Tackling the Management Challenges of Server Consolidation on Multi-core System

Size: px
Start display at page:

Download "Tackling the Management Challenges of Server Consolidation on Multi-core System"

Transcription

1 Tackling the Management Challenges of Server Consolidation on Multi-core System Hui Lv Intel June

2 Agenda SPECvirt_sc2010* Introduction SPECvirt_sc2010* Workload Scalability Analysis Hypervisor Overhead Analysis Credit Scheduler Optimizations Conclusions * The benchmark runs discussed here are for our research and non-compliant with the SPEC run-rules. The data presented here are only to illustrate the points discussed in this paper and cannot be compared with any other SPECvirt_sc2010 results 2

3 SPECvirt_sc2010* Workload Introduction Three sub-workloads: SPECjAppServer*, SPECimap*, SPECweb* Six VMs comprise a Tile to run as many as possible tiles Score: calculate arithmetic mean of the 3 normalized values per tile and sum the scores for all Tiles Infrastructure VM Webserver VM IMAP Server VM App Server VM Database VM Idle Server VM Tile 1 Virtualization Layer (XEN) and Hardware SPECweb2005* Driver SPECimap2007* Driver SPECjAppServer2004* Driver 3

4 Performance Scalability* Overview Performance scaling got worse as system load increased Response time became longer worse Qos * * Response time: Geomean of three kinds of sub-workload s response time * The benchmark runs discussed here are for our research and non-compliant with the SPEC run-rules. The data presented here are only to illustrate the points discussed in this paper and cannot be compared with any other SPECvirt_sc2010 results 4

5 CPU Cycles Components Breakdown Hypervisor occupied 28% of the total CPU cycles per transaction much high overheads! 5

6 Hypervisor Overhead Analysis The VMExit event of Ext Interrupt consumed ~48% of hypervisor cycles Context Switch consumed 27% of total hypervisor Cycles Most of the context switch happened in the VMExit event of External Interrupt Context switches: ~15k per second for one physical core at peak performance -- the average running tile slice for a vcpu once scheduled is less than 0.1 ms. * The cost of VMExit is calculated by removing domain0, cpuidle (7fff). It s the real overhead for hypervisor to process VMExit. * Context Switch means the process of de-schedule the current running vcpu and schedule in the next vcpu 6

7 Optimizations for Scheduler The process of scheduling consumed a big part in hypervisor. Meanwhile, high frequent context switch will also make cache cold thus increase the cycles per instructiion We worked out one way to optimize the scheduling process, so as to reduce overhead and improve performance 7

8 Generic Scheduler Process Pick up next vcpu Xen supplied generic API for specific implementation (credit1 and credit2) Two major parts in this flaw 1. To pick up next vcpu (SCHED_P) 2. To do context switch when selecting a new vcpu (SCHED_C) 8

9 Context Switch Rate Controller (SRC) Solution: To control scheduling rate in the following conditions 1) To skip the current scheduling process, if the frequency of context switch is bigger than the threshold during last period (10 ms) and last running vcpu is still runnable (not blocked) 2) To skip the current scheduling process, if last running vcpu runs less than some time slice (1ms) and still runnable Schedule Triggered Y Y VCPU1? Rate Control? VCPU1 Runnable Ret VCPU1 N? Running less than 1ms N Y N do_schedule 9

10 Performance Increase with SRC Optimization Perf/(cpu utilization) boosted by 15% Number of context switch reduced by 50%, thus cycles of hypervisor reduced by 22% Due to less context switch, decreased cache lower CPI lower CPU cycles for both Guest and Hypervisor Base With SRC SRC/Base Perf/(cpu cycles) 945 1, CPU% (Total) 92.00% 80.88% 0.88 Guest U 31.21% 28.56% 0.92 Guest K 31.58% 28.63% 0.91 Dom0 2.96% 3.20% 1.08 Xen 26.23% 20.48% 0.78 SCHED_Total 7.28% 4.40% 0.60 SCHED_Pick (credit) 2.40% 1.54% 0.64 SCHED_Context_Switch 2.33% 1.16% 0.50 Sched: runs through scheduler 6,312,866 5,304, Sched: context switches 6,008,568 3,329,

11 Credit1 vs. Credit2 Credit2 is the prototype brought in XEN 4.x. So far, it can work in complex consolidation environment Currently, overhead of credit2 is a bit higher than credit1 -- much faster pickup process in credit2, but slower context switch process Credit1 Credit2 Credit2/Credit1 Perf/transaction 1,254 1, CPU% (Total) 46.68% 54.47% 1.17 Guest U 15.21% 16.64% 1.09 Guest K 15.61% 17.24% 1.10 Dom0 1.82% 2.02% 1.11 Xen 14.04% 18.58% 1.32 SCHED_Total (cycles) SCHED_P (cycles) 1.32% 0.62% 0.47 SCHED_C (cycles) 0.95% 1.92% 2.02 Sched: runs through scheduler 6,339,737 5,808, Sched: context switches 4,689,289 4,615,

12 Conclusion Performance scalability got worse as system load increased in consolidation environment. Hypervisor composed a big part of the total system cycles, ~28% Too frequent context switch resulted in high overhead Some kind of rate controller for Credit scheduler benefit performance improvement Call people attention to continue developing a more powerful scheduler for Xen, in complex consolidation environment Intel and Xeon are trademarks of Intel Corporation in the United States and other countries * Other names and brands may be claimed as the property of others. 12

13 Backup 13

14 Hardware Layout SUT 3.33GHz Switch SR-IOV VFs iscsi Direct Link iscsi Target Clients Clients Storage Bay Intel Gbit Ethnet Adapter HBA Card 14

15 Server Under Test Configurations Processor Intel Xeon 5680 Sokets/Cores/Threads 2/12/24 Frequency 3.33GHz LLC 12MB BIOS HT ON, Turbo OFF, Power OFF, NUMA ON Memory 12 x 8GB DDR3 Platform S5520UR Controller LSI 3801 HBA Storage ISCSI for data disk, QEMU disk for OS disk Network G NIC Hypervisor Xen upstream c/s VM configs HVM Guests 15

