Risk-aware Adaptive Virtual CPU Oversubscription in Microsoft Cloud via Prototypical Human-in-the-loop Imitation Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929208818663424 |
|---|---|
| author | Wang, Lu Das, Mayukh Yang, Fangkai Sheng, Junjie Qiao, Bo Dong, Hang Qin, Si Rühle, Victor Bansal, Chetan Cortez, Eli Goiri, Íñigo Rajmohan, Saravan Lin, Qingwei Zhang, Dongmei |
| author_facet | Wang, Lu Das, Mayukh Yang, Fangkai Sheng, Junjie Qiao, Bo Dong, Hang Qin, Si Rühle, Victor Bansal, Chetan Cortez, Eli Goiri, Íñigo Rajmohan, Saravan Lin, Qingwei Zhang, Dongmei |
| contents | Oversubscription is a prevalent practice in cloud services where the system offers more virtual resources, such as virtual cores in virtual machines, to users or applications than its available physical capacity for reducing revenue loss due to unused/redundant capacity. While oversubscription can potentially lead to significant enhancement in efficient resource utilization, the caveat is that it comes with the risks of overloading and introducing jitter at the level of physical nodes if all the co-located virtual machines have high utilization. Thus suitable oversubscription policies which maximize utilization while mitigating risks are paramount for cost-effective seamless cloud experiences. Most cloud platforms presently rely on static heuristics-driven decisions about oversubscription activation and limits, which either leads to overloading or stranded resources. Designing an intelligent oversubscription policy that can adapt to resource utilization patterns and jointly optimizes benefits and risks is, largely, an unsolved problem. We address this challenge with our proposed novel HuMan-in-the-loop Protoypical Imitation Learning (ProtoHAIL) framework that exploits approximate symmetries in utilization patterns to learn suitable policies. Also, our human-in-the-loop (knowledge-infused) training allows for learning safer policies that are robust to noise and sparsity. Our empirical investigations on real data show orders of magnitude reduction in risk and significant increase in benefits (saving stranded cores) in Microsoft cloud platform for 1st party (internal services). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07033 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Risk-aware Adaptive Virtual CPU Oversubscription in Microsoft Cloud via Prototypical Human-in-the-loop Imitation Learning Wang, Lu Das, Mayukh Yang, Fangkai Sheng, Junjie Qiao, Bo Dong, Hang Qin, Si Rühle, Victor Bansal, Chetan Cortez, Eli Goiri, Íñigo Rajmohan, Saravan Lin, Qingwei Zhang, Dongmei Human-Computer Interaction Oversubscription is a prevalent practice in cloud services where the system offers more virtual resources, such as virtual cores in virtual machines, to users or applications than its available physical capacity for reducing revenue loss due to unused/redundant capacity. While oversubscription can potentially lead to significant enhancement in efficient resource utilization, the caveat is that it comes with the risks of overloading and introducing jitter at the level of physical nodes if all the co-located virtual machines have high utilization. Thus suitable oversubscription policies which maximize utilization while mitigating risks are paramount for cost-effective seamless cloud experiences. Most cloud platforms presently rely on static heuristics-driven decisions about oversubscription activation and limits, which either leads to overloading or stranded resources. Designing an intelligent oversubscription policy that can adapt to resource utilization patterns and jointly optimizes benefits and risks is, largely, an unsolved problem. We address this challenge with our proposed novel HuMan-in-the-loop Protoypical Imitation Learning (ProtoHAIL) framework that exploits approximate symmetries in utilization patterns to learn suitable policies. Also, our human-in-the-loop (knowledge-infused) training allows for learning safer policies that are robust to noise and sparsity. Our empirical investigations on real data show orders of magnitude reduction in risk and significant increase in benefits (saving stranded cores) in Microsoft cloud platform for 1st party (internal services). |
| title | Risk-aware Adaptive Virtual CPU Oversubscription in Microsoft Cloud via Prototypical Human-in-the-loop Imitation Learning |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2401.07033 |