Emc Corporation

T David Evans

Qi Zhang

Morrie Gasser

Hongliang Tang

Qing Liu

Nancy Welch

Peter E Tolvanen

An improved technique for managing data replacement in a cache dynamically selects a data replacement protocol from among multiple candidates based on which data replacement protocol produces the greatest cache hit rate. The technique includes selecting one of multiple data replacement protocols using a random selection process that can be biased to favor the selection of certain protocols over others. Data are evicted from the cache using the selected data replacement protocol, and the cache hit rate is monitored. The selected data replacement protocol is then rewarded in response to the detected cache hit rate. The selection process is repeated, and a newly selected data replacement protocol is put into use. Operation tends to converge on an optimal data replacement protocol that best suits the application and current operating environment of the cache.

Dynamic selection of data replacement protocol for cache

An improved technique for managing data replacement in a multi-level cache dynamically selects a data replacement protocol from among multiple candidates based on which data replacement protocol produces the greatest cache hit rate. The technique includes selecting one of multiple data replacement protocols using a random selection process that can be biased to favor the selection of certain protocols over others. Data are evicted from each level of the multi-level cache using the selected data replacement protocol, and the cache hit rate is monitored. The selected data replacement protocol is then rewarded in response to the detected cache hit rate. The selection process is repeated, and a newly selected data replacement protocol is put into use. Operation tends to converge on an optimal data replacement protocol that best suits the application and current operating environment of the multi-level cache.

Dynamic selection of data replacement protocol for multi-level cache

An improved technique for replacing storage elements in a redundant group of storage elements of a storage array dynamically selects a storage element type from among multiple candidates based on which storage element type produces the greatest service level of the redundant group. The technique includes selecting one of multiple storage element types using a random selection process that can be biased to favor the selection of certain storage element types over others. A storage element of the selected type is added to the redundant group. The selected storage element type is then rewarded based on the service level that results from adding the storage element of the selected type. The selection process is repeated, and a newly selected storage element type is put into use. Operation tends to converge on an optimal storage element type that maximizes the service level of the redundant group.

Dynamic selection of spare storage element types in array

A method is used in determining alternate paths in faulted systems. It is detected that a first processor has a problem accessing a target. The first processor has a first path to the target. An alternate path to the target is determined by identifying that a second processor has better access to the target than the first processor. The second processor has a second path to the target. Responsibility for I/O communication with the target is transferred from the first processor to the second processor. Responsibility for I/O communication with the target is transferred back to the first processor upon resolution of the problem.

Determining alternate paths in faulted systems

A technique enables managing distribution of well-defined objects. The technique involves maintaining a database of well-defined objects and a registry of identifiers. The technique further involves receiving an object request from a client device. The object request includes a particular identifier. The technique further involves providing (i) all of the well-defined objects from the database in response to the well-defined object request when the particular identifier of the well-defined object request is at least as recent as the most recent identifier in the registry, and alternatively (ii) less than all of the well-defined objects from the database in response to the well-defined object request when the particular identifier of the well-defined object request is not as recent as the most recent identifier in the registry. Accordingly, an older client device can be prohibited from receiving a newer well-defined object thereby preventing the older client device from attempting to construct the newer object and inadvertently failing.

Techniques for managing distribution of well-defined objects in a client/server system

A technique involves managing state changes of a data storage system in a computerized device configured to obtain object trees representing state information of the data storage system. The technique includes receiving a first object tree which represents the data storage system at a first time, and receiving a second object tree which represents the data storage system at a second time. The second time is after the first time. The technique further includes generating a set of tree comparison results from a comparison between the first object tree representing the data storage system at the first time and the second object tree representing the data storage system at the second time. The set of tree comparison results indicate whether state changes have occurred in the data storage system.

Techniques for managing state changes of a data storage system utilizing the object oriented paradigm

Described are techniques for accessing data. The data is stored in a tree data structure at a first location. A hash value is determined in accordance with a portion of said data. An entry is created in a hash table in accordance with said hash value for said data. The entry includes a reference to said data at said first location, wherein said data is accessible at said first location using a first retrieval technique for said tree data structure and using a second retrieval technique for said hash table.

Synergistic data structures

A data storage system is configured to provide a graphical display that shows the user a logical schematic of interconnected disk enclosures of a data storage system along with any erroneous connections among the disk enclosures. The graphical display, therefore, allows the user to visually identify the disk drive enclosures in the data storage system and any erroneous connections formed between the disk enclosures. Additionally, the data storage system is configured to monitor the connections among the disk enclosures and provide updated graphical displays to the user showing any changes to the connections among the disk enclosures. In the event that a connection between two disk enclosures malfunctions or becomes inoperable, the graphical display allows the user to easily identify the location of connection error.

Growing community of inventors

Rutland, MA, United States of America

T David Evans