Congestion control and avoidance method

• US 20030028616A1
• Filed: 06/28/2002
• Published: 02/06/2003
• Est. Priority Date: 06/28/2001
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Takahashi, Yasuhiro, Yokota, Daisuke, Takeshima, Yoshiteru, Noda, Fumio, Aoki, Hideo, Nishikado, Takashi
• Granted Patent: US 6,931,435 B2
• Time in Patent Office: Days
• US Class Current: 709/217
• CPC Class Codes: H04L 47/10 Flow control; Congestion control
• CPC Class Codes: H04L 47/12 Avoiding congestion; Recovering from congestion
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1014 based on the content of a request
• CPC Class Codes: H04L 67/2885 Hierarchically arranged intermediate devices, e.g. for hierarchical caching
• CPC Class Codes: H04L 67/564 Enhancement of application control based on intercepted application data
• CPC Class Codes: H04L 67/5651 Reducing the amount or size of exchanged application data
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching

Abstract

A congestion control and avoidance method including a method check step of determining whether the request contents is cacheable or uncacheable on the basis of the request inputted from the client terminal, a first URI check step of, when it is determined that the request contents is cacheable in the method check step, checking a URI included in the request from the client terminal to determine whether the request contents is cacheable or uncacheable, a first URI hash search step of, when it is determined that the request contents is cacheable based on determination of the first URI check step, searching a URI hash to determine to execute any of regular caching, priority caching and access limitationing operation, and a step of executing any of the regular caching, priority caching and access limitationing operation according to determination in the first URI hash search step.

Claims

1. A congestion control and avoidance method in a communication relay device provided between a client terminal and a server device for transmitting, according to a request from the client terminal, contents of the request already stored at the time of a cache hit and for receiving the request contents from the server device and transmitting the request contents to the client terminal at the time of a cache mishit or when the request utilizes no cache, said method comprising:

a method check step of determining whether the request contents is cacheable or uncacheable on the basis of the request inputted from the client terminal;

a first URI check step of, when it is determined that the request contents is cacheable in said method check step, checking a URI included in the request from the client terminal to determine whether the request contents is cacheable or uncacheable;

a first URI hash search step of, when it is determined that the request contents is cacheable based on determination of said first URI check step, searching a URI hash to determine to execute any of regular caching, priority caching and access limitation operation; and

a step of executing any of the regular caching, priority caching and access limitation operation according to determination in said first URI hash search step.

4. A congestion control and avoidance method as set forth in claim 1, further comprising a step of, when it is determined that the request contents is uncontrollable in said method check step, performing non-control.

5. A congestion control and avoidance method as set forth in claim 1, further comprising a step of acquiring a request method included in the request from the client terminal and a step of determining that the request contents is cacheable, uncacheable or uncontrollable according to the acquired request method.

6. A congestion control and avoidance method as set forth in claim 1, wherein said first URI check step includes:

a step of confirming that a URI scheme included in the request from the client terminal is a first URI scheme such as HTTP;

a step of processing the URI by removing a query attached in the URI;

a step of checking a path included in the request from the client terminal to examine whether the path contains a predetermined character;

a step of, when the path contains the predetermined character, reserving a character string obtained by processing the URI in a memory to move to uncacheable operation; and

a step of, when the path contains no predetermined character, moving to cacheable operation.

7. A congestion control and avoidance method as set forth in claim 1, wherein said second URI check step includes:

a step of confirming that a URI scheme included in the request from the client terminal is a first URI scheme such as HTTP; and

a step of processing the URI by removing a query attached in the URI.

8. A congestion control and avoidance method as set forth in claim 1, wherein said first or second URI hash search step include:

a step of searching the URI hash;

a step of, when a URI entry is hit, referring a control type included in the URI entry and determining a control described therein; and

a step of, when no hit is found in the URI entry, determining a predetermined operation.

9. A congestion control and avoidance method as set forth in claim 8, wherein the URI entry includes information on the URI, control type, an access counter and cache entry.

10. A congestion control and avoidance method as set forth in claim 9, wherein said cache entry includes URI entry information, cache entry types indicative of various control types, owner session information indicative of a session being mainly used, and caching data information.

11. A congestion control and avoidance method as set forth in claim 10, wherein said control type or cache entry type is any of the regular caching, priority caching, access limitation and access monitoring.

12. A congestion control and avoidance method as set forth in claim 1, wherein said regular caching or priority caching operation includes:

a step of determining whether a cache hit or cache mishit;

a step of determining whether or not a cache is within an expiration date;

a step of, when the cache is within the expiration date, obtaining the cache and forwarding the cache to the client terminal; and

a step of, when the cache is not within the expiration date, transmitting the request from the client terminal to the server device, and further performing regular caching or priority caching operation.

