mirror of https://github.com/facebook/rocksdb.git
Update history, version and format testing for 8.8 (#12004)
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/12004 Reviewed By: cbi42 Differential Revision: D50586984 Pulled By: hx235 fbshipit-source-id: 1480a8c2757340ebf83510557104aaa0e437b3ae
This commit is contained in:
parent
917fd87513
commit
ab15d33566
25
HISTORY.md
25
HISTORY.md
|
@ -1,6 +1,31 @@
|
||||||
# Rocksdb Change Log
|
# Rocksdb Change Log
|
||||||
> NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
|
> NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
|
||||||
|
|
||||||
|
## 8.8.0 (10/23/2023)
|
||||||
|
### 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.
|
||||||
|
|
||||||
|
### 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
|
||||||
|
|
||||||
|
### 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.
|
||||||
|
|
||||||
## 8.7.0 (09/22/2023)
|
## 8.7.0 (09/22/2023)
|
||||||
### New Features
|
### New Features
|
||||||
* Added an experimental new "automatic" variant of HyperClockCache that does not require a prior estimate of the average size of cache entries. This variant is activated when HyperClockCacheOptions::estimated\_entry\_charge = 0 and has essentially the same concurrency benefits as the existing HyperClockCache.
|
* Added an experimental new "automatic" variant of HyperClockCache that does not require a prior estimate of the average size of cache entries. This variant is activated when HyperClockCacheOptions::estimated\_entry\_charge = 0 and has essentially the same concurrency benefits as the existing HyperClockCache.
|
||||||
|
|
|
@ -12,7 +12,7 @@
|
||||||
// NOTE: in 'main' development branch, this should be the *next*
|
// NOTE: in 'main' development branch, this should be the *next*
|
||||||
// minor or major version number planned for release.
|
// minor or major version number planned for release.
|
||||||
#define ROCKSDB_MAJOR 8
|
#define ROCKSDB_MAJOR 8
|
||||||
#define ROCKSDB_MINOR 8
|
#define ROCKSDB_MINOR 9
|
||||||
#define ROCKSDB_PATCH 0
|
#define ROCKSDB_PATCH 0
|
||||||
|
|
||||||
// Do not use these. We made the mistake of declaring macros starting with
|
// Do not use these. We made the mistake of declaring macros starting with
|
||||||
|
|
|
@ -125,7 +125,7 @@ EOF
|
||||||
|
|
||||||
# To check for DB forward compatibility with loading options (old version
|
# To check for DB forward compatibility with loading options (old version
|
||||||
# reading data from new), as well as backward compatibility
|
# reading data from new), as well as backward compatibility
|
||||||
declare -a db_forward_with_options_refs=("6.27.fb" "6.28.fb" "6.29.fb" "7.0.fb" "7.1.fb" "7.2.fb" "7.3.fb" "7.4.fb" "7.5.fb" "7.6.fb" "7.7.fb" "7.8.fb" "7.9.fb" "7.10.fb" "8.0.fb" "8.1.fb" "8.2.fb" "8.3.fb" "8.4.fb" "8.5.fb" "8.6.fb" "8.7.fb")
|
declare -a db_forward_with_options_refs=("6.27.fb" "6.28.fb" "6.29.fb" "7.0.fb" "7.1.fb" "7.2.fb" "7.3.fb" "7.4.fb" "7.5.fb" "7.6.fb" "7.7.fb" "7.8.fb" "7.9.fb" "7.10.fb" "8.0.fb" "8.1.fb" "8.2.fb" "8.3.fb" "8.4.fb" "8.5.fb" "8.6.fb" "8.7.fb" "8.8.fb")
|
||||||
# To check for DB forward compatibility without loading options (in addition
|
# To check for DB forward compatibility without loading options (in addition
|
||||||
# to the "with loading options" set), as well as backward compatibility
|
# to the "with loading options" set), as well as backward compatibility
|
||||||
declare -a db_forward_no_options_refs=() # N/A at the moment
|
declare -a db_forward_no_options_refs=() # N/A at the moment
|
||||||
|
|
|
@ -1 +0,0 @@
|
||||||
For non direct IO, eliminate the file system prefetching attempt for compaction read when `Options::compaction_readahead_size` is 0
|
|
|
@ -1 +0,0 @@
|
||||||
* During a write stop, writes now block on in-progress recovery attempts
|
|
|
@ -1 +0,0 @@
|
||||||
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.
|
|
|
@ -1 +0,0 @@
|
||||||
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()`
|
|
|
@ -1 +0,0 @@
|
||||||
Add bounds check in WBWIIteratorImpl and make BaseDeltaIterator, WriteUnpreparedTxn and WritePreparedTxn respect the upper bound and lower bound in ReadOption. See 11680.
|
|
|
@ -1 +0,0 @@
|
||||||
Fixed the handling of wide-column base values in the `max_successive_merges` logic.
|
|
|
@ -1 +0,0 @@
|
||||||
* 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.
|
|
|
@ -1 +0,0 @@
|
||||||
Fixed a possible underflow when computing the compressed secondary cache share of memory reservations while updating the compressed secondary to total block cache ratio.
|
|
|
@ -1 +0,0 @@
|
||||||
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.
|
|
|
@ -1 +0,0 @@
|
||||||
Added new tickers `rocksdb.fifo.{max.size|ttl}.compactions` to count FIFO compactions that drop files for different reasons
|
|
|
@ -1 +0,0 @@
|
||||||
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
|
|
|
@ -1 +0,0 @@
|
||||||
Users can now change the max bytes granted in a single refill period (i.e, burst) during runtime by `SetSingleBurstBytes()` for RocksDB rate limiter
|
|
|
@ -1 +0,0 @@
|
||||||
Improved the I/O efficiency of DB::Open a new DB with `create_missing_column_families=true` and many column families.
|
|
|
@ -1 +0,0 @@
|
||||||
* 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.
|
|
Loading…
Reference in New Issue