Viral B Shah

US Patent:

8375194, Feb 12, 2013

Filed:

May 27, 2010

Appl. No.:

12/788706

Inventors:

Viral S. Shah - Cupertino CA, US
Sudhir R. Shetiya - Mumbai, IN
Anoop Sharma - San Jose CA, US
Lars B. Plum - Milpitas CA, US

Assignee:

Hewlett-Packard Development Company, L.P. - Houston TX

International Classification:

G06F 9/26
G06F 9/34

US Classification:

711206

Abstract:

There is provided a computer-executed method of freeing memory. One exemplary method comprises receiving a message from a user process. The message may specify a virtual address for a memory segment. The virtual address may be mapped to the memory segment. The memory segment may comprise a physical page. The method may further comprise identifying the physical page based on the virtual address. Additionally, the method may comprise freeing the physical page without unmapping the memory segment.

US Patent:

20060101314, May 11, 2006

Filed:

Aug 31, 2005

Appl. No.:

11/217114

Inventors:

Parry Husbands - Albany CA, US
Long Choy - Hong Kong, HK
Alan Edelman - Newton MA, US
Eckart Jansen - Belmont MA, US
Viral Shah - Goleta CA, US

International Classification:

G06F 11/00

US Classification:

714100000

Abstract:

In one embodiment, a process may be performed in parallel on a parallel server by defining a data type that may be used to reference data stored on the parallel server and overloading a previously-defined operation, such that when the overloaded operation is called, a command is sent to the parallel server to manipulate the data stored on the parallel server. In some embodiments, the previously-defined operation that is overloaded may be an operation of an operating system. Further, in some embodiments, when the data stored on the parallel server is no longer needed, a command may be sent to the parallel server to reallocate the memory used to store the data.

US Patent:

20220253383, Aug 11, 2022

Filed:

Apr 22, 2022

Appl. No.:

17/660374

Inventors:

- Mountain View CA, US
Xun Cheng - Dublin CA, US
Viral Shah - Mountain View CA, US

Assignee:

Google LLC - Mountain View CA

International Classification:

G06F 12/0871
G06F 16/22
G06F 16/2455
G06F 16/27
G06F 9/50
G06F 12/0891

Abstract:

A method for providing elastic columnar cache includes receiving cache configuration information indicating a maximum size and an incremental size for a cache associated with a user. The cache is configured to store a portion of a table in a row-major format. The method includes caching, in a column-major format, a subset of the plurality of columns of the table in the cache and receiving a plurality of data requests requesting access to the table and associated with a corresponding access pattern requiring access to one or more of the columns. While executing one or more workloads, the method includes, for each column of the table, determining an access frequency indicating a number of times the corresponding column is accessed over a predetermined time period and dynamically adjusting the subset of columns based on the access patterns, the maximum size, and the incremental size.

US Patent:

20210081356, Mar 18, 2021

Filed:

Jul 10, 2020

Appl. No.:

16/926425

Inventors:

- Redwood Shores CA, US
Hariharan Lakshmanan - Redwood City CA, US
Viral Shah - Redwood City CA, US
Shasank Kisan Chavan - Menlo Park CA, US

International Classification:

G06F 16/11
G06F 16/901

Abstract:

Techniques are provided for a DBMS automating ILM on indexes, based on index composition, to efficiently reduce index storage footprints. According to an embodiment, a user sets an index-specific ILM (ISILM) policy, which comprises one or both of an index-test requirement and a time requirement. Based on the ISILM policy being met, or on some other way of initiating analysis, the DBMS automatically analyzes the data blocks storing the index to determine an index condition metric (e.g., percentage of free space). This analysis is performed on a sample of data blocks storing the index without blocking the index from other operations during the analysis. The condition metric for the entire index is estimated based on analysis of the sample data blocks. Using the determined condition metric for an index, the DBMS automatically selects an option for optimally managing the index (e.g., coalesce, shrink space, index rebuild, no action, etc.).

US Patent:

20170116269, Apr 27, 2017

Filed:

Oct 21, 2016

Appl. No.:

15/331599

Inventors:

- Redwood Shores CA, US
Viral Shah - Cupertino CA, US
Xia Hua - Mountain View CA, US
Jesse Kamp - Castro Valley CA, US
Shasank K. Chavan - Menlo Park CA, US
Maria Colgan - Menlo Park CA, US
Tirthankar Lahiri - Palo Alto CA, US
Adrian Tsz Him Ng - Redwood City CA, US
Krishnan Meiyyappan - Fremont CA, US
Amit Ganesh - San Jose CA, US
Juan R. Loaiza - Woodside CA, US
Kothanda Umamageswaran - Sunnyvale CA, US
Yiran Qin - Emeryville CA, US

International Classification:

G06F 17/30
G06F 12/0811
G06F 12/0897
G06F 3/06

Abstract:

Techniques are provided for storing in in-memory unit (IMU) in a lower-storage tier and copying the IMU to DRAM when needed for query processing. Techniques are also provided for copying IMUs to lower tiers of storage when evicted from the cache of higher tiers of storage. Techniques are provided for implementing functionality of IMUs within a storage system, to enable database servers to push tasks, such as filtering, to the storage system where the storage system may access IMUs within its own memory to perform the tasks. Metadata associated with a set of data may be used to indicate whether an IMU for the data should be created by the database server machine or within the storage system.