Patents by Inventor Subramony Sesha
Subramony Sesha 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: 11689471Abstract: Technologies for contention-aware cloud compute scheduling include a number of compute nodes in a cloud computing cluster and a cloud controller. Each compute node collects performance data indicative of cache contention on the compute node, for example, cache misses per thousand instructions. Each compute node determines a contention score as a function of the performance data and stores the contention score in a cloud state database. In response to a request for a new virtual machine, the cloud controller receives contention scores for the compute nodes and selects a compute node based on the contention score. The cloud controller schedules the new virtual machine on the selected compute node. The contention score may include a contention metric and a contention score level indicative of the contention metric. The contention score level may be determined by comparing the contention metric to a number of thresholds. Other embodiments are described and claimed.Type: GrantFiled: December 27, 2021Date of Patent: June 27, 2023Assignee: Intel CorporationInventors: Subramony Sesha, Archana Patni, Ananth S. Narayan, Mrittika Ganguli
-
Publication number: 20220368645Abstract: Technologies for contention-aware cloud compute scheduling include a number of compute nodes in a cloud computing cluster and a cloud controller. Each compute node collects performance data indicative of cache contention on the compute node, for example, cache misses per thousand instructions. Each compute node determines a contention score as a function of the performance data and stores the contention score in a cloud state database. In response to a request for a new virtual machine, the cloud controller receives contention scores for the compute nodes and selects a compute node based on the contention score. The cloud controller schedules the new virtual machine on the selected compute node. The contention score may include a contention metric and a contention score level indicative of the contention metric. The contention score level may be determined by comparing the contention metric to a number of thresholds. Other embodiments are described and claimed.Type: ApplicationFiled: December 27, 2021Publication date: November 17, 2022Inventors: Subramony Sesha, Archana Patni, Ananth S. Narayan, Mrittika Ganguli
-
Patent number: 11212235Abstract: Technologies for contention-aware cloud compute scheduling include a number of compute nodes in a cloud computing cluster and a cloud controller. Each compute node collects performance data indicative of cache contention on the compute node, for example, cache misses per thousand instructions. Each compute node determines a contention score as a function of the performance data and stores the contention score in a cloud state database. In response to a request for a new virtual machine, the cloud controller receives contention scores for the compute nodes and selects a compute node based on the contention score. The cloud controller schedules the new virtual machine on the selected compute node. The contention score may include a contention metric and a contention score level indicative of the contention metric. The contention score level may be determined by comparing the contention metric to a number of thresholds. Other embodiments are described and claimed.Type: GrantFiled: May 15, 2020Date of Patent: December 28, 2021Assignee: INTEL CORPORATIONInventors: Subramony Sesha, Archana Patni, Ananth S. Narayan, Mrittika Ganguli
-
Publication number: 20200344175Abstract: Technologies for contention-aware cloud compute scheduling include a number of compute nodes in a cloud computing cluster and a cloud controller. Each compute node collects performance data indicative of cache contention on the compute node, for example, cache misses per thousand instructions. Each compute node determines a contention score as a function of the performance data and stores the contention score in a cloud state database. In response to a request for a new virtual machine, the cloud controller receives contention scores for the compute nodes and selects a compute node based on the contention score. The cloud controller schedules the new virtual machine on the selected compute node. The contention score may include a contention metric and a contention score level indicative of the contention metric. The contention score level may be determined by comparing the contention metric to a number of thresholds. Other embodiments are described and claimed.Type: ApplicationFiled: May 15, 2020Publication date: October 29, 2020Inventors: Subramony Sesha, Archana Patni, Ananth S. Narayan, Mrittika Ganguli
-
Patent number: 10659386Abstract: Technologies for contention-aware cloud compute scheduling include a number of compute nodes in a cloud computing cluster and a cloud controller. Each compute node collects performance data indicative of cache contention on the compute node, for example, cache misses per thousand instructions. Each compute node determines a contention score as a function of the performance data and stores the contention score in a cloud state database. In response to a request for a new virtual machine, the cloud controller receives contention scores for the compute nodes and selects a compute node based on the contention score. The cloud controller schedules the new virtual machine on the selected compute node. The contention score may include a contention metric and a contention score level indicative of the contention metric. The contention score level may be determined by comparing the contention metric to a number of thresholds. Other embodiments are described and claimed.Type: GrantFiled: January 16, 2018Date of Patent: May 19, 2020Assignee: Intel CorporationInventors: Subramony Sesha, Archana Patni, Ananth S. Narayan, Mrittika Ganguli
