US 7,584,301 B1Grant
Host-level policies for global server load balancing
Issue Date:2009-09-01
•31 Claims
•6 Drawing Sheets
Abstract
In a network, a user can configure host-level policies usable for load balancing traffic to servers of a domain. A global server load balancing (GSLB) switch provides load balancing to the servers, and is configured with the GSLB host-level policies. Users can define a host-level policy (alternatively or additionally to a globally applied GSLB policy) and apply the host-level policy to hosts in domains configured on the GSLB switch. Thus, the user can enable different policies for different hosts. This allows the user to have the flexibility to control metrics used for selection of a best address for querying clients, as well as the metric order and additional parameters used in the GSLB process, at the host level.
Metadata
Assignee
- Foundry Networks, Inc.
Inventor
- Prajakta S. Joshi
Application Information
Application Number:US 10/839,919
Filing Date:2004-05-06
Priority Date:2004-05-06
Art Unit:2455
Classifications
IPC:
G06F15/173
Patent Drawings (6 sheets)
Description
Technical Field
[0001] This disclosure relates generally to load balancing among servers. More particularly but not exclusively, the present disclosure relates to techniques to achieve load balancing by, in response to resolving a DNS query by a client, using host-level policies to provide an address of a server that is expected to serve the client with a high performance in a given application.
Background Information
[0002] Under the Transmission Control Protocol/Internet Protocol (TCP/IP), when a client provides a symbolic name (a Uniform Resource Locator or URL) to request access to an application program or another type of resource, the host name portion of the URL needs to be resolved into an IP address of a server for that application program or resource. For example, the URL (e.g., http://www.foundrynet.com/index.htm) includes a host name portion www.foundrynet.com that needs to be resolved into an IP address. The client first provides the host name portion to a local name resolver, which then queries a local Domain Name System (DNS) server to obtain a corresponding IP address. If a corresponding IP address is not locally cached at the time of the query, or if the time-to-live (TTL) of a corresponding IP address cached locally has expired, the DNS server then acts as a resolver and dispatches a recursive query to another DNS server. This process is repeated until an authoritative DNS server for the domain (e.g., foundrynet.com, in this example) is reached. The authoritative DNS server returns one or more IP addresses, each corresponding to an address at which a server hosting the application (“host server”) under the host name can be reached. These IP addresses are propagated back via the local DNS server to the original resolver. The application at the client then uses one of the IP addresses to establish a TCP connection with the corresponding host server. Each DNS server caches the list of IP addresses received from the authoritative DNS server for responding to future queries regarding the same host name, until the TTL of the IP addresses expires.
[0003] To provide some load sharing among the host servers, global server load balancing (GSLB) switches are sometimes used as proxies for authoritative DNS servers, together with one or more site switches each associated with one or more host servers. Each site switch provides the GSLB switch with current site-specific information related to the host servers associated with the site switches. When the DNS server sends the list of IP addresses in response to a client query, the GSLB switch evaluates this list by applying a GSLB policy in conjunction with using the information provided by the site switches. The GSLB policy contains, among other possible specifications, the metrics that are to be applied to the list of IP addresses and the order in which they are to be applied to select the best IP address. After the GSLB switch evaluates the addresses returned by the DNS server using the metrics in the policy, the GSLB switch sends the ordered address list, having the optimum address for access listed at the top, to the client. An example of a GSLB system and description of associated metrics are disclosed in U.S. application Ser. No. 10/376,903, entitled “GLOBAL SERVER LOAD BALANCING,” filed Feb. 28, 2003, assigned to the same assignee as the present application, and which is incorporated herein by reference in its entirety.
[0004] A given GSLB policy may specify which of the metrics are enabled and to be used for selection, parameters for the metrics (such as tolerance, limits, etc.), and the order in which these metrics should be used to evaluate the IP addresses in the DNS reply. Also, a GSLB policy can specify other configuration information, such as returning best IP address only instead of the entire IP list and so on.
[0005] Currently, the user (such as a system administrator) can only define such a GSLB policy (or other load balancing policies) globally. This global GSLB policy is applicable to all the domains for which the GSLB switch is providing GSLB. For instance, consider the example where the GSLB switch is providing GSLB for www.foo.com and www.test.com. (Also note in this example that for the domain www.foo.com, “www” is referred to as the “host” and “foo.com” is referred to as the “zone”). The user may define a GSLB policy with the following example metrics and metric-order:
-
- [0006] Health check
- [0007] Geographic
- [0008] Least-response
This global policy would apply to both www.foo.com and www.test.com.
[0009] If the user wants a round-trip time (RTT) metric to be used for selection of the best IP address for the domain www.foo.com but not for the domain www.test.com, then there is currently no provision for this capability. The reason is that if the user enabled the RTT metric, then since the policy is global and applies to all domains, this metric would get enabled for both of the above domains.
Brief Summary of the Invention
[0010] One aspect provides a method that defines a host-level policy. The method specifies at least one metric and associated parameters, if applicable, to be used by the defined host-level policy. The host-level policy is applied to a host, and traffic to network addresses associated with the host are load balanced based on at least one metric and associated parameters of the host-level policy applied to that host.
Brief Description of the Drawings
[0011] Non-limiting and non-exhaustive embodiments are described with reference to the following figures, wherein like reference numerals refer to like parts throughout the various views unless otherwise specified.
[0012] FIG. 1 illustrates a GSLB system in which an embodiment may be implemented.
[0013] FIG. 2 illustrates a GSLB switch of FIG. 1 according to an embodiment.
[0014] FIG. 3 is a flowchart of an embodiment of a technique to configure/modify a host-level policy on the GSLB switch of FIG. 2 .
[0015] FIG. 4 is a flowchart depicting application of a host-level policy to a host according to one embodiment.
[0016] FIG. 5 is a flowchart 500 depicting use of a host-level policy for selection of addresses during the GSLB process.
Detailed Description
[0017] Embodiments of techniques to provide host-level policies for GSLB are described herein. In the following description, numerous specific details are given to provide a thorough understanding of embodiments. One skilled in the relevant art will recognize, however, that the invention can be practiced without one or more of the specific details, or with other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects.
[0018] Reference throughout this specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0019] As an overview, one embodiment is usable for a network device that provides load balancing capabilities. An example is a GSLB switch that uses a global GSLB policy to provide GSLB for configured domains. Such a GSLB switch is provided with a GSLB host-level policy. Users can define a host-level policy (alternatively or additionally to the global GSLB policy) and apply the host-level policy to hosts in GSLB domains. In effect, the user can enable different policies for different hosts. This allows the user to control the GSLB metrics used for selection, as well as the metric order and additional selection parameters (such as tolerances, various DNS parameters, etc.), at the host level.
[0020] If users need this level of granularity for each host, then they can configure various host-level policies and apply them, as desired, to the each of these hosts. Users can also use the global GSLB policy for some hosts and host-level GSLB policy for other hosts. Alternatively, users can continue to use the global GSLB policy for all hosts, or use the host-level policies for all hosts (eliminating the use of the global GSLB policy).
[0021] GSLB host-level policies provide enormous flexibility for various GSLB implementations. Users can define different host-level policies to reflect the selection criteria they wish to use for different GSLB domains and provide improved and more tailored GSLB selection for each of those GSLB domains.
