Emc IP Holding Company LLC

Other

Dell Products Inc.

Ems Ep Holding Company LLC

Anton Kucherov

David Meiri

Xiangping Chen

Felix Shvaiger

Zvi Schneider

Vladimir Shveidel

Ying Hu

Arieh Don

Svetlana Kronrod

Ronen Gazit

Philippe Armangau

Uri Shabi

Amitai Alkalay

Alexandr Veprinsky

Leron Fliess

Boaz Binia

Vamsi K Vankamamidi

William F Moore

Sorin Faibish

Junping Zhao

Vinay G Rao

Lior Kamran

Istvan Gonczi

Kirill Shoikhet

Vladimir Kleiner

Jehuda Shemer

Elie Antoun Jreij

William C Davenport

Ivan Bassov

Kevin Xu

William R Stronge

Gabriel Benhanokh

Ivan Basov

Philip C Love

Yuval Harduf

Oran Asher Baruch

Tal Ben-Moshe

Nimrod Shani

Leonid Ravich

Boris Glimcher

Kobi Luz

Xunce Zhou

Vasu Subramanian

David Krakov

Niko Farhi

Hillel Costeff

Gilad Braunschvig

Eli Dorfman

Amir Miron

Ophir Buchman

An apparatus includes at least one processing device comprising a processor coupled to a memory, with the processing device being configured to maintain a synchronous replication input-output (IO) request list having a plurality of entries corresponding to respective synchronous replication IO requests, a given such entry identifying at least a sender component and one or more address locks held by the corresponding synchronous replication IO request. The processing device is further configured to detect a failure of a particular one of a plurality of sender components, to access the synchronous replication IO request list to identify one or more address locks held by at least one synchronous replication IO request previously sent by the failed sender component, and to release one or more address lock waiters that are waiting to obtain the one or more identified address locks. Other embodiments include methods and computer program products.

Storage system with efficient release of address lock waiters during synchronous replication

An apparatus includes at least one processing device comprising a processor coupled to a memory, with the processing device being configured to maintain a synchronous replication input-output (IO) request list having a plurality of entries corresponding to respective synchronous replication IO requests, a given such entry identifying at least a sender component and one or more associated component resources to be released responsive to a failure of the sender component. The processing device is further configured to detect a failure of a particular one of a plurality of sender components, to access the synchronous replication IO request list to determine one or more associated component resources to be released, to release the one or more associated component resources, and to update the synchronous replication IO request list by marking the one or more associated component resources as released. Other embodiments include methods and computer program products.

Storage system with efficient release of failed component resources during synchronous replication

Rebalancing the workload of logical devices across multiple nodes may include dynamically modifying preferred paths for one or more logical devices in order to rebalance the I/O workload of the logical devices among the nodes of the data storage system. Determining whether to rebalance the I/O workload between the two nodes may be performed in accordance with one or more criteria. Processing may include monitoring the current workloads of both nodes over time and periodically evaluating, in accordance with the one or more criteria, whether the current workloads of the nodes are imbalanced. Responsive to determining, in accordance with the criteria, that rebalancing of workload between the nodes is needed, the rebalancing may be performed. A notification may be sent to the host regarding any path state changes made as a result of the workload rebalancing.

Techniques for workload balancing using dynamic path state modifications

A method, computer program product, and computer system for obtaining, by a computing device, one or more pages from a log to complete a write transaction. Parity of a line in a multi-line physical layer block may be calculated. The one or more pages may be written to the line in the multi-line physical layer block. The parity to the line may be written in the multi-line physical layer block. A bitmap associated with the physical layer block may be updated based upon, at least in part, writing the one or more pages and the parity to the line in the multi-line physical layer block.

System and method for early tail-release in a log structure log using multi-line PLB structure supporting multiple partial transactions

A method is used in host-based caching. A host receives a request for data, and identifies a host in a plurality of hosts that owns the data.

Method and system for host-based caching

A method is used in issuing alerts for storage volumes using machine learning. A machine learning system analyzes Input/Output (I/O) data of a storage volume in a data storage system. The machine learning system is trained with sample I/O data patterns associated with the storage volume. Based on the I/O data, the machine learning system identifies atypical behavior associated with I/O data patterns of the I/O data. The method then issues an alert.

Issuing alerts for storage volumes using machine learning

An apparatus in one embodiment comprises at least one processing device comprising a processor coupled to a memory. The processing device is configured to identify a dataset to be scanned to generate a compression estimate for that dataset, to designate a scan criterion to be utilized in the scan, and for each of a plurality of pages of the dataset, to scan the page, where scanning the page includes performing a computation on the page to obtain a page result, determining whether or not the page result satisfies the designated scan criterion, and responsive to the page result satisfying the designated scan criterion, updating a corresponding entry of a compression estimate table for the dataset. The processing device generates the compression estimate for the dataset based at least in part on contents of the compression estimate table. The scan criterion may comprise, for example, a designated content-based signature prefix, or a designated subset inclusion characteristic defining a polynomial-based signature subspace.

