626 Implementing the IBM Storwize V5000 Gen2 with IBM Spectrum Virtualize V8.1
The primary component of your round-trip time is the physical distance between sites. For
every 1000 kilometers (621.4 miles), you observe a 5-millisecond delay each way. This delay
does not include the time that is added by equipment in the path. Every device adds a varying
amount of time depending on the device, but a good rule is 25 microseconds for pure
hardware devices.
For software-based functions (such as compression that is implemented in applications), the
added delay tends to be much higher (usually in the millisecond plus range.) Next, we
describe an example of a physical delay.
Company A has a production site that is 1900 kilometers (1180.6 miles) away from its
recovery site. The network service provider uses a total of five devices to connect the two
sites. In addition to those devices, Company A employs a SAN FC router at each site to
provide Fibre Channel over IP (FCIP) to encapsulate the FC traffic between sites.
Now, there are seven devices, and 1900 kilometers (1180.6 miles) of distance delay. All the
devices are adding 200 microseconds of delay each way. The distance adds 9.5 milliseconds
each way, for a total of 19 milliseconds. Combined with the device latency, the delay is
19.4 milliseconds of physical latency minimum, which is under the 80-millisecond limit of
Global Mirror until you realize that this number is the best case number.
The link quality and bandwidth play a large role. Your network provider likely ensures a
latency maximum on your network link. Therefore, be sure to stay as far beneath the Global
Mirror round-trip-time (RTT) limit as possible. You can easily double or triple the expected
physical latency with a lower quality or lower bandwidth network link. Then, you are within the
range of exceeding the limit if high I/O occurs that exceeds the existing bandwidth capacity.
When you get a 1920 event, always check the latency first. If the FCIP routing layer is not
properly configured, it can introduce latency. If your network provider reports a much
lower latency, you might have a problem at your FCIP routing layer. Most FCIP routing
devices have built-in tools to enable you to check the RTT. When you are checking latency,
remember that TCP/IP routing devices (including FCIP routers) report RTT using standard
64-byte ping packets.
In Figure 10-155 on page 627, you can see why the effective transit time must be measured
only by using packets that are large enough to hold an FC frame, or 2148 bytes (2112 bytes
of payload and 36 bytes of header). Allow estimated resource requirements to be a safe
amount, because various switch vendors have optional features that might increase this size.
After you verify your latency by using the proper packet size, proceed with normal hardware
troubleshooting.
Before we proceed, we look at the second largest component of your RTT, which is
serialization delay. Serialization delay is the amount of time that is required to move a packet
of data of a specific size across a network link of a certain bandwidth. The required time to
move a specific amount of data decreases as the data transmission rate increases.
To Next Page
Loading...
Need help?
General