Release Notes of v1.12.3

The following are the highlights in this release:

New Hotspot Algorithm Support

A new algorithm of hotspot detection is supported here, which makes the following improvements:

1. It defined the concept of threshold, and ready for automatic monitoring.
2. It has higher stability

Thanks to @Smityz .

Related PR:

• feat(hotspot): new algorithm of hotspot detection (https://github.com/XiaoMi/pegasus/pull/479)
• feat(collector): add statistics for partition hotspot (https://github.com/XiaoMi/pegasus/pull/444)

Optimization

There are some updates used to optimize memory usage and reduce performance cost.

Related PR:

• feat: limit long time rocksdb iteration operation(https://github.com/XiaoMi/pegasus/pull/500)
• feat: forbid large-size-value writes to Pegasus (https://github.com/XiaoMi/rdsn/pull/414)
• feat: add a new app_env to limit scan time (https://github.com/XiaoMi/rdsn/pull/421)
• feat: tcmalloc memory release improvements (https://github.com/XiaoMi/rdsn/pull/435)

Upgrade from the previous version

[replication]
- allow_non_idempotent_write = false
+ max_allowed_write_size = 1048576 # default = 1MB
+ cold_backup_checkpoint_reserve_minutes = 10

[pegasus.server]
# cluster level restriction {3000, 30MB, 1000, 30s}
+ rocksdb_multi_get_max_iteration_count = 3000
+ rocksdb_multi_get_max_iteration_size = 31457280
+ rocksdb_max_iteration_count = 1000
+ rocksdb_iteration_threshold_time_ms = 30000
+ rocksdb_use_direct_reads = true
+ rocksdb_use_direct_io_for_flush_and_compaction = true
+ rocksdb_compaction_readahead_size = 2097152
+ rocksdb_writable_file_max_buffer_size = 1048576
- perf_counter_cluster_name = %{cluster.name}
- perf_counter_enable_falcon = false
- perf_counter_enable_prometheus = false
+ perf_counter_sink = <falcon | prometheus>

[pegasus.collector]
- cluster = %{cluster.name}
+ hotspot_detect_algorithm = <hotspot_algo_qps_variance | hotspot_algo_qps_skew> 

[replication]
+ cluster_name = %{cluster.name}