InfiniBand: Difference between revisions
No edit summary |
→Performance: NDR line coding |
||
Line 34: | Line 34: | ||
|- |
|- |
||
! colspan="2" | Encoding ([[bit]]s) |
! colspan="2" | Encoding ([[bit]]s) |
||
| colspan="3" align="center" | [[8b/10b encoding|8b/10b]] || colspan="4" align="center" | [[64b/66b encoding|64b/66b]]|| |
| colspan="3" align="center" | [[8b/10b encoding|8b/10b]] || colspan="4" align="center" | [[64b/66b encoding|64b/66b]]|| [[Pulse-amplitude_modulation|PAM4]] || t.b.d. |
||
|- |
|- |
||
! colspan="2" | Adapter latency ([[microsecond|µs]])<ref>http://www.hpcadvisorycouncil.com/events/2014/swiss-workshop/presos/Day_1/1_Mellanox.pdf // Mellanox</ref> |
! colspan="2" | Adapter latency ([[microsecond|µs]])<ref>http://www.hpcadvisorycouncil.com/events/2014/swiss-workshop/presos/Day_1/1_Mellanox.pdf // Mellanox</ref> |
Revision as of 15:08, 26 April 2021
InfiniBand (IB) is a computer networking communications standard used in high-performance computing that features very high throughput and very low latency. It is used for data interconnect both among and within computers. InfiniBand is also used as either a direct or switched interconnect between servers and storage systems, as well as an interconnect between storage systems. It is designed to be scalable and uses a switched fabric network topology.
As of 2014[update], it was the most commonly used interconnect in supercomputers. Mellanox (now Nvidia Networking) manufactures InfiniBand host bus adapters and network switches, and, in February 2016, it was reported that Oracle Corporation had engineered its own InfiniBand switch units and server adapter chips for use in its own product lines and by third parties.[1] Mellanox IB cards are available for Solaris, FreeBSD,[2][3] RHEL, SLES, Windows, HP-UX, VMware ESX,[4] and AIX.[5]
As an interconnect, IB competes with Ethernet, Fibre Channel, and Intel Omni-Path.
The technology is promoted by the InfiniBand Trade Association.
Specification
Performance
SDR | DDR | QDR | FDR10 | FDR | EDR | HDR | NDR | XDR | ||
---|---|---|---|---|---|---|---|---|---|---|
Signaling rate (Gbit/s) | 2.5 | 5 | 10 | 10.3125 | [6] | 14.062525.78125 | 50 | 100 | 250 | |
Theoretical effective throughput (Gb/s)[7] |
for | 1 link2 | 4 | 8 | 10 | 13.64 | 25 | 50 | 100 | 250 |
for | 4 links8 | 16 | 32 | 40 | 54.54 | 100 | 200 | 400 | 1000 | |
for | 8 links16 | 32 | 64 | 80 | 109.08 | 200 | 400 | 800 | 2000 | |
for 12 links | 24 | 48 | 96 | 120 | 163.64 | 300 | 600 | 1200 | 3000 | |
Encoding (bits) | 8b/10b | 64b/66b | PAM4 | t.b.d. | ||||||
Adapter latency (µs)[8] | 5 | 2.5 | 1.3 | 0.7 | 0.7 | 0.5 | less? | t.b.d. | t.b.d. | |
Year[9] | 2001, 2003 | 2005 | 2007 | 2011 | 2011 | 2014[10] | 2018[10] | 2021[10] | after 2023? |
Links can be aggregated: most systems use a 4× aggregate. 8× and 12× links are typically used for cluster and supercomputer interconnects and for inter-switch connections.
InfiniBand also provides RDMA capabilities for low CPU overhead.
Topology
InfiniBand uses a switched fabric topology, as opposed to early shared medium Ethernet. All transmissions begin or end at a channel adapter. Each processor contains a host channel adapter (HCA) and each peripheral has a target channel adapter (TCA). These adapters can also exchange information for security or quality of service (QoS).
Messages
InfiniBand transmits data in packets of up to 4 KB that are taken together to form a message. A message can be:
- a remote direct memory access read or write
- a channel send or receive
- a transaction-based operation (that can be reversed)
- a multicast transmission
- an atomic operation
Physical interconnection
![](http://upload.wikimedia.org/wikipedia/commons/thumb/a/ab/Infinibandport.jpg/195px-Infinibandport.jpg)
In addition to a board form factor connection, it can use both active and passive copper (up to 10 meters) and optical fiber cable (up to 10 km).[11] QSFP connectors are used.
