Search for: All records

SLOWPOKE is a new system to accurately quantify the effects of hypothetical optimizations on end-to-end throughput for microservice applications, without relying on tracing or a priori knowledge of the call graph. Microservice operators can use SLOWPOKE to ask what-if performance analysis questions of the form "What throughput could my retail application sustain if I optimized the shopping cart service from 10K req/s to 20K req/s?". Given a target service and its hypothetical optimization, SLOWPOKE employs a perfor- mance model that determines how to selectively slow down non-target services to preserve the relative effect of the optimization. It then performs profiling experiments to predict the end-to-end throughput, as if the optimization had been implemented. Applied to four real-world microservice applications, SLOWPOKE accurately quantifies optimization effects with a root mean squared error of only 2.07%. It is also effective in more complex scenarios, e.g., predicting throughput after scaling optimizations or when bottlenecks arise from mutex contention. Evaluated in large-scale deployments of 45 nodes and 108 synthetic benchmarks, SLOWPOKE further demonstrates its scalability and coverage of a wide range of microservice characteristics. 

Physics-guided machine learning (PGML) has become a prevalent approach in studying scientific systems due to its ability to integrate scientific theories for enhancing machine learning (ML) models. However, most PGML approaches are tailored to isolated and relatively simple tasks, which lim- its their applicability to complex systems involving multiple interacting processes and numerous influencing features. In this paper, we propose a Physics-Guided Foundation Model (PGFM) that combines pre-trained ML models and physics- based models and leverages their complementary strengths to improve the modeling of multiple coupled processes. To effectively conduct pre-training, we construct a simulated en- vironmental system that encompasses a wide range of influ- encing features and various simulated variables generated by physics-based models. The model is pre-trained in this sys- tem to adaptively select important feature interactions guided by multi-task objectives. We then fine-tune the model for each specific task using true observations, while maintaining con- sistency with established physical theories, such as the prin- ciples of mass and energy conservation. We demonstrate the effectiveness of this methodology in modeling water temper- ature and dissolved oxygen dynamics in real-world lakes. The proposed PGFM is also broadly applicable to a range of sci- entific fields where physics-based models are being used. 

Human-generated Spatial-Temporal Data (HSTD), represented as trajectory sequences, has undergone a data revolution, thanks to advances in mobile sensing, data mining, and AI. Previous studies have revealed the effectiveness of employing attention mechanisms to analyze massive HSTD. However, traditional attention models face challenges when managing lengthy and noisy trajectories as their computation comes with large memory overheads. Furthermore, attention scores within HSTD trajectories are sparse (i.e., most of the scores are zeros), and clustered with varying lengths (i.e., consecutive tokens clustered with similar scores). To address these challenges, we introduce an innovative strategy named Memory-efficient Trajectory Attention (MeTA). We leverage complicated spatial-temporal features (e.g., traffic speed, proximity to PoIs) and design an innovative feature-based trajectory partition technique to shrink trajectory length. Additionally, we present a learnable dynamic sorting mechanism, with which attention is only computed between sub-trajectories that have prominent correlations. Empirical validations using real-world HSTD demonstrate that our approach not only yields competitive results but also significantly lowers memory usage compared with state-of-the-art methods. Our approach presents innovative solutions for memory-efficient trajectory attention, offering valuable insights for handling HSTD efficiently.