[0022] The GSLB host-level policy implementation of one embodiment comprises of:
-
- [0023] Defining a GSLB host-level policy;
- [0024] Configuring parameters for the host-level policy; and
- [0025] Applying the host-level policy to GSLB host(s).
[0026] The parameters for a GSLB host-level policy can be changed at any time after the policy has been defined, and any time before or after the policy has been applied to GSLB hosts. Any type of suitable software command or language can be used to program the GSLB switch with the host-level policy. Command line interface (CLI) commands, for instance, may be used to configure the host-level policy.
[0027] The following provides an illustration of the use of host-level policies for an implementation where the GSLB switch provides load balancing for the domains www.foo.com and www.test.com. First, a user defines a host-level GSLB policy (e.g., metric selection and order of application) called “H1” as follows:
-
- [0028] Health check
- [0029] Geographic
- [0030] Round-trip time
- [0031] Least response.
[0032] The user then defines another host-level GSLB policy called “H2” as follows:
-
- [0033] Health check
- [0034] Geographic
- [0035] Least response.
[0036] The user defines the host “www” for the zone foo.com and associates the GSLB host-level policy H1 with it. The user then defines the host “www” for the zone test.com and associates the GSLB host-level policy H2 with it. Thus, when the GSLB switch selects the best IP address for the domain www.foo.com, the GSLB host-level policy H1 is used for that selection. If best IP address selection is to be made for www.test.com, then the GSLB host-level policy H2 is used for that selection. If the user does not associate a host-level policy for a host, then the global GSLB policy will be associated with that host by default in an embodiment.
[0037] FIG. 1 illustrates one example global server load balancing system with which an embodiment may be implemented. As shown in FIG. 1 , a GSLB switch 12 (i.e., a load balancing switch) is connected to an Internet 14 and acts as a proxy to an authoritative Domain Name System (DNS) server 16 for a domain “foundrynet.com” (for example). That is, while the authoritative DNS server 16 provides the actual DNS service, the IP address known to the rest of the Internet 14 for the authoritative DNS server 16 of the domain “foundrynet.com” is a virtual IP (VIP) address configured on the GSLB switch 12. Of course, authoritative DNS server 16 can also act simultaneously as an authoritative DNS for other domains. The GSLB switch 12 communicates, via the Internet 14, with site switches 18A and 18B at site 20, site switches 22A and 22B at site 24, and any other similarly configured site switches. The site switches 18A, 18B, 22A and 22B are shown, for example, connected to routers 19 and 21 respectively and to servers 26A, . . . ,26I, . . . 26N. Some or all of the servers 26A, . . . , 26I, . . . , 26N may host application server programs (e.g., http and ftp and others). These host servers are reached through the site switches 18A, 18B, 22A and 22B using one or more virtual IP addresses configured at the site switches, which act as proxies to the host servers.
[0038] A suitable switch for implementing either the GSLB switch 12 or any of the site switches 18A, 18B, 22A and 22B is the ServerIron® (SI) product available from Foundry Networks, Inc. of San Jose, Calif. Throughout this description and in the figures, the GSLB switch will be described as the network device that can provide and implement the various load balancing (e.g., host-level and/or global load balancing policies) of an embodiment. It is understood that this use of the GSLB or SI switch is merely for purposes of illustration and explanation. Any suitable non-SI switch or non-SI network device can be used to implement the various geographic features and functions described herein. A router is one example.
[0039] FIG. 1 also shows a client program 28 connected to the Internet 14, and that communicates with a local DNS server 30. When a browser on the client program 28 requests a web page, for example, using a Universal Resource Locator (URL), such as http://www.foundrynet.com/index.htm, a query is sent to the local DNS server 30 to resolve the symbolic host name www.foundrynet.com to an IP address of a host server. The client program 28 receives from the DNS server 30 a list of IP addresses corresponding to the resolved host name. This list of IP addresses is either retrieved from the local DNS server 30's cache, if the TTL of the responsive IP addresses in the cache has not expired, or obtained from the GSLB switch 12, as a result of a recursive query.
[0040] Unlike the prior art, however, this list of IP addresses is ordered by the GSLB switch 12 based on performance metrics. The GSLB switch 12 of one embodiment can use at least some of the following metrics to evaluate the server IP addresses in a DNS reply:
-
- [0041] The server's health (including Layer 4 and application health checks)
- [0042] The weighted IP value assigned to an IP address (i.e., an administratively configured traffic distribution method for the GSLB switch 12 based on weights for IP addresses)
- [0043] The weighted site value assigned to a site (i.e., an administratively configured traffic distribution method for the GSLB switch 12 based on weights for GSLB sites)
- [0044] The site switch's session capacity threshold
- [0045] The IP address with the highest number of active bindings (preference for the IP address with the highest number of active bindings)
- [0046] The round-trip time between the remote site switch and the DNS client's sub-net
- [0047] The geographic location of the server
- [0048] The connection load (e.g., the site switch's average number of new connections per second)
- [0049] The site switch's available session capacity
- [0050] The site switch's flashback speed (e.g., how quickly the GSLB switch 12 receives the health check results)
- [0051] The site switch's administrative preference (e.g.; a numeric preference value assigned to influence the GSLB policy by the user if other policy metrics are equal)
- [0052] The least response selection (i.e., the site switch that has been selected less often than others)
- [0053] Round robin selection (an alternative to the least response metric).
[0054] The above metrics and their parameters may be configured and used in either or both host-level or global GSLB policies, except as noted below for some specific embodiments. The specifics of the above-listed metrics are described in further detail in U.S. application Ser. No. 09/670,487, entitled “GLOBAL SERVER LOAD BALANCING,” filed Sep. 26, 2000; in U.S. application Ser. No. 10/206,580, entitled “GLOBAL SERVER LOAD BALANCING,” filed Jul. 25, 2002 (disclosing embodiments of a connection-load metric for GSLB); in U.S. application Ser. No. 10/305,823, entitled “DISTRIBUTED HEALTH CHECK FOR GLOBAL SERVER LOAD BALANCING,” filed Nov. 27, 2002 (disclosing embodiments for distributing health check tasks to peer metric agents); and in U.S. application Ser. No. 10/376,903, entitled “GLOBAL SERVER LOAD BALANCING,” filed Feb. 28, 2003 (disclosing embodiments of weighted site, weighted IP, and active bindings metrics).
