Building High Performance Server Network Interfaces Joe Gervais - - PowerPoint PPT Presentation

building high performance server network interfaces
SMART_READER_LITE
LIVE PREVIEW

Building High Performance Server Network Interfaces Joe Gervais - - PowerPoint PPT Presentation

Building High Performance Server Network Interfaces Joe Gervais Product Line Manager High Performance Networking Interconnect Hierarchy Interconnect Hierarchy Distance Bandwidth WAN LAN SAN GSN ST SYSTEM Latency Gigabyte System


slide-1
SLIDE 1

Building High Performance Server Network Interfaces

Joe Gervais Product Line Manager High Performance Networking

slide-2
SLIDE 2

Interconnect Hierarchy Interconnect Hierarchy

SYSTEM

SAN LAN WAN Latency Bandwidth Distance GSN ST

slide-3
SLIDE 3

Gigabyte System NetworkTM, or GSNTM Gigabyte System NetworkTM, or GSNTM

  • Is the highest bandwidth and lowest latency interconnect

standard

  • Provides full duplex dual, 6400 megabit (800 megabyte) per

second of error-free, flow controlled data

  • Provides for interoperability with Ethernet, Fibre Channel,

ATM, HIPPI-800 and other standards

slide-4
SLIDE 4

GSN Topology GSN Topology

ethernet Fibre Channel Point-to-point GSN links Switches Media Bridges Computer System Sumac Chips Storage ATM

slide-5
SLIDE 5

10 Gbit/s

  • 6.4 data
  • 1.6 control
  • 2.0 encoding

Copper

  • 40 meters
  • 20 bits wide @500MHz

Fiber

  • 1 Km
  • 10 Bits wide @1GHz

IEEE 802 MAC Header

  • expanded length field

Physical Physical

Multiplexed

  • 32 Byte cells
  • 4 VCs

Error Control

  • Link CRC
  • End to End CRC
  • Go back N retry

Flow Control

  • credits for each VC

Data Buffers

  • n chip

Logical Logical Messaging Messaging

Any IEEE defined ULP

  • TCP/IP
  • Schedule Transfer

Protocol Protocol

GSN Link Features GSN Link Features

Drivers Drivers State Machine State Machine DMA Engine DMA Engine

SuMAC vlsi chip

slide-6
SLIDE 6

The technology is ideal wherever organizations require timely movement of large amounts of information including

  • scientific and technical computing
  • HDTV
  • data mining
  • transaction processing
  • video and film archiving
  • storage management
slide-7
SLIDE 7

SGI XIO GSN Adapter SGI XIO GSN Adapter

Full bandwidth, high performance adapter

slide-8
SLIDE 8

Performance (Beta Software)

¥

Raw GSN 796 MB/s, 791 MB/s bidirectional

¥

ST 560 MB/s, 769 MB/s memory striping

  • Uses 5-8% of one CPU

¥

TCP 280 MB/s, UDP 500 MB/s

¥

BDS/ST 450 MB/s, 690 MB/s mem. striping

¥

One-way latency 4-9 usec (mem-to-mem)

  • 4 - 6 usec pt - pt 5m cable
  • 6 - 9 usec 50m cable plus switch

¥

Packet transmit rate 1.45 million PPS

¥

ST scaling: aggregate bandwidth scales at 98% of linear from 1-3 NICs

… Stay Tuned … Stay Tuned

slide-9
SLIDE 9

SGI XIO GSN Adapter SGI XIO GSN Adapter

Powered on August 1998 Interoperated with Essential Switch September 1998 To be offered in single and dual XIO versions

slide-10
SLIDE 10

SGI XIO GSN Adapter SGI XIO GSN Adapter

To be offered on Origin 200 GigaChannel, Origin 2000 and Onyx2

  • Design has very efficient CPU utilization
  • Memory a different story
slide-11
SLIDE 11

SGI XIO GSN Adapter SGI XIO GSN Adapter

Origin 200 GigaChannel, Onyx2 Deskside

  • Expected to not exceed 400 MB/s total

Origin 2000 Deskside, Onyx2 Rack (8P)

  • Expected to not exceed 500 MB/s, FDX

Origin 2000

  • 12 CPU and larger should be able to achieve full bandwidth

for proper apps

slide-12
SLIDE 12

SGI XIO GSN Adapter SGI XIO GSN Adapter

Bandwidth requirements are very memory intensive

  • Node Boards tested to 504 MB/s memory bandwidth to

GSN boards

  • 6 node boards for full bandwidth
  • Most applications will only be able to take advantage of ~

500 MB/s performance

slide-13
SLIDE 13

SHAC

SuMACª

XIO GSN Memory Adapter Architecture Adapter Architecture XTown XIO XTown XC

XC XIO

slide-14
SLIDE 14

Bus Choices Bus Choices

  • 64 Bit / 33 MHz PCI - ~250 MB/s Total
  • 64 Bit / 66 MHz PCI - ~500 MB/s Total
  • SGI Dual XIO GSN Adapter hardware tested to 99% of line

rate

– 791 MB/s per direction – Software overhead will reduce actual performance

slide-15
SLIDE 15

Latency Latency

  • HIPPI hardware latency with XIO adapter on the order of

80-90 u sec

– MPI adds ~ 30 u sec

  • GSN hardware latency expected to be on the order of 6 u

sec or lower through a switch

– MPI may be as low as 30 u sec total for a 4x decrease

slide-16
SLIDE 16

SGI SHAC ASIC SGI SHAC ASIC

  • DMA Engines per VC
  • ST Data Transfer Engine
  • TCP Checksum support
  • Supports Multiple Interrupt Queues

– true parallel driver architecture - not just multi-threaded