Technique for selecting the number of packets to be concatenated
View Patent ↗A communication node comprises a receiver for receiving packets and a routing device for routing the received packets to one of two output ports. For each output port, the communication node further comprises a classifier for classifying a received packet based on its traffic characteristic and storing that packet in a corresponding queue for that traffic characteristic, and a concatenated packets preparer for concatenating n received packets from each queue to form a concatenated packet to be transmitted by the associated output port, where the maximum of n is determined based on the traffic characteristic of the associated queue.
1. A method for concatenating packets to be transmitted from a first node to a second node, the method comprising the steps of:
(a) receiving packets having at least one traffic characteristic from at least one input port;
(b) concatenating n received packets to form a concatenated packet, wherein the concatenated packet comprises a common header, a content information part of each of the n received packets, and a payload of each of the n received packets; and
(c) transmitting the concatenated packet from the first node to the second node, wherein the n received packets have a common traffic characteristic and n is determined based on the common traffic characteristic and at least one packet characteristic, wherein the at least one packet characteristic comprises a size of the common header, a size of the content information part of each of the n received packets, and one of a size of the payload of each of the n received packets or a maximum possible payload size of a received packet having the common traffic characteristic.
2. The method of claim 1 , wherein the concatenated packet is transmitted through a channel in a communication network, wherein the common traffic characteristic requires a delay of less than p milliseconds.
3. The method of claim 2 , wherein the channel has a bandwidth of B and n is determined by solving n from an equation of the form
(
H
+
n
I
+
∑
i
=
1
n
P
i
)
/
B
<
p
/
1000.
where H is the size of the common header, I is the size of the content information part of each of the n received packets, and P i is the size of the payload of the ith of the n received packets.
4. The method of claim 2 , wherein the channel has a bandwidth of B and if P max represents the maximum possible payload size of a received packet having the common traffic characteristic, n is determined by solving n from an equation of the form (H+n(I+P max ))/B≦p/1000, where H is the size of the common header and I is the size of the content information part of each of the n received packets.
5. The method of claim 1 , wherein the concatenated packet is transmitted through a channel in a communication network, wherein the common traffic characteristic is delay insensitive.
6. The method of claim 5 , wherein a maximum packet size allowed by the communication network is M bytes and n is determined by solving n from an equation of the form
H
+
n
I
+
∑
i
=
1
n
P
i
≤
M
,
where H is the size of the common header, I is the size of the content information part of each of the n received packets, and P i is the size of the payload of the ith of the n received packets.
7. The method of claim 5 , wherein a maximum packet size allowed by the communication network is M bytes and if P max represents the maximum possible payload size of a received packet having the common traffic characteristic, n is determined by solving n from an equation of the form H+n(I+P max )≦M, where H is the size of the common header, and I is the size of the content information part of each of the n received packets.
8. An apparatus for concatenating packets to be transmitted from a first node to a second node, the apparatus comprising:
(a) at least one input port for receiving packets;
(b) a traffic characteristic classifier for classifying and storing received packets of different traffic characteristics into different traffic characteristic groups in memory;
(c) a concatenated packets preparer for forming a concatenated packet from n received packets, wherein the concatenated packet comprises a common header, a content information part of each of the n received packets, and a payload of each of the n received packets; and
(d) at least one output port for transmitting the concatenated packet to the second node, wherein the n packets belong to one traffic characteristic group and n is determined based on the traffic characteristic of the one traffic characteristic group and at least one packet characteristic, wherein the at least one packet characteristic comprises a size of the common header, a size of the content information part of each of the n received packets, and one of a size of the payload of each of the n received packets or a maximum possible payload size of a received packet having the traffic characteristic of the one traffic characteristic group.
9. The apparatus of claim 8 , wherein the concatenated packet is transmitted through a channel in a communication network, wherein the n packets belong to the one traffic characteristic group that requires a delay time of less than p milliseconds, wherein the common header includes H bytes, the content information part of each of the n received packets includes I bytes, and the payload for ith of the n received packets includes P i bytes.
10. The apparatus of claim 9 , wherein the channel has a bandwidth of B and n is determined by solving n from an equation of the form
(
H
+
nI
+
∑
i
=
1
n
P
i
)
/
B
<
p
/
1000.
11. The method of claim 9 , wherein the channel has a bandwidth of B and if P max max represents the maximum possible payload size of a received packet having the common traffic characteristic, n is determined by solving n from an equation of the form (H+n(I+P max ))/B≦p/1000.
12. The apparatus of claim 8 , wherein the concatenated packet is transmitted through a channel in a communication network, wherein the n packets belong to the one traffic characteristic group that is delay insensitive, wherein the common header includes H bytes, the content information part of each of the n received packets includes I bytes, and the payload for ith of the n received packets includes P i bytes.
13. The apparatus of claim 12 , wherein a maximum packet size allowed by the communication network is M bytes and n is determined by solving n from an equation of the form
H
+
n
I
+
∑
i
=
1
n
P
i
≤
M
.
14. The method of claim 12 , wherein a maximum packet size allowed by the communication network is M bytes and if P max represents the maximum possible payload size of a received packet having the common traffic characteristic, n is determined by solving n from an equation of the form H+n(I+P max )≦M.