[0055] Other applications that disclose GSLB features (including metrics) are U.S. application Ser. No. 09/670,487, entitled “GLOBAL SERVER LOAD BALANCING,” filed Sep. 26, 2000; U.S. application Ser. No. 10/211,822, entitled “STATISTICAL TRACKING FOR GLOBAL SERVER LOAD BALANCING,” filed Aug. 1, 2002; U.S. application Ser. No. 10/377,364, entitled “METHOD AND SYSTEM TO CLEAR COUNTERS USED FOR STATISTICAL TRACKING FOR GLOBAL SERVER LOAD BALANCING, filed Feb. 28, 2003; U.S. application Ser. No. 10/214,921, entitled “CANONICAL NAME (CNAME) HANDLING FOR GLOBAL SERVER LOAD BALANCING, filed Aug. 7, 2002; U.S. application Ser. No. 10/674,627, entitled “GLOBAL SERVER LOAD BALANCING SUPPORT FOR PRIVATE VIP ADDRESSES, filed Sep. 29, 2003; U.S. application Ser. No. 10/840,496, entitled “CONFIGURABLE GEOGRAPHIC PREFIXES FOR GLOBAL SERVER LOAD BALANCING,” filed May 6, 2004; and U.S. application Ser. No. 10/924,552, entitled “SMOOTHING ALGORITHM FOR ROUND TRIP TIME (RTT) MEASUREMENTS FOR GLOBAL SERVER LOAD BALANCING,” filed Aug. 23, 2004; all of which are assigned to the same assignee as the present application and incorporated herein by reference in their entireties. These are a few example applications where various GSLB performance metrics are described. For the sake of brevity, these various metrics and the manner in which they are used in a GSLB algorithm or policy (whether at the host level or at the global level) to identify best sites in a list of IP addresses are only summarized and not described in detail herein. Such additional details may be found in these co-pending applications and in the applications that they reference.
[0056] In the remainder of this detailed description, for the purpose of illustrating embodiments only and except where indicated, the list of IP addresses returned are assumed to be the virtual IP addresses configured on the proxy servers at switches 18A, 18B, 22A and 22B (sites 20 and 24). In one embodiment when the authoritative DNS server 16 resolves a host name in a query and returns one or more IP addresses, the GSLB switch 12 determines (using the performance metrics) which site switch would provide the best expected performance (e.g., response time) for the client program 28 and returns the IP address list with a virtual IP address configured at that site switch placed at the top. (Other forms of ranking or weighting the IP addresses in the list can also be possible.) The client program 28 can receive the ordered list of IP addresses, and typically selects the first IP address on the list to access the corresponding host server.
[0057] FIG. 2 is a block diagram showing the functional modules of an embodiment of the GSLB switch 12 and site switch 18A (for instance) relevant to the global server load balancing function, including functions and features associated with global and host-level policies. As shown in FIG. 2 , the GSLB switch 12 includes a GSLB switch controller 201, health check module 202, DNS proxy module 203, metric agent 204, routing metric collector 205, and metric collector 206. The GSLB switch controller 201 provides general control functions for the operation of the GSLB switch 12. The health check module 202 is responsible for querying, either periodically or on demand, host servers and relevant applications hosted on the host servers to determine the “health” (e.g., whether or not it is available) of each host server and each relevant application. The metric collector 206 communicates with metric agents in site-specific switches (e.g., FIG. 2 shows the metric collector 206 communicating with a remote metric agent 207 of a site server load balancing ServerIron® or “SLB SI”) to collect site-specific metrics (e.g., number of available sessions on a specific host server and/or connection-load data indicative of connections-per-second at that host server at the site 18A, or other metrics data).
[0058] The routing metric collector 205 collects routing information from routers (e.g., topological distances between nodes on the Internet). FIG. 2 shows, for example, a router 208 providing the routing metric collector 205 with routing metrics (e.g., topological distance between the load balancing switch and the router), using the Border Gateway Protocol (BGP). The DNS proxy module 203 (A) receives incoming DNS requests, (B) provides the host names to be resolved to the DNS server 16, (C) receives from the DNS server 16 a list of responsive IP addresses, (D) orders the IP addresses on the list received from the DNS server 16, using the metrics collected by the routing-metric collector 405 and the site specific collector 406, and values of any other relevant parameter, and (E) provides the ordered list of IP addresses to the requesting DNS server. Since the GSLB switch 12 can also act as a site switch, the GSLB switch 12 is provided with the metric agent 204 for collecting metrics for a metric collector.
[0059] In one embodiment, the GSLB switch controller 201 can be programmed with and/or can access data to be used for host-level policies (as well as default global policies) and their associated metrics, including at least one of weighted site, weighted IP, active bindings, geographic, RTT, or other metrics described in the co-pending applications identified above. In such an embodiment, the GSLB switch controller 201 can be communicatively coupled to a first storage unit 212 that contains one or more configured GSLB host-level policies. These host-level policies can in turn specify, for each host, the metrics to be used for selection of IP addresses, the order in which the metrics are to be applied, the parameters for the metrics (such as tolerance, limits, and the like), or other associated settings. The GSLB switch controller 201 can also be communicatively coupled to a second storage unit 210 that contains one or more global GSLB policies, some of which may be default policies in some embodiments.
[0060] In an embodiment, the first storage unit 212 and the second storage unit 210 can be in the form of databases having tables. It is appreciated, however, that either or both of these storage units can be embodied by any suitable data structure (including file systems, directory structures, variables, static or dynamic code, or any other suitable technique or structure that can accept and store policy settings and data). Additionally, the first and second storage units need not necessarily be separate, and may be integrated in whole or in part into a single storage unit, for instance.
[0061] FIG. 3 is a flowchart 300 of an embodiment of a technique to configure/modify a host-level policy on the GSLB switch 12 (e.g., on the GSLB controller 201). In one embodiment, at least some of the operations depicted in the flowchart 300 (as well as in the other flowcharts shown herein) can be embodied in software, code, or other machine-readable instruction stored on a machine-readable medium, and which are executable by one or more processors. For instance, the software may be stored in the storage units 210 and/or 212 and executable by the GSLB controller 201. It is appreciated that the various operations need not necessarily occur in the exact order depicted, and that certain operations can be added, removed, modified, or combined.
[0062] Beginning at a block 302, the user specifies a host-level policy name, such as “P1” for purposes of illustration. At a block 304, the GSLB switch 12 (or more specifically, the GSLB controller 201) checks if the policy P1 already exists in the host-policy database (i.e., the storage unit 212). If the policy P1 is determined to not exist therein at a block 306, then the GSLB switch 12 creates new policy “P1” in the host-policy database in the storage unit 212 at a block 308.
[0063] At a block 310, the user specifies the metrics, enables/disables metrics, specifies related parameters, specifies the metric order, and adds other configuration settings for the policy P1. In an embodiment, most of the parameters that can be configured for the global GSLB policy (stored in the storage unit 210) can also be configured for the host-level GSLB policy. For any parameter that can be defined in the global GSLB policy but not under the host-level policy, the GSLB switch 12 of an embodiment will use the parameter from the global GSLB policy for the host-level policy.
[0064] For the sake of brevity, not all of the host-level metric configuration and/or parameter configuration that can be performed at the block 310 will be described herein, since such configuration can be based at least in part on the global GSLB policy configuration. However, a description of configuration considerations for some metric parameters and other host-level policy configuration are nevertheless provided herein, so as to provide a thorough understanding of various embodiments:
-
- [0065] The capacity threshold parameter (for the session capacity metric) of one embodiment can only be configured for the global GSLB policy and the threshold value defined for the global GSLB policy will be used by the host-level policy
- [0066] When the connection-load metric is enabled for a host-level policy, the actual value of the connection-load limit and other connection load parameters will be obtained from the global GSLB policy. These parameters include: site connection limit, sampling intervals and sample rate, and interval weights. According to one example embodiment, if the connection-load limit is not configured in the host-level policy but is configured in the global GSLB policy, and this host-level policy is applied to a host, then the connection-load metric will not be used during GSLB selection process for that host/zone. Therefore, the connection-load limit configuration for the host-level policy serves as way to enable or disable connection-load metric for the host when it is enabled in the global GSLB policy.
