Intelligent Memory Management Improves Burst Absorption; Balances Performance, Cost and Power in Cloud Applications

August 22, 2012 5 Comments »
Intelligent Memory Management Improves Burst Absorption; Balances Performance, Cost and Power in Cloud Applications

Cloud and Web 2.0 applications deployed in private and public cloud environments are significantly influencing network infrastructure design owing to their increasing scale and performance requirements. Data centers must be purpose-built to handle current and future workloads—evolving rapidly and driven by high volumes of end users, application types, cluster nodes and overall data movement in the cloud. A primary design challenge in this networking landscape is to select and deploy intelligent network switches that robustly scale the performance of applications, and to achieve this goal cost effectively. Ethernet switches must be architected at the silicon level to ensure that cloud network requirements can be implemented comprehensively, economically and in volume scale.

The design of a switch device’s memory management unit (MMU), including its packet buffering resources, is a key element in meeting network design challenges. The MMU directly affects both the performance and cost of network switching equipment; most importantly, its performance is closely tied to the switch’s ability to transfer data at line rate and handle congestion without dropping packets under varied and adverse traffic conditions. The MMU must be designed using a holistic approach, enabling cost-effective yet robust data center switches that can absorb the traffic bursts of network-intensive workloads and ensure deterministic performance.

Burst Behavior in Popular Cloud Applications

When application-induced traffic bursts create an imbalance between incoming and outgoing packet rates to a given port, packets must be queued in the switch packet buffer. The allocation and availability of the switch’s packet buffer resources to its ports—influenced not only by size of the buffer memory but also by the MMU architecture choice—determines the burst absorption capabilities of the network switch. This in turn dramatically affects the performance of distributed computing applications over a cloud network.

“Bursty” traffic patterns are prevalent in cloud data centers that have high levels of peak utilization, and workloads that are typically varied and non-uniform in nature. When application traffic exceeds the burst absorption capability in the access layer of a cloud network, TCP (Transmission Control Protocol) incast can become a problem. When multiple child nodes respond synchronously to the singular parent—either because they take the same time to complete the operation or because they return partial results within a parent-specified time limit—significant congestion occurs at the network switch port to which the parent server is connected. If the switch’s egress port to the parent server lacks adequate burst absorption capability, packets overrun their buffer allocation and are dropped, causing the TCP back-off algorithm to kick in. If excessive frame loss occurs in the network, the result can be a TCP collapse phenomenon; many flows simultaneously reduce bandwidth, resulting in link underutilization and a catastrophic loss of throughput results from inadequate switch buffering.

The Need for Integrated Switch Buffers

Overdesigning buffer capacity at each network node would certainly reduce the probability of congestion at any given egress port. This is not realistic or viable given the critical cost and power factors constraining today’s data centers. Traditionally, switch MMU designs have enabled high burst absorption through the use of large, external packet buffer memories. That has evolved however, because of significant increases in switching bandwidth requirements—particularly in the server access layer of the data center—and the need to contain the cost and power of such designs. Today, traditional fixed switch designs using distributed chipsets and external packet buffers have been largely replaced by highly integrated devices with on-chip buffering. Through the advent of new, innovative MMU designs, such as Broadcom’s Smart-Buffer solutions, network performance is enabled using cost-effective, integrated packet buffering; Smart-Buffer switches uniquely maximize burst absorption capability through full resource sharing and dynamic port allocation schemes.

Centralized, Shared, Intelligent MMU is the Solution

Network designers have an alternative to design approaches previously limited by statically allocated, per-port packet buffering schemes. By implementing a centralized, fully shareable, dynamically allocated and adaptive packet memory management architecture, network operators can achieve the holistic approach essential to managing high-performance cloud applications. For example, Broadcom’s StrataXGS switch architecture featuring Smart-Buffer technology incorporates a scalable multi-pipeline design interconnected through a centralized MMU architecture; further, its packet buffer is right-sized and dynamically shared across all ports for excellent burst absorption. Its combined architecture enables global admission control, queuing, policing and shaping functions. These kinds of intelligent switching capabilities deliver optimal buffer utilization and burst absorption for data center workloads by taking a holistic approach to buffer management, using real-life data center traffic scenarios to maximize overall throughput and lossless behavior.

Intelligent Switch Technology Meets Cloud Metrics of Cost, Power and Performance

Excellent burst absorption is the priority, particularly in today’s networks characterized by transient congestion. Data center workloads demand high throughput and robust, consistent performance from Ethernet switches; these performance features are required to handle characteristic traffic patterns in their networks and avoid TCP incast problems. At the same time, cost and power metrics in the cloud drive the need for fully integrated buffers and sophistication in switch MMU design.

Today, innovative and proven switch device technology enables cloud infrastructures based on a more intelligent approach that incorporates centralized, fully shareable, dynamically allocated and adaptive packet memory management architecture. Using cost-effective, integrated packet buffering, intelligent switches maximize burst absorption capability through full resource sharing and dynamic port allocation schemes, creating a holistic approach that proves ideal for cloud network operators facing daunting challenges in scaling their network infrastructure.

About the Authors

Sujal Das, Director of Product Marketing, Infrastructure and Networking Group, Broadcom Corp.

Sujal Das serves as Director of Product Marketing for Broadcom Corporation’s Infrastructure and Networking Group (ING). In this role, Das is responsible for driving Broadcom’s Ethernet switch business in the data center and enterprise LAN market segments, and the development of product, ecosystem and strategy based on technology trends and application workloads.

Das has extensive experience in semiconductors, networking software, data center network architectures, virtualization and server systems. Before joining Broadcom, Das served in senior product development and marketing roles at AMD, Marvell Semiconductor and Mellanox Technologies.

Das earned a Bachelor of Science EEE degree from the Birla Institute of Technology and Science in Pilani, India, and an MBA from Santa Clara University. He has published and presented on numerous data center networking and virtualization related topics in well-known industry publications and events. Das has been active in the open-source community, driving multiple initiatives that have helped proliferate the adoption of high-performance networking in data center applications.

Rochan Sankar, Associate Product Line Director, Infrastructure and Networking Group, Broadcom Corp.

Rochan Sankar serves as Associate Director of Product Line Management for Broadcom Corporation’s Infrastructure and Networking Group (ING). Sankar has 13 years of experience in defining and managing leading-edge semiconductor products for the networking and communications industries. Before joining Broadcom, he held senior positions in chip architecture, strategic marketing and business development at broad-line and startup semiconductor firms.

Sankar earned a Bachelor of Applied Science and Engineering from the University of Toronto and an MBA from The Wharton School, University of Pennsylvania, and holds five U.S. patents in the area of VLSI architecture.

Photo courtesy of Jemimus

5 Comments

  1. Tom McKeown August 22, 2012 at 8:03 pm -

    For all the reasons outlined in this article, building a greener data center makes the most sense.

    an Albany, NY company generates 75 percent of the electricity it needs to run its 1.5 MW data center using solar panels it installed on the roof of the data center building. Apple recently announced that solar panels will account for 60 percent of the Maiden, North Carolina data center’s power requirements and the new data center under construction in Prineville, Oregon will run on 100 percent renewable sources when it’s done.

    http://bit.ly/KgWaXR

Add Comment Register



Leave a Reply