Jeevan Patnaik
2017-Nov-14 17:18 UTC
[Gluster-users] How can replicated and distributed replicated volume benefit read performance in most environments?
Hi, I'm trying to get in over my head with the different glusterFs volume types and their affect on performance. But few things In not clear By analyzing tcpdump, I can see that the reads happen from only one host/brick out of the replicated set. Then what makes replicated type gives better read performance than any other volume type except striped types. Regards, Jeevan. -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20171114/0921afba/attachment.html>
Maybe Matching Threads
- What is the difference between FORGET and UNLINK fops
- What does gluster do when it's idle?
- What is the difference between FORGET and UNLINK fops
- stale file handle on gluster NFS client when trying to remove a directory
- stale file handle on gluster NFS client when trying to remove a directory