Fedora Account System
Red Hat Associate
Red Hat Customer
Description: Currently self-heal does data heal in 128KB chunks. It has been changed to 1MB by default in upstream. See https://github.com/gluster/glusterfs/issues/2067 It would be good to have this in downstream code too. Note that currently, it is still possible even in downstream to tune the chunk size via the 'data-self-heal-window-size' volume option using the CLI. But having a bigger size enabled by default would be good.
Upstream PR: https://github.com/gluster/glusterfs/pull/2111
Link to EC fix upstream: https://github.com/gluster/glusterfs/pull/2071
This bug is for improving the self-heal performance and no impact associated with this, so marking the severity of this bug as LOW
Hi Ravi, Thanks for the clarification. - I upgraded Set1 and performed above steps again. The difference observed in comment 18 is due to specs of the machines. - Based on testing performed in comment 18 & note in comment 19, moving this bug to verified state Please comment/change status accordingly if any other info is required. Thanks, Leela.
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 (RHGS 3.5.z Batch Update 5 glusterfs bug fix and enhancement update), 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-2021:3729