Latency in a packet-switched network is defined as the time from when a source endpoint sends a packet to when it is received by the destination endpoint. Round-trip latency, sometimes referred to as round-trip delay, is the amount of time for a packet to be sent from the source endpoint to the destination endpoint and returned from the destination to the source endpoint.
Minimal latency in any transaction is imperative for several reasons. IP endpoints, switches, and routers operate optimally without network delays. Minimal latency between clients and a PowerScale node ensures performance is not affected. Latency increases between two endpoints might lead to several issues that heavily degrade performance, depending on the application.
To minimize latency, you must measure it accurately between the endpoints. For assessing PowerScale nodes, latency is measured from the clients to a specified node. The measurement could use the IP of a specific node or the SmartConnect hostname. After applying configuration changes that affect latency, verify that the latency has indeed decreased. When attempting to minimize latency, consider the following information:
- Hops: Minimizing hops required between endpoints decreases latency. The implication is not to drag cables across a campus, but the goal is to confirm if any unnecessary hops could be avoided. Minimizing hops applies at the physical level with the number of switches between the endpoints but also applies logically to network protocols and algorithms.
- ASICs: When thinking about network hops, consider the ASICs within a switch. If a packet enters through one ASIC and exits through the other, latency could increase. If possible, keep traffic as part of the same ASIC to minimize latency.
- Network congestion: NFS v3, NFSv4, and SMB employ the TCP protocol. For reliability and throughput, TCP uses windowing to adapt to varying network congestion. At peak traffic, congestion control is triggered, dropping packets, and leading TCP to use smaller windows. In turn, throughput could decrease, and overall latency might increase. Minimizing network congestion ensures it does not affect latency. It is important to architect networks that are resilient to congestion.
- Routing: Packets that pass through a router might induce additional latency. Depending on the router configuration, packets are checked for a match against defined rules, sometimes requiring packet header modification.
- MTU mismatch: Depending on the MTU size configuration of each hop between two endpoints, an MTU mismatch might exist. Therefore, packets must be split to conform to upstream links, creating additional CPU overhead on routers and NICs, creating higher processing times, and leading to additional latency.
- Firewalls: Firewalls provide protection by filtering through packets against set rules for additional steps. The filtering process consumes time and could create further latency. Processing times are heavily dependent upon the number of rules in place. It is good measure to ensure outdated rules are removed to minimize processing times.