- [0067] When both the health check metric and the flashback metric are disabled for a host-level policy, an embodiment of the GSLB switch 12 will not perform any Layer 4 TCP or Layer 7 application health checks for the hosts/zones that this policy is applied to. Commands may be entered to change the tolerances for the response times of TCP and application health checks, when used as a selection metric. The user can change one or both tolerance values, and the tolerance values do not need to be the same. For each tolerance, the user can specify from 0-100, for instance. An example default setting for each tolerance value is 10.
- [0068] The order in which the various metrics identified herein are to be applied can be specified or modified at the block 310, such as by specifying the metrics in a list. In an embodiment, there are no parameters for the least response selection or round robin selection metrics, since these metrics are tie-breakers. Only one of them is enabled at a time in such an embodiment, and the one that is enabled will be the last metric in the host-level policy. A CLI command may be used to reset the order of GSLB policy metrics (or to re-enable all disabled metrics).
- [0069] The round robin selection metric is an alternative to the least response selection metric as the final tie breaker. When the user enables round robin selection, the GSLB switch 12 automatically disables the least response selection metric, and instead uses the round-robin algorithm for GSLB selection.
- [0070] The user can enable or disable the RTT metric and configure the RTT tolerance for the host-level policy at the block 310. Other parameters, in particular, RTT cache interval, RTT cache prefix, and RTT explore percentage can be configured only for the global GSLB policy but not for the host-level policy in one embodiment. If the host-level policy is applied to a host/zone, then the GSLB switch 12 will use the values defined in the global GSLB policy for RTT parameters that cannot be configured under the host-level policy. These parameters are: RTT cache interval, RTT cache prefix length, and RTT explore percentage.
- [0071] According to one embodiment, certain GSLB parameters are not configurable at the host level. For instance, the following configurations/commands are not supported at the host policy level: configuring a geographic prefix; configuring a static prefix; configuring a health-status reporting interval; and configuring a GSLB protocol update interval. These commands are configured under the global GSLB policy, and they will be applicable to all hosts irrespective of whether the global GSLB policy or a host-level policy is being used for the hosts.
[0072] Certain DNS parameters may also be configured at the block 310 for a host-level policy. For example:
-
- [0073] The GSLB switch 12 can be configured to remove IP addresses from DNS replies, for the GSLB domains that this host-level policy is applied to, when those IP addresses fail a health check.
- [0074] The GSLB switch 12 can be configured to remove all addresses except the best address, from the DNS replies for the domain names that this host-level policy is applied to.
- [0075] In one embodiment, GSLB switch 12 uses all other DNS parameters that can be configured under the global GSLB policy but not the host-level policy, from the global GSLB policy for the hosts this policy has been applied to. These parameters include:
- [0076] cache-proxy: Enabling/disabling directly generating DNS responses with the best choice among IP addresses learned from the DNS server 16
- [0077] check-interval: Frequency of verifying current DNS records with DNS servers
- [0078] cname-detect: Enabling/disabling auto detection of CNAME aliases configured for GSLB
- [0079] override: Replace IP addresses in DNS responses with the best choice among the configured IP addresses
- [0080] transparent-intercept: Intercept DNS queries and generate responses with the best choice among configured IP addresses
- [0081] ttl: TTL value in the DNS responses' resource records.
[0082] The various parameter settings and other information described above may be configured into the GSLB switch 12 using CLI commands or other suitable user-entry technique. At a block 312, the GSLB switch 12 stores the host-level policy P1 and all the above information in the GSLB host-policy database at the storage unit 212.
[0083] Back at the block 306, if the GSLB switch 12 determines that the host-level policy P1 already does exist in the host-policy database, then the user may change the metrics, enable/disable metrics, specify/change related parameters, specify/change metric order, or add/change other configuration settings for the policy P1 at a block 314. Then, the GSLB switch 12 updates the above information for the policy P1 in the host-policy database at a block 316.
[0084] FIG. 4 is a flowchart 400 depicting application of a host-level policy to a host according to one embodiment. At a block 402, the user specifies (such as via CLI commands) the host (e.g., referred to herein as the host “H1” for illustrative purposes) for which the user wishes to apply a host-level GSLB policy. At a block 404, the GSLB controller 201 determines whether the host H1 has been defined on the GSLB switch 12. If the host H1 has not been defined, then a message or other notification is printed (or otherwise presented) to the user at a block 406, to request the user to define the host H1.
[0085] If, however, the GSLB controller 201 determines at the block 404 that the host H1 has been defined on the GSLB switch 12, then the user can specify at a block 408 the host-level policy (e.g., the policy P1) that the user wishes to associate with this host H1. At a block 410, the GSLB switch 12 checks the host-policy database to determine if the policy P1 has been defined by the user, such as depicted in FIG. 3 . If the policy P1 is found at a block 412 to not have been defined, then a message or other notification is printed (or otherwise presented to the user) at a block 414, requesting the user to define the host-level policy P1.
[0086] If, at the block 412, the policy P1 is determined to have been defined, then any previous policy associated with the host H1 is disassociated from that host at a block 416. The new policy P1 is associated with the host H1 at a block 418.
[0087] FIG. 5 is a flowchart 500 depicting use of a host-level policy for selection of addresses during the GSLB process. First at a block 502, the client program 28 queries for a domain for which GSLB switch 12 is providing GSLB. At a block 504, the authoritative DNS server 16 sends back a reply containing the IP addresses for the requested domain.
[0088] At a block 506, the GSLB switch 12 receives this reply, and needs to select the best IP address among the IP addresses listed in the reply. The GSLB switch 12 extracts the host/domain for the above query (e.g., the host H1). The GSLB switch 12 checks if there is a host-level GSLB policy associated with the host H1 at a block 508.
[0089] At a block 510, the GSLB switch 12 determines whether there is any host-level policy associated with the host H1. If it is determined that there is an associated host-level policy (e.g., the policy P1), then the GSLB switch 12 retrieves the information for the policy P1 from the GSLB host-policy database at a block 512. The GSLB switch 12 uses this host-level policy P1 for the selection of the best IP address for the client program 28 at a block 514.
[0090] Back at the block 510, if it is determined that there is no host-level policy associated with the host H1, then the GSLB switch 12 uses the global GSLB policy for the host H1 at a block 516. This global policy information is retrieved, and then used for the selection of the best IP address at the block 514.
[0091] A final illustration ties together the above-described concepts. Consider an example where the GSLB switch 12 is providing GSLB for the following three domains:
[0092] www.gslb1.com (IP addresses: 1.1.1.101 (Active), 1.1.1.23 (Down), 1.1.1.54 (Down)};
[0093] ftp.gslb1.com (IP addresses: 1.1.1.78 (Active), 1.1.1.76 (Down)}; and
[0094] ftp.foo.com (IP addresses: 1.1.1.101 (Active), 1.1.1.23 (Active), 1.1.1.63 (Down)}.