16 Which Caused the Worse Scalability Cycles/transaction increase was caused by both CPI and Path Length increase -- Increase of CPI was partially due to increasing cache miss rate -- Increase of PL indicated some software bottlenecks existing 16

17 Hypervisor Events Overview Do we really need so many context switch work ~15k per second for one physical core at peak performance? It means the average running time slice for a vcpu once scheduled is less than 0.1 ms. Events (number/s) 1tile 9tile 9tile/1tile VMExits 55, , Hypercalls 52, , APIC timer interrupts 5,733 31, IRQ 10, , IPI 14, , sched: runs through schedule 42, , sched: context switches 28, , csched: migrate_queued 7 39,757 5,847 csched: migrate_running 0 3 N/A 17

18 VMExit Events Distribution At peak performance, top three VMExit events were APIC Access, External Interrupt and CR Access However, larger number does not mean higher overhead it depends on the cost of related VMExit event 18

Performance and Scalability of Server Consolidation

Performance and Scalability of Server Consolidation Performance and Scalability of Server Consolidation August 2010 Andrew Theurer IBM Linux Technology Center Agenda How are we measuring server consolidation? SPECvirt_sc2010 How is KVM doing in an enterprise

More information

I/O Scalability in Xen

I/O Scalability in Xen I/O Scalability in Xen Kevin Tian kevin.tian@intel.com Eddie Dong eddie.dong@intel.com Yang Zhang yang.zhang@intel.com Sponsored by: & & Agenda Overview of I/O Scalability Issues Excessive Interrupts Hurt

More information

Accelerating NVMe I/Os in Virtual Machine via SPDK vhost* Solution Ziye Yang, Changpeng Liu Senior software Engineer Intel

Accelerating NVMe I/Os in Virtual Machine via SPDK vhost* Solution Ziye Yang, Changpeng Liu Senior software Engineer Intel Accelerating NVMe I/Os in Virtual Machine via SPDK vhost* Solution Ziye Yang, Changpeng Liu Senior software Engineer Intel @optimistyzy Notices & Disclaimers Intel technologies features and benefits depend

More information

Course Review. Hui Lu

Course Review. Hui Lu Course Review Hui Lu Syllabus Cloud computing Server virtualization Network virtualization Storage virtualization Cloud operating system Object storage Syllabus Server Virtualization Network Virtualization

More information

SR-IOV support in Xen. Yaozu (Eddie) Dong Yunhong Jiang Kun (Kevin) Tian

SR-IOV support in Xen. Yaozu (Eddie) Dong Yunhong Jiang Kun (Kevin) Tian SR-IOV support in Xen Yaozu (Eddie) Dong (Eddie.Dong@intel.com) Yunhong Jiang Kun (Kevin) Tian Agenda SR-IOV specification overview Xen/SR-IOV architecture Discussions 2 SR-IOV specification overview Start

More information

CS-580K/480K Advanced Topics in Cloud Computing. VM Virtualization II

CS-580K/480K Advanced Topics in Cloud Computing. VM Virtualization II CS-580K/480K Advanced Topics in Cloud Computing VM Virtualization II 1 How to Build a Virtual Machine? 2 How to Run a Program Compiling Source Program Loading Instruction Instruction Instruction Instruction

More information

Intel Graphics Virtualization on KVM. Aug KVM Forum 2011 Rev. 3

Intel Graphics Virtualization on KVM. Aug KVM Forum 2011 Rev. 3 Intel Graphics Virtualization on KVM Aug-16-2011 allen.m.kay@intel.com KVM Forum 2011 Rev. 3 Agenda Background on IO Virtualization Device Operation on Native Platform QEMU IO Virtualization Device Direct

More information

Changpeng Liu. Cloud Storage Software Engineer. Intel Data Center Group

Changpeng Liu. Cloud Storage Software Engineer. Intel Data Center Group Changpeng Liu Cloud Storage Software Engineer Intel Data Center Group Notices & Disclaimers Intel technologies features and benefits depend on system configuration and may require enabled hardware, software

More information

Nested Virtualization and Server Consolidation

Nested Virtualization and Server Consolidation Nested Virtualization and Server Consolidation Vara Varavithya Department of Electrical Engineering, KMUTNB varavithya@gmail.com 1 Outline Virtualization & Background Nested Virtualization Hybrid-Nested

More information

Accelerating NVMe-oF* for VMs with the Storage Performance Development Kit

Accelerating NVMe-oF* for VMs with the Storage Performance Development Kit Accelerating NVMe-oF* for VMs with the Storage Performance Development Kit Jim Harris Principal Software Engineer Intel Data Center Group Santa Clara, CA August 2017 1 Notices and Disclaimers Intel technologies

More information

Optimizing and Enhancing VM for the Cloud Computing Era. 20 November 2009 Jun Nakajima, Sheng Yang, and Eddie Dong

Optimizing and Enhancing VM for the Cloud Computing Era. 20 November 2009 Jun Nakajima, Sheng Yang, and Eddie Dong Optimizing and Enhancing VM for the Cloud Computing Era 20 November 2009 Jun Nakajima, Sheng Yang, and Eddie Dong Implications of Cloud Computing to Virtualization More computation and data processing

More information

How to abstract hardware acceleration device in cloud environment. Maciej Grochowski Intel DCG Ireland

How to abstract hardware acceleration device in cloud environment. Maciej Grochowski Intel DCG Ireland How to abstract hardware acceleration device in cloud environment Maciej Grochowski Intel DCG Ireland Outline Introduction to Hardware Accelerators Intel QuickAssist Technology (Intel QAT) as example of

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results Page 1 of 9 VMware VMmark V1.1 Results Vendor and Hardware Platform: Dell PowerEdge R710 Virtualization Platform: ESX build 150817 VMmark V1.1 Score = 24.00 @ 17 Tiles Tested By: Dell Inc. Test Date: 03/26/2009