13. A congestion control and avoidance method as set forth in claim 12, further including a step of, when a cache mishit is found, performing caching preprocessing operation including any one or a plurality of creation of a regular or priority URI entry, creation of the regular or priority cache entry, registration to the URI hash and setting of an owner in the cache entry;

and

a step of transmitting the request from the client terminal to the server device, transmitting a response received from the server device to the client terminal, and further performing the regular caching operation.

14. A congestion control and avoidance method as set forth in claim 12, further including an access aggregation step of, when said cache is hit and when a plurality of requests for the same contents are over-lapped before the response is returned from the server device, relaying only the first request to the server device, putting the remaining requests once in a processing wait state, and resuming the processing after a response to the first request is returned.

15. A congestion control and avoidance method as set forth in claim 1, wherein, in a garbage collecting operation of, when a usable area of the cache become null or small, erasing a cache area having a low access frequency for its reuse, treating the priority cache entry as a non-target and also treating a data area being used for the priority caching as a non-target.

16. A congestion control and avoidance method as set forth in claim 1, wherein said access limitation operation include:

a step of acquiring a limitation message relating to a requested contents;

a step of creating the contents based on the limitation message; and

a step of forwarding the contents to the client terminal.

17. A congestion control and avoidance method as set forth in claim 1, wherein said access monitoring operation include:

a restriction determination step of, when restriction is executed, acquiring a restriction message, creating contents based on the restriction message and forwarding the contents to the client terminal; and

a step of, when no restriction is executed, transmitting a request to the server device and forwarding a response received from the server device to the client terminal.

18. A congestion control and avoidance method as set forth in claim 17, further including an access monitoring pre-processing operation of creating a URI entry if not created and registering the URI entry in the URI hash and/or incrementing an access count in the URI entry by 1.

19. A congestion control and avoidance method as set forth in claim 17, wherein said restriction determination step includes:

a step of referring to {circle over (1)} an access counter of the URI entry, {circle over (2)} a restriction execution flag of the URI entry, {circle over (3)} the number of restriction start connections set for the device, and {circle over (4)} the number of restriction end connections set for the device;

a step of executing the restriction if {circle over (1)}>

{circle over (3)} when the restriction execution flag of {circle over (2)} is not set, and executing no restriction otherwise;

a step of executing the restriction if {circle over (1)}>

{circle over (3)} when the restriction execution flag of {circle over (2)} is set, and executing no restriction otherwise.

20. A congestion control and avoidance method as set forth in claim 17, further including an access monitoring post-processing operation of decrementing an access count in the URI entry by 1, and when the access count is 0, deleting the access count from the URI hash to delete the URI entry.

21. A congestion control and avoidance method as set forth in claim 1, wherein said non-control operation includes:

a step of transmitting a request to the server device;

a step of receiving a response from the server device; and

a step of forwarding the response to the client terminal.

2. A congestion control and avoidance method in a communication relay device provided between a client terminal and a server device for transmitting, according to a request from the client terminal, contents of the request already stored at the time of a cache hit and for receiving the request contents from the server device and transmitting the request contents to the client terminal at the time of a cache mishit or when the request utilizes no cache, said method comprising:

a method check step of determining whether the request contents is cacheable or uncacheable on the basis of the request inputted from the client terminal;

a second URI check step of, when it is determined that the request contents is uncacheable in said method check step, checking a URI included in the request from the client terminal;

a second URI hash search step of searching a URI hash to determine any of access limitation and access monitoring operation;

a step of executing any of the access limitation and access monitoring operation according to determination in said second URI hash search step.

3. A congestion control and avoidance method in a communication relay device provided between a client terminal and a server device for transmitting, according to a request from the client terminal, contents of the request already stored at the time of a cache hit and for receiving the request contents from the server device and transmitting the request contents to the client terminal at the time of a cache mishit or when the request utilizes no cache, said method comprising:

a method check step of determining whether the request contents is cacheable or uncacheable on the basis of the request inputted from the client terminal;

a first URI check step of, when it is determined that the request contents is cacheable in said method check step, checking a URI included in the request from the client terminal to determine whether the request contents is cacheable or uncacheable;

a first URI hash search step of, when it is determined that the request contents is cacheable based on determination of said first URI check step, searching a URI hash to determine to execute any of regular caching and priority caching operation;

a second URI check step of, when it is determined that the request contents is uncacheable in said method check step, checking a URI hash to determine to execute any of access limitation and access monitoring operation;

a second URI hash search step of, when it is determined that the request contents is uncacheable based on determination of said first URI check step or is moved through said second URI check step, searching a URI hash to determine any of access limitation and access monitoring operation; and

a step of executing any of the regular caching, priority caching, access limitation and access monitoring operation according to determination in said first or second URI hash search step.