[0095] The user defines (and stores in the GSLB host-policy database) a host-level policy named “test” as follows:
-
- [0096] Metric order: health check, least response
- [0097] Use DNS best-only (i.e., return only the best IP address to the client, and discard the other IP addresses in the response).
[0098] The user now configures the following global GSLB policy as follows:
-
- [0099] Metric order: health check, least response
[0100] The user then applies the host-level policy “test” to the host “www” for the zone gslb1.com and to the host “ftp” for the zone foo.com. Since the user does not associate the domain ftp.gslb1.com with any host-level policy, this domain will be associated with the global GSLB policy by default according to an embodiment.
[0101] If the client program 28 queries for the domain www.gslb1.com, then the GSLB switch 12 evaluates the IP addresses in the response from the DNS server 16. In particular, an embodiment of the GSLB switch 12 extracts the host (“www”) and domain (“gslb.com”) and retrieves the policy associated with it (e.g., the host-level policy “test” in this example). The GSLB switch then evaluates the IP addresses 1.1.1.101, 1.1.1.23, and 1.1.1.54 using the metrics at a metric order specified in the host-policy “test” (e.g., health check, least response). Since 1.1.1.101 is the only IP address that passes the health check, this address is selected as the best IP address. Furthermore, the GSLB switch 12 returns only this address and discards the other two addresses, since DNS best-only is enabled in the host-level policy “test.” If the client program 28 queries for the domain ftp.gslb1.com, since the global policy is in effect for this host, the GSLB switch 12 will return all the IP addresses for this domain with the best IP address on the top (e.g., the GSLB switch 12 returns the IP addresses 1.1.1.78, 1.1.1.76).
[0102] All of the above U.S. patents, U.S. patent application publications, U.S. patent applications, foreign patents, foreign patent applications and non-patent publications referred to in this specification and/or listed in the Application Data Sheet, are incorporated herein by reference, in their entirety.
[0103] The above description of illustrated embodiments, including what is described in the Abstract, is not intended to be exhaustive or to limit the invention to the precise forms disclosed. While specific embodiments and examples are described herein for illustrative purposes, various equivalent modifications are possible within the scope of the invention and can be made without deviating from the spirit and scope of the invention.
[0104] For example, various embodiments have been described above in terms of IP addresses. It is appreciated that other embodiments for using GSLB host-level policies can be implemented for systems that use an addressing scheme that is not necessarily IP-address based.
[0105] These and other modifications can be made to the invention in light of the above detailed description. The terms used in the following claims should not be construed to limit the invention to the specific embodiments disclosed in the specification and the claims. Rather, the scope of the invention is to be determined entirely by the following claims, which are to be construed in accordance with established doctrines of claim interpretation.
Claims
Post-issuance certificates present
The text shown below may not reflect later post-issuance changes.
What is claimed is:
1. A method, comprising:
storing, in a load balance switch, a first load balancing policy associated with a first domain and a second load balancing policy associated with a second domain different from the first domain, wherein said first load balancing policy specifies an order in which a first plurality of metrics of said first load balancing policy are to be applied; and
load balancing traffic, by said load balance switch, to network addresses associated with the first and second domains, using corresponding said first and second load balancing policies that are respectively associated to the first and second domains,
wherein said metrics of said first load balancing policy each include at least one parameter, wherein said at least one parameter includes at least one of a tolerance, limit, threshold, DNS parameter, preference, and alternative tie-breaker metric use.
2. The method of claim 1, further comprising using, by said load balance switch, a global load balancing policy to load balance traffic to at least a third domain for which said load balance switch is configured to perform load balancing.
3. The method of claim 2 wherein if a particular metric of the first load balancing policy does not have said at least one parameter specified, a parameter related to said global load balancing policy is associated with that particular metric by said load balance switch.
4. The method of claim 2 wherein said global load balancing policy is a same load balancing policy that is associated with a plurality of different domains, other than said first and second domains, for which said load balance switch is configured to perform load balancing.
5. The method of claim 1 wherein said second load balancing policy specifies an order in which a second plurality of metrics of said second load balancing policy are to be applied.
6. The method of claim 1 wherein said load balancing traffic to the network addresses associated with the first and second domains includes re-ordering, by said load balance switch, a list of addresses that are specified in a response to a query for the addresses.
7. The method of claim 1, further comprising updating, in said load balance switch, one or more metrics and associated parameters for each of the first and second load balancing policies.
8. The method of claim 1, further comprising:
determining, by said load balance switch, whether the first load balancing policy has been defined;
if the first load balancing policy is determined to have been defined, disassociating by said load balance switch a previous load balancing policy from the first domain; and
associating, by said load balance switch, the defined first load balancing policy to the first domain.
9. The method of claim 1 wherein said load balancing traffic to network addresses associated with the first domain includes:
receiving, by said load balance switch, a reply having a list of said network addresses associated with said first domain;
determining, by said load balance switch, whether said first load balance policy has been associated with the first domain; and
obtaining, by said load balance switch, metric information pertaining said first load balancing policy, and using by said load balance switch this obtained metric information to select a preferred network address from said list to receive traffic directed to the first domain,
wherein the method further comprises if said first load balancing policy associated with the first domain cannot be determined by said load balance switch:
obtaining, by said load balance switch, metric information pertaining to a global load balancing policy, and using by said load balance switch this obtained metric information pertaining to said global load balancing policy to select the preferred network address from said list.
10. The method of claim 1 wherein said first domain is identified by at least one of a www, ftp, and other host designation associated with one or more zones.
11. A method, comprising:
associating, by a load balance switch, a first load balancing policy to a first domain associated with a first site switch, wherein said first load balancing policy specifies an order in which a first plurality of metrics of said first load balancing policy are to be applied;
associating, by said load balance switch, a second load balancing policy to a second domain associated with a second site switch and different from said first domain; and
using said first and second load balancing policies at said load balance switch to respectively rank addresses associated with said first and second domains,
wherein said metrics of said first load balancing policy each include at least one parameter, wherein said at least one parameter includes at least one of a tolerance, limit, threshold, DNS parameter, preference, and alternative tie-breaker metric use.
12. The method of claim 11, wherein said second load balancing policy specifies an order in which a second plurality of metrics of said second load balancing policy are to be applied.
13. The method of claim 11, further comprising if a particular load balancing policy is not associated to a particular domain, using by said load balance switch a global load balancing policy to rank addresses associated with said particular domain.
14. The method of claim 11, further comprising if some parameters to be used by the metrics of said first load balancing policy are not specified, using by said load balance switch, parameters from a global load balancing policy for these metrics.
15. An article of manufacture, comprising:
a storage medium having instructions stored thereon that are executable by a processor of a load balance switch to enable load balancing, by:
associating, by said load balance switch, a first load balancing policy to a first domain associated with a first site switch, wherein said first load balancing policy specifies an order in which a first plurality of metrics of said first load balancing policy are to be applied;
associating, by said load balance switch, a second load balancing policy to a second domain associated with a second site switch and different from said first domain; and
using said first and second load balancing policies by the load balance switch to respectively rank addresses associated with said first and second domains,
wherein said metrics of said first load balancing policy each include at least one parameter, wherein said at least one parameter includes at least one of a tolerance, limit, threshold, DNS parameter, preference, and alternative tie-breaker metric use.