More information

VT-d Posted Interrupts. Feng Wu, Jun Nakajima <Speaker> Intel Corporation

VT-d Posted Interrupts. Feng Wu, Jun Nakajima <Speaker> Intel Corporation VT-d Posted Interrupts Feng Wu, Jun Nakajima Intel Corporation Agenda Motivation Difference btw CPU-based and VT-d Posted Interrupts Architecture Implementation Details Performance Summary 2

More information

Performance & Scalability Testing in Virtual Environment Hemant Gaidhani, Senior Technical Marketing Manager, VMware

Performance & Scalability Testing in Virtual Environment Hemant Gaidhani, Senior Technical Marketing Manager, VMware Performance & Scalability Testing in Virtual Environment Hemant Gaidhani, Senior Technical Marketing Manager, VMware 2010 VMware Inc. All rights reserved About the Speaker Hemant Gaidhani Senior Technical

More information

Practical Xen Testing at Intel

Practical Xen Testing at Intel Practical Xen Testing at Intel Nov. 2009 Haicheng Li Jiajun Xu Xen Summit Asia 2009 Legal Information INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION

More information

VMware VMmark V1.1.1 Results

VMware VMmark V1.1.1 Results VMware VMmark V1.1.1 Results Vendor and Hardware Platform: SGI XE500 Virtualization Platform: VMware ESX 4.0 Update 1 (build 208167) Performance Section Performance Tested By: SGI Test Date: 02/16/10 Configuration

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results VMware VMmark V1.1 Results Vendor and Hardware Platform: HP ProLiant DL370 G6 Virtualization Platform: VMware ESX 4.0 build 148783 VMmark V1.1 Score = 23.96 @ 16 Tiles Performance Section Performance Tested

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results VMware VMmark V1.1 Results Vendor and Hardware Platform: Inspur NF5280 Virtualization Platform: VMware ESX Server 4.0 build 148592 Performance Section Performance Tested By: Inspur Inc. Configuration Section

More information

Towards More Power Friendly Xen

Towards More Power Friendly Xen Towards More Power Friendly Xen June 2008 Yu Ke Tian Kevin Wei Gang Liu Jinsong Agenda Xen power management current

More information

W H I T E P A P E R. Comparison of Storage Protocol Performance in VMware vsphere 4

W H I T E P A P E R. Comparison of Storage Protocol Performance in VMware vsphere 4 W H I T E P A P E R Comparison of Storage Protocol Performance in VMware vsphere 4 Table of Contents Introduction................................................................... 3 Executive Summary............................................................

More information

Making Nested Virtualization Real by Using Hardware Virtualization Features

Making Nested Virtualization Real by Using Hardware Virtualization Features Making Nested Virtualization Real by Using Hardware Virtualization Features May 28, 2013 Jun Nakajima Intel Corporation 1 Legal Disclaimer INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL

More information

Microsoft SQL Server in a VMware Environment on Dell PowerEdge R810 Servers and Dell EqualLogic Storage

Microsoft SQL Server in a VMware Environment on Dell PowerEdge R810 Servers and Dell EqualLogic Storage Microsoft SQL Server in a VMware Environment on Dell PowerEdge R810 Servers and Dell EqualLogic Storage A Dell Technical White Paper Dell Database Engineering Solutions Anthony Fernandez April 2010 THIS

More information

Changpeng Liu. Senior Storage Software Engineer. Intel Data Center Group

Changpeng Liu. Senior Storage Software Engineer. Intel Data Center Group Changpeng Liu Senior Storage Software Engineer Intel Data Center Group Legal Notices and Disclaimers Intel technologies features and benefits depend on system configuration and may require enabled hardware,

More information

Dell PowerEdge R910 SQL OLTP Virtualization Study Measuring Performance and Power Improvements of New Intel Xeon E7 Processors and Low-Voltage Memory

Dell PowerEdge R910 SQL OLTP Virtualization Study Measuring Performance and Power Improvements of New Intel Xeon E7 Processors and Low-Voltage Memory Dell PowerEdge R910 SQL OLTP Virtualization Study Measuring Performance and Power Improvements of New Intel Xeon E7 Processors and Low-Voltage Memory A Dell Technical White Paper Dell, Inc. Waseem Raja

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results VMware VMmark V1.1 Results Vendor and Hardware Platform: HP Proliant DL580 G5 Virtualization Platform: VMware ESX 3.5.0 Update 1, build 82663 VMmark V1.1 Score = 14.14 @ 10 Tiles Tested By: Hewlett Packard

More information

Nested Virtualization Update From Intel. Xiantao Zhang, Eddie Dong Intel Corporation

Nested Virtualization Update From Intel. Xiantao Zhang, Eddie Dong Intel Corporation Nested Virtualization Update From Intel Xiantao Zhang, Eddie Dong Intel Corporation Legal Disclaimer INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL PRODUCTS. NO LICENSE, EXPRESS OR IMPLIED,

More information

I/O virtualization. Jiang, Yunhong Yang, Xiaowei Software and Service Group 2009 虚拟化技术全国高校师资研讨班

I/O virtualization. Jiang, Yunhong Yang, Xiaowei Software and Service Group 2009 虚拟化技术全国高校师资研讨班 I/O virtualization Jiang, Yunhong Yang, Xiaowei 1 Legal Disclaimer INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL PRODUCTS. NO LICENSE,

More information

Achieve Low Latency NFV with Openstack*

Achieve Low Latency NFV with Openstack* Achieve Low Latency NFV with Openstack* Yunhong Jiang Yunhong.Jiang@intel.com *Other names and brands may be claimed as the property of others. Agenda NFV and network latency Why network latency on NFV

More information

Maximizing Six-Core AMD Opteron Processor Performance with RHEL

Maximizing Six-Core AMD Opteron Processor Performance with RHEL Maximizing Six-Core AMD Opteron Processor Performance with RHEL Bhavna Sarathy Red Hat Technical Lead, AMD Sanjay Rao Senior Software Engineer, Red Hat Sept 4, 2009 1 Agenda Six-Core AMD Opteron processor

