Sandisk Corporation

Quantum Corporation

Sandisk Technologies Inc.

Bryan John Mee

Stephen Jeffrey Gross

Alan David Bennett

Clifford M Gold

Yosief Ataklti

William N Thanos

David B Jeppson

Trinh C Bui

Hoa V Luong

Hang Diem Nguyen

Norman H Wulferdinger

Joseph C Liu

Minnie Uppuluri

George Li

Steve Paul

A portion of a nonvolatile memory array that is likely to contain, partially programmed data may be identified from a high sensitivity read, by applying stricter than usual ECC requirements, or using pointers to programmed sectors. The last programmed data may be treated as likely to be partially programmed data. Data in the identified portion may be copied to another location, or left where it is with an indicator to prohibit further programming to the same cells. To avoid compromising previously stored data during subsequent programming, previously stored data may be backed up. Backing up may be done selectively, for example, only for nonsequential data, or only when the previously stored data contains an earlier version of data being programmed. If a backup copy already exists, another backup copy is not created. Sequential commands are treated as a single command if received within a predetermined time period.

Data protection after possible write abort or erase abort

A portion of data stored in a non-volatile memory may be found to be corrupted when it is read. Where parity data is generated from portions of data and the parity data is stored with the portions of data, the corrupted data may be reconstructed from the parity data and uncorrupted portions of data.

Method of storing downloadable firmware on bulk media

A portion of data stored in a non-volatile memory may be found to be corrupted when it is read. Where parity data is generated from portions of data and parity data is stored with the portions of data, the corrupted data may be reconstructed from the parity data and uncorrupted portions of data.

Storing downloadable firmware on bulk media

A method of coordinating access to a data buffer including a plurality of data blocks, using a buffer list with a plurality of entries corresponding to the data blocks. Each buffer list entry includes: (i) a status code for indicating the status of data in the corresponding data block, and (ii) a partial address common to both the next buffer list entry and a data block corresponding to said next buffer list entry. A status code is selected from a cyclical set of sequential status codes having a period of N, the status codes sequentially, and alternately, representing the most recent history of a data block, including: (i) full status, indicating data in the data block has been retrieved from the storage device or is to be stored to the storage device, or (ii) empty status, indicating data transferred out of the data block to a host or to the storage device. A store flag maintains a status code representing empty status, and a retrieve flag maintains a status code representing full status. When storing data into the data buffer, locating a desired buffer list entry list with an empty status code by traversing the buffer list, calculating the address of each entry using the partial address in the previous entry, until the desired entry is found. The address of the data block corresponding to the found entry is calculated and data is stored in the data block when the status code of the entry matches the store flag status code. The found entry status code is advanced once, and if the entry is last in the buffer list the store flag status code is advanced twice. Similarly, when retrieving data from the data buffer, locating a desired entry in the buffer list with a full status code by traversing the buffer list, calculating the address of each entry using the partial address in the previous entry, until the desired entry is found. The address of the data block corresponding to the found entry is calculated and data is retrieved from the data block when the status code of the entry matches the retrieve flag status code. The found entry status code is advanced once, and if the entry is last in the buffer list the retrieve flag status code is advanced twice.

Buffer management and system coordination method

A method is provided for allocating digital processing activities of an embedded microcontroller within a disk drive between repetitive periodic digital servo loop service routines synchronized to rotation of a data storage disk of the drive and irregularly occurring host service routines supporting a high level, digital interface to a host computing environment. The new method comprises the steps of:

Servo pause for disk drive embedded multi-tasked controller

Growing community of inventors

San Jose, CA, United States of America

Bryan John Mee