Permabit Technology Corporation

Red Hat, Inc.

Burnside Acquisition, LLC

Michael Fortson

Jonathan Coburn

Assar Westerlund

Michael Sclafani

Norman H Margolus

Jered J Floyd

Edwin Olson

J Corwin Coburn

Hooman Vassef

Thomas Jaskiewicz

Among other things, in one aspect, in general, a system for managing data in a data storage system includes a plurality of index nodes each storing a map of entries, each entry of the map including an identifier corresponding to a particular portion of data stored in the data storage system, and metadata indicating a location where the particular portion of data is stored in the data storage system, and one or more supernodes configured to return an identification of an index node that recently submitted a request for a particular identifier associated with at least one of the portions of data.

Managing a deduplicated data index

In general, in one aspect, a method for managing data in a data storage system includes receiving identifiers corresponding to different respective entries of a map stored in the data storage system, with a particular identifier corresponding to a particular entry of the map, the particular entry including a computed value corresponding to a particular portion of data stored in the data storage system and metadata indicating a location where the particular portion of data is stored in the data storage system, selecting, according to a first selection criterion, at least some of the identifiers for storage in a first portion of an index, and selecting, according to a second selection criterion, at least some of the identifiers for storage in a second portion of the index.

Indexing deduplicated data

In one aspect, in general, a method for managing data includes receiving, at a data deduplication engine of a computer system, data to be stored in a data storage system, computing a first value corresponding to at least one portion of the received data, determining that the first value matches a second value stored in a collection of identifiers, each identifier corresponding to a particular portion of data stored in the data storage system, each identifier comprising a computed value corresponding to the particular portion of data and including metadata indicating a location where the particular portion of data is being stored in the data storage system, and based on the determination that the first value matches a second value stored in the collection of identifiers, reallocating one or more physical locations from corresponding one or more virtual locations to different respective one or more virtual locations.

Managing deduplication of stored data

A method for constructing an index suitable for indexing a large set of records identified by long generally randomly distributed record names and for answering membership queries about the set, the method comprising assigning each different record a different record name, determining that a new record name is not already represented in the index by checking an entry in a first level index that is shorter than the complete new record name, and determining that a queried record name is already represented in the index by determining that the queried record name is represented in a second level index that contains enough information to reconstruct the complete queried record name.

Storage system for randomly named blocks of data

In one aspect, in general, a method for managing data in a data storage system comprises receiving data to be stored in the data storage system, computing values corresponding to different respective portions of the received data, generating identifiers corresponding to different respective portions of the received data, with an identifier corresponding to a particular portion of data including the computed value corresponding to the particular portion of data and metadata indicating a location where the particular portion of data is being stored in the data storage system, and storing at least some of the identifiers in an index until the index reaches a predetermined size.

Managing data in a data storage system includes: receiving data to be stored in the data storage system; computing values corresponding to different respective portions of the received data; generating identifiers corresponding to different respective portions of the received data, with an identifier corresponding to a particular portion of data including the computed value corresponding to the particular portion of data and metadata indicating a location where the particular portion of data is being stored in the data storage system; storing at least some of the identifiers in an index until the index reaches a predetermined size; and in response to determining that a first identifier corresponding to a first portion of data, received after the index reached the predetermined size, was not already stored in the index before the first portion of data was received, storing the first identifier in the index and designating for removal at least a second identifier corresponding to a second portion of data to be removed from the index such that the index does not exceed the predetermined size.

An index is constructed that is suitable for indexing a large set of records identified by randomly distributed record names and for answering membership queries about the set. The index has more than one level and the first-level index typically resides in RAM. Like a Bloom Filter, the first level index provides a non-membership indication with certainty and a membership indication with a controlled probability of error. Unlike a Bloom filter, entries in the first level index correspond uniquely to distinct records. Use is made of the statistical properties of a sorted list of random numbers in order to represent the first level index compactly.

Growing community of inventors

Cambridge, MA, United States of America

Michael Fortson