arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.26422cs.LGcs.AI
收藏

STLGT:一种可扩展的基于跟踪的线性图变压器,用于微服务中的尾部延迟预测

STLGT: A Scalable Trace-Based Linear Graph Transformer for Tail Latency Prediction in Microservices

East China Normal University(华东师范大学)

Yongliang Ding, Qigong Bi, Peng Pu

AI总结:

STLGT通过构建跨度图编码跟踪信息,实现多步p95尾部延迟预测,相比PERT-GNN提升8.5%的MAPE精度,并在N=32时达到12倍的CPU推理速度。

摘要:

准确的端到端尾部延迟预测对于微服务系统中的主动SLO管理至关重要。然而,建模长距离依赖传播和非平稳、突发性工作负载同时保持大规模推理效率仍具挑战性。我们提出STLGT(可扩展的基于跟踪的线性图变压器),一种针对每个API的预测器,将跟踪编码为跨度图以进行多步p95尾部延迟预测。STLGT使用结构感知的线性图Transformer来传播跨服务依赖关系,推理时间与跨度图大小成线性关系,并使用解耦的时间模块来捕捉工作负载动态。在个性化教育微服务应用DeathStarBench和阿里巴巴跟踪数据上,STLGT在平均MAPE上比PERT-GNN提升8.5%,并在N=32时达到12倍的CPU推理速度,匹配预处理后的阿里巴巴跟踪的最大跨度图大小。消融研究进一步证明了每个组件的有效性,特别是在突发流量下。

英文摘要:

Accurate end-to-end tail-latency forecasting is critical for proactive SLO management in microservice systems. However, modeling long-range dependency propagation and non-stationary, bursty workloads while maintaining inference efficiency at scale remains challenging. We present STLGT (Scalable Trace-based Linear Graph Transformer), a per-API predictor that encodes traces as span graphs for multi-step p95 tail-latency forecasting. STLGT uses a structure-aware linear graph Transformer to propagate cross-service dependencies with inference time linear in span graph size, and a decoupled temporal module to capture workload dynamics. Across a personalized education microservice application, DeathStarBench, and Alibaba traces, STLGT improves forecasting accuracy over PERT-GNN by 8.5% MAPE on average and achieves up to 12x faster CPU inference at N=32, matching the maximum span graph size after preprocessing the Alibaba traces. Ablation studies further demonstrate the effectiveness of each component, especially under bursty traffic.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