Processing device configured for efficient generation of compression estimates for datasets

An apparatus in one embodiment comprises at least one processing device comprising a processor coupled to a memory. The processing device is configured to identify at least first and second datasets to be scanned to generate a data reduction estimate for a prospective combination of the first and second datasets, to designate a scan criterion to be utilized in the scan of each of the datasets, and for each of a plurality of pages of each of the datasets, to scan the page, where scanning the page comprises performing a computation on the page to obtain a page result, determining whether or not the page result satisfies the designated scan criterion, and responsive to the page result satisfying the designated scan criterion, updating a corresponding entry of a data reduction estimate table for the dataset. The processing device merges contents of the data reduction estimate tables, and generates the data reduction estimate based at least in part on the merged contents.

Processing device configured for efficient generation of data reduction estimates for combinations of datasets

Techniques for processing data may include: receiving a data block stored in a data set, wherein a hash value is derived from the data block; determining, in accordance with selection criteria, whether the hash value is included in a subset; responsive to determining the hash value is included in the subset, performing processing that updates a table in accordance with the hash value and the data set, and determining, in accordance with the information in the table, whether to perform deduplication processing for the data block to determine whether the data block is a duplicate of another stored data block. The table may include an entry for the hash value. The entry may include information identifying data sets referencing the data block and, for each of the data sets, may specify a reference count denoting a number of times the data set references the data block.

Techniques for data deduplication

A storage system comprises a plurality of storage nodes each comprising one or more storage devices and a processor coupled to a memory. The storage system is configured to store data blocks across the storage devices of the storage nodes utilizing a redundant array of independent disks (RAID) arrangement. At least a given one of the storage nodes is configured to store a plurality of RAID metadata bitmaps in persistent storage of the storage node so as to be available for a recovery operation in the event of a detected failure, to identify a particular subset of the RAID metadata bitmaps to be updated in conjunction with an additional operation other than the recovery operation, and to temporarily store the identified subset of the RAID metadata bitmaps in the memory of the storage node in a manner determined based at least in part on an operation type of the additional operation.

Memory-efficient processing of RAID metadata bitmaps

Techniques are provided for application tracing for inline performance analysis. One method comprises obtaining trace events generated by instructions executed in response to trace points in instrumented software; updating, for each trace event, a buffer entry of a sampling buffer that corresponds to a particular processing core and a time window, wherein the buffer entry is identified based on (a) a flow type identifier associated with the instructions, (b) an identifier of a respective trace event, and (c) an identifier of an adjacent trace event to the respective trace event, and wherein the updating comprises updating, for the time window: (i) a first counter indicating a cumulative number of events for the respective and adjacent trace events, and (ii) a second counter indicating a cumulative amount of time between the respective and adjacent trace events; and determining one or more performance metrics associated with the respective and adjacent trace events in the time window using the first and second counters.

Application execution path tracing for inline performance analysis

Host I/O requests directed to a logical storage volume are initially processed by accessing physical pages of non-volatile data storage having a default page size. An indication of an optimal page size for the logical storage volume is received, and the size of the physical pages of non-volatile data storage accessed to process host I/O requests directed to the logical storage volume is changed from the default page size to the optimal page size for the logical storage volume. The default page size is changed to the optimal page size for the logical storage volume by changing a size of physical pages of non-volatile data storage indicated by a mapping structure that maps logical addresses in an address space the logical storage volume to corresponding physical pages of non-volatile data storage from the default page size to the optimal page size for the logical storage volume.

Changing page size in an address-based data storage system

A storage system in one embodiment comprises multiple storage nodes each comprising at least one storage device. Each of the storage nodes further comprises a set of processing modules configured to communicate over one or more networks with corresponding sets of processing modules on other ones of the storage nodes. The sets of processing modules of the storage nodes each comprise at least one control module. The storage system is configured to assign portions of a logical address space of the storage system to respective ones of the control modules, to receive a plurality of tracks of data records in a count-key-data format, and to store the tracks in respective ones of the portions of the logical address space assigned to respective ones of the control modules. Each of the tracks is stored in its entirety in the portion of the logical address space assigned to a corresponding one of the control modules.

Clustered storage system with stateless inter-module communication for processing of count-key-data tracks

A storage system in one embodiment comprises a plurality of storage devices and a storage controller. The storage system is configured by the storage controller to receive a plurality of data records in a count-key-data format, to separate count and key portions of the data records from remaining portions of the data records, to store the count and key portions of the data records in at least one designated page of a set of pages of a logical storage volume of the storage system, and to store the remaining portions of the data records in one or more other pages of the set of pages of the logical storage volume of the storage system. The designated page of the set of pages of the logical storage volume may comprise a first page of the set of pages, and the one or more other pages of the set of pages may comprise respective ones of a sequence of consecutive pages following the first page.

Content addressable storage system configured for efficient storage of count-key-data tracks

Growing community of inventors

Dudley, MA, United States of America

Anton Kucherov