基于Facebook开源的 rocksdb 分布式数据库模块 [迭代]

Buei

更新日志  2023/11/28 15:00  - V1.6 [rocksdb内核版本:8.8.1]

增加 设置  预读取缓存大小 [默认未开启
增加 设置  可见性等级  
增加 设置  日志备份次数 [LOG.old 开头的文件每次启动数据库时备份次数]
增加 自定义日志目录
修复 当value为空时写入失败
...



以下为Facebook官方更新日志

8.8.1 (2023-11-17)Bug fixes

• Make the cache memory reservation accounting in Tiered cache (primary and compressed secondary cache) more accurate to avoid over/under charging the secondary cache.
• Allow increasing the compressed_secondary_ratio in the Tiered cache after setting it to 0 to disable.
  

8.8.0 (2023-10-23)New Features

• Introduce AttributeGroup by adding the first AttributeGroup support API, MultiGetEntity(). Through the use of Column Families, AttributeGroup enables users to logically group wide-column entities. More APIs to support AttributeGroup will come soon, including GetEntity, PutEntity, and others.
• Added new tickers rocksdb.fifo.{max.size|ttl}.compactions to count FIFO compactions that drop files for different reasons
• Add an experimental offpeak duration awareness by setting DBOptions::daily_offpeak_time_utc in "HH:mm-HH:mm" format. This information will be used for resource optimization in the future
• Users can now change the max bytes granted in a single refill period (i.e, burst) during runtime by SetSingleBurstBytes() for RocksDB rate limiter
  

Public API Changes

• The default value of DBOptions::fail_if_options_file_error changed from false to true. Operations that set in-memory options (e.g., DB::Open*(), DB::SetOptions(), DB::CreateColumnFamily*(), and DB::DropColumnFamily()) but fail to persist the change will now return a non-OK Status by default.
• Add new Cache APIs GetSecondaryCacheCapacity() and GetSecondaryCachePinnedUsage() to return the configured capacity, and cache reservation charged to the secondary cache.
  

Behavior Changes

• For non direct IO, eliminate the file system prefetching attempt for compaction read when Options::compaction_readahead_size is 0
• During a write stop, writes now block on in-progress recovery attempts
• Deleting stale files upon recovery are delegated to SstFileManger if available so they can be rate limited.
  

Bug Fixes

• Fix a bug in auto_readahead_size where first_internal_key of index blocks wasn't copied properly resulting in corruption error when first_internal_key was used for comparison.
• Fixed a bug where compaction read under non direct IO still falls back to RocksDB internal prefetching after file system's prefetching returns non-OK status other than Status::NotSupported()
• Add bounds check in WBWIIteratorImpl and make BaseDeltaIterator, WriteUnpreparedTxn and WritePreparedTxn respect the upper bound and lower bound in ReadOption. See 11680.
• Fixed the handling of wide-column base values in the max_successive_merges logic.
• Fixed a rare race bug involving a concurrent combination of Create/DropColumnFamily and/or Set(DB)Options that could lead to inconsistency between (a) the DB's reported options state, (b) the DB options in effect, and (c) the latest persisted OPTIONS file.
• Fixed a possible underflow when computing the compressed secondary cache share of memory reservations while updating the compressed secondary to total block cache ratio.
  

Performance Improvements

• Improved the I/O efficiency of DB::Open a new DB with create_missing_column_families=true and many column families.
  

• https://wwqr.lanzouw.com/b09ivrlpc
• 密码:7l4b
  

shaokui123

感谢分享，很给力！~

Ahiki

感谢分享，很给力

Ahiki

感谢分享，很给力！

aai888

非常好！！！

inmyheart

666666666666666666666666666666666666666

a897887419

牛逼，收藏了

feifei331

66666666666666666666666666666666666666666

c勇往直前

支持支持支持支持支持

jtucar

感谢分享，很给力！~