Download presentation
Presentation is loading. Please wait.
Published byDortha Perry Modified over 9 years ago
1
Remote Direct Memory Access (RDMA) over IP PFLDNet 2003, Geneva Stephen Bailey, Sandburst Corp., steph@sandburst.com Allyn Romanow, Cisco Systems, allyn@cisco.com
2
RDDP Is Coming Soon “ST [RDMA] Is The Wave Of The Future” – S Bailey & C Good, CERN 1999 Need: –standard protocols –host software –accelerated NICs (RNICs) –faster host buses (for > 1G) Vendors are finally serious: Broadcom, Intel, Agilent, Adaptec, Emulex, Microsoft, IBM, HP (Compaq, Tandem, DEC), Sun, EMC, NetApp, Oracle, Cisco & many, many others
3
Overview Motivation Architecture Open Issues
4
CFP SigComm Workshop NICELI SigComm 03 Workshop Workshop on Network-I/O Convergence: Experience, Lessons, Implications http://www.acm.org/sigcomm/sigcomm2003/w orkshop/niceli/index.html
5
High Speed Data Transfer Bottlenecks –Protocol performance –Router performance –End station performance, host processing CPU Utilization The I/O Bottleneck –Interrupts –TCP checksum –Copies
6
What is RDMA? Avoids copying by allowing network adapter under control of application to steer data directly into application buffers Bulk data transfer or kernel bypass for small messages Grid, cluster, supercomputing, data centers Historically, special purpose fabrics – Fibre Channel, VIA, Infiniband, Quadrics, Servernet
7
Ethernet/ IP Storage Network (Fibre Channel) Database Intermachine Network (VIA, IB, Proprietary) Servers The World application A Machine Traditional Data Center
8
Why RDMA over IP? Business Case TCP/IP not used for high bandwidth interconnection, host processing costs too high High bandwidth transfer to become more prevalent – 10 GE, data centers Special purpose interfaces are expensive IP NICs are cheap, volume
9
The Technical Problem- I/O Bottleneck With TCP/IP host processing can’t keep up with link bandwidth, on receive Per byte costs dominate, Clark (89) Well researched by distributed systems community, mid 1990’s. Industry experience. Memory bandwidth doesn’t scale, processor memory performance gap– Hennessy(97), D.Patterson, T. Anderson(97), Stream benchmark
10
Copying Using IP transports (TCP & SCTP) requires data copying NIC 1 User Buffer Packet Buffer Packet Buffer 2 Data copies
11
Why Is Copying Important? Heavy resource consumption @ high speed (1Gbits/s and up) –Uses large % of available CPU –Uses large fraction of avail. bus bw – min 3 trips across the bus TestThroughput (Mb/sec) Tx CPUsRx CPUs 1 GBE, TCP7690.5 CPUs1.2 CPUs 1 Gb/s RDMA SAN - VIA 8910.2 CPUs 64 KB window, 64 KB I/Os, 2P 600 MHz PIII, 9000 B MTU
12
What’s In RDMA For Us? Network I/O becomes `free’ (still have latency though) 2500 machines using 30% CPU for I/O 1750 machines using 0% CPU for I/O
13
Approaches to Copy Reduction On-host – Special purpose software and/or hardware e.g., Zero Copy TCP, page flipping –Unreliable, idiosyncratic, expensive Memory to memory copies, using network protocols to carry placement information –Satisfactory experience – Fibre Channel, VIA, Servernet FOR HARDWARE, not software
14
RDMA over IP Standardization IETF RDDP Remote Direct Data Placement WG –http://ietf.org/html.charters/rddp-charter.html RDMAC RDMA Consortium –http://www.rdmaconsortium.org/home
15
RDMA over IP Architecture Two layers: DDP – Direct Data Placement RDMA - control IP Transport DDP RDMA control ULP
16
Upper and Lower Layers ULPs- SDP Sockets Direct Protocol, iSCSI, MPI DAFS is standardized NFSv4 on RDMA SDP provides SOCK_STREAM API Over reliable transport – TCP, SCTP
17
Open Issues Security TCP order processing, framing Atomic ops Ordering constraints – performance vs. predictability Other transports, SCTP, TCP, unreliable Impact on network & protocol behaviors Next performance bottleneck? What new applications? Eliminates the need for large MTU (jumbos)?
Similar presentations
© 2024 SlidePlayer.com Inc.
All rights reserved.