More information

VMmark V1.0.0 Results

VMmark V1.0.0 Results VMmark V1.0.0 Results Vendor and Hardware Platform: HP DL 580 G5 Virtualization Platform: VMware ESX Server, 3.0.2, 52542 VMmark V1.0.0 Score = 11.54 @ 8 Tiles Tested By: HP Technology Solutions Group

More information

WHITE PAPER FUJITSU PRIMERGY SERVERS PERFORMANCE REPORT PRIMERGY BX924 S2

WHITE PAPER FUJITSU PRIMERGY SERVERS PERFORMANCE REPORT PRIMERGY BX924 S2 WHITE PAPER PERFORMANCE REPORT PRIMERGY BX924 S2 WHITE PAPER FUJITSU PRIMERGY SERVERS PERFORMANCE REPORT PRIMERGY BX924 S2 This document contains a summary of the benchmarks executed for the PRIMERGY BX924

More information

Agilio CX 2x40GbE with OVS-TC

Agilio CX 2x40GbE with OVS-TC PERFORMANCE REPORT Agilio CX 2x4GbE with OVS-TC OVS-TC WITH AN AGILIO CX SMARTNIC CAN IMPROVE A SIMPLE L2 FORWARDING USE CASE AT LEAST 2X. WHEN SCALED TO REAL LIFE USE CASES WITH COMPLEX RULES TUNNELING

More information

MultiLanes: Providing Virtualized Storage for OS-level Virtualization on Many Cores

MultiLanes: Providing Virtualized Storage for OS-level Virtualization on Many Cores MultiLanes: Providing Virtualized Storage for OS-level Virtualization on Many Cores Junbin Kang, Benlong Zhang, Tianyu Wo, Chunming Hu, and Jinpeng Huai Beihang University 夏飞 20140904 1 Outline Background

More information

CFS-v: I/O Demand-driven VM Scheduler in KVM

CFS-v: I/O Demand-driven VM Scheduler in KVM CFS-v: Demand-driven VM Scheduler in KVM Hyotaek Shim and Sung-Min Lee (hyotaek.shim, sung.min.lee@samsung.com) Software R&D Center, Samsung Electronics 2014. 10. 16 Problem in Server Consolidation 2/16

More information

Version 1.0 October Reduce CPU Utilization by 10GbE CNA with Hardware iscsi Offload

Version 1.0 October Reduce CPU Utilization by 10GbE CNA with Hardware iscsi Offload Version 1.0 October 2012 Reduce CPU Utilization by 10GbE CNA with Hardware iscsi Offload Copyright Copyright@2004~2012, Qsan Technology, Inc. All rights reserved. No part of this document may be reproduced

More information

Amazon EC2 Deep Dive. Michael #awssummit

Amazon EC2 Deep Dive. Michael #awssummit Berlin Amazon EC2 Deep Dive Michael Hanisch @hanimic #awssummit Let s get started Amazon EC2 instances AMIs & Virtualization Types EBS-backed AMIs AMI instance Physical host server New root volume snapshot

More information

Red Hat Enterprise Virtualization Hypervisor Roadmap. Bhavna Sarathy Senior Technology Product Manager, Red Hat

Red Hat Enterprise Virtualization Hypervisor Roadmap. Bhavna Sarathy Senior Technology Product Manager, Red Hat Red Hat Enterprise Virtualization Hypervisor Roadmap Bhavna Sarathy Senior Technology Product Manager, Red Hat RHEV Hypervisor 1 RHEV Hypervisor Themes & 2 Architecture & Use cases 3 Q&A 4 Future 5 } HYPERVISOR

More information

Status Update About COLO (COLO: COarse-grain LOck-stepping Virtual Machines for Non-stop Service)

Status Update About COLO (COLO: COarse-grain LOck-stepping Virtual Machines for Non-stop Service) Status Update About COLO (COLO: COarse-grain LOck-stepping Virtual Machines for Non-stop Service) eddie.dong@intel.com arei.gonglei@huawei.com yanghy@cn.fujitsu.com Agenda Background Introduction Of COLO

More information

Evaluation and improvements of I/O Scalability for Xen. Jun Kamada, Fujitsu Limited Simon Horman, VA Linux Systems Japan

Evaluation and improvements of I/O Scalability for Xen. Jun Kamada, Fujitsu Limited Simon Horman, VA Linux Systems Japan Evaluation and improvements of I/O Scalability for Xen Jun Kamada, Fujitsu Limited Simon Horman, VA Linux Systems Japan Agenda Part : I/O Scalability Improvements (Bandwidth Control) Part2 : I/O Scalability

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results VMware VMmark V1.1 Results Vendor and Hardware Platform: HP ProLiant DL585G5 Virtualization Platform: VMware ESX 4.0 (build 148783) Performance Section Performance Tested By: Hewlett Packard Test Date:

More information

The Missing Piece of Virtualization. I/O Virtualization on 10 Gb Ethernet For Virtualized Data Centers

The Missing Piece of Virtualization. I/O Virtualization on 10 Gb Ethernet For Virtualized Data Centers The Missing Piece of Virtualization I/O Virtualization on 10 Gb Ethernet For Virtualized Data Centers Agenda 10 GbE Adapters Built for Virtualization I/O Throughput: Virtual & Non-Virtual Servers Case

More information

Intel Virtualization Technology Roadmap and VT-d Support in Xen

Intel Virtualization Technology Roadmap and VT-d Support in Xen Intel Virtualization Technology Roadmap and VT-d Support in Xen Jun Nakajima Intel Open Source Technology Center Legal Disclaimer INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL PRODUCTS.

