Emc IP Holding Company LLC

Emc Corporation

Other

Seachange International, Inc.

William C Davenport

Jean-Pierre Bono

Philippe Armangau

Miles Aram De Forest

Walter Forrester

Ye Zhang

Yingchao Zhou

Himabindu Tummala

Michal Marko

Sairam Veeraswamy

Socheavy D Heng

Morgan A Clark

Qi Mao

Xiangping Chen

Sitaram D Pawar

Ivan Basov

Peter Puhov

Richard P Ruef

Karl M Owen

Rohit K Chawla

Alexander S Mathews

Yining Si

Srinivasa Rao Vempati

Michael Scheer

Jia Zhai

Vamsi K Vankamamidi

Alan Lee Taylor

Dennis Thomas Duprey

Xiaoye Jiang

Christopher Alan Seibel

Daniel E Cummins

Nagapraveen Veeravenkata Seela

Chao Zheng

Yubing Wang

Michael C Brundage

Joris Johannes Wils

Yaming Kuang

Marc DeSouter

Xunce Zhou

Diane Delgado

Dixit Patel

Yunfei Chen

Michael D Schouten

Alexander Daniel

Marshall Hansi Wu

Kumar Kanteti

James O Owens

Assaf Natanzon

Anton Kucherov

Junping Zhao

Ahsan Rashid

Marc A De Souter

Jun Guo

Lili Chen

Frederic Corniquet

Girish Sheelvant

Dixitkumar Vishnubhai Patel

Xianlong Liu

Alexei Karaban

Kamakshi Viswanadha

Steve Morley

Changyong Yu

Henry Hao Fang

Wengang Wang

Piers Yu

Alex Zhongbing Yang

John H Lee

Pu Wang

Li Wan

Lawrence Yetto

Changxin Liu

Xiaoqin Chen

Paul Hao Pan

George Danforth McNair, Jr

Haijia Shen

Techniques for performing processing to recover metadata may include: shadow top structures, and performing processing that uses the shadow top structures to recover information for an index node associated with an object of a file system having a file system logical address space. One of the shadow top structures is created for each metadata (MD) top node of a MD mapping structure used to determine storage locations of data stored at corresponding logical addresses in the file system logical address space. Each MD top node is used in determining storage locations for a specified subrange of logical addresses of the file system logical address space. Each shadow top structure corresponding to a MD top node describes each file system object mapped to a logical address included in the specified subrange of logical addresses of the file system address space associated with the corresponding MD top node.

Techniques for duplicating inode state to prevent loss of inode metadata

A method performed by a data storage apparatus of maintaining filesystem object attributes in connection with a plurality of drivers is provided. Each driver of the plurality is configured to operate on a respective set of filesystem objects. The method includes (a) for each driver of the plurality, creating a respective driver-specific storage volume; (b) storing, within each driver-specific storage volume, attributes specific to respective filesystem objects operated on by the driver of that driver-specific storage volume; and (c) while operating a particular driver of the plurality on a particular filesystem object, using values of the stored attributes specific to that particular filesystem object operated on by that particular driver. An apparatus, system, and computer program product for performing a similar method are also provided.

Per-service storage of attributes

A method, computer program product, and computer system for setting a preferred alignment value to a size of an address space mapped by one or more root pages. An allocation request may be received for the address space. A binary buddy allocation scheme may be executed to allocate an extent for the allocation request based upon, at least in part, the preferred alignment value.

System and method for reduced lock contention and improved performance

A method, computer program product, and computer system for organizing a plurality of log records into a plurality of buckets, wherein each bucket is associated with a range of a plurality of ranges within a backing store. A bucket of the plurality of buckets from which a portion of the log records of the plurality of log records are to be flushed may be selected. The portion of the log records may be organized into parallel flush jobs. The portion of the log records may be flushed to the backing store in parallel.

System and method for parallel flushing with bucketized data

Successful storing of extent operations into corresponding records of a transaction log results in acknowledgement of completion of the extent operations being indicated to one or more hosts. In response to determining that the extent operations are unrelated to each other, the extent operations are flushed in parallel from the transaction log to back-end non-volatile data storage. During the flushing, dependencies between the extent operations and other operations stored in the transaction log are maintained. Dependency chains are identified within the transaction log, and at least one tree data structure representing the dependencies between each of the extent operations and the other operations stored in the transaction log may be generated and traversed in order to select the correct operations stored in the transaction log to flush.

Extent operation processing

A method, computer program product, and computer system for receiving, at a computing device, a write request from a host, wherein a first portion of a process may receive the write request. A callback and context may be set in the write request by the first portion of the process. The write request may be passed to a second portion of the process. The first process may be provided with the context. The first process may use the context to replicate the write request data to a destination.

