jingkl

Results 93 comments of jingkl

[Bug]: [benchmark] diskann inserted 100 million data, load failed, and reported "collection xxx has not been loaded to memory or load failed"

image：master-20230614-35cb0b5b ` [2023-06-14 08:44:14,237 - INFO - fouram]: [check_params] scene_concurrent_locust required params: {'dataset_params': {'metric_type': 'L2', 'dim': 128, 'dataset_name': 'sift', 'dataset_size': '1m', 'ni_per': 50000}, 'collection_params': {'other_fields': []}, 'load_params': {}, 'query_params': {},...

[Bug]: [benchmark] diskann inserted 100 million data, load failed, and reported "collection xxx has not been loaded to memory or load failed"

release_name_prefix perf-single-1686731400 deploy_config fouramf-server-standalone-8c16m-disk case_params fouramf-client-gist1m-concurrent-diskann image：master-20230614-35cb0b5b `[2023-06-14 08:40:24,911 - INFO - fouram]: [check_params] scene_concurrent_locust required params: {'dataset_params': {'metric_type': 'L2', 'dim': 768, 'dataset_name': 'gist', 'dataset_size': 1000000, 'ni_per': 1000}, 'collection_params': {'other_fields':...

[Bug]: [perf][cluster] Milvus insert 1m data and build hnsw index, then concurrent search error“fail to search on all shard leaders”

release_name_prefix： perf-cluster-master-1680566400 deploy_config fouramf-server-cluster-8c16m case_params fouramf-client-sift1m-concurrent-hnsw other_params --milvus_tag_prefix=master -s --deploy_mode=cluster case_name test_concurrent_locust_custom_parameters server： ``` perf-cluster-ma66400-1-71-9223-etcd-0 1/1 Running 0 4h16m 10.104.4.148 4am-node11 perf-cluster-ma66400-1-71-9223-etcd-1 1/1 Running 0 4h16m 10.104.1.44 4am-node10 perf-cluster-ma66400-1-71-9223-etcd-2 1/1...

[Bug]: [perf]Milvus search reports an error in the search parameter nprobe of 512

@yanliang567 It's a timeout problem, but it recurs every time

[Bug]: [perf][nightly]Constant load release operations on milvus lead to pod oom

update： image：master-20230506-ad75afdc pymilvus：2.4.0dev12 server： ``` perf-standalone41000-7-8-2694-etcd-0 1/1 Running 0 64m 10.104.4.93 4am-node11 perf-standalone41000-7-8-2694-milvus-standalone-5db766d557nqndm 1/1 Running 4 (6m26s ago) 64m 10.104.17.99 4am-node23 perf-standalone41000-7-8-2694-minio-6dbf44f5b8-wqvjg 1/1 Running 0 64m 10.104.5.32 4am-node12 ``` log：...

[Bug]: [perf][nightly]Constant load release operations on milvus lead to pod oom

release_name_prefix perf-single-1685521800 deploy_config fouramf-server-standalone-8c16m case_params fouramf-client-sift1m-load-search-release image：2.2.0-20230531-ee45c791 grafana： ```` I0531 08:40:10.603857 382 request.go:665] Waited for 1.149781982s due to client-side throttling, not priority and fairness, request: GET:https://kubernetes.default.svc.cluster.local/apis/authorization.k8s.io/v1?timeout=32s NAME READY STATUS RESTARTS...

[Bug]: [perf][nightly]Constant load release operations on milvus lead to pod oom

@jiaoew1991 @aoiasd

[Bug]: [perf][nightly]Constant load release operations on milvus lead to pod oom

master-20230712-fc12d399 pymilvus 2.4.0dev81 This issue has been verified to be fixed

[Bug]: [perf][standalone] Milvus concurrently search with an error and restart, the error message is"failed to connect to all addresses"

This problem still exists release_name_prefix perf-standalone-master-1-1680786000 deploy_config fouramf-server-standalone-8c16m case_params empty-file other_params --milvus_tag_prefix=master -s case_name test_concurrent_locust_glove_ivf_flat_search_standalone server： ``` NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES perf-standalone86000-2-88-6229-etcd-0 1/1...

[Bug]: [perf][cluster]Milvus concurrent search with error "StatusCode.DEADLINE_EXCEEDED"

release_name_prefix perf-cluster-master-1680652800 deploy_config fouramf-server-cluster-8c16m case_params fouramf-client-gist1m-concurrent-hnsw other_params --milvus_tag_prefix=master -s --deploy_mode=cluster case_name test_concurrent_locust_custom_parameters server： ``` perf-cluster-ma52800-2-96-4095-pulsar-zookeeper-2 1/1 Running 0 4h17m 10.104.5.51 4am-node12 (cli_client.py:130) --   |   | perf-cluster-ma52800-2-96-4095-pulsar-zookeeper-1 1/1 Running 0 4h18m...