More information

Vendor and Hardware Platform: Cisco UCS B200 M2 Virtualization Platform: VMware ESX Build

Vendor and Hardware Platform: Cisco UCS B200 M2 Virtualization Platform: VMware ESX Build Vendor and Hardware Platform: Cisco UCS B200 M2 Virtualization Platform: VMware ESX 4.1.0 Build 260247 Performance Section Performance Tested By: Cisco Systems Test Date: 12-22-2010 Configuration Section

More information

Xen. past, present and future. Stefano Stabellini

Xen. past, present and future. Stefano Stabellini Xen past, present and future Stefano Stabellini Xen architecture: PV domains Xen arch: driver domains Xen: advantages - small surface of attack - isolation - resilience - specialized algorithms (scheduler)

More information

VMware VMmark V2.5.2 Results

VMware VMmark V2.5.2 Results VMware VMmark V2.5.2 Results Vendor and Hardware Platform: Fujitsu Server PRIMERGY RX1330 M3 Virtualization Platform: VMware ESXi 6.0.0 U3 Build 5050593 VMware vcenter Server : VMware vcenter Server 6.0.0

More information

VMmark 3.0 Results. Number of Hosts: 4 Uniform Hosts [yes/no]: Yes Total sockets/cores/threads in test: 8/128/256

VMmark 3.0 Results. Number of Hosts: 4 Uniform Hosts [yes/no]: Yes Total sockets/cores/threads in test: 8/128/256 VMmark 3.0 Results Vendor and Hardware Platform: Supermicro SuperServer SYS-2029BT-HNR Virtualization Platform: VMware ESXi 6.5 U1 (Build 5969303) VMware vcenter Server : VMware vcenter Server 6.5 U1d

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results VMware VMmark V1.1 Results Vendor and Hardware Platform: IBM BladeCenter HS21 XM Virtualization Platform: ESX Server 3.5 Update 1 (build 82663) VMmark V1.1 Score = 8.44 @ 6 Tiles Tested By: Principled

More information

VMware VMmark V1.1.1 Results

VMware VMmark V1.1.1 Results VMware VMmark V1.1.1 Results Vendor and Hardware Platform: HP ProLiant ML370 G6 Virtualization Platform: VMware ESX 4.0 Update 1 (build 208167) Performance Section Performance Tested By: HP Test Date:

More information

SFO17-403: Optimizing the Design and Implementation of KVM/ARM

SFO17-403: Optimizing the Design and Implementation of KVM/ARM SFO17-403: Optimizing the Design and Implementation of KVM/ARM Christoffer Dall connect.linaro.org Efficient, isolated duplicate of the real machine Popek and Golberg [Formal requirements for virtualizable

More information

SANDPIPER: BLACK-BOX AND GRAY-BOX STRATEGIES FOR VIRTUAL MACHINE MIGRATION

SANDPIPER: BLACK-BOX AND GRAY-BOX STRATEGIES FOR VIRTUAL MACHINE MIGRATION SANDPIPER: BLACK-BOX AND GRAY-BOX STRATEGIES FOR VIRTUAL MACHINE MIGRATION Timothy Wood, Prashant Shenoy, Arun Venkataramani, and Mazin Yousif * University of Massachusetts Amherst * Intel, Portland Data

More information

WORKLOAD CHARACTERIZATION OF INTERACTIVE CLOUD SERVICES BIG AND SMALL SERVER PLATFORMS

WORKLOAD CHARACTERIZATION OF INTERACTIVE CLOUD SERVICES BIG AND SMALL SERVER PLATFORMS WORKLOAD CHARACTERIZATION OF INTERACTIVE CLOUD SERVICES ON BIG AND SMALL SERVER PLATFORMS Shuang Chen*, Shay Galon**, Christina Delimitrou*, Srilatha Manne**, and José Martínez* *Cornell University **Cavium

More information

NVMe Over Fabrics: Scaling Up With The Storage Performance Development Kit

NVMe Over Fabrics: Scaling Up With The Storage Performance Development Kit NVMe Over Fabrics: Scaling Up With The Storage Performance Development Kit Ben Walker Data Center Group Intel Corporation 2018 Storage Developer Conference. Intel Corporation. All Rights Reserved. 1 Notices

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results VMware VMmark V1.1 Results Vendor and Hardware Platform: Sun Microsystems Sun Fire X4450 Virtualization Platform: VMware ESX 3.5.0 Update 2 (build 110268) Performance Section Performance Tested By: Sun

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results VMware VMmark V1.1 Results Vendor and Hardware Platform: IBM System x3650 Virtualization Platform: ESX Server 3.5 Update 1 (build 82663) VMmark V1.1 Score = 8.63 @ 6 Tiles Tested By: Principled Technologies

More information

Oracle VM 3.3. Planning and Implementing

Oracle VM 3.3. Planning and Implementing Oracle VM 3.3 Planning and Implementing Agenda 1. Introduction 2. What are we doing 3. Why did we want to virtualize 4. Building the case for virtualization 5. Hardware sizing for Oracle VM 6. Oracle VM

More information

Comparing the Performance and Power of Dell VRTX and HP c3000

Comparing the Performance and Power of Dell VRTX and HP c3000 Comparing the Performance and Power of Dell VRTX and HP c3000 This white paper compares the power efficiency of shared infrastructure solutions based on the Dell PowerEdge VRTX and the HP BladeSystem c3000

More information

Munara Tolubaeva Technical Consulting Engineer. 3D XPoint is a trademark of Intel Corporation in the U.S. and/or other countries.

