Multi-tenant clouds enhance resource sharing among Virtual Machines (VMs) to boost overall utilization and reduce power consumption. However, this also introduces interference among workloads from different tenants and impedes VM performance isolation. In this article, we first demonstrate that the last-level cache (LLC) in CPUs, which is inherently shared by all VMs on the same physical machine, becomes a significant contending resource for LLC-critical workloads, leading to notable performance imbalances under the default hardware caching strategy. Although recent studies on LLC scheduling have progressed, they often require detailed profiling of user workloads or rely on hyperparameter tuning, limiting their applicability to private clusters or specific scenarios. We propose SpiderSense, a software-initiated LLC partitioner for managing Virtual Machine Monitors (VMM), to address these limitations. SpiderSense leverages modern yet off-the-shelf server CPU features to adaptively orchestrate LLC allocation among running black-boxed user VMs. SpiderSense dynamically samples VMs and calculates their fair share of LLC to allocate them while fully improving performance isolation among VMs. We experiment with SpiderSense using typical LLC-critical workloads, representative of the types of applications that stress LLC performance, such as Memcached and Llama. Our results show that SpiderSense improves performance by up to 40% in numerous colocation scenarios compared to current solutions.

The complexity of host-peripheral interactions during high-load tasks poses significant challenges for system optimization, with existing tracing tools degrading performance by up to 5.39×. We introduce DevTrace, a novel low-overhead tracing framework for peripheral interactions. Its modular architecture separates data collection from kernel-level operations, enabling lightweight tracing with minimal driver modifications across entire classes of devices. By eliminating heavy kernel tracing interrupts, DevTrace reduces overhead to negligible levels while maintaining data accuracy. In edge-based intelligence deployments, DevTrace achieves a 128× reduction in memory usage and approximately 10× lower CPU overhead compared to page-fault-based solutions. It significantly reduces data loss and performance degradation under high-load conditions, establishing it as a reliable tool for analyzing host-peripheral interactions and optimizing performance in resource-constrained environments. We also discuss potential extensions to eBPF to further decouple tracing from driver frameworks.