String search scheme in a distributed architecture

• US 7,917,509 B2
• Filed: 11/05/2007
• Issued: 03/29/2011
• Est. Priority Date: 07/26/1999
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Beylin, Boris
• Primary Examiner(s): Chen; Susan Y
• Application Number:
  US11/935,358
• Publication Number:
  US 20080059465A1
• Time in Patent Office: 1,240 Days
• Field of Search: 717/136
• US Class Current: 707/736
• CPC Class Codes: G06F 16/90344 by using string matching techniques
• CPC Class Codes: Y10S 707/959 Network
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

Methods and apparatuses for searching network data for one or more predetermined strings are disclosed. In one embodiment, the string search is a multi-stage search where the stages of the search are performed by different hardware components. In one embodiment in a first search stage, a first processor performs a comparison of blocks of incoming data to determine whether the blocks potentially represent the beginning of one of the predetermined strings. If a potential predetermined string is identified, a second processor performs a further search to determine whether the string matches one of the predetermined strings. Because the first processor searches only for the beginning of the predetermined strings, the first stage comparison can be performed quickly, which improves network performance as compared to more detailed searching. The second stage is performed by second processor, which allows the first processor to search for potential matching strings. Because many strings do not match the one or more predetermined strings, the more detailed search preformed by the second processor is performed selectively, which increases network performance as compared to more detailed searches on all network data.

Claims

1. A hardware-implemented method for searching for pre-defined string patterns by a network electronic device, the method comprising:

receiving a network packet containing data via a network at one or more classification engines;

performing a first stage search at the one or more classification engines on the data contained in the network packet, wherein the first stage search identifies multiple potential strings of interest having a first block of data matching a corresponding block of data of one or more predetermined strings;

generating a first stage search report with the one or more classification engines indicating multiple potential strings of interest and a location of the multiple potential strings of interest within the data contained in the network packet;

sending the first stage search report to a policy processor;

performing a second stage search on the data contained in the network packet with the policy processor, wherein the second stage search compares a second block of data of the multiple potential strings of interest indicated in the first stage search report to the one or more predetermined strings to determine whether a match exists;

generating a message with the policy processor to indicate that at least one of the multiple potential strings of interest is a string of interest if a match exists between the second block of data of at least one multiple potential string of interest and the one or more predetermined strings, wherein the message includes a packet destination of the network packet; and

outputting the network packet with the policy processor to the network if no potential strings of interest are identified.

2. The method of claim 1, wherein performing the second stage search comprises maintaining a queue having entries for each potential string of interest.

3. The method of claim 2, wherein one or more queue entries are maintained for multiple sets of data.

4. The method of claim 1, wherein the second block of data includes data other than the first block of data.

5. An article of manufacture for use by a network electronic device for searching for pre-defined string patterns, the article of manufacture comprising:

data that, when accessed by a hardware component, cause the hardware component to perform operations comprising;

performing a first stage search on a network packet received via a network, wherein the network packet contains data, and wherein the first stage search identifies multiple potential strings of interest having a first block of data matching a corresponding block of data of one or more predetermined strings;

generating a first stage search report indicating multiple potential strings of interest and a location of the multiple potential strings of interest within the data contained in the network packet;

sending the first stage search report to a policy processor;

performing a second stage search on the data contained in the network packet with the policy processor, wherein the second stage search compares a second block of data of the multiple potential strings of interest indicated in the first stage search report to the one or more predetermined strings to determine whether a match exists; and

generating a message to indicate that at least one of the multiple potential strings of interest is a string of interest if a match exists between the second block of data of at least one multiple potential string of interest and the one or more predetermined strings, wherein the message includes a packet destination of the network packet; and

outputting the network packet with the policy processor to the network if no potential strings of interest are identified.

6. The article of manufacture of claim 5, wherein the hardware component is a first processor and the article of manufacture further includes data that, when accessed by the first processor, causes the first processor to generate the first stage search report identifying one or more potential strings of interest, wherein the article of manufacture further comprises data that when accessed by the policy processor, cause the policy processor to perform the second stage search.

7. The article of manufacture of claim 5, wherein performing the second stage search further comprises maintaining a queue having entries for each potential string of interest.

8. The article of manufacture of claim 5, wherein the corresponding block of data of the one or more predetermined strings comprises a beginning block of data from the one or more predetermined strings.

9. The article of manufacture of claim 5, wherein the corresponding block of data of the one or more predetermined strings comprises a first and a second one-byte entry stored in a look-up table, the first and second one-byte entries representative of a beginning two bytes of the one or more predetermined strings.

10. The article of manufacture of claim 5, wherein the second block of data includes data other than the first block of data.