Distributed health check for global server load balancing
First Claim
1. A system comprising:
- a first network device to site switch, adapted to collect health check information indicative of access conditions to components for which the first network device performs switching, wherein the collection of health check information occurs independently of a request; and
a metric agent, at the first network device, adapted to communicate the collected health check information to a second network device to load balance, the communication occurring a plurality of times over a persistent connection between the first network device and the second network device, wherein the persistent connection comprises a single TCP connection initiated by the second network device; and
wherein the health check information comprises information indicative of which ports of one or more host servers coupled to the first network device are up or down and the health status of applications hosted on the one or more host servers.
9 Assignments
0 Petitions
Accused Products
Abstract
A global server load-balancing (GSLB) switch serves as a proxy to an authoritative DNS and communicates with numerous site switches that are coupled to host servers serving specific applications. The GSLB switch receives from site switches operational information regarding host servers within the site switches neighborhood. This operational information includes health check information that is remotely obtained in a distributed manner from remote metric agents at the site switches. When a client program requests a resolution of a host name, the GSLB switch, acting as a proxy of an authoritative DNS, returns one or more ordered IP addresses for the host name. The IP addresses are ordered using metrics, including the health check metric that evaluates these IP addresses based on the health check information communicated to the GSLB switch in a distributed manner by the distributed health check site switches. In one instance, the GSLB switch places the address that is deemed “best” at the top of the list.
295 Citations
20 Claims
-
1. A system comprising:
-
a first network device to site switch, adapted to collect health check information indicative of access conditions to components for which the first network device performs switching, wherein the collection of health check information occurs independently of a request; and a metric agent, at the first network device, adapted to communicate the collected health check information to a second network device to load balance, the communication occurring a plurality of times over a persistent connection between the first network device and the second network device, wherein the persistent connection comprises a single TCP connection initiated by the second network device; and wherein the health check information comprises information indicative of which ports of one or more host servers coupled to the first network device are up or down and the health status of applications hosted on the one or more host servers. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method of providing load balancing, the method comprising:
-
establishing a persistent connection between a first network device to load balance and at least one second network device to site switch, the at least one second network device remote from the first network device, wherein the persistent connection comprises a single TCP connection initiated by the first network device; receiving a plurality of times, at the first network device through the persistent connection, health check information collected at the at least one second network device and indicative of access conditions to respective host servers for which the at least one second network device performs switching, wherein the collection of health check information occurs independently of a request; arranging, at the first network device, network addresses in accordance with a set of performance metrics that include the health check information collected by and received from the at least one second network device; and disabling a flashback metric, from among the set of performance metrics, indicative of a time to respond to a health check request sent by the first network device. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. An article of manufacture, comprising:
-
a non-transitory storage medium having instructions stored thereon that are executable by a first network device to load balance, to; process health check information remotely collected by at least one of a plurality of second network devices to site switch, the health check information indicative of access conditions to respective host servers for which at least one of the second network devices performs switching, wherein the collection of health check information occurs independently of a request; and arrange network addresses in accordance with a set of performance metrics that include the health check information, wherein one of the performance metrics includes a flashback metric representing a speed to respond to a request from the first network device for health check information, the flashback metric being disabled based on the health check information remotely collected a plurality of times over a persistent connection by at least one of the second network devices, wherein the persistent connection comprises a single TCP connection initiated by the first network device. - View Dependent Claims (14, 15, 16)
-
-
17. An article of manufacture, comprising:
-
a non-transitory storage medium having instructions stored thereon that are executable by a first network device to load balance, to; establish a persistent connection between the first network device and at least one of a plurality of second network devices to site switch remote from the first network device, wherein the persistent connection comprises a single TCP connection initiated by the first network device, and; process health check information remotely collected by the at least one of the plurality of second network devices and indicative of access conditions to respective host servers for which the at least one of the plurality of second network devices perform switching, the health check information being received a plurality of times by the first network device through the persistent connection between the at least one of the plurality of second network devices, and the collection of health check information occurring independently of a request; and arrange network addresses in accordance with a set of performance metrics that include the health check information, wherein the health check information includes addresses associated with each of the plurality of second network devices and includes indications of which ports associated with each of the addresses are up or are down. - View Dependent Claims (18)
-
-
19. A system comprising:
-
a first network device to site switch, adapted to receive health check information, the health check information being indicative of access conditions to components for which the first network device collects health check information and for which the first network device performs switching, wherein the collection of health check information occurs independently of a request; and a metric agent, at the first network device, adapted to communicate the health check information to a second network device to load balance, the communication occurring a plurality of times using a persistent connection between the first network device and the second network device, wherein the persistent connection comprises a single TCP connection initiated by the second network device; and wherein the first network device is adapted to be communicatively coupled to the second network device and is adapted to convey the health check information a plurality of times on the persistent connection to the second network device as part of a keep-alive message, wherein the health check information comprises information indicative of which ports of one or more host servers coupled to the first network device are up or down and the health status of applications hosted on the one or more host servers.
-
-
20. A system to balance load, the system comprising:
-
a first network device to site switch, to collect health check information indicative of access conditions to components for which the first network device performs switching and the health status of applications hosted on one or more servers coupled to the first network device, wherein the collection of health check information occurs independently of a request; and a metric agent, at the first network device, to communicate the collected health check information to a second network device to load balance, the communication occurring a plurality of times using a persistent connection between the first network device and the second network device, wherein the persistent connection comprises a single TCP connection initiated by the second network device; and wherein a flashback metric representing a time to respond to a query for the health check information is disabled based on the collection of the health check information distributed from the second network device to the first network device.
-
Specification