[KV] Support hot standby mode for KVTablet replicas to accelerate failover recovery when the leader changes
- Dominant language
- Java
- Stars
- 2.1k
- Forks
- 625
- Avg merge
- 3d 14h
- Merged PRs (30d)
- 97
Description
### Search before asking
- [x] I searched in the [issues](https://github.com/alibaba/fluss/issues) and found nothing similar.
### Motivation
Currently, only the leader replica maintains an active KVTablet for serving, with followers replicating logs only. When leader switching occurs, it can result in failover recovery times of up to ten minutes to half an hour when the KV snapshot is large.
### Solution
Replicas support hot standby mode for KVTablet. At any time, the system will try to maintain one leader replica, one hot standby replica, and the rest as normal replicas.
### Anything else?
_No response_
### Willingness to contribute
- [x] I'm willing to submit a PR!
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by tracing the KVTablet replica and leader-switching paths described in the issue, including how followers replicate logs and how recovery is triggered after a leader change. Define completion as maintaining one leader, one hot standby, and remaining normal replicas while reducing failover recovery time for large KV snapshots.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java
- Domain
- distributed-systems
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100