Simultaneously writing from multiple cluster nodes to a gfs2 filesystem
Issue
- I would like to ascertain if the behavior when simultaneously writing to correct GFS2 is correct.
- What I see is that when I write in a file from the 5 nodes at exactly the same time, only two of the 5 nodes can write in the file.
- I expect that all 5 nodes write in the file.
- Is that normal behavior?
- Is
write()
atomic on gfs2 files?
Environment
- Red Hat Enterprise Linux Server 5 (with Clustering and Cluster Storage)
- Red Hat Enterprise Linux Server 6, 7 (with the High Availability Add On and Resilient Storage Add Ons)
- A Global Filesystem 2(
gfs2
)
Subscriber exclusive content
A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.