Forwarding packet fragments using L4-L7 headers without reassembly in a software-defined networking (SDN) system

Patent metadata

Field	Value
Publication number	US-9736057-B2
Application number	US-201414462442-A
Country	US
Kind code	B2
Filing date	Aug 18, 2014
Priority date	Aug 18, 2014
Publication date	Aug 15, 2017
Grant date	Aug 15, 2017

Abstract

A network element of a software-defined networking (SDN) system forwards IP packet fragments without reassembly is disclosed. The network element receives an IP packet fragment and determines whether the fragment is the first fragment of an original IP packet. If the fragment is the first fragment, then fields in the first fragment that are associated with open systems interconnection layers (OSI) 4-7 are retrieved and placed in an entry in a fragment information table so that the entry is associated with the original IP packet. If the received fragment is not the first fragment, then a matching entry in the fragment information table is to be identified and the associated OSI layers 4-7 information is retrieved for processing the non-first fragment.

First claim

What is claimed is:

1. A method implemented in a network element managed by a software-defined networking (SDN) controller, the method comprising:
receiving a packet at the network element implemented by one or more network devices;
determining whether the packet contains a fragment of an original Internet protocol (IP) packet, wherein the original IP packet is fragmented into a plurality of ordered fragments, and wherein a first fragment of the plurality of ordered fragments contains one or more fields associated with open system interconnection layers 4-7;
upon determining the packet contains a fragment of the original IP packet, determining whether the packet contains the first fragment of the original IP packet;
upon determining that the packet contains the first fragment of the original IP packet,
adding an entry to a fragment information table of the network element, the entry being associated with the original IP packet and comprising data contained in the first fragment in the one or more fields associated with open system interconnection layers 4-7, wherein the entry is used by the network element to process non-first fragments of the original IP packet; and
before all fragments of the original IP packet are received and after the entry is added to the fragment information table, processing, by the network element, the first fragment of the original IP packet based on the data contained in the first fragment in the one or more fields associated with open system interconnection layers 4-7; and

upon determining that the packet contains a non-first fragment of the original IP packet, processing, by the network element, the packet based on the fragment information table unless no matching entry is found and delay of processing the packet is over a delay threshold, wherein processing the packet includes forwarding the packet or discarding the packet.

2. The method of claim 1 , the processing the packet based on the fragment information table further comprising:
upon determining that the packet contains the non-first fragment of the original IP packet, checking the fragment information table for a matching entry associated with the original IP packet; and
upon finding the matching entry, processing the packet based on the data included in the matching entry.

3. The method of claim 2 , further comprising:
upon not finding the matching entry, delaying processing of the non-first fragment of the original IP packet for a period of time;
continuing to check the fragment information table for a matching entry;
while delaying for the period of time the processing of the non-first fragment of the original IP packet, receiving a subsequent packet that contains the first fragment of the original IP packet; and
responsive to finding in the fragment information table a matching entry associated with the original IP packet, the matching entry containing data from the first fragment of the original IP packet, processing the non-first fragment of the original IP packet based on the data in the matching entry.

4. The method of claim 3 , further comprising:
monitoring the delay threshold prior to continuing to check the fragment information table for a matching entry; and
discarding the packet when the delay threshold is exceeded.

5. The method of claim 1 , wherein the processing the first fragment of the original IP packet includes forwarding the first fragment to a specific network element based on the data contained in the first fragment in the one or more fields associated with open system interconnection layers 4-7.

6. The method of claim 1 , wherein the fragment information table entry comprises data includes at least one of:
a source IP address;
a destination IP address;
a protocol type;
a destination port number; and
an original IP packet identification.

7. The method of claim 1 , wherein the network element is an OpenFlow switch.

8. The method of claim 1 , wherein the one or more fields of the original IP packet associated with open system interconnection layers 4-7are header fields of the original IP packet.

9. An apparatus to be managed by a software-defined networking (SDN) controller, comprising:
a processor; and
a non-transitory machine readable storage media coupled to the processor and storing packet processing software that is executed by the processor, causes the processor to:
receive a packet,
determine whether the packet contains a fragment of an original Internet protocol (IP) packet, wherein the original IP packet is fragmented into a plurality of ordered fragments, and wherein a first fragment of the plurality of ordered fragments contains one or more fields associated with open system interconnection layers 4-7,
upon a determination that the packet contains a fragment of the original IP packet, determine whether the packet contains the first fragment of the original IP packet,
upon a determination that the packet contains the first fragment of the original IP packet,
add an entry into a fragment information table of the apparatus, the entry being associated with the original IP packet and comprising data contained in the first fragment in the one or more fields associated with open system interconnection layers 4-7, wherein the entry is used to process non-first fragments of the original IP packet, and
process the first fragment of the original IP packet, after the addition of the entry to the fragment information table, based on the data contained in the first fragment in the one or more fields associated with open system interconnection layers 4-7, and

upon a determination that the packet contains a non-first fragment of the original IP packet, process the packet based on the fragment information table unless no matching entry is found and delay of processing the packet is over a delay threshold, wherein processing the packet includes forwarding the packet or discarding the packet.

10. The apparatus of claim 9 , wherein the processing of the packet based on the fragment information table is further to:
upon the determination that the packet contains the non-first fragment of the original IP packet, check the fragment information table for a matching entry associated with the original IP packet, and
upon finding the matching entry, process the packet based on the data included in the matching entry.

11. The apparatus of claim 10 , wherein the check of the fragment information table for a matching entry is to:
upon failure to find the matching entry, delay processing of the non-first fragment of the original IP packet for a period of time,
continue to check the fragment information table for a matching entry, and
after receiving a subsequent packet that contains the first fragment of the original IP packet, find in the fragment information table a matching entry associated with the original IP packet, the matching entry containing data from the first fragment of the original IP packet, process the non-first fragment of the original IP packet based on the data in the matching entry.

12. The apparatus of claim 11 , wherein the check of the fragment information table for a matching entry is further to:
monitor the delay threshold prior to continuing to check the fragment information table for a matching entry, and
discard the packet upon determining the delay threshold is exceeded.

13. The apparatus of claim 12 , wherein the delay threshold is configured with a maximum number of tries, and the packet processing software further causes the processor to:
upon failure to find a matching entry from the fragment information table:
increment a counter value, and
determine that the delay threshold is e

Assignees

• Ericsson Telefon Ab L M
• ERICSSON TELEFON AB L M (publ)

Inventors

• Chinni Bhaskara
• Hlady Mark
• Helmajer Barnabás

Classifications

• H04L47/32

  by discarding or delaying data units, e.g. packets or frames · CPC title

• H04L45/14 Primary

  Routing performance; Theoretical aspects · CPC title

• H04L47/34 Primary

  ensuring sequence integrity, e.g. using sequence numbers · CPC title