Pooling PCIe devices across multiple hosts offers a promising solution to mitigate stranded I/O resources, enhance device utilization, address device failures, and reduce total cost of ownership. The only viable option today are PCIe switches, which decouple PCIe devices from hosts by connecting them through a hardware switch. However, the high cost and limited flexibility of PCIe switches hinder their widespread adoption beyond specialized datacenter use cases.

PCIe devices, such as NICs and SSDs, are frequently underutilized in cloud platforms. PCIe device pools, in which multiple hosts can share a set of PCIe devices, could increase PCIe device utilization and reduce their total cost of ownership. The main way to achieve PCIe device pools today is via PCIe switches, but they are expensive and inflexible. We design Oasis,1 a system that pools PCIe devices in software over CXL memory pools. CXL memory pools are already being deployed to boost datacenter memory utilization and reduce costs. Once CXL pools are in place, they can serve as an efficient data path between hosts and PCIe devices. Oasis provides a control plane and datapath over CXL pools, mapping and routing PCIe device traffic across host boundaries. PCIe devices with different functionalities can be supported by adding an Oasis engine for each device class. We implement an Oasis network engine to demonstrate NIC pooling. Our evaluation shows that Oasis improves the NIC utilization by 2× and handles NIC failover with only a 38 ms interruption.

With serverless computing, users develop scalable applications using lightweight functions as building blocks, while cloud providers own most of the computing stack, allowing for better resource optimizations. In this paper, we observe that modern server-class processors are inefficiently utilized in serverless environments. Cores perform frequent context switches within function invocations and have a high degree of oversubscription. In such an environment, functions frequently lose their micro-architectural state in stateful hardware structures like caches, TLBs, and branch predictors, causing performance degradation. At the same time, modern processors are dimensioned for the needs of a broad set of applications, rendering them suboptimal for serverless workloads. Based on these insights, we propose Mosaic, an architecture optimized for serverless environments that maintains generality to efficiently support other workloads. Mosaic has two components: (1) MosaicCPU, a processor architecture that efficiently runs both serverless workloads and traditional monolithic applications, and (2) MosaicScheduler, a software stack for serverless systems that maximizes the benefits of MosaicCPU. MosaicCPU slices micro-architectural structures into small chunks and assigns tiles of such chunks to functions. The processor retains the state of functions in their tiles across context switches, thereby improving performance. Furthermore, currently-inactive tiles are set to a low power mode, thereby reducing energy consumption. In addition, MosaicScheduler maximizes efficiency by introducing predictive right-sizing of the per-function tiles, alongside with smart scheduling based on the state of the tiles. Overall, compared to conventional server-class processors, Mosaic improves the throughput of serverless workloads by 225% while using 22% less power.

With the proliferation of high bandwidth cameras and AR/VR devices, and their increasing use in situation awareness applications, edge computing is gaining prominence to meet the throughput requirements of such applications. This work focuses on camera applications that perform real-time Machine Learning inferences on camera frames. We find that Machine Learning based camera applications suffer from hardware resource fragmentation due to models under-utilizing or over-utilizing the accelerator. Meanwhile, it is challenging to support fine-grained resource sharing for accelerators such as TPUs because they can only process requests sequentially in a run to completion fashion. We present MicroEdge, a multi-tenant low-cost edge cluster for camera processing applications running at the edge. MicroEdge provides multi-tenancy support for Coral TPUs by extending K3s, an edge-specific distribution of Kubernetes. Through an admission control algorithm, it allows for fractional assignment of TPU resources commensurate with the application pipeline requirements to ensure that the TPUs are fully utilized. Using real-time camera processing applications and a real-world trace, we show that MicroEdge can support up to 2.8x camera streams for a given hardware configuration compared to vanilla K3s, while maintaining scalability and performance requirements.

Resource management for geo-distributed infrastructures is challenging due to the scarcity and non-uniformity of edge resources, as well as the high client mobility and workload surges inherent to situation awareness applications. Due to their centralized nature, state-of-the-art schedulers that work well in datacenters lack the performance and feature requirements of such applications. We present OneEdge, a hybrid control plane that enables autonomous decision-making at edge sites for localized, rapid single-site application deployment. Edge sites handle mobility, churn, and load spikes, by cooperating with a centralized controller that allows coordinated multi-site scheduling and dynamic reconfiguration.

Many geo-distributed services at web-scale companies still rely on databases (DBs) primarily optimized for single-site performance. At AT&T this is exemplified by services in the network control plane that rely on third-party software that uses DBs like MariaDB and PostgreSQL, which do not provide strict serializability across sites without a significant performance impact. Moreover, it is often impractical for these services to re-purpose their code to use newer DBs optimized for geo-distribution. In this paper, a novel drop-in solution for DB clustering across sites called Metric is presented that can be used by services without changing a single line of code. Metric leverages the single-site performance of an existing service's DB and combines it with a cross-site clustering solution based on an entry-consistent redo log that is specifically tailored for geo-distribution. Detailed correctness arguments are presented and extensive evaluations with various benchmarks show that Metric outperforms other solutions for the access patterns in our production use-cases where service replicas access different tables on different sites. In particular, Metric achieves up to 56% less latency and 5.2x higher throughput than MariaDB and PostgreSQL clustering, and up to 90% less latency and 26x higher throughput than CockroachDB and TiDB, systems that are designed to support geo-distribution.

Enabling next generation technologies such as self-driving cars or smart cities requires us to rethink the way we support their applications. The emergence of these technologies is fueled by the proliferation of a large number of devices in the Internet of Things. These devices have the potential to generate massive amounts of data, and applications supporting them often require this data to be processed in a timely manner. Because of these requirements, we must augment and extend the Cloud computing model to better serve such applications. The backhaul links connecting clients to Cloud data centers could quickly become overwhelmed by such data, and the physical distance of these data centers from clients prevents low-latency response times. To meet the challenges posed by emerging IoT applications, we must provide Cloudlike functionality closer to the edge of the network, where clients and their data live. We propose to elevate the Edge to be a peer of the Cloud for addressing these challenges.