Edge computing is a trending notion introduced a decade ago as a new computing paradigm for interactive mobile applications. The initial vision of the edge was a multi-tenant resource that will be used opportunistically for low-latency mobile applications. Despite that vision, we see in practice a different set of applications, driven by large-scale enterprises that have emerged and are driving realworld edge deployments today. In these applications, the edge is the primary place of storage and computation and, if network conditions allow, the cloud is opportunistically used alongside. We show how these enterprise deployments are driving innovation in edge computing. Enterprise-driven scenarios have a different motivation for using the edge. Instead of latency, the primary factors are limited bandwidth and unreliability of the network link to the cloud. The enterprise deployment layout is also unique: on-premise, single-tenant edges with shared, redundant outbound links. These previously unexplored characteristics of enterprise-driven edge scenarios open up a number of unique and exciting future research challenges for our community.

Distributed stream processing systems need to support stateful processing, recover quickly from failures to resume such processing, and reprocess an entire data stream quickly. We present Apache Samza, a distributed system for stateful and fault-tolerant stream processing. Samza utilizes a partitioned local state along with a low-overhead background changelog mechanism, allowing it to scale to massive state sizes (hundreds of TB) per application. Recovery from failures is sped up by re-scheduling based on Host Affinity. In addition to processing infinite streams of events, Samza supports processing a finite dataset as a stream, from either a streaming source (e.g., Kafka), a database snapshot (e.g., Databus), or a file system (e.g. HDFS), without having to change the application code (unlike the popular Lambda-based architectures which necessitate maintenance of separate code bases for batch and stream path processing). Samza is currently in use at LinkedIn by hundreds of production applications with more than 10, 000 containers. Samza is an open-source Apache project adopted by many top-tier companies (e.g., LinkedIn, Uber, Netflix, TripAdvisor, etc.). Our experiments show that Samza: a) handles state efficiently, improving latency and throughput by more than 100X compared to using a remote storage; b) provides recovery time independent of state size; c) scales performance linearly with number of containers; and d) supports reprocessing of the data stream quickly and with minimal interference on real-time traffic.

No abstract

No abstract

During the past decade, machine learning has become extremely popular and can be found in many aspects of our every day life. Nowayadays with explosion of data while rapid growth of computation capacity, Distributed Deep Neural Networks (DDNNs) which can improve their performance linearly with more computation resources, have become hot and trending. However, there has not been an in depth study of the performance of these systems, and how well they scale.In this paper we analyze CNTK, one of the most commonly used DDNNs, by first building a performance model and then evaluating the system two settings: a small cluster with all nodes in a single rack connected to a top of rack switch, and in large scale using Blue Waters with arbitary placement of nodes. Our main focus was the scalability of the system with respect to adding more nodes. Based on our results, this system has an excessive initialization overhead because of poor I/O utilization which dominates the whole execution time. Because of this, the system does not scale beyond a few nodes (4 in Blue Waters). Additionally, due to a single server-multiple worker design the server becomes a bottleneck after 16 nodes limiting the scalability of the CNTK.