Cisco Technology, Inc.

Johnu George

Debojyoti Dutta

Amit Kumar Saha

Kai Zhang

Marc Solanas Tarre

Yathiraj B Udupi

Ralf Rantzau

Madhu S Kumar

Xinyuan Huang

Arun Saha

Manoj Sharma

Komei Shimamura

Purushotham Kamath

Sourav Chakraborty

Aparupa Das Gupta

Seth Mason

Amit Agarwal

Ramdoot Kumar Pydipaty

Adhita Selvaraj

Aspects of the subject technology relate to ways to determine the optimal storage of data structures in a hierarchy of memory types. In some aspects, a process of the technology can include steps for identifying a retrieval cost associated with retrieving a field in an object from data storage, comparing the retrieval cost for the field to a cost threshold for storing data in persistent memory, and selectively storing the field in either a persistent memory device or a non-persistent memory device based on a comparison of the retrieval cost for the field to the cost threshold. Systems and machine-readable media are also provided.

Intelligent layout of composite data structures in tiered storage with persistent memory

Systems, methods, and computer-readable media for managing storing of data in a data storage system using a client tag. In some examples, a first portion of a data load as part of a transaction and a client identifier that uniquely identifies a client is received from the client at a data storage system. The transaction can be tagged with a client tag including the client identifier and the first portion of the data load can be stored in storage at the data storage system. A first log entry including the client tag is added to a data storage log in response to storing the first portion of the data load in the storage. The first log entry is then written from the data storage log to a persistent storage log in persistent memory which is used to track progress of storing the data load in the storage.

Using persistent memory to enable restartability of bulk load transactions in cloud databases

A method can include receiving, at a workflow controller, a machine learning workflow, the machine learning workflow associated with a first task and a second task. The first task is training a machine learning model and the second task is deploying the model. The method can include segmenting, by the workflow controller, the machine learning workflow into a first sub-workflow associated with the first task and a second sub-workflow associated with the second task, assigning a first workflow agent to the first sub-workflow and assigning a second workflow agent to the second sub-workflow, selecting, by the first workflow agent and based on first resources needed to perform the first task, a first cluster for performing the first task and selecting, by the second workflow agent and based on second resources needed to perform the second task, a second cluster for performing the second task.

Systems and methods for providing management of machine learning components

A method for accelerating data operations across a plurality of nodes of one or more clusters of a distributed computing environment. Rack awareness information characterizing the plurality of nodes is retrieved and a non-volatile memory (NVM) capability of each node is determined. A write operation is received at a management node of the plurality of nodes and one or more of the rack awareness information and the NVM capability of the plurality of nodes are analyzed to select one or more nodes to receive at least a portion of the write operation, wherein at least one of the selected nodes has an NVM capability. A multicast group for the write operation is then generated wherein the selected nodes are subscribers of the multicast group, and the multicast group is used to perform hardware accelerated read or write operations at one or more of the selected nodes.

Accelerating data replication using multicast and non-volatile memory enabled nodes

Embodiments include receiving an indication of a data storage module to be associated with a tenant of a distributed storage system, allocating a partition of a disk for data of the tenant, creating a first association between the data storage module and the disk partition, creating a second association between the data storage module and the tenant, and creating rules for the data storage module based on one or more policies configured for the tenant. Embodiments further include receiving an indication of a type of subscription model selected for the tenant, and selecting the disk partition to be allocated based, at least in part, on the subscription model selected for the tenant. More specific embodiments include generating a storage map indicating the first association between the data storage module and the disk partition and indicating the second association between the data storage module and the tenant.

Tenant-level sharding of disks with tenant-specific storage modules to enable policies per tenant in a distributed storage system

Aspects of the technology provide improvements to a Serverless Computing (SLC) workflow by determining when and how to optimize SLC jobs for computing in a Distributed Computing Framework (DCF). DCF optimization can be performed by abstracting SLC tasks into different workflow configurations to determined optimal arrangements for execution in a DCF environment. A process of the technology can include steps for receiving an SLC job including one or more SLC tasks, executing one or more of the tasks to determine a latency metric and a throughput metric for the SLC tasks, and determining if the SLC tasks should be converted to a Distributed Computing Framework (DCF) format based on the latency metric and the throughput metric. Systems and machine-readable media are also provided.

Optimizing serverless computing using a distributed computing framework

Systems, methods, and computer-readable storage media are provided for storing machine learned models in a tiered storage. The model serving network evaluates where the models should be stored based on the model corresponding service level agreement. The model is generally stored at the lowest tiered storage device that is still capable of satisfying the model's service level agreement. In this way, the model serving network aims to store data that achieves the cheapest cost.

Using tiered storage and ISTIO to satisfy SLA in model serving and updates

Aspects of the disclosed technology relate to ways to determine the optimal storage of data structures across different memory device is associated with physically disparate network nodes. In some aspects, a process of the technology can include steps for receiving a first retrieval request for a first object, searching a local PMEM device for the first object based on the first retrieval request, in response to a failure to find the first object on the local PMEM device, transmitting a second retrieval request to a remote node, wherein the second retrieval request is configured to cause the remote node to retrieve the first object from a remote PMEM device. Systems and machine-readable media are also provided.

Accessing composite data structures in tiered storage across network nodes

Aspects of the subject technology relate to ways to determine the optimal storage of data structures in a hierarchy of memory types. In some aspects, a process of the technology can include steps for determining a latency cost for each of a plurality of fields in an object, identifying at least one field having a latency cost that exceeds a predetermined threshold, and determining whether to store the at least one field to a first memory device or a second memory device based on the latency cost. Systems and machine-readable media are also provided.

Intelligent layout of composite data structures in tiered storage

Systems, methods, and computer-readable media for storing data in a data storage system using a child table. In some examples, a trickle update to first data in a parent table is received at a data storage system storing the first data in the parent table. A child table storing second data can be created in persistent memory for the parent table. Subsequently the trickle update can be stored in the child table as part of the second data stored in the child table. The second data including the trickle update stored in the child table can be used to satisfy, at least in part, one or more data queries for the parent table using the child table.

Efficient trickle updates in large databases using persistent memory

Systems, methods, and computer-readable media are provided for consistent data to be used for streaming and batch processing. The system includes one or more devices; a processor coupled to the one or more devices; and a non-volatile memory coupled to the processor and the one or more devices, wherein the non-volatile memory stores instructions that are configured to cause the processor to perform operations including receiving data from the one or more devices; validating the data to yield validated data; storing the validated data in a database on the non-volatile memory, the validated data being used for streaming processing and batch processing; and sending the validated data to a remote disk for batch processing.

Using persistent memory to enable consistent data for batch processing and streaming processing

Approaches are disclosed for improving performance of logical disks. A logical disk can comprise several storage devices. In an object storage system (OSS), when a logical disk stores a file, fragments of the file are stored distributed across the storage devices. Each of the fragments of the file is asymmetrically stored in (write) and retrieved from (read) the storage devices. The performance of the logical disk is improved by reconfiguring one or more of the storage devices based on an influence that each of the storage devices has on performance of the logical disk and the asymmetric read and write operations of each of the storage devices. For example, latency of the logical disk can be reduced by reconfiguring one or more of the plurality of storage disks based on a proportion of the latency of the logical device that is attributable to each of the plurality of storage devices.

Performance of object storage system by reconfiguring storage devices based on latency that includes identifying a number of fragments that has a particular storage device as its primary storage device and another number of fragments that has said particular storage device as its replica storage device

Growing community of inventors

San Jose, CA, United States of America

Johnu George