Patents by Inventor Oscar Pinto
Oscar Pinto has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11262915Abstract: A storage system configured to mitigate the effect of a long latency tail in solid state drives. The system includes a host and a plurality of solid state drives. The host sets a latency threshold in each solid state drive. Each solid state drive may abort any read command when the execution time exceeds the latency threshold, and the host may then send the same read command to another solid state drive.Type: GrantFiled: May 18, 2020Date of Patent: March 1, 2022Assignee: Samsung Electronics Co., Ltd.Inventors: Ramdas Kachare, Oscar Pinto
-
Publication number: 20200278796Abstract: A storage system configured to mitigate the effect of a long latency tail in solid state drives. The system includes a host and a plurality of solid state drives. The host sets a latency threshold in each solid state drive. Each solid state drive may abort any read command when the execution time exceeds the latency threshold, and the host may then send the same read command to another solid state drive.Type: ApplicationFiled: May 18, 2020Publication date: September 3, 2020Inventors: Ramdas Kachare, Oscar Pinto
-
Patent number: 10732849Abstract: A storage system configured to mitigate the effect of a long latency tail in solid state drives. The system includes a host and a plurality of solid state drives. The host sets a latency threshold in each solid state drive. Each solid state drive may abort any read command when the execution time exceeds the latency threshold, and the host may then send the same read command to another solid state drive.Type: GrantFiled: September 21, 2018Date of Patent: August 4, 2020Assignee: Samsung Electronics Co., Ltd.Inventors: Ramdas Kachare, Oscar Pinto
-
Patent number: 10691368Abstract: A data replication system has a chassis including a plurality of eSSDs, a fabrics switch, and a baseboard management controller (BMC). The BMC configures one of the plurality of eSSDs as an active eSSD and one or more of the plurality of eSSDs as one or more passive eSSDs. The fabrics switch of the chassis is programmed to forward packets destined for the active eSSD to both the active eSSD and the one or more passive eSSDs. In response to a host data write command received from the host, the active eSSD stores the host data and sends an address and an instruction corresponding to the host data to the one or more passive eSSDs. Each of the one or more passive eSSDs stores a copy of the host data using the address and the instruction received from the active eSSD and the host data received in the packets forwarded by the fabrics switch.Type: GrantFiled: June 8, 2017Date of Patent: June 23, 2020Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Ramdas Kachare, Fred Worley, Sompong P. Olarig, Oscar Pinto
-
Patent number: 10649667Abstract: A system and method for managing garbage collection in Solid State Drives (SSDs) in a Redundant Array of Independent Disks (RAID) configuration, using a RAID controller is described. A control logic can control read and write requests for the SSDs in the RAID configuration. A selection logic can select an SSD for garbage collection. Setup logic can instruct the selected SSD to enter a garbage collection setup phase. An execute logic can instruct the selected SSD to enter and exit the garbage collection execute phase.Type: GrantFiled: September 22, 2017Date of Patent: May 12, 2020Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Oscar Pinto, Sreenivas Krishnan
-
Patent number: 10585749Abstract: A system and method for distributed erasure coding. A plurality of storage devices is directly connected to one or more host computers, without an intervening central controller distributing data to the storage devices and providing data protection. Parity codes are stored in one or more dedicated storage devices or distributed over a plurality of the storage devices. When a storage device receives a write command, it calculates a partial parity code, and, if the parity code for the data being written is on another storage device, sends the partial parity code to the other storage device, which updates the parity code using the partial parity code.Type: GrantFiled: October 20, 2017Date of Patent: March 10, 2020Assignee: Samsung Electronics Co., Ltd.Inventors: Ramdas P. Kachare, Fred Worley, Stephen Fischer, Oscar Pinto
-
Patent number: 10275174Abstract: A method includes: preconditioning a reference solid-state drive (SSD) to a steady state by writing to physical media of the reference SSD; transferring metadata of the reference SSD to an application; storing the metadata of the reference SSD in a persistent storage; normalizing the metadata of the reference SSD to a target SSD; and applying the normalized metadata to the target SSD to precondition the target SSD to the steady state.Type: GrantFiled: September 30, 2016Date of Patent: April 30, 2019Assignee: Samsung Electronics Co., Ltd.Inventors: Harry Rogers, Oscar Pinto, Yang Seok Ki
