Stateless Datacenter Load-balancing with Beamer

被引:0
|
作者
Olteanu, Vladimir [1 ]
Agache, Alexandru [1 ]
Voinescu, Andrei [1 ]
Raiciu, Costin [1 ]
机构
[1] Univ Politehn Bucuresti, Bucharest, Romania
基金
欧盟地平线“2020”;
关键词
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Datacenter load balancers (or muxes) steer traffic destined to a given service across a dynamic set of backend machines. To ensure consistent load balancing decisions when backends come or leave, existing solutions make a load balancing decision per connection and then store it as per-connection state to be used for future packets. While simple to implement, per-connection state is brittle: SYN-flood attacks easily fill state memory, preventing muxes from keeping state for good connections. We present Beamer, a datacenter load-balancer that is designed to ensure stateless mux operation. The key idea is to leverage the connection state already stored in backend servers to ensure that connections are never dropped under churn: when a server receives a mid-connection packet for which it doesn't have state, it forwards it to another server that should have state for the packet. Stateless load balancing brings many benefits: our software implementation of Beamer is twice faster than Google's Maglev, the state of the art software load balancer, and can process 40Gbps of HTTP uplink traffic on 7 cores. Beamer is simple to deploy both in software and in hardware as our P4 implementation shows. Finally, Beamer allows arbitrary scale-out and scale-in events without dropping any connections.
引用
收藏
页码:125 / 139
页数:15
相关论文
共 50 条
  • [41] Improved Analysis of Deterministic Load-Balancing Schemes
    Berenbrink, Petra
    Klasing, Ralf
    Kosowski, Adrian
    Mallmann-Trenn, Frederik
    Uznanski, Przemyslaw
    PODC'15: PROCEEDINGS OF THE 2015 ACM SYMPOSIUM ON PRINCIPLES OF DISTRIBUTED COMPUTING, 2015, : 301 - 310
  • [42] Beowulf parallel processing for dynamic load-balancing
    Bennett, BH
    Davis, E
    Kunau, T
    2000 IEEE AEROSPACE CONFERENCE PROCEEDINGS, VOL 4, 2000, : 389 - 395
  • [43] Randomized Algorithms for Dynamic Storage Load-Balancing
    Liu, Liang
    Fortnow, Lance
    Li, Jin
    Wang, Yating
    Xu, Jun
    PROCEEDINGS OF THE SEVENTH ACM SYMPOSIUM ON CLOUD COMPUTING (SOCC 2016), 2016, : 210 - 222
  • [44] LOAD-BALANCING HEURISTICS AND PROCESS BEHAVIOR.
    Leland, Will E.
    Ott, Teunis J.
    1600, (14):
  • [45] Enhancing Load-Balancing of MPI Applications with Workshare
    Dionisi, Thomas
    Bouhrour, Stephane
    Jaeger, Julien
    Carribault, Patrick
    Perache, Marc
    EURO-PAR 2021: PARALLEL PROCESSING, 2021, 12820 : 466 - 481
  • [46] Load-Balancing Energy Usage of Household Appliances
    Fahlen, Lennart E.
    ERCIM NEWS, 2009, (77): : 42 - 43
  • [47] Load-balancing scatter operations for grid computing
    Genaud, S
    Giersch, A
    Vivien, F
    PARALLEL COMPUTING, 2004, 30 (08) : 923 - 946
  • [48] Effective Load-Balancing Framework for Distributed WebGIS
    Shang Yan-Ling
    Xu Xu-Dong
    2009 INTERNATIONAL CONFERENCE ON NEW TRENDS IN INFORMATION AND SERVICE SCIENCE (NISS 2009), VOLS 1 AND 2, 2009, : 1130 - 1133
  • [49] Load-Balancing for Advance Reservation Connection Rerouting
    Xie, C.
    Xu, F.
    Ghani, N.
    Chaniotakis, E.
    Guok, C.
    Lehman, T.
    IEEE COMMUNICATIONS LETTERS, 2010, 14 (06) : 578 - 580
  • [50] On variants of a load-balancing problem with unit-load jobs
    Gyorgyi, Peter
    Kis, Tamas
    Szogi, Evelin
    JOURNAL OF SCHEDULING, 2024, : 121 - 138