zilliztech / zilliztech/VectorDBBench

Timeout issue with Milvus

Open
#333 7 comments 0 reactions 2 assignees View on GitHub

@XuanYang-cn is already working on this.

Since Jul 3, 2024.

Dominant language
Python
Stars
1.2k
Forks
438
Avg merge
1d 4h
Merged PRs (30d)
1

Description

Getting consistent timeout issues when testing Milvus with standard Cohere 1M vectors, 768 dimensions test
On c5a.8xlarge EC2 instance 32vCPU and 64Gb RAM and 128Gb SSD

2024-06-05 10:59:09,978 | WARNING: VectorDB optimize timeout in 900 (task_runner.py:204) (197576)
2024-06-05 10:59:10,041 | WARNING: Failed to run performance case, reason = Performance case optimize timeout (task_runner.py:146) (197576)
Traceback (most recent call last):
File "/home/ubuntu/repos/vector-dbs/env/lib/python3.12/site-packages/vectordb_bench/backend/task_runner.py", line 202, in _optimize
return future.result(timeout=self.ca.optimize_timeout)[1]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/concurrent/futures/_base.py", line 458, in result
raise TimeoutError()
TimeoutError

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/home/ubuntu/repos/vector-dbs/env/lib/python3.12/site-packages/vectordb_bench/backend/task_runner.py", line 134, in _run_perf_case
build_dur = self._optimize()
^^^^^^^^^^^^^^^^
File "/home/ubuntu/repos/vector-dbs/env/lib/python3.12/site-packages/vectordb_bench/backend/task_runner.py", line 207, in _optimize
raise PerformanceTimeoutError("Performance case optimize timeout") from e
vectordb_bench.models.PerformanceTimeoutError: Performance case optimize timeout

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.