SCSI RDMA Protocol

In computing the SCSI RDMA Protocol (SRP) is a protocol that allows one computer to access SCSI devices attached to another computer via remote direct memory access (RDMA).[1][2] The SRP protocol is also known as the SCSI Remote Protocol. The use of RDMA makes higher throughput and lower latency possible than what is possible through e.g. the TCP/IP communication protocol. RDMA is only possible with network adapters that support RDMA in hardware. Examples of such network adapters are InfiniBand HCAs and 10 GbE network adapters with iWARP support. While the SRP protocol has been designed to use RDMA networks efficiently, it is also possible to implement the SRP protocol over networks that do not support RDMA.

SRP was published as an ANSI standard (ANSI INCITS 365-2002) in 2002 and renewed in 2007.[3]

As with the ISCSI Extensions for RDMA (iSER) communication protocol, there is the notion of a target (a system that stores the data) and an initiator (a client accessing the target) with the target performing the actual data movement. In other words, when a user writes to a target, the target actually executes a read from the initiator and when a user issues a read, the target executes a write to the initiator.

While the SRP protocol is easier to implement than the iSER protocol, iSER offers more management functionality, e.g. the target discovery infrastructure enabled by the iSCSI protocol.

In order to use the SRP protocol, an SRP initiator implementation, an SRP target implementation and networking hardware supported by the initiator and target are needed. The following software SRP initiator implementations exist:

The following SRP target implementations exist:

Bandwidth and latency of storage targets supporting the SRP or the iSER protocol should be similar. On Linux, there are two SRP and two iSER storage target implementations available that run inside the kernel (SCST[11] and LIO) and an iSER storage target implementation that runs in user space (STGT). Measurements have shown that the SCST SRP target has a lower latency and a higher bandwidth than the STGT iSER target. This is probably because the RDMA communication overhead is lower for a component implemented in the Linux kernel than for a user space Linux process, and not because of protocol differences.[19]

See also

References

  1. ANSI T10 SRPr16a, www.t10.org.
  2. ANSI T10 SRPr16a, web.archive.org
  3. ANSI webstore for purchasing standards - ANSI INCITS 365-2002
  4. OpenFabrics Enterprise Distribution for Windows.
  5. Mellanox OFED Drivers for VMware Infrastructure 3 and vSphere 4.
  6. Sun's download page.
  7. "Configuring SRP Devices With COMSTAR". Retrieved 4 February 2013.
  8. 1 2 Linux kernel version 2.6.24 change log.
  9. 1 2 D. Boutcher and D. Engebretsen, Linux Virtualization on IBM POWER5 Systems, Proceedings of the Linux Symposium, Vol. 1, July 2004, pp. 113-120.
  10. 1 2 IBM Systems Hardware Information Center, Virtual SCSI.
  11. 1 2 The SCST Project, an open source SCSI target implementation for Linux that includes an SRP target implementation.
  12. OFED 1.5.4.1 Release Notes, OpenFabrics website, January 2012.
  13. "SCSI RDMA Protocol". linux-iscsi.org.
  14. Linus Torvalds (2012-01-18). "InfiniBand/SRP merge". lkml.org.
  15. "DDN SFA10000 User Guide" (PDF). ddn.com. 2012-01-18.
  16. "DDN Corporate Overview, IB Storage 101 section" (PDF). ddn.com. 2012-01-18.
  17. IBM (10 March 2014). "IBM FlashSystem Integration Guide".
  18. Moellenkamp, Joerg. "PSARC/2009/111: SRP Target in Comstar". Retrieved 4 February 2013.
  19. Performance of SCST versus STGT.
This article is issued from Wikipedia - version of the Wednesday, November 05, 2014. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.