Abstract
Layer-4 load balancing is fundamental to creating scale-out web services. We designed and implemented Ananta, a scale-out layer-4 load balancer that runs on commodity hardware and meets the performance, reliability and operational requirements of multi-tenant cloud computing environments. Ananta combines existing techniques in routing and distributed systems in a unique way and splits the components of a load balancer into a consensus-based reliable control plane and a decentralized scale-out data plane. A key component of Ananta is an agent in every host that can take over the packet modification function from the load balancer, thereby enabling the load balancer to naturally scale with the size of the data center. Due to its distributed architecture, Ananta provides direct server return (DSR) and network address translation (NAT) capabilities across layer-2 boundaries. Multiple instances of Ananta have been deployed in the Windows Azure public cloud with combined bandwidth capacity exceeding 1Tbps. It is serving traffic needs of a diverse set of tenants, including the blob, table and relational storage services. With its scale-out data plane we can easily achieve more than 100Gbps throughput for a single public IP address. In this paper, we describe the requirements of a cloud-scale load balancer, the design of Ananta and lessons learnt from its implementation and operation in the Windows Azure public cloud.
- A10 Networks AX Series. http://www.a10networks.com.Google Scholar
- Aryaka WAN Optimization. http://www.aryaka.com.Google Scholar
- Amazon Web Services. http://aws.amazon.com.Google Scholar
- Microsoft Windows Azure. http://www.windowsazure.com.Google Scholar
- T. Benson, A. Akella, A. Shaikh, and S. Sahu. CloudNaaS: A Cloud Networking Platform for Enterprise Applications. In Symposium on Cloud Computing, 2011. Google ScholarDigital Library
- M. Dobrescu, N. Egi, K. Argyraki, B.-G. Chun, K. Fall, G. Iannaccone, A. Knies, M. Manesh, and S. Ratnasamy. RouteBricks: exploiting parallelism to scale software routers. In SOSP, 2009. Google ScholarDigital Library
- N. Egi, A. Greenhalgh, M. Handley, M. Hoerdt, F. Huici, and L. Mathy. Towards high performance virtual routers on commodity hardware. In CoNEXT, 2008. Google ScholarDigital Library
- Embrane. http://www.embrane.com.Google Scholar
- F5 BIG-IP. http://www.f5.com.Google Scholar
- Google Cloud Platform. http://cloud.google.com.Google Scholar
- A. Greenberg et al. VL2: A scalable and flexible data center network. In SIGCOMM, 2009. Google ScholarDigital Library
- HA Proxy Load Balancer. http://haproxy.1wt.eu.Google Scholar
- A. Heffernan. RFC 2385: Protection of BGP Sessions via the TCP MD5 Signature Option, 1998. Google ScholarDigital Library
- L. Lamport. The Part-Time Parliament. ACM TOCS, 16(2):133--169, May 1998. Google ScholarDigital Library
- LoadBalancer.org Virtual Appliance. http://www.load-balancer.org.Google Scholar
- N. Mckeown, T. Anderson, H. Balakrishnan, G. M. Parulkar, L. L. Peterson, J. Rexford, S. Shenker, and J. S. Turner. OpenFlow: Enabling Innovation in Campus Networks. In SIGCOMM, 2008. Google ScholarDigital Library
- NetScalar VPX Virtual Appliance. http://www.citrix.com.Google Scholar
- C. Perkins. RFC 2003: IP Encapsulation within IP, 1996. Google ScholarDigital Library
- Rackspace. http://www.rackspace.com.Google Scholar
- Y. Rekhter, T. Li, and S. Hares. RFC 4271: A Border Gateway Protocol 4 (BGP-4), 2006.Google Scholar
- Riverbed Virtual Steelhead. http://www.riverbed.com.Google Scholar
- Receive Side Scaling. http://msdn.microsoft.com.Google Scholar
- V. Sekar, S. Ratnasamy, M. K. Reiter, N. Egi, and G. Shi. The Middlebox Manifesto: Enabling Innovation in Middlebox Deployment. In HotNets, 2011. Google ScholarDigital Library
- J. Sherry, S. Hasan, C. Scott, A. Krishnamurthy, S. Ratnasamy, and V. Sekar. Making Middleboxes Someone Else's Problem: Network Processing as a Cloud Service. In SIGCOMM, 2012. Google ScholarDigital Library
- D. Thaler and C. Hopps. RFC 2991: Multipath Issues in Unicast and Multicast Next-Hop Selection, 2000. Google ScholarDigital Library
- H. Uppal, V. Brajkovic, D. Brandon, T. Anderson, and A. Krishnamurthy. ETTM: A Scalable Fault Tolerant Network Manager. In NSDI, 2011. Google ScholarDigital Library
- Vyatta Software Middlebox. http://www.vyatta.com.Google Scholar
- R. Wang, D. Butnariu, and J. Rexford. OpenFlow-Based Server Load Balancing GoneWild. In Hot-ICE, 2011. Google ScholarDigital Library
- M. Welsh, D. Culler, and E. Brewer. SEDA: An Architecture for Well-Conditioned, Scalable Internet Services. In SOSP, 2001. Google ScholarDigital Library
- Windows Filtering Platform. http://msdn.microsoft.com.Google Scholar
- ZScalar Cloud Security. http://www.zscalar.com.Google Scholar
Index Terms
- Ananta: cloud scale load balancing
Recommendations
Ananta: cloud scale load balancing
SIGCOMM '13: Proceedings of the ACM SIGCOMM 2013 conference on SIGCOMMLayer-4 load balancing is fundamental to creating scale-out web services. We designed and implemented Ananta, a scale-out layer-4 load balancer that runs on commodity hardware and meets the performance, reliability and operational requirements of multi-...
Fast and Accurate Load Balancing for Geo-Distributed Storage Systems
SoCC '18: Proceedings of the ACM Symposium on Cloud ComputingThe increasing density of globally distributed datacenters reduces the network latency between neighboring datacenters and allows replicated services deployed across neighboring locations to share workload when necessary, without violating strict ...
Virtual Infrastructure Management in Private and Hybrid Clouds
One of the many definitions of "cloud" is that of an infrastructure-as-a-service (IaaS) system, in which IT infrastructure is deployed in a provider's data center as virtual machines. With IaaS clouds' growing popularity, tools and technologies are ...
Comments