Description of problem: This is to prevent any unforeseen problems that might arise due to writevs and readvs being wound with @flag parameter containing O_TRUNC or O_APPEND especially wrt translators like sharding and ec where O_TRUNC write or O_APPEND write on individual shards/fragments is not the same as O_TRUNC write or O_APPEND write as expected by the application. Version-Release number of selected component (if applicable): How reproducible: Steps to Reproduce: 1. 2. 3. Actual results: Expected results: Additional info:
An upstream patch http://review.gluster.org/#/c/14665/ is posted for review.
Downstream patch https://code.engineering.redhat.com/gerrit/#/c/76078/ is merged now.
Tested with RHGS 3.1.3 nightly build - glusterfs-3.7.9-10.elrhgs with the following test 1. Created replica 3 volume and optimized the volume for virt-store 2. Disabled remote-dio & enable strict-o-direct on the volume 3. Created the RHEV data domain with the above created volume 4. Created 30 Application VMs 5. Ran the 100% write workload ( random write ) on all the VMs using FIO tool 6. Repeated the test twice and there are no issues found
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://access.redhat.com/errata/RHBA-2016:1240