Don't Forget the I/O When Allocating Your LLC
Yifan Yuan, Mohammad Alian, Yipeng Wang, Ren Wang, Ilia Kurakin, Charlie Tai, Nam Sung Kim
摘要
In modern server CPUs, last-level cache (LLC) is a critical hardware resource that exerts significant influence on the performance of the workloads, and how to manage LLC is a key to the performance isolation and QoS in the cloud with multi-tenancy. In this paper, we argue that in addition to CPU cores, high-speed I/O is also important for LLC management. This is because of an Intel architectural innovation -Data Direct I/O (DDIO) -that directly injects the inbound I/O traffic to (part of) the LLC instead of the main memory. We summarize two problems caused by DDIO and show that (1) the default DDIO configuration may not always achieve optimal performance, (2) DDIO can decrease the performance of non-I/O workloads that share LLC with it by as high as 32%.
We then present IAT, the first LLC management mechanism that treats the I/O as the first-class citizen. IAT monitors and analyzes the performance of the core/LLC/DDIO using CPU's hardware performance counters and adaptively adjusts the number of LLC ways for DDIO or the tenants that demand more LLC capacity. In addition, IAT dynamically chooses the tenants that share its LLC resource with DDIO to minimize the performance interference by both the tenants and the I/O. Our experiments with multiple microbenchmarks and real-world applications demonstrate that with minimal overhead, IAT can effectively and stably reduce the performance degradation caused by DDIO.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper23
- Demystifying CXL Memory with Genuine CXL-Ready Systems and DevicesYan Sun, Yifan Yuan, Zeduo Yu, Reese Kuper 等MICRO 2023 · 被引用 133 次
- Rearchitecting the TCP Stack for I/O-Offloaded Content DeliveryTaehyun Kim, Deondre Martin Ng, Junzhi Gong, Youngjin Kwon 等NSDI 2023 · 被引用 42 次
- The benefits of general-purpose on-NIC memoryBoris Pismenny, Liran Liss, Adam Morrison, Dan TsafrirASPLOS 2022 · 被引用 28 次
- A Quantitative Analysis and Guidelines of Data Streaming Accelerator in Modern Intel Xeon Scalable ProcessorsReese Kuper, Ipoom Jeong, Yifan Yuan, Ren Wang 等ASPLOS 2024 · 被引用 24 次
- Domain specific run time optimization for software data planesSebastiano Miano, Alireza Sanaee, Fulvio Risso, Gábor Rétvári 等ASPLOS 2022 · 被引用 20 次
它引用的顶会 Paper10
- FIRM: An Intelligent Fine-grained Resource Management Framework for SLO-Oriented MicroservicesHaoran Qiu, Subho S. Banerjee, Saurabh Jha, Zbigniew T. Kalbarczyk 等OSDI 2020 · 被引用 350 次
- Borg: the next generationMuhammad Tirmazi, Adam Barker, Nan Deng, Md E. Haque 等EuroSys 2020 · 被引用 323 次
- Caladan: Mitigating Interference at Microsecond TimescalesJoshua Fried, Zhenyuan Ruan, Amy Ousterhout, Adam BelayOSDI 2020 · 被引用 213 次
- CLITE: Efficient and QoS-Aware Co-Location of Multiple Latency-Critical Jobs for Warehouse Scale ComputersTirthak Patel, Devesh TiwariHPCA 2020 · 被引用 153 次
- Reexamining Direct Cache Access to Optimize I/O Intensive Applications for Multi-hundred-gigabit NetworksAlireza Farshin, Amir Roozbeh, Gerald Q. Maguire Jr., Dejan KosticUSENIX ATC 2020 · 被引用 88 次
相关 Paper
- IDIO: Network-Driven, Inbound Network Data Orchestration on Server ProcessorsMohammad Alian, Siddharth Agarwal, Jongmin Shin, Neel Patel 等MICRO 2022 · 被引用 21 次
- A4: Microarchitecture-Aware LLC Management for Datacenter Servers with Emerging I/O DevicesHaneul Park, Jiaqi Lou, Sangjin Lee, Yifan Yuan 等ISCA 2025 · 被引用 2 次
- : Practical Cache Attacks from the NetworkMichael Kurth, Ben Gras, Dennis Andriesse, Cristiano Giuffrida 等S&P 2020 · 被引用 78 次
- When DDIO Meets Page Coloring: Revisiting DDIO Performance with SepiaChangwoo Song, Sanghyun Kim, Jinhyeok Oh, Qizhe Cai 等OSDI 2026
- CEIO: A Cache-Efficient Network I/O Architecture for NIC-CPU Data PathsBowen Liu, Xinyang Huang, Qijing Li, Zhuobin Huang 等SIGCOMM 2025 · 被引用 10 次