System and method for synchronous replication write handling

Techniques for providing a direct IO path to compressed data on storage media of a storage system. The techniques include triggering a transaction cache to perform a flush operation for updating mapping metadata for a storage object containing the compressed data. Having updated the mapping metadata for the storage object, the techniques further include issuing, by a copier module, an IO read request for the compressed data of the storage object to a namespace layer, which issues the IO read request to a mapping layer. The techniques further include forwarding the IO read request to a logical layer of the mapping layer, bypassing the transaction cache. The techniques further include reading, by the logical layer, the compressed data of the storage object from the storage media, and providing, via the mapping layer and the namespace layer, the compressed data to the copier module for transfer to a destination storage system.

Direct input/output path to compressed data

Techniques for creating snapshots of data storage objects that can perform certain operations (e.g., flushing dirty data, setting up extent pointers, allocating block storage space, etc.) during background (or deferred) processing. The disclosed techniques employ one or more extent copy trackers that can be created during processing of a transaction, while I/O request from host computers are suspended. The extent copy trackers are configured to perform some or all of the certain operations in the background, after the transaction has been committed and/or the processing of the transaction has been completed. By performing such operations during background processing, a processing time required to complete the snapshot transaction is reduced, thereby reducing latency in the resumption of the I/O requests from the host computers.

Fast object snapshot via background processing

A data storage system operates a file system as a thinly provisioned file system having a host-visible virtual space and a smaller allocated space of underlying physical storage from a pool. The file system applies formatting to the allocated space and utilizes formatted allocated space for storing host files. The file system receives a file I/O request that requires increasing the allocated space of the file system, and in response (1) obtains an extent of physical storage from the pool and adds it to the file system as added allocated space, and (2) formats an initial portion of the added allocated space and satisfies the file I/O request using the formatted initial portion. Over a subsequent period the file system incrementally formats additional portions of the added allocated space and satisfies subsequent file I/O requests from the added portions.

Dense file reservation in thinly provisioned file system

A method, computer program product, and computer system for staging writes into a log in chronological order, wherein each write may have a log record of a plurality of log records describing data of the write. The log record may be organized into a bucket of a plurality of buckets associated with a range of a plurality of ranges within a backing store, wherein each bucket of the plurality of buckets may include two keys respectively. The log record of the plurality of log records may be flushed from the bucket of the plurality of buckets to the backing store at a location and in an order determined based upon, at least in part, the two keys included with the bucket.

System and method for balance localization and priority of pages to flush in a sequential log

A technique for replicating a data object from a source data storage system (source) to a destination data storage system (destination) preserves QoS (Quality of Service) by transmitting QoS information from the source to the destination and applying the QoS information when storing data at the destination that arrive in replication instructions sent from the source. The QoS information indicates desired storage tiering for the data object at the source. In the event of a failure at the source, which results in failover from the source to the destination, the destination is able to provide users with the same quality of service as was desired at the source.

Preserving quality of service when replicating data objects

Techniques for handling pattern identifiers in a data storage system. By replacing a block pointer with a pattern identifier, the techniques can identify a data block (or an indirect data block) as a bad block, without resorting to the use of a separate flag or bad block (BB) bit in per-block metadata (e.g., a mapping pointer) of the data block. The techniques can also avoid waste of valuable metadata space by using pattern identifiers at various levels of a mapping tree, leveraging pointer granularity at lower levels, mid-levels, and progressively higher levels of the mapping tree.

Handling pattern identifiers in a data storage system

Techniques for processing I/O operations include: receiving a write I/O operation that writes first data to a target location, wherein the target location is represented as a logical device and offset within a logical address space of the logical device; storing a log record for the write I/O operation in a log file; and performing first processing of the log record. The log record includes log data, comprising the first data, and a log descriptor. The log descriptor includes a target logical address for the target location in a file system logical address space. The log descriptor includes a first value denoting the binary logarithm of an extent size of the first logical device. The first processing includes flushing the log record from the log file to store the first data of the log record on an extent of physical storage provisioned for the logical device.

Techniques for reducing size of log records

In response to detecting that at least one snapshot group identifier has been allocated that has a maximum snapshot group identifier value, snapshot group identifiers are allocated to each newly created snapshot group by finding a previously allocated snapshot group identifier that is currently unused, and allocating the previously allocated snapshot group identifier that is currently unused to the newly created snapshot group.

Allocating snapshot group identifiers

A separate family space is provisioned as a separate fault domain for each production device in a storage system. The space provisioned for each family has contiguous logical block addresses that do not overlap with the address space of any other family. Snaps and clones in a first family space are used for fault recovery without interrupting IOs to a second family space. If the first family space points to the same virtual block as other families as a result of deduplication then the virtual block is un-deduped. For example, another instance of the virtual block may be created and pointers updated such that only the first family space points to one of the virtual block instances.

Reducing the size of fault domains

Growing community of inventors

Burlington, MA, United States of America

William C Davenport