I am trying to RemoteBulkWrite to a standalone instance using parquet files. It does not appear to work unless you use RemoteBulkWrite (see issue here: https://github.com/milvus-io/milvus/issues/36445)

I am trying to RemoteBulkWrite to a standalone instance using parquet files. It does not appear to work unless you use RemoteBulkWrite (see issue here: https://github.com/milvus-io/milvus/issues/36445)

I am trying to RemoteBulkWrite to a standalone instance using parquet files. It does not appear to work unless you use RemoteBulkWrite (see issue here: https://github.com/milvus-io/milvus/issues/36445)

I am trying to RemoteBulkWrite to a standalone instance using parquet files. It does not appear to work unless you use RemoteBulkWrite (see issue here: https://github.com/milvus-io/milvus/issues/36445)

I notice when inserting 50-60 vectors/sec to certain collection , read latency is increasing significantly only to this collection , reads to other collections in same milvus cluster 2.4.4 are not impacted , I have set no limits for cpu and memory for all nodes in my k8s milvus cluster , but perhaps some internal limits are most probably reached , with the above details could you suggest some suitable internal milvus parameters that may need to be increased so I can reduce read latency to this collection ?
Thanks

If I have compaction on and a large amount of data, will this increase memory usage, background tasks and slow down searches.

If I have compaction on and a large amount of data, will this increase memory usage, background tasks and slow down searches.

I am currently working with the following setup: