yanxiaoqi932

### Describe the feature Can enterprises use the model base here? For commercialization. ### Will you implement it? - [ ] I would like to implement this feature and create...

Auto Compaction

1

auto compaction #144

Add monitoring component

3

Add monitoring components to facilitate users to check the running status of the engine.

Can pqos bind LLC and MB to PID? Wiki only show how to bind LLC and MB to CPU cores.

enhancement(plugin): Support inter-pod affinity and anti-affinity at NUMA level

2

#### What type of PR is this? Enhancement #### What this PR does / why we need it: Support inter-pod affinity and anti-affinity at NUMA level，#220

Can katalyst add the scheduling function for LLC and memory bandwidth resources?

6

### What would you like to be added? Not only CPU cores, LLC and memory bandwidth resources are bottleneck resources sometimes, can you add scheduling functions for LLC and MB?...

enhancement(plugin): Support inter-pod affinity and anti-affinity at NUMA level

1

#### What type of PR is this? Enhancement #### What this PR does / why we need it: Support inter-pod affinity and anti-affinity at NUMA level，https://github.com/kubewharf/katalyst-core/issues/220 #### Special notes for...

OSPP 2024: Process and performance optimization of Value Log Compaction

2

# OSPP 2024 项目发布：Value Log Compaction 的流程与性能优化 ## LotusDB当前Compaction存在的不足 当前LotusDB的Value Log Compaction模块存在比较大的性能瓶颈，主要包括三个方面： 1. Compaction只能由用户手动执行，如果用户长期没有执行Compaction，则会导致磁盘中冗余数据过多； 2. Value Log Compaction过程中需要大量访问磁盘中的BPTree，以判断对应的数据是否失效，这会降低compaction的效率，同时影响读写性能； 3. Value Log Compaction过程中无法进行Memory Table的刷盘，当写负载非常大时，compaction会影响到写入性能。 因此，希望从这三个性能瓶颈入手，对Value Log Compaction模块进行优化。 ## 希望实现的目标 项目需要实现的目标为优化Value Log...

Can the milvus benchmark 2.1 measure recall? I find that it can only measure throughput now.