SDRF/S and DWDM

Hi,

Welcome to EMC support forums ,

Let me try and get some information on this.

Thanks

Vanitha

Can I use DWDM to multiplex multiple FC lambdas, or do the lambdas have to be of various transports?

DWDM is a technology that puts data from different sources and protocols together on an optical fiber with each signal carried on its own separate and private light wavelength. This is commonly referred to as a lambda. Using DWDM technology, up to 80 and, theoretically, more separate wavelengths of data can be multiplexed into a light stream transmitted on a single optical fiber. On the receiving side, each channel is then de-multiplexed back into the original source.

A set of wavelengths has been allocated by the ITU standards body, establishing more than 50 optical channels (lambdas) within the wavelength range of 1520-1570 nm, with a nominal channel spacing of 100GHz (-0.80 nm). Within this range, wavelengths are grouped together in what are referred to as bands

If the issue is with IO latency and not bandwidth, does the DWDM solution make any difference at all?  Is there any point in using it, other than the fact that it's already sitting on our dark fibre network?

DWDM links only incur latency from the speed of light through fiber.

Cisco DWDM systems enable high density, 32-channel (lambda) aggregation between data centers up to 320 km apart. Each channel can operate up to 10 Gbps for a total of 320 Gbps over a single fiber pair. In contrast with the passive multiplexing of CWDM, DWDM platforms, such as the Cisco ONS 15530, Cisco ONS 15540, and Cisco ONS 15454, offer intelligent protection schemes to guard against failures in the fiber plant.

Additional advantages include a comprehensive selection of DWDM transmission elements enabling support for amplification, multiple network architectures, node configurations, in-service scalability, and easy-to-use network management capabilities for point-and-click provisioning

Does write acceleration and buffer-to-buiffer credit spoofing "break" the SRDF/S model?  Is that considered a semi-synchronous replication model is using DWDM hardware to accelerate these kinds of writes?

Semisynchronous operation masks any performance impact that results from I/O propagation delays. Semisynchronous mode writes data to the source system, completes the I/O, and then synchronizes the data with the target system. Because the I/O is completed prior to synchronizing data with the target system, this mode provide san added performance advantage. A second write is not accepted on a volume until the target has been synchronized, so this is not asynchronous.

By presenting an earlier I/O complete signal to the host/server, the host/server continues processing reads to the logical volume. Most applications do a read before they do a write. This implementation successfully masks the I/O elongation that is created by the propagation delay to the target system in a pure synchronous mode