16. The article of manufacture of claim 15 wherein the storage medium further includes instructions stored thereon that are executable by said processor to:
use, by said load balance switch, a global load balancing policy, associated with a plurality of domains different from said first and second domains, to rank addresses associated with at least a third domain.
17. The article of manufacture of claim 15 wherein if some parameters of said metrics of said first load balancing policy are not specified, the storage medium further includes instructions stored thereon that are executable by said processor to:
use, by said load balance switch, parameters from a global load balancing policy for these metrics of said first load balancing policy.
18. The article of manufacture of claim 15 wherein the second load balancing policy specifies an order in which a second plurality of metrics of the second load balancing policy are to be applied.
19. A system, comprising:
a means in a load balance switch for storing a plurality of load balancing polices that are respectively associated to a plurality of domains, wherein each of said load balancing policies specify an order of application of a plurality of metrics of each respective load balancing policy; and
a means in said load balance switch for load balancing traffic to network addresses associated with each domain based on at least one of said metrics of a respective one of said load balancing policies respectively associated to each domain,
wherein said metrics, of each respective load balancing policy, each include at least one parameter, wherein said at least one parameter includes at least one of a tolerance, limit, threshold, DNS parameter, preference, and alternative tie-breaker metric use.
20. The system of claim 19 wherein said means for load balancing uses a global load balancing policy to load balance traffic to another domain that does not have one of said stored load balancing policies associated thereto.
21. The system of claim 19 wherein said plurality of metrics are usable by said means for load balancing for determining a preferred address, among a plurality of said network address associated with each domain, to route traffic, said preferred address being placed on top of a list of addresses.
22. The system of claim 19, further comprising:
a means in said load balance switch for sending a query to remote site switches for metric information to be used for each of said load balancing policies.
23. The system of claim 19 wherein said means for load balancing updates said at least one parameter of each metric said stored load balancing policies.
24. An apparatus, comprising:
a load balance switch that includes:
a first storage unit to store a plurality of load balancing policies, which are to be applied by said load balance switch to rank addresses of different domains,
wherein each of said load balancing policies specify an order of application of a plurality of metrics of each respective load balancing policy; and
a controller coupled to the first storage unit to use a respective one of said stored load balancing policies to rank addresses of each one of said domains,
wherein said metrics, of each respective load balancing policy, each include at least one parameter, wherein said at least one parameter includes at least one of a tolerance, limit, threshold, DNS parameter, preference, and alternative tie-breaker metric use.
25. The apparatus of claim 24 wherein the first storage unit includes a database.
26. The apparatus of claim 24 wherein said load balance switch further includes a second storage unit to store a global load balancing policy, and wherein said controller is adapted to use the global load balancing policy to rank addresses of at least one domain that has not been associated with any of the load balancing policies stored in the first storage unit.
27. The apparatus of claim 26 wherein said controller is adapted to use some parameters from the global load balancing policy for any other load balancing policy that does not have corresponding said at least one parameter specified.
28. The apparatus of claim 24 wherein said controller is adapted to update at least one of said load balancing policies.
29. The apparatus of claim 24 wherein said controller is adapted to provide notification if at least one of: (a) a domain for which a load balancing policy is to be associated is undefined and (b) a load balancing policy for a particular domain is undefined.
30. The apparatus of claim 24 wherein the controller of said load balance switch is adapted to communicate with remote site switches to obtain metric data to be used in said load balancing policies.
31. The apparatus of claim 24 wherein said controller is adapted to use a global load balancing policy for all said domains if said controller is unable to determine which of the stored said load balancing policies to associate to respective said domains.
Patent Citations (149)
| Patent | Date | Inventor | Cited By |
|---|---|---|---|
| US5031094(A) | 1991-07-01 | Toegel et al. | Applicant |
| US5359593(A) | 1994-10-01 | Derby et al. | Applicant |
| US5948061(A) | 1999-09-01 | Merriman et al. | Applicant |
| US5951634(A) | 1999-09-01 | Sitbon et al. | Applicant |
| US6006269(A) | 1999-12-01 | Phaal | Examiner |
| US6006333(A) | 1999-12-01 | Nielsen | Examiner |
| US6092178(A) | 2000-07-01 | Jindal et al. | Examiner |
| US6112239(A) | 2000-08-01 | Kenner et al. | Applicant |
| US6115752(A) | 2000-09-01 | Chauhan | Applicant |
| US6119143(A) | 2000-09-01 | Dias et al. | Applicant |
| US6128279(A) | 2000-10-01 | O'Neil et al. | Applicant |
| US6128642(A) | 2000-10-01 | Doraswamy et al. | Applicant |
| US6148410(A) | 2000-11-01 | Baskey et al. | Applicant |
| US6167445(A) | 2000-12-01 | Gai et al. | Examiner |
| US6167446(A) | 2000-12-01 | Lister et al. | Applicant |
| US6182139(B1) | 2001-01-01 | Brendel | Applicant |
| US6195691(B1) | 2001-02-01 | Brown | Applicant |
