On Tue, Feb 6, 2018 at 3:15 PM, Pranith Kumar Karampuri <[email protected] > wrote:
> > > On Sun, Feb 4, 2018 at 5:09 PM, Raghavendra Gowdappa <[email protected]> > wrote: > >> All, >> >> One of our users pointed out to the documentation that glusterfs is not >> good for storing "Structured data" [1], while discussing an issue [2]. Does >> any of you have more context on the feasibility of storing "structured >> data" on Glusterfs? Is one of the reasons for such a suggestion "staleness >> of metadata" as encountered in bugs like [3]?\ >> > > I think the default configuration of glusterfs leads to unwanted behaviour > with structured data workloads. Based on my experience with customers I > handled, structured data usecase needs stronger read after write > consistency guarantees from multiple clients which I don't think we got a > chance to qualify. People who get it working generally disable perf > xlators. Then there are some issues that happen because of distributed > nature of glusterfs (For example: ctime). So technically we can get > glusterfs to work for structured data workloads. We will need to find and > fix issues by trying out that workload. Performance qualification on that > will also be useful to analyse. > > A note on this for people who are not aware about 'gluster-block' project: https://github.com/gluster/gluster-block could be used to handle some such workloads. If anyone gets into issues on top of Gluster Filesystem mount, then feel free to try gluster-block out, and give us feedback to help improving it. -Amar >> [1] http://docs.gluster.org/en/latest/Install-Guide/Overview/ >> [2] https://bugzilla.redhat.com/show_bug.cgi?id=1512691 >> [3] https://bugzilla.redhat.com/show_bug.cgi?id=1390050 >> >> regards, >> Raghavendra >> _______________________________________________ >> Gluster-devel mailing list >> [email protected] >> http://lists.gluster.org/mailman/listinfo/gluster-devel >> > > > > -- > Pranith > > _______________________________________________ > Gluster-devel mailing list > [email protected] > http://lists.gluster.org/mailman/listinfo/gluster-devel > -- Amar Tumballi (amarts)
_______________________________________________ Gluster-devel mailing list [email protected] http://lists.gluster.org/mailman/listinfo/gluster-devel
