db replicator missing priority handoff options
Bug #1668399 reported by
clayg
This bug affects 1 person
Affects | Status | Importance | Assigned to | Milestone | |
---|---|---|---|---|---|
OpenStack Object Storage (swift) |
Fix Released
|
Medium
|
Unassigned |
Bug Description
There's no way to force the database replicators (account or container) to do handoffs only and prioritize rebalance.
Worse, it's difficult to do priority rebalance by hand because of lp bug #1663016
The db replicators should support a handoffs_only mode that allows you to raise concurrency and switch on handoffs only and get most disks reading handoff databases.
Changed in swift: | |
importance: | Undecided → High |
status: | New → Confirmed |
Changed in swift: | |
importance: | High → Medium |
tags: | added: low-hanging-fruit |
To post a comment you must log in.
Reviewed: https:/ /review. openstack. org/545497 /git.openstack. org/cgit/ openstack/ swift/commit/ ?id=47fed6f2f96 0a2cd56960b8aeb 2eeace405c3afa
Committed: https:/
Submitter: Zuul
Branch: master
commit 47fed6f2f960a2c d56960b8aeb2eea ce405c3afa
Author: Samuel Merritt <email address hidden>
Date: Fri Feb 16 16:37:58 2018 -0800
Add handoffs-only mode to DB replicators.
The object reconstructor has a handoffs-only mode that is very useful
when a cluster requires rapid rebalancing, like when disks are nearing
fullness. This mode's goal is to remove handoff partitions from disks
without spending effort on primary partitions. The object replicator
has a similar mode, though it varies in some details.
This commit adds a handoffs-only mode to the account and container
replicators.
Change-Id: I588b151ee65ae4 9d204bd6bf58555 504c15edf9f
Closes-Bug: 1668399