| US6233604(B1) | 2001-05-01 | Van Horne et al. | Applicant |
| US6286039(B1) | 2001-09-01 | Van Horne et al. | Applicant |
| US6286047(B1) | 2001-09-01 | Ramanathan et al. | Applicant |
| US6304913(B1) | 2001-10-01 | Rune | Applicant |
| US6324580(B1) | 2001-11-01 | Jindal et al. | Examiner |
| US6327622(B1) | 2001-12-01 | Jindal et al. | Examiner |
| US6336137(B1) | 2002-01-01 | Lee et al. | Examiner |
| US6381627(B1) | 2002-04-01 | Kwan et al. | Applicant |
| US6389462(B1) | 2002-05-01 | Cohen et al. | Applicant |
| US6393473(B1) | 2002-05-01 | Chu | Examiner |
| US6405252(B1) | 2002-06-01 | Gupta et al. | Applicant |
| US6427170(B1) | 2002-07-01 | Sitaraman et al. | Applicant |
| US6434118(B1) | 2002-08-01 | Kirschenbaum | Applicant |
| US6438652(B1) | 2002-08-01 | Jordan et al. | Applicant |
| US6446121(B1) | 2002-09-01 | Shah et al. | Applicant |
| US6449657(B2) | 2002-09-01 | Stanbach, Jr. et al. | Applicant |
| US6470389(B1) | 2002-10-01 | Chung et al. | Applicant |
| US6473802(B2) | 2002-10-01 | Masters | Applicant |
| US6480508(B1) | 2002-11-01 | Mwikalo et al. | Applicant |
| US6487555(B1) | 2002-11-01 | Bharat et al. | Applicant |
| US6490624(B1) | 2002-12-01 | Sampson et al. | Examiner |
| US6549944(B1) | 2003-04-01 | Weinberg et al. | Applicant |
| US6578066(B1) | 2003-06-01 | Logan et al. | Examiner |
| US6578077(B1) | 2003-06-01 | Rakoshitz et al. | Applicant |
| US6606643(B1) | 2003-08-01 | Emens et al. | Applicant |
| US6611861(B1) | 2003-08-01 | Schairer et al. | Applicant |
| US6665702(B1) | 2003-12-01 | Zisapel et al. | Applicant |
| US6681232(B1) | 2004-01-01 | Sistanizadeh et al. | Applicant |
| US6681323(B1) | 2004-01-01 | Fontanesi et al. | Applicant |
| US6691165(B1) | 2004-02-01 | Bruck et al. | Applicant |
| US6725253(B1) | 2004-04-01 | Okano et al. | Applicant |
| US6745241(B1) | 2004-06-01 | French et al. | Applicant |
| US6754699(B2) | 2004-06-01 | Swildens et al. | Applicant |
| US6760775(B1) | 2004-07-01 | Anerousis et al. | Examiner |
| US6772211(B2) | 2004-08-01 | Lu et al. | Applicant |
| US6779017(B1) | 2004-08-01 | Lamberton et al. | Applicant |
| US6789125(B1) | 2004-09-01 | Aviani et al. | Applicant |
| US6826198(B2) | 2004-11-01 | Turina et al. | Applicant |
| US6839700(B2) | 2005-01-01 | Doyle et al. | Applicant |
| US6850984(B1) | 2005-02-01 | Kalkunte et al. | Applicant |
| US6874152(B2) | 2005-03-01 | Vermeire et al. | Examiner |
| US6879995(B1) | 2005-04-01 | Chinta et al. | Applicant |
| US6898633(B1) | 2005-05-01 | Lyndersay et al. | Applicant |
| US6901081(B1) | 2005-05-01 | Ludwig | Applicant |
| US6928485(B1) | 2005-08-01 | Krishnamurthy et al. | Applicant |
| US6963914(B1) | 2005-11-01 | Breibart et al. | Applicant |
| US6963917(B1) | 2005-11-01 | Callis et al. | Applicant |
| US6985956(B2) | 2006-01-01 | Luke et al. | Applicant |
| US6987763(B2) | 2006-01-01 | Rochberger et al. | Applicant |
| US6996615(B1) | 2006-02-01 | McGuire | Applicant |
| US6996616(B1) | 2006-02-01 | Leighton et al. | Applicant |
| US7000007(B1) | 2006-02-01 | Valenti | Applicant |
| US7020698(B2) | 2006-03-01 | Andrews et al. | Applicant |
| US7020714(B2) | 2006-03-01 | Kalyanaraman et al. | Applicant |
| US7028083(B2) | 2006-04-01 | Levine et al. | Applicant |
| US7032010(B1) | 2006-04-01 | Swildens et al. | Applicant |
| US7032031(B2) | 2006-04-01 | Jungck et al. | Applicant |
| US7036039(B2) | 2006-04-01 | Holland | Applicant |
| US7058717(B2) | 2006-06-01 | Chao et al. | Examiner |
| US7062642(B1) | 2006-06-01 | Langrind et al. | Examiner |
| US7082102(B1) | 2006-07-01 | Wright | Examiner |
| US7086061(B1) | 2006-08-01 | Joshi et al. | Applicant |
| US7089293(B2) | 2006-08-01 | Grosner et al. | Applicant |
| US7114008(B2) | 2006-09-01 | Jungck et al. | Applicant |
| US7127713(B2) | 2006-10-01 | Davis et al. | Applicant |
| US7136932(B1) | 2006-11-01 | Schneider | Applicant |
| US7139242(B2) | 2006-11-01 | Bays | Examiner |
| US7177933(B2) | 2007-02-01 | Foth | Applicant |
| US7185052(B2) | 2007-02-01 | Day | Applicant |
| US7197547(B1) | 2007-03-01 | Miller et al. | Applicant |
| US7206806(B2) | 2007-04-01 | Pineau | Examiner |
| US7225272(B2) | 2007-05-01 | Kelley et al. | Applicant |
| US7240015(B1) | 2007-07-01 | Karmouch et al. | Examiner |
| US7240100(B1) | 2007-07-01 | Wein et al. | Applicant |
| US7254626(B1) | 2007-08-01 | Kommula et al. | Applicant |
| US7257642(B1) | 2007-08-01 | Bridger et al. | Examiner |
| US7260645(B2) | 2007-08-01 | Bays | Examiner |
| US7277954(B1) | 2007-10-01 | Stewart et al. | Applicant |
| US7296088(B1) | 2007-11-01 | Padmanabhan et al. | Applicant |
| US7321926(B1) | 2008-01-01 | Zhang et al. | Examiner |
| US7330908(B2) | 2008-02-01 | Jungck | Applicant |
| US7383288(B2) | 2008-06-01 | Miloushev et al. | Applicant |
| US7423977(B1) | 2008-09-01 | Joshi et al. | Applicant |
| US7454500(B1) | 2008-11-01 | Hsu et al. | Applicant |
| US7496651(B1) | 2009-02-01 | Joshi | Applicant |
| US2001/0049741(A1) | 2001-12-01 | Skene et al. | Applicant |
| US2001/0052016(A1) | 2001-12-01 | Skene et al. | Applicant |
| US2002/0026551(A1) | 2002-02-01 | Kamimaki et al. | Applicant |
| US2002/0038360(A1) | 2002-03-01 | Andrews et al. | Applicant |
| US2002/0055939(A1) | 2002-05-01 | Nardone et al. | Examiner |
| US2002/0059170(A1) | 2002-05-01 | Vange | Applicant |
| US2002/0059464(A1) | 2002-05-01 | Hata et al. | Applicant |
| US2002/0062372(A1) | 2002-05-01 | Hong et al. | Applicant |
| US2002/0078233(A1) | 2002-06-01 | Biliris et al. | Applicant |
| US2002/0087722(A1) | 2002-07-01 | Datta et al. | Applicant |
| US2002/0091840(A1) | 2002-07-01 | Pulier et al. | Applicant |
| US2002/0112036(A1) | 2002-08-01 | Bohannon et al. | Applicant |
| US2002/0120743(A1) | 2002-08-01 | Shabtay et al. | Applicant |
| US2002/0120763(A1) | 2002-08-01 | Miloushev et al. | Applicant |
| US2002/0124096(A1) | 2002-09-01 | Loguinov et al. | Applicant |
| US2002/0133601(A1) | 2002-09-01 | Kennamer et al. | Applicant |
