सभी किताबें

पेशेवर

ऐप्स परिचय Coach लॉग इन पढ़ना शुरू करें

Quantitative Finance · शब्दावली

Line rate, serialisation delay, maximum transmission unit क्या है?

अन्य नाम: line rate · serialisation delay · maximum transmission unit

Definition 1.2 Networks, Hardware and Trading Infrastructure · अध्याय 1 — Networking for Trading

The line rate RLR_{\mathrm L} of a link is the rate at which it clocks bits onto the medium (1, 10, 25 or 100 Gbit/s100\,\mathrm{G}\mathrm{bit}/\mathrm{s}). The serialisation delay of a frame is the time the link takes to put it on the wire. The maximum transmission unit (MTU) is the largest payload a link carries in one frame, 1 500 bytes for standard Ethernet.

One add-order message on the wire, in the simulator’s feed format (a MoldUDP64 packet in a UDP datagram in an Ethernet frame). The 36 bytes the strategy reads are 29% of the line time the frame occupies. Boxes are not to scale; byte counts from  and the formats’ headers.
Figure 1.1. One add-order message on the wire, in the simulator’s feed format (a MoldUDP64 packet in a UDP datagram in an Ethernet frame). The 36 bytes the strategy reads are 29% of the line time the frame occupies. Boxes are not to scale; byte counts from Proposition 1.3 and the formats’ headers.
Frame (bytes)1 Gbit/s1\,\mathrm{G}\mathrm{bit}/\mathrm{s}10 Gbit/s10\,\mathrm{G}\mathrm{bit}/\mathrm{s}25 Gbit/s25\,\mathrm{G}\mathrm{bit}/\mathrm{s}100 Gbit/s100\,\mathrm{G}\mathrm{bit}/\mathrm{s}
64672.067.226.96.7
1281 184.0118.447.411.8
2562 208.0220.888.322.1
5124 256.0425.6170.242.6
1 0248 352.0835.2334.183.5
1 51812 304.01 230.4492.2123.0
Table 1.1. Serialisation delay in nanoseconds by frame size and line rate (Proposition 1.3, preamble and inter-frame gap included). Computed by nw_wire.frame_table.

उदाहरण

Example 1.4 (One add order)

The exchange simulator of One Quant Book 10 publishes its feed as MoldUDP64 packets: a 20-byte header (session, sequence number, message count), then each message behind a 2-byte length. An add-order message is 36 bytes, so a packet carrying one is 58 bytes of UDP payload; with 8 bytes of UDP header, 20 of IPv4 header and 18 of Ethernet header and check sequence the frame is 104 bytes and occupies 124 bytes of line time (Figure 1.1): 99.2 ns99.2\,\mathrm{n}\mathrm{s} at 10 Gbit/s10\,\mathrm{G}\mathrm{bit}/\mathrm{s}, 39.7 ns39.7\,\mathrm{n}\mathrm{s} at 25. A venue that packs eight such messages in one packet spends the 66 bytes of fixed overhead once for eight messages instead of eight times.

अध्याय में पढ़ें →