gluster-users
