[Gluster-users] GlusterFS and Kafka

Vijay Bellur vbellur at redhat.com
Wed May 24 04:23:27 UTC 2017


On 05/23/2017 11:15 AM, Joe Julian wrote:
> If this was multiple clients I could see that possibility, but the
> single fuse client by which this file is being accessed should have a
> consistent state to the single application regardless of the state of
> the servers. How (and be specific, please, so I can understand the
> actual mechanism and explain it to others) is there a path through the
> graph in which this isn't true?

There are some subtle races which were discovered in the context of 
using elasticsearch with  a single gluster client [1]. Some races have 
been addressed and some are still open yet. The referenced bug has a lot 
of details, the upstream clone [2] has the list of patches evolved to 
address these races. Please go through these bugs and let us know if you 
need help in understanding more.

Thanks,
Vijay

[1] https://bugzilla.redhat.com/show_bug.cgi?id=1379568

[2] https://bugzilla.redhat.com/show_bug.cgi?id=1390050




More information about the Gluster-users mailing list