| US2002/0150048(A1) | 2002-10-01 | Ha et al. | Applicant |
| US2002/0154600(A1) | 2002-10-01 | Ido et al. | Applicant |
| US2002/0188862(A1) | 2002-12-01 | Trethewey et al. | Applicant |
| US2002/0194324(A1) | 2002-12-01 | Guha | Examiner |
| US2002/0194335(A1) | 2002-12-01 | Maynard | Applicant |
| US2003/0018796(A1) | 2003-01-01 | Chou et al. | Applicant |
| US2003/0031185(A1) | 2003-02-01 | Kikuchi et al. | Applicant |
| US2003/0035430(A1) | 2003-02-01 | Islam et al. | Applicant |
| US2003/0065711(A1) | 2003-04-01 | Acharya et al. | Applicant |
| US2003/0065763(A1) | 2003-04-01 | Swildens et al. | Applicant |
| US2003/0105797(A1) | 2003-06-01 | Dolev et al. | Applicant |
| US2003/0115283(A1) | 2003-07-01 | Barbir et al. | Applicant |
| US2003/0135509(A1) | 2003-07-01 | Davis et al. | Applicant |
| US2003/0154239(A1) | 2003-08-01 | Davis et al. | Applicant |
| US2003/0210686(A1) | 2003-11-01 | Terrell et al. | Applicant |
| US2003/0210694(A1) | 2003-11-01 | Jayaraman et al. | Applicant |
| US2003/0229697(A1) | 2003-12-01 | Borella | Applicant |
| US2004/0019680(A1) | 2004-01-01 | Chao et al. | Examiner |
| US2004/0024872(A1) | 2004-02-01 | Kelley et al. | Applicant |
| US2004/0039847(A1) | 2004-02-01 | Persson | Applicant |
| US2004/0194102(A1) | 2004-09-01 | Neerdaels | Applicant |
| US2004/0249939(A1) | 2004-12-01 | Amini et al. | Applicant |
| US2004/0249971(A1) | 2004-12-01 | Klinker | Examiner |
| US2005/0021883(A1) | 2005-01-01 | Shishizuka et al. | Applicant |
| US2005/0033858(A1) | 2005-02-01 | Swildens et al. | Applicant |
| US2005/0086295(A1) | 2005-04-01 | Cunningham et al. | Applicant |
| US2005/0149531(A1) | 2005-07-01 | Srivastava | Applicant |
| US2005/0169180(A1) | 2005-08-01 | Ludwig | Applicant |
| US2005/0286416(A1) | 2005-12-01 | Shimonishi et al. | Applicant |
| US2006/0020715(A1) | 2006-01-01 | Jungck | Applicant |
| US2007/0168547(A1) | 2007-07-01 | Krywaniuk | Examiner |
Non-Patent Literature (33)
- Albitz, P., et al., “DNS and BIND in a Nutshell,” O'Reilly & Associates, Sebastopol, CA, 1992, pp. 214-215.Applicant
- Alteon Systems, “Alteon WebSystems Introduces New Layer 4+ Switching Technology that Speeds User Access to Internet Servers,” Dec. 7, 1998, retrieved Nov. 5, 2002, from http://web.archive.org/web/20000919190409/www.alteonwebsystems.com/press/releases/1998/120798.asp, pp. 1-4.Applicant
- Alteon WebSystems, Inc., “Enhancing Web User Experience with Global Server Load Balancing,” Jun. 1999, 8 pages.Applicant
- Krapf, E., “Alteon's Global Server Load Balancing,” Business Communications Review, Jan. 1999, p. 60, retrieved Oct. 25, 2002, from http://www.bcr.com/bcrmag/1999/01/p60.asp, 3 pages.Applicant
- Nortel Networks, “Alteon Personal Content Director,” © 2001, can be retrieved from http://www.nortelnetworks.com/personalinternet, 4 pages.Applicant
- IBM Corp., IBM WebSphere Performance Pack: Load Balancing with IBM SecureWay Network Dispatcher, First Edition, Chapters 1, 2, 4, and 8, Oct. 1999.Applicant
- IBM Corp., SecureWay® Network Dispatcher: User's Guide—Version 2.1 for AIX, Solaris, and Windows NT, Third Edition, Chapters 3, 4, 9, 10, 11, and Appendices C & E, Mar. 1999.Applicant
- Yerxa, G., “ACElerate on Fast Track for Load-Balancing,” Mar. 8, 1999, retrieved Nov. 5, 2002, from http://www.networkcomputing.com/1005/1005sp2.html, pp. 1-4.Applicant
- Alteon WebSystems, “PCD White Paper,” AlteonWebSystems, pp. 1-8, Mar. 2001.Applicant
- Cardellini, V., et al., “Dynamic Load Balancing on Web-server Systems,” IEEE Internet Computing, 3(3):28-39, May-Jun. 1999.Applicant
- Foundry Networks, Inc., “Server Load Balancing in Today's Web-enabled Enterprises,” White Paper, pp. 1-10, Apr. 2002.Applicant
- Genova, Z., et al., “Challenges in URL Switching for Implementing Globally Distributed Web Sites,” IEEE, pp. 89-94, 2000.Applicant
- Genova, Z., et al., “Challenges to URL Switching for Implementing Globally Distributed Web Sites,” Department of Computer Science and Engineering, University of South Florida, pp. 1-9, Aug. 11, 2000.Applicant
- Bestavros, Azer, “WWW Traffic Reduction and Load Balancing through Server-Based Caching,” IEEE Concurrency, pp. 56-67, Jan.-Mar. 1997.Applicant
- Paul, Arindam et al., “Balancing Web Server Load for Adaptable Video Distribution,” IEEE pp. 469-476, 2000.Applicant
- U.S. Appl. No. 09/670,487, filed Sep. 26, 2000, Hsu et al.Applicant
- U.S. Appl. No. 10/206,580, filed Jul. 25, 2002, Kommula et al.Applicant
- U.S. Appl. No. 10/214,921, filed Aug. 7, 2002, Kommula.Applicant
- U.S. Appl. No. 10/305,823, filed Nov. 27, 2002, Joshi et al.Applicant
- U.S. Appl. No. 10/376,903, filed Feb. 28, 2003, Kommula.Applicant
- U.S. Appl. No. 10/377,364, filed Feb. 28, 2003, Kommula.Applicant
- U.S. Appl. No. 10/674,627, filed Sep. 29, 2003, Joshi.Applicant
- U.S. Appl. No. 10/840,496, filed May 6, 2004, Joshi.Applicant
- U.S. Appl. No. 10/924,552, filed Aug. 23, 2004, Joshi.Applicant
- U.S. Appl. No. 11/429,177, filed May 5, 2006, Joshi et al.Applicant
- U.S. Appl. No. 11/707,697, filed Feb. 16, 2007, entitled “Global Server Load Balancing,” inventor: Sunanda L. Kommula et al.Applicant
- Cisco Document, “Configuring the CSS Domain Name Service,”, posted on Dec. 2000, Cisco Systems Inc., http://www.ciscosystems.com, pp. 1-13.Applicant
- Venkataramani, A., et al., “TCP Nice: a Mechanism for Background Transfer,” Proceedings of the Fifth Symposium on Operating Systems Design and Implementation (OSDI'02), ISBN:1-931971-06-4, 329-343, 2002.Applicant
- Joshi, “Smoothing Algorithm for Round Trip Time (RTT) Measurements,” assigned U.S. Appl. No. 12/177,021, filed Jul. 21, 2008.Applicant
- U.S. Appl. No. 11/741, 480, filed Apr. 27, 2007, Hus et al.Applicant
- U.S. Appl. No. 12/272,618, filed Nov. 17, 2008, Hus et al.Applicant
- U.S. Appl. No. 12/353,701, filed Jan. 14, 2009, Joshi.Applicant
- Doeringer et al., “Routing on Longest-Matching Prefixes,” IEEE/ACM Transactions on Networking, vol. 4, No. 1, Feb. 1996, pp. 86-97.Applicant