[server][da-vinci] Bumped RocksDB dep and adopt multiget async io by default #950
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
majisourav99
reviewed
May 7, 2024
clients/da-vinci-client/src/main/java/com/linkedin/davinci/store/AbstractStorageEngine.java
Outdated
Show resolved
Hide resolved
majisourav99
previously approved these changes
May 7, 2024
…default This PR bumps up the RocksDB dep and expose a config to enable async io for multi-get and the default value is true. rocksdb.read.async.io.enabled: default true In theoy, with this config and posix filesystem, RocksDB multiget API will be speeded up quite a bit based on the benchmarking: https://rocksdb.org/blog/2022/10/07/asynchronous-io-in-rocksdb.html So far, such optimization only applies to the chunk lookup for large value/rmd, and if it is proved to be more performant by checking the lookup latency for large value in the read path, we can apply such optimization in more areas: 1. DaVinci with DISK mode. 2. Ingestion code path by looking up entries in batch for AA/WC use cases. 3. Regular read path. So far, multi-get API can only be used against the same RocksDB database, so we might need some re-org of RocksDB databases if this API is truly helpful.
gaojieliu
force-pushed
the
rocksdb_dep_bump
branch
from
8ad4090
to
e5e22b5
Compare
We have existing both unit test and integration test to cover this change, so I think it is enough. |
majisourav99
approved these changes
May 7, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR bumps up the RocksDB dep and expose a config to enable async io for multi-get and the default value is true.
rocksdb.read.async.io.enabled: default true
In theoy, with this config and posix filesystem, RocksDB multiget API will be speeded up quite a bit based on the benchmarking: https://rocksdb.org/blog/2022/10/07/asynchronous-io-in-rocksdb.html
So far, such optimization only applies to the chunk lookup for large value/rmd, and if it is proved to be more performant by checking the lookup latency for large value in the read path, we can apply such optimization in more areas:
How was this PR tested?
CI
Does this PR introduce any user-facing changes?