Ubuntu Linux 12.10 Xen KVM Virtualization A comparison of Xen and KVM virtualization against bare metal from an Intel Core i7 3960X Extreme Edition system running a development snapshot of Ubuntu 12.10 Quantal from 27 June 2012. Benchmarking for a future article on Phoronix.com.
HTML result view exported from: https://openbenchmarking.org/result/1206282-SU-XENKVMUBU15 .
Ubuntu Linux 12.10 Xen KVM Virtualization Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution System Layer Bare Metal Xen HVM 4.1.2 KVM Virtualization Intel Core i7-3960X @ 3.30GHz (12 Cores) Intel DX79SI Intel Xeon E5/Core 8192MB 64GB OCZ VERTEX AMD Radeon HD 4650 512MB Realtek ALC892 DELL S2409W Intel 82579LM Gigabit Connection Ubuntu 12.10 3.5.0-2-generic (x86_64) Unity 5.12.0 X Server 1.11.3 radeon 6.14.4 2.1 Mesa 8.0.3 Gallium 0.4 GCC 4.7 ext4 1920x1080 Xen HVM domU v4.1.2 Intel 440FX- 82441FX PMC 6144MB 22GB LLVMpipe Ensoniq ES1370 Unity 2D 5.12.0 cirrus 1.4.0 1024x768 Xen HVM domU 4.1.2 QEMU Virtual 1.1.0 @ 3.30GHz (12 Cores) Bochs 18GB Generic 1af4 ID 21 Red Hat Virtio device QEMU 1.1.0 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-arch-32=i686 --with-tune=generic -v Disk Details - CFQ / data=ordered,errors=remount-ro,relatime,rw Processor Details - Bare Metal: Scaling Governor: ondemand System Details - Bare Metal: Disk Scheduler: CFQ. Compiz was running on this system. - Xen HVM 4.1.2: Disk Scheduler: CFQ. - KVM Virtualization: Disk Scheduler: CFQ.
Ubuntu Linux 12.10 Xen KVM Virtualization dbench: 1 tiobench: Rand Write - 64MB - 8 npb: EP.B npb: LU.A npb: MG.B npb: SP.A lammps: Rhodopsin Protein hmmer: Pfam Database Search mafft: Multiple Sequence Alignment scimark2: Composite scimark2: Monte Carlo scimark2: Fast Fourier Transform scimark2: Sparse Matrix Multiply scimark2: Dense LU Matrix Factorization scimark2: Jacobi Successive Over-Relaxation john-the-ripper: Blowfish vpxenc: vpxenc x264: H.264 Video Encoding graphics-magick: Sharpen graphics-magick: Resizing graphics-magick: Local Adaptive Thresholding himeno: Poisson Pressure Solver compress-7zip: Compress Speed Test build-linux-kernel: Time To Compile c-ray: Total Time smallpt: Global Illumination Renderer; 100 Samples ffmpeg: AVI To NTSC VCD openssl: RSA 4096-bit Performance pgbench: TPC-B Transactions Per Second apache: Static Web Page Serving Bare Metal Xen HVM 4.1.2 KVM Virtualization 35.91 3.07 401.84 12804.56 2711.72 3689.33 39.25 15.54 6.17 1262.68 416.59 333.92 2005.39 2378.31 1179.18 8116 27.43 201.46 106 175 102 1632.27 25011 61.53 22.74 64 10.10 92.00 314.05 16780.16 17.95 3.33 378.80 10603.07 2520.88 3472.48 40.22 15.89 12.87 1211.82 405.58 310.11 1930.46 2260.28 1152.69 7664 28.78 192.80 95 153 91 1592.15 24021 103.14 23.71 64 10.79 87.28 176.97 16499.00 26.18 1.75 394.69 11630.58 2471.40 3460.69 39.94 16.10 12.04 1167.57 414.58 232.04 1843.00 2179.17 1169.08 7933 23.05 166.95 104 169 100 1616.82 22812 70.71 23.81 65 10.32 91.53 211.47 16318.92 OpenBenchmarking.org
Dbench Client Count: 1 OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 1 Bare Metal Xen HVM 4.1.2 KVM Virtualization 8 16 24 32 40 SE +/- 0.36, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 35.91 17.95 26.18 1. (CC) gcc options: -lpopt
Threaded I/O Tester Test: Random Write - Size Per Thread: 64MB - Thread Count: 8 OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 0.3.3 Test: Random Write - Size Per Thread: 64MB - Thread Count: 8 Bare Metal Xen HVM 4.1.2 KVM Virtualization 0.7493 1.4986 2.2479 2.9972 3.7465 SE +/- 0.05, N = 8 SE +/- 0.04, N = 4 SE +/- 0.01, N = 4 3.07 3.33 1.75
