A High-Speed Stateful Packet Processing Approach for Tbps Programmable Switches

被引:0
|
作者
Scazzariello, Mariano [1 ,2 ]
Caiazzi, Tommaso [1 ,2 ]
Ghasemirahni, Hamid [1 ]
Barbette, Tom [3 ]
Kostic, Dejan [1 ]
Chiesa, Marco [1 ]
机构
[1] KTH Royal Inst Technol, Stockholm, Sweden
[2] Roma Tre Univ, Rome, Italy
[3] UCLouvain, Louvain, Belgium
来源
PROCEEDINGS OF THE 20TH USENIX SYMPOSIUM ON NETWORKED SYSTEMS DESIGN AND IMPLEMENTATION, NSDI 2023 | 2023年
基金
欧洲研究理事会; 瑞典研究理事会;
关键词
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
High-speed ASIC switches hold great promise for offloading complex packet processing pipelines directly in the high-speed data-plane. Yet, a large variety of today's packet processing pipelines, including stateful network functions and packet schedulers, require storing some (or all the) packets for short amount of times in a programmatic manner. Such a programmable buffer feature is missing on today's high-speed ASIC switches. In this work, we present RIBOSOME, a system that extends programmable switches with external memory (to store packets) and external general-purpose packet processing devices such as CPUs or FPGAs (to perform stateful operations). As today's packet processing devices are bottlenecked by their network interface speeds, RIBOSOME carefully transmits only the relevant bits to these devices. RIBOSOME leverages spare bandwidth from any directly connected servers to store the incoming payloads through RDMA. Our evaluation shows that RIBOSOME can process 300G of traffic through a stateful packet processing pipeline (e.g., firewall, load balancer, packet scheduler) by running the pipeline logic on a single server equipped with one 100G interface.
引用
收藏
页码:1237 / 1255
页数:19
相关论文
共 50 条
  • [31] High-speed programmable camera
    Test & Measurement World, 1995, 15 (02):
  • [32] Query-transaction acceleration using a DRP enabling high-speed stateful packet-by-packet self-reconfiguration
    Isobe, Takashi
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2007, E90D (12): : 1905 - 1913
  • [33] High-speed stateful packet classifier based on TSS algorithm optimized for off-chip memories
    Orsak, Michal
    Benes, Tomas
    2021 24TH INTERNATIONAL SYMPOSIUM ON DESIGN AND DIAGNOSTICS OF ELECTRONIC CIRCUITS & SYSTEMS (DDECS), 2021, : 151 - 156
  • [34] INP OPTOELECTRONIC SWITCHES AND THEIR HIGH-SPEED SIGNAL-PROCESSING APPLICATIONS
    COX, CH
    DIADIUK, V
    YAO, I
    LEONBERGER, FJ
    WILLIAMSON, RC
    PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS, 1983, 439 : 164 - 168
  • [35] The Dual Round Robin Pseudo-grant Matching for high-speed packet switches
    Manivasakan, R
    Hamdi, M
    Tsang, DHK
    HPSR 2002: WORKSHOP ON HIGH PERFORMANCE SWITCHING AND ROUTING, PROCEEDINGS: MERGING OPTICAL AND IP TECHNOLOGIES, 2002, : 64 - 68
  • [36] PROGRAMMABLE LOGIC, HIGH-SPEED SIGNAL-PROCESSING HIGHLIGHT THE CICC
    BURSKY, D
    ELECTRONIC DESIGN, 1994, 42 (09) : 64 - &
  • [37] Batched packet processing for high-speed software data plane functions
    Barach, David
    Linguaglossa, Leonardo
    Marion, Damjan
    Pfister, Pierre
    Pontarelli, Salvatore
    Rossi, Dario
    Tollet, Jerome
    IEEE INFOCOM 2018 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (INFOCOM WKSHPS), 2018,
  • [38] High-Speed Software Data Plane via Vectorized Packet Processing
    Barach, David
    Linguaglossa, Leonardo
    Marion, Damjan
    Pfister, Pierre
    Pontarelli, Salvatore
    Rossi, Dario
    IEEE COMMUNICATIONS MAGAZINE, 2018, 56 (12) : 97 - 103
  • [39] Dynamically extending the Corral with native code for high-speed packet processing
    Bos, Herbert
    Samwel, Bart
    Booij, Ilja
    COMPUTER NETWORKS, 2006, 50 (14) : 2444 - 2461
  • [40] A Parallel Architecture for Stateful, High-Speed Intrusion Detection
    Foschini, Luca
    Thapliyal, Ashish V.
    Cavallaro, Lorenzo
    Kruegel, Christopher
    Vigna, Giovanni
    INFORMATION SYSTEMS SECURITY, PROCEEDINGS, 2008, 5352 : 203 - 220