Munara Tolubaeva Technical Consulting Engineer. 3D XPoint is a trademark of Intel Corporation in the U.S. and/or other countries. Munara Tolubaeva Technical Consulting Engineer 3D XPoint is a trademark of Intel Corporation in the U.S. and/or other countries. notices and disclaimers Intel technologies features and benefits depend

More information

Notes Section Notes for Workload. Configuration Section Configuration. mailserver olio dvdstorea dvdstoreb dvdstorec

Notes Section Notes for Workload. Configuration Section Configuration. mailserver olio dvdstorea dvdstoreb dvdstorec Vendor and Hardware Platform: Cisco UCS B260 M4 Virtualization Platform: VMware ESXi 5.1.0 U2 Build 1483097 VMware vcenter Server : VMware vcenter Server 5.1.0 Build 799731 Number of Hosts: 2 Uniform Hosts

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results VMware VMmark V1.1 Results Vendor and Hardware Platform: HP ProLiant DL585G5 Virtualization Platform: VMware ESX 3.5 Update 3 (build 123630) Performance Section Performance Tested By: Hewlett Packard Test

More information

Arrakis: The Operating System is the Control Plane

Arrakis: The Operating System is the Control Plane Arrakis: The Operating System is the Control Plane Simon Peter, Jialin Li, Irene Zhang, Dan Ports, Doug Woos, Arvind Krishnamurthy, Tom Anderson University of Washington Timothy Roscoe ETH Zurich Building

More information

WHITE PAPER FUJITSU PRIMERGY SERVERS PERFORMANCE REPORT PRIMERGY RX600 S6

WHITE PAPER FUJITSU PRIMERGY SERVERS PERFORMANCE REPORT PRIMERGY RX600 S6 WHITE PAPER PERFORMANCE REPORT PRIMERGY RX600 S6 WHITE PAPER FUJITSU PRIMERGY SERVERS PERFORMANCE REPORT PRIMERGY RX600 S6 This document contains a summary of the benchmarks executed for the PRIMERGY RX600

More information

VMmark 3.0 Results. Number of Hosts: 2 Uniform Hosts [yes/no]: yes Total sockets/cores/threads in test: 4/112/224

VMmark 3.0 Results. Number of Hosts: 2 Uniform Hosts [yes/no]: yes Total sockets/cores/threads in test: 4/112/224 VMmark 3.0 Results Vendor and Hardware Platform: Dell EMC PowerEdge R740xd Virtualization Platform: VMware ESXi 6.5.0a (Build 4887370) VMware vcenter Server : VMware vcenter Server 6.5 U1 (Build 5973321)

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results Vendor and Hardware Platform: IBM System x3850 M2 Virtualization Platform: VMware ESX 3.5.0 U2 Build 103908 VMware VMmark V1.1 Results Tested By: IBM Inc., RTP, NC Test Date: 2008-08-14 Performance Section

More information

Improving CPU Performance of Xen Hypervisor in Virtualized Environment

Improving CPU Performance of Xen Hypervisor in Virtualized Environment ISSN: 2393-8528 Contents lists available at www.ijicse.in International Journal of Innovative Computer Science & Engineering Volume 5 Issue 3; May-June 2018; Page No. 14-19 Improving CPU Performance of

More information

Page 2 of 6 SUT Model Form Factor CPU CPU Characteristics Number of Systems 1 Nodes Per System 1 Chips Per System 2 Hardware hw_1 Cores Per System 44

Page 2 of 6 SUT Model Form Factor CPU CPU Characteristics Number of Systems 1 Nodes Per System 1 Chips Per System 2 Hardware hw_1 Cores Per System 44 Page 1 of 6 SPECjbb2015 Copyright 2015-2016 Standard Performance Evaluation Corporation Cisco Systems Cisco UCS C220 M4 Tested by: Cisco Systems SPEC license #: 9019 94667 SPECjbb2015-Multi max-jops 71951

More information

Kemari: Virtual Machine Synchronization for Fault Tolerance using DomT

Kemari: Virtual Machine Synchronization for Fault Tolerance using DomT Kemari: Virtual Machine Synchronization for Fault Tolerance using DomT Yoshi Tamura NTT Cyber Space Labs. tamura.yoshiaki@lab.ntt.co.jp 2008/6/24 Outline Our goal Design Architecture overview Implementation

More information

Java. Measurement of Virtualization Overhead in a Java Application Server. Kazuaki Takahashi 1 and Hitoshi Oi 1. J2EE SPECjAppServer2004

Java. Measurement of Virtualization Overhead in a Java Application Server. Kazuaki Takahashi 1 and Hitoshi Oi 1. J2EE SPECjAppServer2004 Vol.1-EVA-3 No. 1//3 1. Java 1 1 JEE SPECjAppServer CPU SPECjAppServer 3 CPU Measurement of Virtualization Overhead in a Java Application Server Kazuaki Takahashi 1 and Hitoshi Oi 1 In this technical report,

More information

VMware VMmark V1.1 Results

VMware VMmark V1.1 Results VMware VMmark V1.1 Results Vendor and Hardware Platform: HP ProLiant ML370 G5 Virtualization Platform: VMware ESX 3.5 Update 3 BETA (build 119679) VMmark V1.1 Score = 9.15 @ 7 Tiles Tested By: Hewlett

More information

IOmark- VM. HP HP ConvergedSystem 242- HC StoreVirtual Test Report: VM- HC b Test Report Date: 27, April

IOmark- VM. HP HP ConvergedSystem 242- HC StoreVirtual Test Report: VM- HC b Test Report Date: 27, April IOmark- VM HP HP ConvergedSystem 242- HC StoreVirtual Test Report: VM- HC- 150427- b Test Report Date: 27, April 2015 Copyright 2010-2015 Evaluator Group, Inc. All rights reserved. IOmark- VM, IOmark-

More information

Xen Summit Spring 2007

Xen Summit Spring 2007 Xen Summit Spring 2007 Platform Virtualization with XenEnterprise Rich Persaud 4/20/07 Copyright 2005-2006, XenSource, Inc. All rights reserved. 1 Xen, XenSource and XenEnterprise

More information

WHITE PAPER FUJITSU PRIMERGY SERVERS PERFORMANCE REPORT PRIMERGY BX920 S2

WHITE PAPER FUJITSU PRIMERGY SERVERS PERFORMANCE REPORT PRIMERGY BX920 S2 WHITE PAPER PERFORMANCE REPORT PRIMERGY BX920 S2 WHITE PAPER FUJITSU PRIMERGY SERVERS PERFORMANCE REPORT PRIMERGY BX920 S2 This document contains a summary of the benchmarks executed for the PRIMERGY BX920

