Table of Contents
Advertisement
Appendix J
Remote replication over Metropolitan Area Networks (MAN) and Wide Area Networks
(WAN) has become increasingly widespread with the mass adoption and deployment of
iSCSI-based StorTrends storage appliances. However, despite its popularity, this activity
is not bereft of challenges. One of the biggest challenges now facing replication over
significant distances is the delay incurred when doing so. Signals transported at nearly the
speed of light are saddled with delays, resulting in latencies that can no longer be
ignored, as is the case with LAN data transfers. These round-trip delays range from a
couple of milliseconds for inter-city connections to around 80-100 ms from coast-to-
coast, and as much as 250-300 ms for submarine transmissions across the globe. When
geostationary satellites are used, naturally the distances covered are much greater,
resulting in delays of about 700ms.
This whitepaper will examine the impact of transport distance and latency on the
efficiency of network bandwidth in WAN remote replication situations over TCP/IP. It
will then demonstrate how StorTrends iTX and its powerful WAN acceleration (called
WDS) and deduplication technologies improve bandwidth utilization, through
sophisticated compression and data reduction techniques.
Since it is founded in iSCSI technology, StorTrends relies heavily on the TCP/IP
protocol, optimized for LAN and SAN environments, for serving front-end I/Os and for
synchronous replication operations. StorTrends iTX harnesses standards-based transport
protocols to minimize the inefficiencies and high latencies of TCP/IP in WAN situations,
and greatly improve and increase data transfer speed, approaching the theoretical
maximum of the connection speed. StorTrends iTX also provides additional performance
gains through data reduction technologies such as compression and data deduplication.
The Effects of Packet Loss and Latency on TCP/IP Efficiency
The core technology behind iSCSI and remote replication is the TCP/IP protocol, which
is a connection-oriented protocol that employs various congestion control algorithms with
checks and balances to ensure guaranteed delivery of packets. Due to the very nature of
the protocol, and its dependence on round-trip acknowledgments and sliding windows,
the round trip time (RTT) it incurs plays a very dominant role.
A second major factor that adds additional challenges is the issue of packet loss. At such
significant transport distances, packets can be dropped due to congestion or bit errors.
While recovering from these hiccups, the TCP protocol gets into a "slow start" mode,
where it carries out more conservative corrective actions, resulting in even more
restricted performance. In essence, the throughput achieved in long distance replication
depends on two basic parameters: The link bandwidth and the transport delays and losses.
WDS and Deduplication in
StorTrends iTX
Appendix J : WDS and Deduplication in StorTrends iTX 255
Advertisement
Table of Contents
