Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[pull] main from ydb-platform:main #28

Open
wants to merge 10,000 commits into
base: main
Choose a base branch
from
Open

Conversation

pull[bot]
Copy link

@pull pull bot commented May 12, 2022

See Commits and Changes for more details.


Created by pull[bot]

Can you help keep this open source service alive? 💖 Please sponsor : )

va-kuznecov and others added 21 commits October 17, 2024 15:34
commit_hash:12d86de033f73ea238ebde7f47b689d30014119a
Motivation:
Network is limited, we need to reduce amount of transfers between nodes.

One of problem:
Session actor has no knowledge about key range distribution (data shard locations). Which means we have to transfer data between data shard and kqp executor to perform read or write.

Workaround:
Provide estimation about keyRange -> nodeId distribution to use session (which means executor and other kqp components) created on the same node where located corresponding data shard.
- yt/client: include async_stream.h in file_reader.h
  NApi::IFileReader needs NConcurrency::IAsyncZeroCopyInputStream.

- Declare yt/yt/client/api/rpc_proxy/protocol_version_variables.h using CONFIGURE_FILE
  Otherwise resulting file does not materialize after:
  ya make --build-all --force-build-depends --replace-result --add-result=.h yt/yt/client/

  Proper source file generation is required at least for making clangd happy.

---

Pull Request resolved: ytsaurus/ytsaurus#894
commit_hash:b27f7963bc113543c0ac3842f78636be4f33416f
Co-authored-by: Dmitriy Orlov <[email protected]>
naspirato and others added 30 commits October 26, 2024 11:17
…10935)

Motivation:
Network is limited, we need to reduce amount of transfers between nodes.

One of problem:
Session actor has no knowledge about key range distribution (data shard locations). Which means we have to transfer data between data shard and kqp executor to perform read or write.

The solution:
Provide estimation about keyRange -> nodeId distribution to use session (which means executor and other kqp components) created on the same node where located corresponding data shard.

This commit contains server side code, and basic c++ sdk functions to perform describe.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
⤵️ pull merge-conflict Resolve conflicts manually
Projects
None yet
Development

Successfully merging this pull request may close these issues.