Sandisk Technologies Inc.

Wind Jammer Technologies, LLC

Sun Microsystems, Inc.

Sandisk Enterprise IP LLC

Sandisk Enterprises IP LLC

John Richard Busch

Brian Walter O'Krafka

Manavalan Krishnan

Darpan Dinker

Darryl Ouye

Kai Rothauge

Yan Li

Steven Theodore Sprouse

David Vengerov

Tomy Ammuthan Cheru

Ilya Gluhovsky

Executing a query in a disaggregated cluster. A query is received at the disaggregated cluster. A query graph is created based on the query that identifies a hierarchy of vertices, where each vertex is associated with a set of data responsive to at least a portion of the query. The compute nodes process the query graph by first identifying a minimum set of tables, files, and objects stored on the storage nodes required to retrieve data that satisfy the query. Next, the compute nodes selectively assign the identified tables, files, and objects to a leaf vertex of the query graph to optimize retrieving data from the storage nodes. Thereafter, the compute nodes process the retrieved data sets associated with each vertex using separate threads of execution for each vertex of the query graph such that leaf vertices are performed in parallel. The compute nodes then provide a result set.

Disaggregated query processing utilizing precise, parallel, asynchronous shared storage repository access

Executing a query in a disaggregated cluster. A query is received at the disaggregated cluster. A query graph is created based on the query that identifies a hierarchy of vertices, where each vertex is associated with a set of data responsive to at least a portion of the query. The compute nodes process the query graph by first identifying all tables, files, and objects stored on the storage nodes whose access is required to retrieve data that satisfy the query. Next, the compute nodes selectively assign the identified tables, files, and objects to a leaf vertex of the query graph to optimize retrieving data from the storage nodes. Thereafter, the compute nodes process the retrieved data sets associated with each vertex using separate threads of execution for each vertex of the query graph such that leaf vertices are performed in parallel. The compute nodes then provide a result set.

Disaggregated query processing on data lakes based on pipelined, massively parallel, distributed native query execution on compute clusters utilizing precise, parallel, asynchronous shared storage repository access

A computer system detects a request to access a first data object stored in a tiered data structure that includes internal nodes and leaf nodes. In response to detecting the request, the computer system determines whether the first data object is stored in a cache that includes a plurality of data objects from the tiered data structure that are stored separately from their corresponding leaf node in the cache. When the first data object is stored in the cache, the computer system returns the first data object from the cache and when the first data object is not stored in the cache, the computer system traverses the tiered data structure to a leaf node that includes the first data object and returns the first data object from the leaf node for the first data object in the tiered data structure.

Efficient cache utilization in a tiered data structure

A data analytic system allows for analytic operations be moved from a server on to a solid state drive (SSD) type analytic system, where a CAM NAND structure can be used in the analytic operations. The server can run a software using database language can issue command to the analytic system. On the data analytic system (that can interface with common, existing database language), the software commands are translated into firmware language and broken down into multiple small tasks. The small tasks are executed on the SSD flash controllers or on NAND flash according to the task specifications. The mid-product from the NAND flash or the SSD controllers can be merged within each SSD blade and also further merged on the top server level.

Architectures for data analytics using computational NAND memory

Approaches for an object store implemented, at least in part, on one or more solid state devices. The object store may store objects on a plurality of solid state devices. The object store may include a transaction model means for ensuring that the object store performs transactions in compliance with atomicity, concurrency, isolation, and durability (ACID) properties. The object store may include means for providing parallel flushing in a write cache maintained on each of the solid state devices. The object store may include means for maintaining one or more double-write buffers, for the object store, at a location other than the solid state devices. The object store may optionally comprise means for maintaining one or more circular transaction logs, for the object store, at a location other than the solid state devices. The object store may operate to minimize write operations performed on the solid state devices.

Efficient flash memory-based object store

Approaches for performing a write operation on a solid state device (SSD). One or more containers are maintained on the solid state device. Each container is a logical grouping of objects independent from where the logical grouping of objects are physically stored on the solid state device. When a write operation is received at the SSD, the manner is which changes requested by the write operation should be stored are determined based on which container is being written. Containers provide a flexible approach for specifying attributes of how data should be stored and accessed which is independent from where the data is physically stored. Containers also have particular utility in performing load balancing and ensuring high availability and recovery.

Flexible way of specifying storage attributes in a flash memory-based object store

One embodiment of the present invention provides a system that selects bases to form a regression model for cache performance. During operation, the system receives empirical data for a cache rate. The system also receives derivative constraints for the cache rate. Next, the system obtains candidate bases that satisfy the derivative constraints. For each of these candidate bases, the system: (1) computes an aggregate error E incurred using the candidate basis over the empirical data; (2) computes an instability measure I of an extrapolation fit for using the candidate basis over an extrapolation region; and then (3) computes a selection criterion F for the candidate basis, wherein F is a function of E and I. Finally, the system minimizes the selection criterion F across the candidate bases to select the basis used for the regression model.

Growing community of inventors

Cupertino, CA, United States of America

John Richard Busch