JIN HUA LI, LMP
Massage Therapy at Bel Red Rd, Bellevue, WA

2012016, Jun 28, 2012

Dec 28, 2010

12/979748

Jin Li - Bellevue WA, US
Sudipta Sengupta - Redmond WA, US
Ran Kalach - Bellevue WA, US
Ronakkumar N. Desai - Redmond WA, US
Paul Adrian Oltean - Redmond WA, US
James Robert Benton - Seattle WA, US

MICROSOFT CORPORATION - Redmond WA

G06F 17/30

707692, 707E17005

The subject disclosure is directed towards a data deduplication technology in which a hash index service's index is partitioned into subspace indexes, with less than the entire hash index service's index cached to save memory. The subspace index is accessed to determine whether a data chunk already exists or needs to be indexed and stored. The index may be divided into subspaces based on criteria associated with the data to index, such as file type, data type, time of last usage, and so on. Also described is subspace reconciliation, in which duplicate entries in subspaces are detected so as to remove entries and chunks from the deduplication system. Subspace reconciliation may be performed at off-peak time, when more system resources are available, and may be interrupted if resources are needed. Subspaces to reconcile may be based on similarity, including via similarity of signatures that each compactly represents the subspace's hashes.

2011027, Nov 10, 2011

May 5, 2010

12/773859

Sudipta Sengupta - Redmond WA, US
Biplob Kumar Debnath - Minneapolis MN, US
Jin Li - Bellevue WA, US

Microsoft Corporation - Redmond WA

G06F 12/02, G06F 12/10, G06F 12/00

711103, 711104, 711216, 711E12001, 711E12059

Described is using flash memory, RAM-based data structures and mechanisms to provide a flash store for caching data items (e.g., key-value pairs) in flash pages. A RAM-based index maps data items to flash pages, and a RAM-based write buffer maintains data items to be written to the flash store, e.g., when a full page can be written. A recycle mechanism makes used pages in the flash store available by destaging a data item to a hard disk or reinserting it into the write buffer, based on its access pattern. The flash store may be used in a data deduplication system, in which the data items comprise chunk-identifier, metadata pairs, in which each chunk-identifier corresponds to a hash of a chunk of data that indicates. The RAM and flash are accessed with the chunk-identifier (e.g., as a key) to determine whether a chunk is a new chunk or a duplicate.

2012010, Apr 26, 2012

Oct 20, 2010

12/908153

Sudipta Sengupta - Redmond WA, US
Biplob Kumar Debnath - Minneapolis MN, US
Jin Li - Bellevue WA, US

Microsoft Corporation - Redmond WA

G06F 12/10, G06F 12/00

711216, 711E1206, 711E12001

Described is using flash memory (or other secondary storage), RAM-based data structures and mechanisms to access key-value pairs stored in the flash memory using only a low RAM space footprint. A mapping (e.g. hash) function maps key-value pairs to a slot in a RAM-based index. The slot includes a pointer that points to a bucket of records on flash memory that each had keys that mapped to the slot. The bucket of records is arranged as a linear-chained linked list, e.g., with pointers from the most-recently written record to the earliest written record. Also described are compacting non-contiguous records of a bucket onto a single flash page, and garbage collection. Still further described is load balancing to reduce variation in bucket sizes, using a bloom filter per slot to avoid unnecessary searching, and splitting a slot into sub-slots.

2012016, Jun 28, 2012

Dec 28, 2010

12/979681

Jin Li - Bellevue WA, US
Sudipta Sengupta - Redmond WA, US

MICROSOFT CORPORATION - Redmond WA

G06F 17/30

707747, 707E17002

The subject disclosure is directed towards a data deduplication technology in which a hash index service's index and/or indexing operations are adaptable to balance deduplication performance savings, throughput and resource consumption. The indexing service may employ hierarchical chunking using different levels of granularity corresponding to chunk size, a sampled compact index table that contains compact signatures for less than all of the hash index's (or subspace's) hash values, and/or selective subspace indexing based on similarity of a subspace's data to another subspace's data and/or to incoming data chunks.