NAS Parallel Benchmarks Test / Class: EP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: EP.B Bare Metal Xen HVM 4.1.2 KVM Virtualization 90 180 270 360 450 SE +/- 0.27, N = 3 SE +/- 5.68, N = 6 SE +/- 0.34, N = 3 401.84 378.80 394.69 1. (F9X) gfortran options: -fopenmp
NAS Parallel Benchmarks Test / Class: LU.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: LU.A Bare Metal Xen HVM 4.1.2 KVM Virtualization 3K 6K 9K 12K 15K SE +/- 17.50, N = 3 SE +/- 225.13, N = 6 SE +/- 232.55, N = 3 12804.56 10603.07 11630.58 1. (F9X) gfortran options: -fopenmp
NAS Parallel Benchmarks Test / Class: MG.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: MG.B Bare Metal Xen HVM 4.1.2 KVM Virtualization 600 1200 1800 2400 3000 SE +/- 1.62, N = 3 SE +/- 26.68, N = 3 SE +/- 37.34, N = 3 2711.72 2520.88 2471.40 1. (F9X) gfortran options: -fopenmp
NAS Parallel Benchmarks Test / Class: SP.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: SP.A Bare Metal Xen HVM 4.1.2 KVM Virtualization 800 1600 2400 3200 4000 SE +/- 7.20, N = 3 SE +/- 23.94, N = 3 SE +/- 42.40, N = 3 3689.33 3472.48 3460.69 1. (F9X) gfortran options: -fopenmp
LAMMPS Molecular Dynamics Simulator Test: Rhodopsin Protein OpenBenchmarking.org Loop Time, Fewer Is Better LAMMPS Molecular Dynamics Simulator 1.0 Test: Rhodopsin Protein Bare Metal Xen HVM 4.1.2 KVM Virtualization 9 18 27 36 45 SE +/- 0.05, N = 3 SE +/- 0.24, N = 3 SE +/- 0.02, N = 3 39.25 40.22 39.94 1. (CXX) g++ options: -lfftw -lmpich
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search Bare Metal Xen HVM 4.1.2 KVM Virtualization 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 15.54 15.89 16.10 1. (CC) gcc options: -O2 -pthread -lhmmer -lsquid -lm
Timed MAFFT Alignment Multiple Sequence Alignment OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 6.864 Multiple Sequence Alignment Bare Metal Xen HVM 4.1.2 KVM Virtualization 3 6 9 12 15 SE +/- 0.17, N = 6 SE +/- 0.22, N = 4 SE +/- 0.32, N = 6 6.17 12.87 12.04 1. (CC) gcc options: -O3 -lm -lpthread
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite Bare Metal Xen HVM 4.1.2 KVM Virtualization 300 600 900 1200 1500 SE +/- 0.68, N = 4 SE +/- 4.94, N = 4 SE +/- 2.83, N = 4 1262.68 1211.82 1167.57
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo Bare Metal Xen HVM 4.1.2 KVM Virtualization 90 180 270 360 450 SE +/- 0.41, N = 4 SE +/- 1.15, N = 4 SE +/- 1.13, N = 4 416.59 405.58 414.58
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform Bare Metal Xen HVM 4.1.2 KVM Virtualization 70 140 210 280 350 SE +/- 1.23, N = 4 SE +/- 3.17, N = 4 SE +/- 0.30, N = 4 333.92 310.11 232.04
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply Bare Metal Xen HVM 4.1.2 KVM Virtualization 400 800 1200 1600 2000 SE +/- 2.45, N = 4 SE +/- 20.40, N = 4 SE +/- 3.98, N = 4 2005.39 1930.46 1843.00
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization Bare Metal Xen HVM 4.1.2 KVM Virtualization 500 1000 1500 2000 2500 SE +/- 2.64, N = 4 SE +/- 17.22, N = 4 SE +/- 7.58, N = 4 2378.31 2260.28 2179.17
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation Bare Metal Xen HVM 4.1.2 KVM Virtualization 300 600 900 1200 1500 SE +/- 0.00, N = 4 SE +/- 6.38, N = 4 SE +/- 2.80, N = 4 1179.18 1152.69 1169.08
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.9 Test: Blowfish Bare Metal Xen HVM 4.1.2 KVM Virtualization 2K 4K 6K 8K 10K SE +/- 5.33, N = 3 SE +/- 146.21, N = 3 SE +/- 0.67, N = 3 8116 7664 7933 1. (CC) gcc options: -fopenmp -lcrypt
