overlord-1.9.4

• fix panic when master fail
• add slots -> node map checker
• extend the fetch interval to once a week which avoid incorrect cluster nodes from bad instance
• suppress prom invalid label value problem

overlord-1.9.0

• complete memcache binary protocol.
• fix memcache text request key&data no copy bug.

overlord-1.8.5

• add slowlog file rotate based on size
• add slowlog file total limit
• add slowlog config to command line flag
• increasing node connection inputs size

overlord-1.8.4

• fix time record MarkEndInput, which reduce memory consumption by 60%
• try fetch cluster nodes when key moved
• memcache command support (quit, version, noreply)

overlord-1.8.2

• add slowlog feature
• fixed reload bugs
• fixed anzi bugs
• fixed memcache.NodeConn bug

support reload config and add fuzz test

• add reload feature for cache type: redis, memcache, memcache_binary
• add more metrics
• add fuzz test for redis/memcache protocol

add tool and fix some bug

1. add migrate tools named anzi
2. add cluster manager tools enri
3. fixed overlord panic when all cluster seed nodes down
4. add back prometheus monitor metrics

Proxy Version 1.5.5

1. change pinger as long connection.

Platform Version 2.0.0

1. add apiserver: http front end
2. add cmd/executor: mesos executor
3. add cmd/scheduler: mesos framework
4. add mesos support: mesos library
5. add job library: job is a work progress abstraction(support balance/create now)
6. add lib/myredis: myredis is a simple redis client.
7. add lib/etcd: etcd is the etcd helper based on etcd api/v1
8. add front-end: front-end design and completed

Version 1.5.3

1. fix pipe read when occurs a err