-
公开(公告)号：US10771584B2
公开(公告)日：2020-09-08
申请号：US15827969
申请日：2017-11-30
Applicant: Cisco Technology, Inc.
Inventor： Komei Shimamura , Amit Kumar Saha , Debojyoti Dutta
Abstract: A method for data provisioning a serverless computing cluster. A plurality of user defined functions (UDFs) are received for execution on worker nodes of the serverless computing cluster. For a first UDF, one or more data locations of UDF data needed to execute the first UDF are determined. At a master node of the serverless computing cluster, a plurality of worker node tickets are received, each ticket indicating a resource availability of a corresponding worker node. The one or more data locations and the plurality of worker node tickets are analyzed to determine eligible worker nodes capable of executing the first UDF. The master node transmits a pre-fetch command to one or more of the eligible worker nodes, causing the eligible worker nodes to become a provisioned worker node for the first UDF by storing a pre-fetched first UDF data before the first UDF is assigned for execution.
-
公开(公告)号：US10545823B2
公开(公告)日：2020-01-28
申请号：US15783281
申请日：2017-10-13
Applicant: Cisco Technology, Inc.
Inventor： Ramdoot Kumar Pydipaty , Amit Kumar Saha
Abstract: The present disclosure involves systems and methods for managing data in a distributed storage system. The distributed storage system may include non-volatile memory (NVM) storage devices and utilize erasure code replication for storage of data. A controller may first store at least some of the K data chunks in NVM devices before storing the coding chunks in other storage devices. In addition, the controller may transmit read requests to the NVM devices of the system first to begin receiving data chunks or coding chunks related to the data object. By writing to and reading from NVM devices first, storage and reading of the data object may occur faster than conventional storage systems.
-
公开(公告)号：US20190208011A1
公开(公告)日：2019-07-04
申请号：US15856716
申请日：2017-12-28
Applicant: Cisco Technology, Inc.
Inventor： Debojyoti Dutta , Amit Kumar Saha , Johnu George , Ramdoot Kumar Pydipaty , Marc Solanas Tarre
CPC classification number: H04L67/1095 , G06F3/065 , G06F3/0683 , G06F11/1464 , G06F16/22
Abstract: 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.
-
4.发明申请公开(公告)号：US20190197146A1
公开(公告)日：2019-06-27
申请号：US15850168
申请日：2017-12-21
Applicant: Cisco Technology, Inc.
Inventor： Johnu George , Amit Kumar Saha , Debojyoti Dutta , Madhu S. Kumar , Ralf Rantzau
Abstract: 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.
-
公开(公告)号：US20190114080A1
公开(公告)日：2019-04-18
申请号：US15783229
申请日：2017-10-13
Applicant: Cisco Technology, Inc.
Inventor： Ramdoot Kumar Pydipaty , Amit Kumar Saha , Arun Saha
Abstract: Systems, methods, and computer-readable media for replicating data in a distributed storage cluster using an underlying network. In some examples, a primary node of a placement group in a network overlay of a distributed storage cluster can receive data for replication in the placement group. The primary node can provide the data to a first slave node of a plurality of slave nodes within the placement group in an underlying network of the distributed storage cluster. The data can subsequently be replicated using the underlying network by providing the data to at least one other slave node of the plurality of slave nodes within the placement group in the underlying network directly from the first slave node in the underlying network.
-
Patent Agency Ranking
公开(公告)号：US11740935B2
公开(公告)日：2023-08-29
申请号：US17519395
申请日：2021-11-04
Applicant: Cisco Technology, Inc.
Inventor： Komei Shimamura , Xinyuan Huang , Amit Kumar Saha , Debojyoti Dutta
CPC classification number: G06F9/4881 , G06F9/5038 , G06F9/5066 , G06F9/5088
Abstract: In one embodiment, a method for FPGA accelerated serverless computing comprises receiving, from a user, a definition of a serverless computing task comprising one or more functions to be executed. A task scheduler performs an initial placement of the serverless computing task to a first host determined to be a first optimal host for executing the serverless computing task. The task scheduler determines a supplemental placement of a first function to a second host determined to be a second optimal host for accelerating execution of the first function, wherein the first function is not able to accelerated by one or more FPGAs in the first host. The serverless computing task is executed on the first host and the second host according to the initial placement and the supplemental placement.
-
公开(公告)号：US11570272B2
公开(公告)日：2023-01-31
申请号：US17008520
申请日：2020-08-31
Applicant: Cisco Technology, Inc.
Inventor： Komei Shimamura , Amit Kumar Saha , Debojyoti Dutta
IPC: G06F15/16 , H04L67/5681 , G06F9/50 , H04L67/10
Abstract: A method for data provisioning a serverless computing cluster. A plurality of user defined functions (UDFs) are received for execution on worker nodes of the serverless computing cluster. For a first UDF, one or more data locations of UDF data needed to execute the first UDF are determined. At a master node of the serverless computing cluster, a plurality of worker node tickets are received, each ticket indicating a resource availability of a corresponding worker node. The one or more data locations and the plurality of worker node tickets are analyzed to determine eligible worker nodes capable of executing the first UDF. The master node transmits a pre-fetch command to one or more of the eligible worker nodes, causing the eligible worker nodes to become a provisioned worker node for the first UDF by storing a pre-fetched first UDF data before the first UDF is assigned for execution.
-
8.发明申请公开(公告)号：US20220414065A1
公开(公告)日：2022-12-29
申请号：US17899097
申请日：2022-08-30
Applicant: Cisco Technology, Inc.
Inventor： Ralf Rantzau , Madhu S. Kumar , Johnu George , Amit Kumar Saha , Debojyoti Dutta
Abstract: 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.
-
公开(公告)号：US20220058054A1
公开(公告)日：2022-02-24
申请号：US17519395
申请日：2021-11-04
Applicant: Cisco Technology, Inc.
Inventor： Komei Shimamura , Xinyuan Huang , Amit Kumar Saha , Debojyoti Dutta
Abstract: In one embodiment, a method for FPGA accelerated serverless computing comprises receiving, from a user, a definition of a serverless computing task comprising one or more functions to be executed. A task scheduler performs an initial placement of the serverless computing task to a first host determined to be a first optimal host for executing the serverless computing task. The task scheduler determines a supplemental placement of a first function to a second host determined to be a second optimal host for accelerating execution of the first function, wherein the first function is not able to accelerated by one or more FPGAs in the first host. The serverless computing task is executed on the first host and the second host according to the initial placement and the supplemental placement.
-
公开(公告)号：US10972364B2
公开(公告)日：2021-04-06
申请号：US16412604
申请日：2019-05-15
Applicant: Cisco Technology, Inc.
Inventor： Johnu George , Amit Kumar Saha
Abstract: 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.
-
-
-
-
-
-
-
-
-
Search Results
42
records
(took 0.023 seconds)
