Talking to customers who are interested in lowest latency solutions, the term "Bit Time" comes up over and over again. But it is not clear what it actually means in terms of low latency and whether a lower "Bit Time" is always better than a higher one. So let's try to explore the background and the implications here.
In general, "Bit Time" stands for the time it takes to transmit a bit for a given network data rate. At Gigabit Ethernet (=1Gbps data rate) the "Bit Time" is 1/(1Gbps) = 1/109 = 1 nanosecond. In other words it takes 1 nanosecond to transmit a bit at 1Gbps. For higher data rates like 10GE the "Bit Time" is even shorter with just 0.1 nanoseconds = 100 picoseconds. But make no mistake - this does not say anything about the actual speed of the signal - it only indicates how many bits can be transmitted during a given second. The speed at which those bits travel over a fiber link is still subject to the maximum speed of light in a fiber, which is approximately 200,000 km/s.
So let's assume we would start a race between a GbE NIC (Network Interface Card) and a 10GbE NIC over a given fiber link. The first bit of the signal would leave both NICs at the very same time. But since the "Bit Time" with 10GE is shorter, the end of the corresponding bit would leave the 10GE NIC earlier than it would leave the GbE NIC. One could also think of it like the bit occupying a certain length on the transmission link. While the bit out of the 10GE NIC only occupies 2 cm, the bit out of the GbE NIC occupies 20 cm, but still their speed on the fiber is the same. So finally they arrive at the end of the link at the very same time. But while the 10GE link has already received the bit completely the GbE link is still waiting for the tail of its bit to arrive. In general the 10GE link has an advantage of 18 cm (20 cm - 2 cm) for each bit received, which translates into a time advantage of 9 picoseconds.
Comments | Post a Comment
3 Comments to "Let's Take a "Bit Time" to Talk About Low Latency":
jbiesi
29 July 2010
Christian, I think you did a great job of breaking down the numbers and enumerating the key points for decision making when considering the leap to 10 GbE. I think it is important to expand on the first factor because customers need to know how their market centers work. First is is critical to know if information is treated in a pro-rata or time-price-priority fashion and what implications that has whether they are acting a customer (sending orders) or a market maker (sending quotes). Secondly, it is important to have a profile of the exchange and it's systems to judge how quickly they match trades and what risks that poses while orders are live. Much of the low latency business is driven by the equities markets, but as more and more people discover deriviates (futures and options) markets things get really interesting in the choices they can make. Or perhaps this would be an interesting topic for another series... Thanks, -John B Victory Networks
Comments (1)
datacenterstocks
02 August 2010
You can get down to about 400 nanoseconds on 10GBASE-CX4, but can go even lower with QDR InfiniBand. With 10GigE Server NICs dropping in price, I'm seeing a lot less debate over GigE vs. 10GigE and more 10GigE vs. 40G InfiniBand.
Comments (1)
tquinn
03 August 2010
Interesting article, and the the trend for best platform, for ultra low latency, is a combination of Adva gear, and the Anova Technologies routes(NY/NJ metro), called OptiWave. The Adva equipment can allow for Layer 1 transmission end-to-end(CHI-NJ metro sites), eliminating serial delay. In the metro, only 3 nanos per side is added for each lit circuit. Anova is the only provider that offers these efficiencies, and the mission is to maximize tradde execution performance. For more detail, email tquinn@anova-tech.com.
Comments (1)