-
Publication number: 20180309692Abstract: Technologies for contention-aware cloud compute scheduling include a number of compute nodes in a cloud computing cluster and a cloud controller. Each compute node collects performance data indicative of cache contention on the compute node, for example, cache misses per thousand instructions. Each compute node determines a contention score as a function of the performance data and stores the contention score in a cloud state database. In response to a request for a new virtual machine, the cloud controller receives contention scores for the compute nodes and selects a compute node based on the contention score. The cloud controller schedules the new virtual machine on the selected compute node. The contention score may include a contention metric and a contention score level indicative of the contention metric. The contention score level may be determined by comparing the contention metric to a number of thresholds. Other embodiments are described and claimed.Type: ApplicationFiled: January 16, 2018Publication date: October 25, 2018Inventors: Subramony Sesha, Archana Patni, Ananth S. Narayan, Mrittika Ganguli
-
Patent number: 9921866Abstract: A method comprising is described. The method includes receiving a virtual machine and a service level objective compute consumption metrics (SLO) parameters from a cloud controller, mapping the SLO parameters to resources at the compute node, monitoring utilization and performance of the virtual machine and dynamically adjusting performance of the virtual machine based on monitored performance data.Type: GrantFiled: December 22, 2014Date of Patent: March 20, 2018Assignee: INTEL CORPORATIONInventors: Mrittika Ganguli, Rajneesh Bhardwaj, Ananth Sankaranarayanan, Sunil Raghavan, Subramony Sesha, Gilbert Hyatt, Muralidharan Sundararajan, Arkadiusz Chylinski, Alok Prakash
-
Patent number: 9871742Abstract: Technologies for contention-aware cloud compute scheduling include a number of compute nodes in a cloud computing cluster and a cloud controller. Each compute node collects performance data indicative of cache contention on the compute node, for example, cache misses per thousand instructions. Each compute node determines a contention score as a function of the performance data and stores the contention score in a cloud state database. In response to a request for a new virtual machine, the cloud controller receives contention scores for the compute nodes and selects a compute node based on the contention score. The cloud controller schedules the new virtual machine on the selected compute node. The contention score may include a contention metric and a contention score level indicative of the contention metric. The contention score level may be determined by comparing the contention metric to a number of thresholds. Other embodiments are described and claimed.Type: GrantFiled: December 22, 2016Date of Patent: January 16, 2018Assignee: Intel CorporationInventors: Subramony Sesha, Archana Patni, Ananth S. Narayan, Mrittika Ganguli
-
Publication number: 20170237681Abstract: Technologies for contention-aware cloud compute scheduling include a number of compute nodes in a cloud computing cluster and a cloud controller. Each compute node collects performance data indicative of cache contention on the compute node, for example, cache misses per thousand instructions. Each compute node determines a contention score as a function of the performance data and stores the contention score in a cloud state database. In response to a request for a new virtual machine, the cloud controller receives contention scores for the compute nodes and selects a compute node based on the contention score. The cloud controller schedules the new virtual machine on the selected compute node. The contention score may include a contention metric and a contention score level indicative of the contention metric. The contention score level may be determined by comparing the contention metric to a number of thresholds. Other embodiments are described and claimed.Type: ApplicationFiled: December 22, 2016Publication date: August 17, 2017Inventors: Subramony Sesha, Archana Patni, Ananth S. Narayan, Mrittika Ganguli
-
Patent number: 9614779Abstract: Technologies for contention-aware cloud compute scheduling include a number of compute nodes in a cloud computing cluster and a cloud controller. Each compute node collects performance data indicative of cache contention on the compute node, for example, cache misses per thousand instructions. Each compute node determines a contention score as a function of the performance data and stores the contention score in a cloud state database. In response to a request for a new virtual machine, the cloud controller receives contention scores for the compute nodes and selects a compute node based on the contention score. The cloud controller schedules the new virtual machine on the selected compute node. The contention score may include a contention metric and a contention score level indicative of the contention metric. The contention score level may be determined by comparing the contention metric to a number of thresholds. Other embodiments are described and claimed.Type: GrantFiled: December 24, 2013Date of Patent: April 4, 2017Assignee: Intel CorporationInventors: Subramony Sesha, Archana Patni, Ananth S. Narayan, Mrittika Mrittika Ganguli
-
Publication number: 20160179560Abstract: A method comprising is described.Type: ApplicationFiled: December 22, 2014Publication date: June 23, 2016Inventors: Mrittika Ganguli, Rajneesh Bhardwaj, Ananth Sankaranarayanan, Sunil Raghavan, Subramony Sesha, Gilbert Hyatt, Muralidharan Sundararajan, Arkadiusz Chylinski, Alok Prakash