System and method for surge protection and rate acceleration in a traffic director environment

Patent metadata

Field	Value
Publication number	US-9733983-B2
Application number	US-201213601428-A
Country	US
Kind code	B2
Filing date	Aug 31, 2012
Priority date	Sep 27, 2011
Publication date	Aug 15, 2017
Grant date	Aug 15, 2017

Abstract

Described herein are systems and methods for use with a load balancer or traffic director, and administration thereof. In accordance with an embodiment the system comprises a traffic director having one or more traffic director instances, which is configured to receive and communicate requests, from clients, to origin servers having one or more pools of servers. A traffic monitor, at the traffic director, monitors traffic, including the number of connections, between the traffic director instances and one or more of the resource servers within the origin servers. The traffic director can set a traffic rate which controls the traffic, including the number of connections, to provide surge protection, or rate acceleration/deceleration.

First claim

What is claimed is:

1. A system for use in a networked computing environment which includes a traffic director component, comprising:
a first physical node having a microprocessor and a computer memory; a traffic director operating on the first physical node, and comprising having at least one active traffic director server instance;
a collection of resource servers, wherein each resource server operates on at least one physical resource node, wherein the at least one physical resource node and the first physical node are separate nodes, and wherein the at least one physical resource node and first physical node are connected via the networked computing environment;
a configuration which defines an origin-server pool, wherein the defined origin-server pool includes a plurality of resource servers from the collection of resource servers, wherein each of the included plurality of resource servers host the same application or service, and wherein the configuration includes, for each of the included plurality of resource servers, a specified maximum number of network connections and a specified ramp-up time;
a traffic monitor at the traffic director, which monitors traffic, including a number of current network connections between the at least one active traffic director server instance and each resource server in the defined origin-server pool, wherein the current network connections serve client requests through, and received by, the at least one active traffic director server instance; and
wherein the traffic monitor is configured to determine the availability of a particular resource server of the plurality of resource servers, the particular resource server being previously unavailable to receive current network connections from the at least one traffic director server instance; and
wherein the at least one active traffic director server instance is configured to use information provided by the traffic monitor, including the number of current network connections between the at least one active traffic director and the particular resource server, to:
wait to open new current network connections with the particular resource server until after the passing of a specified delay time:
after the passing of the specified delay time, gradually increase the number of current network connections to the particular resource server over the ramp-up time that is specified for the particular resource server in the configuration; and
increase the number of current network connections to the particular resource server up to the maximum number of network connections that is specified for the particular resource server in the configuration, at which point client request traffic is temporarily direct away from the particular resource server and directed to a connection queue.

2. The system of claim 1 , wherein the traffic director provides an information message to a log file or to an administrator to inform of a traffic surge beyond the maximum number of network connections that is specified for the particular resource server.

3. The system of claim 1 , wherein two or more traffic director instances are provided within a failover group, wherein the at least one active traffic director instance is in the failover group, wherein requests received at the failover group are first routed to the at least one active traffic director instance within the failover group, and if the at least one active traffic director instance is not reachable, then to a backup instance within the failover group.

4. The system of claim 3 , wherein the two or more traffic director instances are grouped by a single internet protocol (IP) address.

5. The system of claim 1 , wherein the configuration includes, for each of the included plurality of resource servers, a specified ramp-down time.

6. The system of claim 5 , wherein, in response to an instruction to decelerate traffic to the particular resource server, the at least one traffic director server instance is configured to gradually decrease the number of connections to the particular resource server over the ramp-down time that is specified for the particular resource server in the configuration.

7. The system of claim 1 , wherein, after the passing of the specified delay time, the number of network connections to the particular resource server is gradually increased, over the ramp-up time that is specified for the particular server in the configuration, by a predefined value after a certain number of responses are received from the particular resource server.

8. The system of claim 1 , wherein, after the passing of the specified delay time, the number of network connections to the particular resource server is gradually increased by a fixed value per unit time over the ramp-up time that is specified for the particular server in the configuration.

9. A method for use in a networked computing environment which includes a traffic director component, comprising the steps of: providing a traffic director having at least one active traffic director server instance that operates on a microprocessor and a computer memory of a first physical node;
providing a collection of resource servers, wherein each resource server operates on at least one physical resource node, wherein the at least one physical resource node and the first physical node are separate nodes, and wherein the at least one physical resource node and first physical node are connected via the networked computing environment;
providing a configuration which defines an origin-server pool, wherein the defined origin-server pool includes a plurality of resource servers from the collection of resource servers, wherein each of the included plurality of resource servers host the same application or service, and wherein the configuration includes, for each of the included plurality of resource servers, a specified maximum number of network connections and a specified ramp-up time;
providing a traffic monitor at the traffic director, which monitors traffic, including a number of current network connections between the at least one active traffic director server instance and each resource server in the defined origin-server pool, wherein the current network connections serve client requests through, and received by, the at least one active traffic director server instance;
determining, by the traffic monitor, the availability of a particular resource server of the plurality of resource servers, the particular resource server being previously unavailable to receive current network connections from the at least one traffic director server instance;
using, by the at least one active traffic director server instance, information provided by the traffic monitor, including the number of current network connections between the at least one active traffic director and the particular resource server, to perform the steps of:
waiting to open new current network connections with the particular resource server until after the passing of a specified delay time;

after the passing of the specified delay time, gradually increasing the number of current network connections to the particular resource server over the ramp-up time that is specified for the particular resource server in the configuration; and
increasing the number of current network connections to the particular resource server up to the maximum number of network connections that is specified for the particular resource server in the configuration, at which point client request traffic is temporarily direct away from the particular resource server and directed to a connection queue.

10. The method of claim 9 , further comprising the steps of:
providing an informational message to a log file or to an admini

Assignees

• Kukreja Basant
• Xu Zhong
• Leftik Adam
• Srinivasan Arvind
• Oracle Int Corp

Inventors

• Kukreja Basant
• Xu Zhong
• Leftik Adam
• Srinivasan Arvind

Classifications

• G06F40/274

  Converting codes to words; Guess-ahead of partial word inputs · CPC title

• G06F9/451

  Execution arrangements for user interfaces · CPC title

• H04L67/1034

  Reaction to server failures by a load balancer · CPC title

• G06F9/45512

  Command shells · CPC title

• H04L63/0853

  using an additional device, e.g. smartcard, SIM or a different communication terminal (cryptographic mechanisms or cryptographic arrangements for entity authentication involving additional secure or trusted devices H04L9/3234) · CPC title