-
Notifications
You must be signed in to change notification settings - Fork 1.8k
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
Optimising node to node communication by serializing node attribute in DiscoveryNode only in scenarioes where it is required #15341
Conversation
b2d6402
to
56ce8d0
Compare
❌ Gradle check result for b2d6402: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
❌ Gradle check result for 56ce8d0: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
56ce8d0
to
f7ea283
Compare
❌ Gradle check result for f7ea283: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
f7ea283
to
157d6dc
Compare
❌ Gradle check result for 157d6dc: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
157d6dc
to
0603f45
Compare
❌ Gradle check result for 0603f45: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
0603f45
to
13054e6
Compare
❌ Gradle check result for 13054e6: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
13054e6
to
b7e9ae8
Compare
❌ Gradle check result for b7e9ae8: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
b7e9ae8
to
c0b85f4
Compare
❌ Gradle check result for c0b85f4: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
74d3660
to
6c0e2c4
Compare
❌ Gradle check result for 74d3660: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
❌ Gradle check result for 6c0e2c4: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
6b0ec1a
to
b4c4a57
Compare
❌ Gradle check result for 6b0ec1a: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
❌ Gradle check result for b4c4a57: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
...c/main/java/org/opensearch/action/admin/cluster/allocation/ClusterAllocationExplanation.java
Show resolved
Hide resolved
❌ Gradle check result for b4c4a57: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
b4c4a57
to
c2a85c3
Compare
❕ Gradle check result for c2a85c3: UNSTABLE Please review all flaky tests that succeeded after retry and create an issue if one does not already exist to track the flaky failure. |
server/src/main/java/org/opensearch/action/support/nodes/BaseNodeResponse.java
Show resolved
Hide resolved
c2a85c3
to
f87e338
Compare
❌ Gradle check result for f87e338: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
f87e338
to
da7f5a5
Compare
❌ Gradle check result for da7f5a5: FAILURE Please examine the workflow log, locate, and copy-paste the failure(s) below, then iterate to green. Is the failure a flaky test unrelated to your change? |
…it is required Signed-off-by: RS146BIJAY <[email protected]>
da7f5a5
to
ca25f58
Compare
❕ Gradle check result for ca25f58: UNSTABLE Please review all flaky tests that succeeded after retry and create an issue if one does not already exist to track the flaky failure. |
The backport to
To backport manually, run these commands in your terminal: # Navigate to the root of your repository
cd $(git rev-parse --show-toplevel)
# Fetch latest updates from GitHub
git fetch
# Create a new working tree
git worktree add ../.worktrees/OpenSearch/backport-2.x 2.x
# Navigate to the new working tree
pushd ../.worktrees/OpenSearch/backport-2.x
# Create a new branch
git switch --create backport/backport-15341-to-2.x
# Cherry-pick the merged commit of this pull request and resolve the conflicts
git cherry-pick -x --mainline 1 451606535752a73be80d5203ae417e7d57fc5cef
# Push it to GitHub
git push --set-upstream origin backport/backport-15341-to-2.x
# Go back to the original working tree
popd
# Delete the working tree
git worktree remove ../.worktrees/OpenSearch/backport-2.x Then, create a pull request where the |
…oject#15341) Signed-off-by: RS146BIJAY <[email protected]>
…oject#15341) Signed-off-by: RS146BIJAY <[email protected]>
…oject#15341) Signed-off-by: RS146BIJAY <[email protected]>
…oject#15341) Signed-off-by: RS146BIJAY <[email protected]>
Description
A significant amount of compute and memory goes into ser/de during node to node communications for DiscoveryNode containing a bunch of node properties and attributes which are largely static and doesn't need to passed around for most of the node to node communication. Further, in scenarios like NodeStats call or FollowerChecker requests, single master thread needs to broadcast this DiscoveryNode object containing all these attributes to all the nodes of cluster. In case cluster is very large, this becomes a major bottleneck for master transport thread (which handles other critical operation like ClusterStateUpdate, IndexCreate etc,), which remains blocked till DiscoveryNode object is written.
In this PR we propose to optimise this node to node communication by serializing node attributes in DiscoveryNode only in scenarioes where it is required.
We are serialising attributes in the following scenarioes:
Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.