[Remote Store] Batch translog upload per x ms to achieve high index throughput #5692
Labels
enhancement
Enhancement or improvement to existing feature or request
Performance
This is for any performance related enhancements or bugs
Storage:Durability
Issues and PRs related to the durability framework
v2.6.0
'Issues and PRs related to version v2.6.0'
Is your feature request related to a problem? Please describe.
Currently the upload to remote store happens on translog fsync to disk. This can be optimised to occur every x milliseconds to avoid network hops that currently happens for every request. We can batch translog upload to occur periodically in which case we can achieve higher throughput. This however can impact on the latency but keeping throughput same or more.
Describe the solution you'd like
A clear and concise description of what you want to happen.
Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.
Additional context
Add any other context or screenshots about the feature request here.
The text was updated successfully, but these errors were encountered: