Emc IP Holding Company LLC

Emc IP Holding Corporation LLC

Rahul Ugale

Satish Visvanathan

Colin Yong Zou

Mahesh Kamat

Krishna Chaitanya Gudipati

Anil Ravindranath

Yong Colin Zou

Satish Kumar Kashi Visvanathan

Tao Chen

Wei Lin

Yujuan Li

Yamini Allu

Ganesh Karuppur Rajagopalan

Dheer Moghe

Shuang Liang

Akshay Narayan Muramatti

Yong Zou

Vrushali A Kulkarni

Ganesh Rajagopalan

Shuai Hua

Wenhao Hu

Satish Kumar Kashi Viswanathan

A memory tier including persistent memory (PMEM) devices is established in nodes of a cluster system having a deduplicated file system. At least a portion of metadata generated by the deduplicated file system is persisted to the memory tier. The portion of metadata includes an index of fingerprints corresponding to data segments stored by the deduplicated file system to a storage pool. A determination is made that an instance of the deduplicated file system has failed. A new instance of the deduplicated file system is started to recover file system services by loading the index of fingerprints from the memory tier.

Persistent memory tiering supporting fast failover in a deduplicated file system

A memory tier is established in a cluster system having a deduplicated file system. The memory tier includes memory pages configured as huge pages, where writes to the huge pages are exported in a device file that is outside of a user process namespace within which processes of the deduplicated file system run. At least a portion of metadata generated by the deduplicated file system is written to the memory tier. The portion of metadata includes an index of fingerprints corresponding to data segments stored by the deduplicated file system to a storage pool. A determination is made that an instance of the deduplicated file system has failed. A new instance of the deduplicated file system is started to recover file system services by loading the index of fingerprints from the device file.

Fast failover of a deduplicated file system through huge memory pages

System identifies multiple data blocks in workload stored in slow access persistent storage, data blocks copied to fast access persistent storage, and, after speed of accessing workload satisfies threshold, copied data blocks that remained in fast access persistent storage. System annotates some remaining data blocks with cache label and derives features for some data blocks in workload, based on corresponding bits set and/or time stamp. System uses cache labels and features for some data blocks in workload to train machine-learning model to predict which data blocks in workload will remain in fast access persistent storage after workload access satisfies threshold. System derives features for data block requested from production workload. System copies requested data block to production fast access persistent storage if trained machine-learning model uses features for requested data block to predict requested data block will remain in production fast access persistent storage after production workload access satisfies threshold.

Intelligent cache warm-up on data protection systems

Embodiments are described for prioritizing input/output (I/O) operations dispatched from a storage media to a host bus adapter in a network, by tagging, in an I/O tagging module, the I/O operations in a file system supporting applications generating the I/O operations, wherein all child I/O operations initiated from a parent I/O operation are tagged with a same unique tag ID; tracking a time of arrival of each I/O operation of the I/O operations; and dispatching, in a transactional I/O scheduler, all sibling I/O's of the parent I/O operation based on a unique tag ID for the sibling I/Os, a respective time of arrival of each of the sibling I/Os, and defined quality of service (QoS) requirements.

Achieving storage system performance guarantees by applying transactional I/O scheduling

One embodiment provides a computer implemented method of data compression including segmenting user data into data segments; deduplicating the data segments to form deduped data segments; compressing the deduped data segments into compression units using a hardware accelerator; packing the compression units into compression regions; and packing the compression regions into one or more containers.

System and method for increasing logical space for native backup appliance

One embodiment provides a computer implemented method of balancing mixed workload performance including monitoring the compression and decompression workload at a hardware accelerator using the hardware accelerator quality of service (QoS) scheduler; monitoring the compression and decompression workload at a CPU using the CPU QoS scheduler; comparing the workload at the hardware accelerator and the workload at the CPU; and allocating tasks between the hardware accelerator and the CPU to obtain an optimal bandwidth at the hardware accelerator and the CPU.

System and method of balancing mixed workload performance

Embodiments are described for prioritizing input/output (I/O) operations dispatched to a solid-state device (SSD) cache in a network, by defining a maximum write I/O operation size for writing data to the SSD cache, splitting large write I/O operations into smaller write I/O operations, each with a size less than the maximum write I/O operation size, interleaving cache read I/O operations in between the smaller write I/O operations, and performing the cache read I/O operations and the smaller write I/O operations in an order created by the interleaving. The network may comprise a deduplication backup system storing data to storage media including the SSD cache.

Achieving guaranteed application performance using transactional I/O scheduling for SSD storage by interleaving and splitting read/write I/Os with required latency configurations

A method, apparatus, and system for decompressing data with a hardware compression/decompression accelerator is disclosed. The operations comprise: submitting compressed data from a plurality of stored compression units in a compression region to a hardware compression/decompression accelerator in a single submission for decompression, wherein each compression unit stores a checksum calculated based on corresponding uncompressed data; decompressing, at the hardware compression/decompression accelerator, the compressed data from the plurality of stored compression units, the decompressing generating combined decompressed data corresponding to the compressed data; calculating, at the hardware compression/decompression accelerator, a first combined checksum based on the combined decompressed data; calculating a second combined checksum based on individual checksums stored in the plurality of compression units; determining whether the first combined checksum matches the second combined checksum; and if the combined checksums match, forwarding the combined decompressed data to a storage device for storage as uncompressed data.

Approach to improve decompression performance by scatter gather compression units and also updating checksum mechanism

Embodiments are described for prioritizing input/output (I/O) operations dispatched to a solid-state device (SSD) storage in a network, determining properties of the SSD storage based on SSD device type, where the SSD storage maintains a plurality of caches, receiving a plurality of SSD I/Os from an application I/O request comprising at least one of a cache read or a cache write operation, creating a respective queue for each SSD I/O of the SSD I/Os based on a type of SSD I/O, prioritizing the each SSD I/O based on the type of the SSD I/O and the properties of the SSD storage that is the target for a respective SSD I/O, and dispatching, in a transactional I/O SSD scheduler, all queued SSD I/Os to the SSD storage based on the prioritizing.

Achieving guaranteed application performance using transactional I/O scheduling for SSD storage using known read/write latencies

A method, apparatus, and system for handling a failure of a hardware cryptography/compression accelerator is disclosed. The operations comprise: detecting that a hardware cryptography/compression accelerator at a first data storage system has failed; determining one or more failed cryptography and/or compression operation tasks that were submitted to the hardware cryptography/compression accelerator but were not completed due to the failure of the hardware cryptography/compression accelerator; and performing a remedial operation in response to the hardware cryptography/compression accelerator failure to prevent a systemic failure.

Method for gracefully handling QAT hardware or CPU software failures by dynamically switching between QAT hardware and CPU software for data compression and decompression

A method, article of manufacture, and apparatus for creating a fingerprint to container id index is discussed. The index may be stored in-memory, on disk, and on a solid-state device. The index may be used to quickly locate a container identifier given a data segment fingerprint.

Solid state cache index for a deduplicate storage system

One embodiment provides a computer implemented method of dynamically allocating compression jobs including monitoring compression performance at a plurality of compression levels within a hardware accelerator; comparing compression performance between the plurality of compression levels; and dynamically allocating compression jobs between the plurality of compression levels to achieve a guaranteed average performance.

System and method of dynamically allocating compression jobs

According to some embodiments, a backup storage system receives a request from a client to access a data segment. The system looks up an in-memory index for a first entry based on a fingerprint of the data segment, such that the in-memory index includes a number of entries, each entry mapping a fingerprint to a storage location of a solid state device (SSD) storing a corresponding data segment. In the event a first entry is found, the system retrieves the data segment from the SSD device based on the first entry. In the event of a read failure while accessing the SSD device, the system determines failed data blocks of the SSD device associated with the failure event and invalidates the failed data blocks of the SSD device such that subsequent access to the failed data blocks are denied without having to access a corresponding SSD device.

Method and system for accessing data stored in data cache with fault tolerance

According to some embodiment, a backup storage system receives a request from a client to read a data segment associated with a file object stored in a storage system. In response to the request, the system performs a lookup operation in a first index stored in a memory to identify a first index entry based on a fingerprint of the requested data segment to obtain a first write-evict unit (WEU) identifier (ID) identifying a first WEU storing the requested data segment. The system accesses a solid state device (SSD) operating as a cache memory device to retrieve the data segment from the first WEU. The system extracts and decompresses a compressed data segment retrieved from the first WEU and returns the decompressed data segment to the client without accessing a storage unit for retrieving the same data segment.

Accessing deduplicated data from write-evict units in solid-state memory cache

One embodiment provides a computer implemented method of data compression using a hardware accelerator. A first thread pool for compression jobs, and a first polling thread is allocated for polling the status of a hardware accelerator. A compression thread is retrieved from the first thread pool in response to a compression request from a file system. Multiple source data buffers from the file system are aggregated into a compression unit, and a scatter gather list and destination buffer are submitted to the hardware accelerator. A checksum of result data is calculated from the destination buffer. A zlib header is added to the result data, and the checksum is added as a zlib footer to the result data.

Growing community of inventors

Santa Clara, CA, United States of America

Rahul Ugale