VP8 libvpx Encoding vpxenc OpenBenchmarking.org Frames Per Second, More Is Better VP8 libvpx Encoding 0.9.7-p1 vpxenc Bare Metal Xen HVM 4.1.2 KVM Virtualization 7 14 21 28 35 SE +/- 0.22, N = 3 SE +/- 0.39, N = 3 SE +/- 0.38, N = 3 27.43 28.78 23.05 1. (CC) gcc options: -m64 -lvpx -lm -lpthread
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2011-12-06 H.264 Video Encoding Bare Metal Xen HVM 4.1.2 KVM Virtualization 40 80 120 160 200 SE +/- 2.94, N = 5 SE +/- 3.67, N = 6 SE +/- 5.08, N = 6 201.46 192.80 166.95
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Sharpen Bare Metal Xen HVM 4.1.2 KVM Virtualization 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 106 95 104 1. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Resizing Bare Metal Xen HVM 4.1.2 KVM Virtualization 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 1.20, N = 3 SE +/- 0.67, N = 3 175 153 169 1. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Local Adaptive Thresholding OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Local Adaptive Thresholding Bare Metal Xen HVM 4.1.2 KVM Virtualization 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 1.00, N = 3 SE +/- 0.00, N = 3 102 91 100 1. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver Bare Metal Xen HVM 4.1.2 KVM Virtualization 400 800 1200 1600 2000 SE +/- 1.21, N = 3 SE +/- 7.54, N = 3 SE +/- 3.25, N = 3 1632.27 1592.15 1616.82 1. (CC) gcc options: -O3
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 9.20.1 Compress Speed Test Bare Metal Xen HVM 4.1.2 KVM Virtualization 5K 10K 15K 20K 25K SE +/- 82.72, N = 3 SE +/- 69.43, N = 3 SE +/- 139.43, N = 3 25011 24021 22812 1. (CXX) g++ options: -pipe -lpthread
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 3.1 Time To Compile Bare Metal Xen HVM 4.1.2 KVM Virtualization 20 40 60 80 100 SE +/- 0.58, N = 3 SE +/- 0.66, N = 3 SE +/- 1.36, N = 3 61.53 103.14 70.71
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time Bare Metal Xen HVM 4.1.2 KVM Virtualization 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 22.74 23.71 23.81 1. (CC) gcc options: -lm -lpthread -O3
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples Bare Metal Xen HVM 4.1.2 KVM Virtualization 15 30 45 60 75 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 64 64 65 1. (CXX) g++ options: -fopenmp
FFmpeg AVI To NTSC VCD OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 0.10 AVI To NTSC VCD Bare Metal Xen HVM 4.1.2 KVM Virtualization 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.16, N = 3 SE +/- 0.01, N = 3 10.10 10.79 10.32 1. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lm -pthread
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.0.0e RSA 4096-bit Performance Bare Metal Xen HVM 4.1.2 KVM Virtualization 20 40 60 80 100 SE +/- 0.23, N = 4 SE +/- 0.95, N = 4 SE +/- 0.26, N = 4 92.00 87.28 91.53 1. (CC) gcc options: -m64 -O3 -lssl -lcrypto -ldl
PostgreSQL pgbench TPC-B Transactions Per Second OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 8.4.11 TPC-B Transactions Per Second Bare Metal Xen HVM 4.1.2 KVM Virtualization 70 140 210 280 350 SE +/- 2.51, N = 3 SE +/- 0.70, N = 3 SE +/- 2.14, N = 3 314.05 176.97 211.47 1. (CC) gcc options: -O2 -fno-strict-aliasing -fwrapv -lpgport -lpq -lcrypt -ldl -lm
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.2.21 Static Web Page Serving Bare Metal Xen HVM 4.1.2 KVM Virtualization 4K 8K 12K 16K 20K SE +/- 101.52, N = 3 SE +/- 69.42, N = 3 SE +/- 124.98, N = 3 16780.16 16499.00 16318.92 1. (CC) gcc options: -O2 -pthread -lm -lrt -lcrypt -lpthread -ldl
Phoronix Test Suite v10.8.4