Bug #55026
closed
multisite: expose config option for data sync's polling interval
Added by Casey Bodley about 2 years ago.
Updated over 1 year ago.
Description
in rgw_data_sync.cc this interval is hard-coded as:
#define INCREMENTAL_INTERVAL 20
- Status changed from New to Fix Under Review
- Pull request ID set to 45784
- Assignee set to Casey Bodley
- Status changed from Fix Under Review to Resolved
This looks like an important fix for the situation where the multi-site replication is going over a high-latency link, and the buckets to be replicated contain a lot of small objects. Can we have this backported to previous releases?
Right now I am looking at a pair of Pacific clusters that have 40 ms latency between them. One of them had an extended downtime, yet the catch-up process only uses ~50 Mbps out of 1 Gbps available. That's sad.
Also available in: Atom
PDF