2011027, Nov 10, 2011

Dec 28, 2010

12/979644

Sudipta Sengupta - Redmond WA, US
Biplob Debnath - Minneapolis MN, US
Jin Li - Bellevue WA, US
Ronakkumar N. Desai - Redmond WA, US
Paul Adrian Oltean - Redmond WA, US

MICROSOFT CORPORATION - Redmond WA

G06F 12/08

711216, 711E12018

The subject disclosure is directed towards a data deduplication technology in which a hash index service's index maintains a hash index in a secondary storage device such as a hard drive, along with a compact index table and look-ahead cache in RAM that operate to reduce the I/O to access the secondary storage device during deduplication operations. Also described is a session cache for maintaining data during a deduplication session, and encoding of a read-only compact index table for efficiency.

2013026, Oct 3, 2013

Apr 3, 2012

13/438465

Jin Li - Bellevue WA, US
Cheng Huang - Redmond WA, US
Sudipta Sengupta - Redmond WA, US
Christopher Broder Wilson - Santa Barbara CA, US

MICROSOFT CORPORATION - Redmond WA

G06F 9/46

718105

Described is a technology by which a consistent hashing table of bins maintains values representing nodes of a distributed system. An assignment stage uses a consistent hashing function and a selection algorithm to assign values that represent the nodes to the bins. In an independent mapping stage, a mapping mechanism deterministically maps an object identifier/key to one of the bins as a mapped-to bin.

8326980, Dec 4, 2012

Apr 28, 2010

12/769270

Cheng Huang - Redmond WA, US
Nicholas Leonard Holt - Seattle WA, US
Albert G. Greenberg - Seattle WA, US
Jin Li - Bellevue WA, US

Microsoft Corporation - Redmond WA

G06F 15/173, G06F 15/16

709224, 709239, 709219

A top level domain name system (DNS) server receives a DNS query from a local DNS resolver, the DNS query requesting a network address corresponding to a domain name. The top level DNS server reflects the local DNS resolver to a reflector DNS server. The reflector DNS server reflects the local DNS resolver to a collector DNS server, which in turn returns the network address to the local DNS resolver. The reflector DNS server and collector DNS server are both in the same data center, and one or more network performance measurements for communications between the local DNS resolver and the data center are determined based on the communications between the local DNS resolver and both the reflector DNS server and the collector DNS server.

8305271, Nov 6, 2012

Mar 17, 2010

12/725840

Jin Li - Bellevue WA, US
Aravind Krishnamachari Seshadri - Redmond WA, US

Microsoft Corporation - Redmond WA

G01S 1/08, G01S 3/02

342386, 342451

Storing and retrieving beacon reference data in a truncated cuckoo hash table. Checksums of beacon identifiers associated with beacons are used to retrieve beacon reference data describing locations of the beacons in a hash table. The data is stored in one or more hash tables by cuckoo hashing to eliminate aliasing. The hash tables are provided to devices such as mobile devices. The devices retrieve the beacon reference data from the tables based using beacon identifiers of observed beacons. Location information for the devices is inferred using the retrieved beacon reference data. The cuckoo hash tables consume less memory storage space and obfuscate the beacon reference data.

2013011, May 9, 2013

Nov 4, 2011

13/288968

Tin Qian - Bellevue WA, US
Jin Li - Bellevue WA, US
Tanner M. Hodgeson - Redmond WA, US
Sanjeev Mehrotra - Kirkland WA, US
Jiannan Zheng - Sammamish WA, US
Timothy M. Moore - Bellevue WA, US

MICROSOFT CORPORATION - Redmond WA

H04L 12/26

370252

It can be determined whether relative one way delay for data packets in a data stream exceeds a delay threshold. If so, then a delay congestion signal indicating that the relative one way delay exceeds the delay threshold can be generated. The delay congestion signal can be used in calculating an adaptive bandwidth estimate for the data stream. A packet loss rate congestion signal may also be used in calculating the bandwidth estimate. It can be determined whether a data stream of data packets is in a contention state. If the data stream is in the contention state, then an adaptive bandwidth estimate can be calculated for the data stream using a first bandwidth estimation technique. If the data stream is not in the contention state, then the bandwidth estimate for the data stream can be calculated using a second bandwidth estimation technique.