[Bugs] [Bug 1271729] Data Tiering: Database locks observed on tiered volumes on continous writes to a file

[bugzilla at redhat.com]

https://bugzilla.redhat.com/show_bug.cgi?id=1271729

Sweta Anandpara <sanandpa at redhat.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|ON_QA                       |VERIFIED



--- Comment #3 from Sweta Anandpara <sanandpa at redhat.com> ---
Tested and verified this on the build glusterfs-3.7.5-11.el7rhgs.x86_64

Had a 4+2 EC volume as cold tier. Mounted it via fuse and created 100000 files.
While the file creation was in progress, attached a 2*2 dist-rep volume as hot
tier. While the file creation continued, mounted the same volume via fuse on
another client, and appended all 100000 files. Both the commands (command1 of
creating a lakh files, and command2 of appending the created lakh files)
continued for a while. Checked the tier logs for any sqlite error message, and
none was seen. 

Verified that first n number of creates happened in the cold tier, and the
remaining (after attaching a tier) continued in the hot tier. 

Detailed logs are attached. Moving this bug to verified in 3.1.2.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
Unsubscribe from this bug https://bugzilla.redhat.com/token.cgi?t=jJJAeb0d4X&a=cc_unsubscribe