SMTcheck: Accurate SMT Interference Prediction to Improve Scheduling Efficiency in Datacenters

计算机科学 调度(生产过程) 实时计算 干扰(通信) 作业车间调度 可靠性工程 性能预测 数据收集 噪音(视频) 数据处理
作者
Jiyeon Kim,Jinhyeok Oh,Taehun Kim,Gyutae Kim,Youngsok Kim,Jaehyun Hwang,Joonsung Kim
出处
期刊:Proceedings [Institute of Electrical and Electronics Engineers]
卷期号:: 1-15 被引量:2
标识
DOI:10.1109/hpca68181.2026.11408462
摘要

Simultaneous multithreading (SMT) is widely used in modern x86 processors to improve core utilization by sharing hardware resources between co-located threads. However, such resource sharing often leads to severe performance interference, making efficient workload co-scheduling difficult, especially given the complexity and diversity of modern x86 CPUs. Our analysis reveals that SMT-aware workload scheduling can significantly improve system throughput and reduce tail latency for datacenter workloads, but identifying optimal thread combinations is challenging due to the lack of visibility into platform-specific resource sharing behaviors. In this paper, we present SMTcheck, a lightweight, accurate, and platformindependent methodology for predicting SMT interference for diverse x86 processors. SMTcheck uses carefully designed code snippets (Diags) to extract hidden microarchitectural features of performance-critical shared resources. With these extracted features, SMTcheck builds per-resource microbenchmarks (Injectors) to apply pinpoint pressure to specific target resources in order to capture workload-specific contention characteristics. SMTcheck then constructs a hardware-aware contention model to predict performance interference between arbitrary workload pairs without requiring exhaustive profiling. We evaluate SMTcheck on six x86 desktop processors and five x86 server processors from Intel and AMD across different generations and show that it achieves high prediction accuracy by up to 95.5 % (94.6 % on average). We further demonstrate its effectiveness by implementing a contention-aware scheduler in the Linux kernel. Compared to the default Linux scheduler, our contention-aware scheduler significantly reduces tail latency for latency-critical workloads (e.g., database, key-value store) by up to 36.09 %, and improves the overall system throughput by up to$1.072 \times$. Finally, using real-world cluster traces from Alibaba and Google, we demonstrate that SMTcheck incurs negligible profiling overheads ($\approx 0.113 \%$), making it practical for deployment in productionscale datacenter environments.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Bambookiller完成签到,获得积分10
1秒前
1秒前
tzhang16完成签到 ,获得积分10
2秒前
炸薯条发布了新的文献求助10
2秒前
2秒前
小安发布了新的文献求助10
2秒前
科研通AI6.2的应助被细心斑马采纳,获得10
3秒前
Ly发布了新的文献求助10
3秒前
5秒前
7秒前
hannah发布了新的文献求助10
7秒前
酷波er的应助被xun采纳,获得10
7秒前
7秒前
7秒前
8秒前
bkagyin的应助被撒拉嘿呀噻采纳,获得10
9秒前
Liu发布了新的文献求助30
9秒前
畅快访蕊完成签到,获得积分20
10秒前
优美的梦岚的应助被木叶流2022采纳,获得10
11秒前
12秒前
wanci的应助被路lu采纳,获得10
12秒前
ghost完成签到,获得积分10
13秒前
研友_VZG7GZ的应助被机智宛亦采纳,获得10
14秒前
kiluto发布了新的文献求助10
15秒前
15秒前
15秒前
15秒前
LynShen完成签到 ,获得积分20
15秒前
18秒前
18秒前
科研通AI65的应助被Mortal采纳,获得10
18秒前
18秒前
18秒前
为了精彩的活完成签到,获得积分10
18秒前
二三发布了新的文献求助10
19秒前
蒲公英完成签到 ,获得积分10
20秒前
哭泣雅绿发布了新的文献求助10
20秒前
英俊的铭的应助被动听的翠桃采纳,获得10
21秒前
hhh完成签到 ,获得积分20
22秒前
机灵语山完成签到,获得积分10
22秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Agyptische Geschichte der 21.30. Dynastie 510
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
基于界面调控的高效湿气发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8192723
求助须知:如何正确求助?哪些是违规求助? 9579144
关于积分的说明 21863903
捐赠科研通 7792268
什么是DOI,文献DOI怎么找? 3437013
关于科研通互助平台的介绍 2560633
邀请新用户注册赠送积分活动 2483864