The InfiniBand Association also specified the CXP connector system for speeds up to 120 Gbit/s over copper, active optical cables, and optical transceivers using parallel multi-mode fiber cables with 24-fiber MPO connectors.[citation needed]
API
InfiniBand has no standard API. The standard only lists a set of verbs such as ibv_open_device
or ibv_post_send
, which are abstract representations of functions or methods that must exist. The syntax of these functions is left to the vendors. Sometimes for reference this is called the verbs API. The de facto standard software stack is developed by OpenFabrics Alliance. It is released under two licenses GPL2 or BSD license for Linux and FreeBSD, and as Mellanox OFED for Windows (product names: WinOF / WinOF-2; attributed as host controller driver for matching specific ConnectX 3 to 5 devices)[12] under a choice of BSD license for Windows. It has been adopted by most of the InfiniBand vendors, for Linux, FreeBSD, and Windows. IBM states this at their knowledge center on verbs API:
- An AIX® application can determine the verbs API that is either the Open Fabrics Enterprise Distribution (OFED) verbs or the AIX InfiniBand (IB) verbs that must communicate with a specific destination.[13]
A presentation from Mellanox Technologies, dated 2014, with title "Verbs programming tutorial" states on page 31:[14]
- libibverbs, developed and maintained by Roland Dreier since 2006, are de facto the verbs API standard in *nix
- Developed as an Open source
- The kernel part of the verbs is integrated in the Linux kernel since 2005 – Kernel 2.6.11
- Inbox in several *nix distributions
- There are level low-level libraries from several HW vendors
History
InfiniBand originated in 1999 from the merger of two competing designs: Future I/O and Next Generation I/O. This led to the formation of the InfiniBand Trade Association (IBTA), which included Compaq, Dell, Hewlett-Packard, IBM, Intel, Microsoft, and Sun. At the time it was thought some of the more powerful computers were approaching the interconnect bottleneck of the PCI bus, in spite of upgrades like PCI-X.[15] Version 1.0 of the InfiniBand Architecture Specification was released in 2000. Initially the IBTA vision for IB was simultaneously a replacement for PCI in I/O, Ethernet in the machine room, cluster interconnect and Fibre Channel. IBTA also envisaged decomposing server hardware on an IB fabric. Following the burst of the dot-com bubble there was hesitation in the industry to invest in such a far-reaching technology jump.[16]
Timeline
- 2001: Mellanox ships InfiniBridge 10Gbit/s devices and ships over 10,000 InfiniBand ports.[17]
- 2002: adoption takes a setback when Intel announces that instead of shipping IB chips it would focus on developing PCI Express, and Microsoft discontinues IB development in favor of extending Ethernet, although Sun and Hitachi continue to support IB.[18]
- 2003: Virginia Tech builds an InfiniBand cluster ranked number three on the Top500 at the time.
- 2004: IB starts to see adoption as a clustering interconnect, beating Ethernet on latency and price.[16] The OpenFabrics Alliance develops a standardized, Linux-based InfiniBand software stack. The following year Linux adds IB support.[19]
- 2005: IB begins to be implemented as an interconnect for storage devices.[20]
- 2009: of the top 500 supercomputers in the world, Gigabit Ethernet is the internal interconnect technology in 259 installations, compared with 181 using InfiniBand.[21]
- 2010: Market leaders Mellanox and Voltaire merge, leaving just one other IB vendor, QLogic, primarily a Fibre Channel vendor.[22] Oracle makes a major investment in Mellanox.
- 2011: FDR switches and adapters announced at the International Supercomputing Conference.[23]
- 2012: Intel acquires QLogic's InfiniBand technology.[24]
- 2016: Oracle Corporation manufactures its own InfiniBand interconnect chips and switch units.[25]
- 2019: Nvidia acquired Mellanox for $6.9B[26]
Ethernet over InfiniBand
Ethernet over InfiniBand, abbreviated to EoIB, is an Ethernet implementation over the InfiniBand protocol and connector technology.
EoIB enables multiple Ethernet bandwidths varying on the InfiniBand (IB) version.
Ethernet's implementation of The Internet Protocol Suite, usually referred to as TCP/IP, is different to some of the implementations used on top of the InfiniBand protocol in IP over IB (IPoIB).