-
Publication number: 20190050289Abstract: A system and method for distributed erasure coding. A plurality of storage devices is directly connected to one or more host computers, without an intervening central controller distributing data to the storage devices and providing data protection. Parity codes are stored in one or more dedicated storage devices or distributed over a plurality of the storage devices. When a storage device receives a write command, it calculates a partial parity code, and, if the parity code for the data being written is on another storage device, sends the partial parity code to the other storage device, which updates the parity code using the partial parity code.Type: ApplicationFiled: October 20, 2017Publication date: February 14, 2019Inventors: Ramdas P. Kachare, Fred Worley, Stephen Fischer, Oscar Pinto
-
Publication number: 20190026031Abstract: A storage system configured to mitigate the effect of a long latency tail in solid state drives. The system includes a host and a plurality of solid state drives. The host sets a latency threshold in each solid state drive. Each solid state drive may abort any read command when the execution time exceeds the latency threshold, and the host may then send the same read command to another solid state drive.Type: ApplicationFiled: September 21, 2018Publication date: January 24, 2019Inventors: Ramdas Kachare, Oscar Pinto
-
Patent number: 10146444Abstract: A storage system configured to mitigate the effect of a long latency tail in solid state drives. The system includes a host and a plurality of solid state drives. The host sets a latency threshold in each solid state drive. Each solid state drive may abort any read command when the execution time exceeds the latency threshold, and the host may then send the same read command to another solid state drive.Type: GrantFiled: November 23, 2016Date of Patent: December 4, 2018Assignee: Samsung Electronics Co., Ltd.Inventors: Ramdas Kachare, Oscar Pinto
-
Patent number: 10108450Abstract: A method for notifying a host to manage background activities in a data storage device is disclosed. The method includes: receiving a query from a host operation system (OS); sending to the host OS, in response to the query, a list of background tasks to be performed in a data storage device; receiving a threshold value for one or more of the background tasks from the host OS; setting a timeout value associated with the threshold value; determining and notifying the timeout value to the host OS; determining that the threshold value is reached for a background task; and notifying the host OS that the SSD may perform the background task in the data storage device after the timeout value expires.Type: GrantFiled: June 17, 2016Date of Patent: October 23, 2018Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Oscar Pinto, Vishwanath Maram
-
Publication number: 20180284989Abstract: A data replication system has a chassis including a plurality of eSSDs, a fabrics switch, and a baseboard management controller (BMC). The BMC configures one of the plurality of eSSDs as an active eSSD and one or more of the plurality of eSSDs as one or more passive eSSDs. The fabrics switch of the chassis is programmed to forward packets destined for the active eSSD to both the active eSSD and the one or more passive eSSDs. In response to a host data write command received from the host, the active eSSD stores the host data and sends an address and an instruction corresponding to the host data to the one or more passive eSSDs. Each of the one or more passive eSSDs stores a copy of the host data using the address and the instruction received from the active eSSD and the host data received in the packets forwarded by the fabrics switch.Type: ApplicationFiled: June 8, 2017Publication date: October 4, 2018Inventors: Ramdas Kachare, Fred Worley, Sompong P. Olarig, Oscar Pinto
-
Publication number: 20180095675Abstract: A storage system configured to mitigate the effect of a long latency tail in solid state drives. The system includes a host and a plurality of solid state drives. The host sets a latency threshold in each solid state drive. Each solid state drive may abort any read command when the execution time exceeds the latency threshold, and the host may then send the same read command to another solid state drive.Type: ApplicationFiled: November 23, 2016Publication date: April 5, 2018Inventors: Ramdas Kachare, Oscar Pinto
-
Publication number: 20180059983Abstract: A method includes: preconditioning a reference solid-state drive (SSD) to a steady state by writing to physical media of the reference SSD; transferring metadata of the reference SSD to an application; storing the metadata of the reference SSD in a persistent storage; normalizing the metadata of the reference SSD to a target SSD; and applying the normalized metadata to the target SSD to precondition the target SSD to the steady state.Type: ApplicationFiled: September 30, 2016Publication date: March 1, 2018Inventors: Harry ROGERS, Oscar PINTO, Yang Seok KI
