-
Notifications
You must be signed in to change notification settings - Fork 83
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
Improve IVF index mmap performance by cache policy #167
Conversation
Please provide some results from benchmarking :) |
two comments
|
And the way of running benchmarks, please :) |
Signed-off-by: yah01 <[email protected]>
72a9c2c
to
7d8ea78
Compare
We evaluate this with an end-to-end benchmark, the dataset is 8M rows with 128 dim vectors. Before this PR: https://argo-workflows.zilliz.cc/workflows/qa/fouramf-85grz?tab=workflow&nodeId=fouramf-85grz-3384434876&nodePanelView=summary&sidePanel=logs:fouramf-85grz-3384434876:main After this PR: https://argo-workflows.zilliz.cc/workflows/qa/fouramf-nlhgl?tab=workflow&nodeId=fouramf-nlhgl-2020693927&sidePanel=logs:fouramf-nlhgl-2020693927:main You could start the test by argo like the links mentioned above. NOTE: the result is based on |
|
/approve |
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: PwzXxm, yah01 The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
/kind improvement
As we tested for HSNW index,
MADV_RANDOM
perform the best