Type | Lanes | Bandwidth (Gbit/s) | Compatible Ethernet type(s) | Compatible Ethernet quantity |
---|---|---|---|---|
SDR | 1 | 2.5 | GbE to 2.5 GbE | 2 × GbE to 1 × 2.5 GbE |
4 | 10 | GbE to 10 GbE | 10 × GbE to 1 × 10 GbE | |
8 | 20 | GbE to 10 GbE | 20 × GbE to 2 × 10 GbE | |
12 | 30 | GbE to 25 GbE | 30 × GbE to 1 × 25 GbE + 1 × | 5 GbE|
DDR | 1 | 5 | GbE to 5 GbE | 5 × GbE to 1 × 5 GbE |
4 | 20 | GbE to 10 GbE | 20 × GbE to 2 × 10 GbE | |
8 | 40 | GbE to 40 GbE | 40 × GbE to 1 × 40 GbE | |
12 | 60 | GbE to 50 GbE | 60 × GbE to 1 × 50 GbE + 1 × 10 GbE | |
QDR | 1 | 10 | GbE to 10 GbE | 10 × GbE to 1 × 10 GbE |
4 | 40 | GbE to 40 GbE | 40 × GbE to 1 × 40 GbE |
See also
- 100 Gigabit Ethernet
- iSCSI Extensions for RDMA
- iWARP
- List of interface bit rates
- Optical communication
- Parallel optical interface
- SCSI RDMA Protocol
References
- ^ "Oracle Engineers Its Own InfiniBand Interconnects". 23 February 2016.
- ^ "Mellanox OFED for FreeBSD". Mellanox. Retrieved 19 September 2018.
- ^ Mellanox Technologies (3 December 2015). "FreeBSD Kernel Interfaces Manual, mlx5en". FreeBSD Man Pages. FreeBSD. Retrieved 19 September 2018.
- ^ "InfiniBand Cards - Overview". Mellanox. Retrieved 30 July 2014.
- ^ "Implementing InfiniBand on IBM System p (IBM Redbook SG24-7351-00)" (PDF).
- ^ https://cw.infinibandta.org/document/dl/7260
- ^ "Archived copy". Archived from the original on 2011-09-29. Retrieved 2009-10-27.
{{cite web}}
: CS1 maint: archived copy as title (link) - ^ http://www.hpcadvisorycouncil.com/events/2014/swiss-workshop/presos/Day_1/1_Mellanox.pdf // Mellanox
- ^ Panda, Dhabaleswar K.; Sayantan Sur (2011). "Network Speed Acceleration with IB and HSE" (PDF). Designing Cloud and Grid Computing Systems with InfiniBand and High-Speed Ethernet. Newport Beach, CA, USA: CCGrid 2011. p. 23. Retrieved 13 September 2014.
- ^ a b c "InfiniBand Roadmap - Advancing InfiniBand". InfiniBand Trade Association.
- ^ "Specification FAQ". ITA. Archived from the original on 24 November 2016. Retrieved 30 July 2014.
- ^ Mellanox OFED for Windows - WinOF / WinOF-2
- ^ Verbs API
- ^ Verbs programming tutorial
- ^ Pentakalos, Odysseas. "An Introduction to the InfiniBand Architecture". O'Reilly. Retrieved 28 July 2014.
- ^ a b Kim, Ted. "Brief History of InfiniBand: Hype to Pragmatism". Oracle. Archived from the original on 8 August 2014. Retrieved 28 July 2014.
- ^ "Timeline". Mellanox Technologies. Retrieved 28 July 2014.
- ^ "Sun confirms commitment to InfiniBand". The Register. Retrieved 28 July 2014.
- ^ "Linux Kernel 2.6.11 Supports InfiniBand". Retrieved 29 July 2014.
- ^ "Is InfiniBand poised for a comeback?", Infostor, 10 (2)
- ^ Lawson, Stephen. "Two rival supercomputers duke it out for top spot". COMPUTERWORLD. Retrieved 29 July 2014.
- ^ Raffo, Dave. "Largest InfiniBand vendors merge; eye converged networks". Retrieved 29 July 2014.
- ^ "Mellanox Demos Souped-Up Version of InfiniBand". CIO. 20 June 2011. Retrieved 1 August 2011.
- ^ "Intel Snaps Up InfiniBand Technology, Product Line from QLogic". HPCwire. January 23, 2012. Retrieved 2012-01-27.
- ^ "Oracle Engineers Its Own InfiniBand Interconnects". The Next Platform. Retrieved 2016-02-24.
- ^ https://nvidianews.nvidia.com/news/nvidia-to-acquire-mellanox-for-6-9-billion
External links
- Kerr, Gregory (2011), Dissecting a Small InfiniBand Application Using the Verbs API, arXiv:1105.1827, Bibcode:2011arXiv1105.1827K