-
Publication number: 20180011641Abstract: A system and method for managing garbage collection in Solid State Drives (SSDs) in a Redundant Array of Independent Disks (RAID) configuration, using a RAID controller is described. A control logic can control read and write requests for the SSDs in the RAID configuration. A selection logic can select an SSD for garbage collection. Setup logic can instruct the selected SSD to enter a garbage collection setup phase. An execute logic can instruct the selected SSD to enter and exit the garbage collection execute phase.Type: ApplicationFiled: September 22, 2017Publication date: January 11, 2018Inventors: Oscar PINTO, Sreenivas KRISHNAN
-
Patent number: 9804787Abstract: A system and method for managing garbage collection in Solid State Drives (SSDs) (120-1, 120-2, 120-3, 120-4, 120-5) in a Redundant Array of Independent Disks (RAID) configuration, using a RAID controller (115) is described. A control logic (505) can control read and write requests (805, 810) for the SSDs (120-1, 120-2, 120-3, 120-4, 120-5) in the RAID configuration. A selection logic (515) can select an SSD for garbage collection. Setup logic (520) can instruct the selected SSD to enter a garbage collection setup phase (920). An execute logic (525) can instruct the selected SSD to enter and exit the garbage collection execute phase (925).Type: GrantFiled: January 19, 2016Date of Patent: October 31, 2017Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Oscar Pinto, Sreenivas Krishnan
-
Publication number: 20170308398Abstract: A method for notifying a host to manage background activities in a data storage device is disclosed. The method includes: receiving a query from a host operation system (OS); sending to the host OS, in response to the query, a list of background tasks to be performed in a data storage device; receiving a threshold value for one or more of the background tasks from the host OS; setting a timeout value associated with the threshold value; determining and notifying the timeout value to the host OS; determining that the threshold value is reached for a background task; and notifying the host OS that the SSD may perform the background task in the data storage device after the timeout value expires.Type: ApplicationFiled: June 17, 2016Publication date: October 26, 2017Inventors: Oscar PINTO, Vishwanath MARAM
-
Publication number: 20170123686Abstract: A system and method for managing garbage collection in Solid State Drives (SSDs) (120-1, 120-2, 120-3, 120-4, 120-5) in a Redundant Array of Independent Disks (RAID) configuration, using a RAID controller (115) is described. A control logic (505) can control read and write requests (805, 810) for the SSDs (120-1, 120-2, 120-3, 120-4, 120-5) in the RAID configuration. A selection logic (515) can select an SSD for garbage collection. Setup logic (520) can instruct the selected SSD to enter a garbage collection setup phase (920). An execute logic (525) can instruct the selected SSD to enter and exit the garbage collection execute phase (925).Type: ApplicationFiled: January 19, 2016Publication date: May 4, 2017Inventors: Oscar PINTO, Sreenivas KRISHNAN
-
Patent number: 8572321Abstract: In some embodiments, a non-volatile cache memory may include a segmented non-volatile cache memory configured to be located between a system memory and a mass storage device of an electronic system and a controller coupled to the segmented non-volatile cache memory, wherein the controller is configured to control utilization of the segmented non-volatile cache memory. The segmented non-volatile cache memory may include a file cache segment, the file cache segment to store complete files in accordance with a file cache policy, and a block cache segment, the block cache segment to store one or more blocks of one or more files in accordance with a block cache policy, wherein the block cache policy is different from the file cache policy.Type: GrantFiled: June 26, 2012Date of Patent: October 29, 2013Assignee: Intel CorporationInventors: Dale Jeunemann, R. Scott Tetrick, Oscar Pinto
-
Patent number: 8433854Abstract: In some embodiments, an electronic system may include a cache located between a mass storage and a system memory, and code stored on the electronic system to prevent storage of stream data in the cache and to send the stream data directly between the system memory and the mass storage based on a comparison of first metadata of a first request for first information and pre-boot stream information stored in a previous boot context. Other embodiments are disclosed and claimed.Type: GrantFiled: June 25, 2008Date of Patent: April 30, 2013Assignee: Intel CorporationInventors: R. Scott Tetrick, Dale Juenemann, Jordan Howes, Jeanna Matthews, Steven Wells, Glenn Hinton, Oscar Pinto