More information

VMmark 3.0 Results. Number of Hosts: 4 Uniform Hosts [yes/no]: yes Total sockets/cores/threads in test: 16/448/896

VMmark 3.0 Results. Number of Hosts: 4 Uniform Hosts [yes/no]: yes Total sockets/cores/threads in test: 16/448/896 VMmark 3.0 Results Vendor and Hardware Platform: Fujitsu Server PRIMEQUEST 3800E Virtualization Platform: VMware ESXi 6.7.0 EP 02a Build 9214924 VMware vcenter Server : VMware vcenter Server 6.7.0d Build

More information

CS 350 Winter 2011 Current Topics: Virtual Machines + Solid State Drives

CS 350 Winter 2011 Current Topics: Virtual Machines + Solid State Drives CS 350 Winter 2011 Current Topics: Virtual Machines + Solid State Drives Virtual Machines Resource Virtualization Separating the abstract view of computing resources from the implementation of these resources

More information

Spring 2017 :: CSE 506. Introduction to. Virtual Machines. Nima Honarmand

Spring 2017 :: CSE 506. Introduction to. Virtual Machines. Nima Honarmand Introduction to Virtual Machines Nima Honarmand Virtual Machines & Hypervisors Virtual Machine: an abstraction of a complete compute environment through the combined virtualization of the processor, memory,

More information

Hypervisor security. Evgeny Yakovlev, DEFCON NN, 2017

Hypervisor security. Evgeny Yakovlev, DEFCON NN, 2017 Hypervisor security Evgeny Yakovlev, DEFCON NN, 2017 whoami Low-level development in C and C++ on x86 UEFI, virtualization, security Jetico, Kaspersky Lab QEMU/KVM developer at Virtuozzo 2 Agenda Why hypervisor

More information

Xen on ARM ARMv7 with virtualization extensions

Xen on ARM ARMv7 with virtualization extensions Xen on ARM ARMv7 with virtualization extensions Stefano Stabellini Why? Why? smartphones: getting smarter Quad-core 1.4 GHz Cortex-A9 ARM Servers coming to market 4GB RAM, 4 cores per node 3 x 6 x 4 x

More information

SOLUTION BRIEF. QxStack vsan ReadyNode -Solution Brief for MSSQL

SOLUTION BRIEF. QxStack vsan ReadyNode -Solution Brief for MSSQL SOLUTION BRIEF QxStack vsan ReadyNode -Solution Brief for MSSQL Solution Brief MS SQL Server Performance- QxStack QuantaGrid D51BP-1U All NVMe Value of Information IT organizations are increasingly turning

More information

Enhancing pass through device support with IOMMU. Haitao Shan Yunhong Jiang Allen M Kay Eddie (Yaozu) Dong

Enhancing pass through device support with IOMMU. Haitao Shan Yunhong Jiang Allen M Kay Eddie (Yaozu) Dong Enhancing pass through device support with IOMMU Haitao Shan (haitao.shan@intel.com) Yunhong Jiang Allen M Kay Eddie (Yaozu) Dong Agenda Current Status Further enhancement Hardening host Improving functionality

More information

Virtuozzo Hyperconverged Platform Uses Intel Optane SSDs to Accelerate Performance for Containers and VMs

Virtuozzo Hyperconverged Platform Uses Intel Optane SSDs to Accelerate Performance for Containers and VMs Solution brief Software-Defined Data Center (SDDC) Hyperconverged Platforms Virtuozzo Hyperconverged Platform Uses Intel Optane SSDs to Accelerate Performance for Containers and VMs Virtuozzo benchmark

More information

TIPS TO. ELIMINATE LATENCY in your virtualized environment

TIPS TO. ELIMINATE LATENCY in your virtualized environment 6 TIPS TO ELIMINATE LATENCY in your virtualized environment SOLUTION 1 Background Latency is the principal enemy of an administrator. If your virtual infrastructure is running smoothly and latency is at

More information

Managing Performance Variance of Applications Using Storage I/O Control

Managing Performance Variance of Applications Using Storage I/O Control Performance Study Managing Performance Variance of Applications Using Storage I/O Control VMware vsphere 4.1 Application performance can be impacted when servers contend for I/O resources in a shared storage

More information

NetApp AFF A300 Review

NetApp AFF A300 Review StorageReview StorageReview takes an in-depth look at features, and performance of NetApp AFF A300 storage array. 1395 Crossman Ave Sunnyvale, CA 94089 United States Table of Contents INTRODUCTION... 3-5

More information

AIST Super Green Cloud

AIST Super Green Cloud AIST Super Green Cloud A build-once-run-everywhere high performance computing platform Takahiro Hirofuchi, Ryosei Takano, Yusuke Tanimura, Atsuko Takefusa, and Yoshio Tanaka Information Technology Research

More information

Keeping up with the hardware

Keeping up with the hardware Keeping up with the hardware Challenges in scaling I/O performance Jonathan Davies XenServer System Performance Lead XenServer Engineering, Citrix Cambridge, UK 18 Aug 2015 Jonathan Davies (Citrix) Keeping

More information

VMmark 3.0 Results. Number of Hosts: 2 Uniform Hosts [yes/no]: yes Total sockets/cores/threads in test: 4/112/224

VMmark 3.0 Results. Number of Hosts: 2 Uniform Hosts [yes/no]: yes Total sockets/cores/threads in test: 4/112/224 VMmark 3.0 Results Vendor and Hardware Platform: Fujitsu Server PRIMERGY RX2540 M4 Virtualization Platform: VMware ESXi 6.5.0b Build 5146846 VMware vcenter Server : VMware vcenter Server 6.5.0a Build 4944578

More information

Vendor and Hardware Platform: Cisco UCS C460 M1 Virtualization Platform: VMware ESX 4.0 U2 Build

