Loading patent…
AssigneeHewlett-Packard Development Company, L.P.
InventorsSujoy Basu, Rajendra Kumar
Estimating the term…
A special-purpose appliance (SPA) works in conjunction with a server farm consisting of multiple caching server appliances (CSAs) to supervise a local storage medium (i.e., a shared cache) that is accessible by all the CSAs for storing at least some of the remote objects such as web pages and their embedded objects and/or streaming media objects that have been and/or will be served by one or more of the CSAs to its respective clients. The SPA preferably also determines when to prefetch remote objects such as web pages and their embedded objects and/or streaming media objects that are not currently stored in the shared cache, but which the SPA has determined are likely to be requested in the future by one or more of the CSAs one behalf of one or more of the CSA's respective clients. In that regard, the SPA (and/or PSA) does not merely monitor the file requests from each CSA to the remote servers, but rather monitors and aggregates the individual requests from each client to its respective CSA, for example, by monitoring the access logs of each CSA and using that data to decide what to prefetch into the shared cache from the remote server or servers, what is still of value and needs to be updated, and what is no longer of value and can be replaced. What it prefetches can be based, for example, on links present in an already requested web page, on patterns of recent accesses to web pages and streaming media objects, on user profiles, and on past trends.
A caching system for local storage of objects originating from one or more remote origin servers, comprising:
A method for caching objects originating from one or more remote servers, comprising:
Dependencies are inferred from the claim text.
From the US filing history. Foreign family members aren’t listed.
Backward citations are indexed for grants only.
Browsing optimisation, e.g. caching or content distillation: of access to content, e.g. by caching
Computing and data processing
Term end not estimated
The present invention relates generally to networks having clients served by both remote and local servers, and more particularly to means for supervising shared local storage in which selected objects are cached.
Higher bandwidth and lower latency for web and streaming media clients dependent on remote central servers can be accomplished by providing caching servers at more local points in the network that keep copies of files previously retrieved from the remote server for subsequent repeated access by the local clients. Multiple caching servers can be arranged in hierarchical fashion to share a common cache of objects, in effect forming a shared second level cache of objects in response to aggregated requests for files that were not available from a respective server's first level cache. The theory underlying “caching” is that since the same file may be used more than once, it may be more efficient (both in terms of speed and resource utilization) to keep a copy locally rather than retrieve it a second time from a remote source. Typically, each caching server caches a small set of “hot” recently accessed objects in a fast and relatively expensive random access memory attached to its internal bus, and a somewhat larger set of such objects in a slower and cheaper random access peripheral storage device such as a magnetic or optical disk.
An even bigger set of objects can be locally cached in a networked storage medium such as a SAN (“Storage Area Network”) or a NAS (“Network Attached Storage”) that is accessible by the caching server (and also by other local clients and/or servers) via a relatively short and fast transmission medium such as fiber optic cable that offers higher bandwidth and lower latency than is available from the remote server.
FIG. 1 shows an exemplary Caching Server Complex including a Prefetch Server Appliance and multiple Caching Server Appliances connected either to a Storage Area Network (SAN) and/or to Network Attached Storage (NAS).
FIG. 2 is an architectural block diagram of a typical Caching Server Complex Appliance.
FIG. 3 shows how the same Application Programmer Interface (API) may be used for either a single CSA or for a Caching Server Complex including multiple CSAs.
As shown in FIG. 1, a Caching Server Complex (CSC) preferably includes multiple caching server appliances (CSAs ) as well as a shared prefetch server appliance (PSA) and a Traffic Director Appliance (TDA) which provides a transparent interface and a load balancing function between the CSAs and an external network NET.
It should be understood that although shown as separate functional blocks, some or all of the CSAs, the PSA, and the TDA could be physically integrated into a single cabinet, or even as separate applications running on the same machine. In other embodiments, the PSA may be physically collocated with the storage or it can be in some other location, and/or the TDA functionality could be replaced with individual switched or unswitched connections to the external network NET. In any event, both the PSA and each CSA are physically connected through a switching router (FC or SW1) to the shared local storage (SAN or NAS) via a robust high speed connection (preferably a dedicated channel of a fiber optic network, but possibly a demand based network such as Ethernet).
A second switching router SW2 not only connects the TDA with the external NET, but also preferably provides separate bypass connections from NET to the PSA and also to the NAS (either directly, or via SW1) thereby avoiding any delays that might otherwise be imposed by the TDA. In particular, these bypassed connections would facilitate the downloading (under the supervision of the PSA) of a large volume of prefetched objects into the shared local cache in the NAS. Although not shown, it would also be possible for each of the CSAs to also have a direct connection to SW2 for downloading from the origin servers S without going through TDA.