Vendor and Hardware Platform: Cisco UCS C460 M1 Virtualization Platform: VMware ESX 4.0 U2 Build Vendor and Hardware Platform: Cisco UCS C460 M1 Virtualization Platform: VMware ESX 4.0 U2 Build 261974 Performance Section Performance Tested By: Cisco Systems Test Date: 8-17-2010 Configuration Section

More information

Meet the Increased Demands on Your Infrastructure with Dell and Intel. ServerWatchTM Executive Brief

Meet the Increased Demands on Your Infrastructure with Dell and Intel. ServerWatchTM Executive Brief Meet the Increased Demands on Your Infrastructure with Dell and Intel ServerWatchTM Executive Brief a QuinStreet Excutive Brief. 2012 Doing more with less is the mantra that sums up much of the past decade,

More information

Linux Virtualization Update

Linux Virtualization Update Linux Virtualization Update Chris Wright Japan Linux Symposium, November 2007 Intro Virtualization mini summit Paravirtualization Full virtualization Hardware changes Libvirt Xen Virtualization

More information

IOmark- VM. HP MSA P2000 Test Report: VM a Test Report Date: 4, March

IOmark- VM. HP MSA P2000 Test Report: VM a Test Report Date: 4, March IOmark- VM HP MSA P2000 Test Report: VM- 140304-2a Test Report Date: 4, March 2014 Copyright 2010-2014 Evaluator Group, Inc. All rights reserved. IOmark- VM, IOmark- VDI, VDI- IOmark, and IOmark are trademarks

More information

Notes Section Notes for Workload. Configuration Section Configuration

Notes Section Notes for Workload. Configuration Section Configuration Vendor and Hardware Platform: Fujitsu Server PRIMERGY RX300 S8 Virtualization Platform: VMware ESXi 5.5.0 U3 Build 3029944 VMware vcenter Server : VMware vcenter Server 6.0.0 U1 Build 3018524 Number of

More information

VMmark 3.0 Results. Number of Hosts: 2 Uniform Hosts [yes/no]: yes Total sockets/cores/threads in test: 8/224/448

VMmark 3.0 Results. Number of Hosts: 2 Uniform Hosts [yes/no]: yes Total sockets/cores/threads in test: 8/224/448 Vendor and Hardware Platform: Fujitsu Server PRIMERGY RX4770 M4 Virtualization Platform: VMware ESXi 6.5.0 U1 Build 5969303 VMware vcenter Server : VMware vcenter Server 6.5.0 U1e Build 7515524 VMmark

More information

Number of Hosts: 2 Uniform Hosts [yes/no]: yes Total sockets/core/threads in test: 4/32/64

Number of Hosts: 2 Uniform Hosts [yes/no]: yes Total sockets/core/threads in test: 4/32/64 1 of 7 9/18/2012 11:27 AM Vendor and Hardware Platform: Cisco UCS B200 M3 Virtualization Platform: VMware ESXi 5.1.0 Build 774985 VMware VCenter Server: VMware VCenter Server 5.1.0 Build 775229 Number

More information

Reducing CPU and network overhead for small I/O requests in network storage protocols over raw Ethernet

Reducing CPU and network overhead for small I/O requests in network storage protocols over raw Ethernet Reducing CPU and network overhead for small I/O requests in network storage protocols over raw Ethernet Pilar González-Férez and Angelos Bilas 31 th International Conference on Massive Storage Systems

More information

Avid Configuration Guidelines HP Z820 Dual Six-Core / Dual Eight-Core CPU Workstation

Avid Configuration Guidelines HP Z820 Dual Six-Core / Dual Eight-Core CPU Workstation Avid Configuration Guidelines HP Z820 Dual Six-Core / Dual Eight-Core CPU Workstation Page 1 of 24 Joe Conforti Avid Technology January 24th, 2013 1.) HP Z820 AVID Qualified System Specification: Z820

More information

Introduction of AMD Advanced Virtual Interrupt Controller

Introduction of AMD Advanced Virtual Interrupt Controller Introduction of AMD Advanced Virtual Interrupt Controller XenSummit 2012 Wei Huang August 2012 What is AVIC? AVIC is Advanced Virtual Interrupt Controller A virtual APIC to guest OSs with hardware acceleration

More information

To EL2, and Beyond! connect.linaro.org. Optimizing the Design and Implementation of KVM/ARM

To EL2, and Beyond! connect.linaro.org. Optimizing the Design and Implementation of KVM/ARM To EL2, and Beyond! Optimizing the Design and Implementation of KVM/ARM LEADING COLLABORATION IN THE ARM ECOSYSTEM Christoffer Dall Shih-Wei Li connect.linaro.org

More information

Implementing Virtual NVMe for Flash- Storage Class Memory

Implementing Virtual NVMe for Flash- Storage Class Memory Implementing Virtual NVMe for Flash- Storage Class Memory Jinpyo Kim, Sr. Staff Engineer, VMware Murali Rajagopal, Storage Architect, VMware Santa Clara, CA 1 Virtual NVMe: Motivations (1) Increasing demands

More information

IOmark-VM. VMware VSAN Intel Servers + VMware VSAN Storage SW Test Report: VM-HC a Test Report Date: 16, August

IOmark-VM. VMware VSAN Intel Servers + VMware VSAN Storage SW Test Report: VM-HC a Test Report Date: 16, August IOmark-VM VMware VSAN Intel Servers + VMware VSAN Storage SW Test Report: VM-HC-160816-a Test Report Date: 16, August 2016 Copyright 2010-2016 Evaluator Group, Inc. All rights reserved. IOmark-VM, IOmark-VDI,

More information

High-End Graphics Everywhere! UCS C240 and NVIDIA Grid

High-End Graphics Everywhere! UCS C240 and NVIDIA Grid In Collaboration with Intel High-End Graphics Everywhere! UCS C240 and NVIDIA Grid Mike Brennan Manager, Desktop Virtualization Performance Solutions May 2015 Evolving to VDI 2.0 VDI BC RDP to W2K VM on

More information