Tests for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1808277-RA-MICROCODE34 Linux 4.19 + New Microcode: Bare Metal vs. KVM Guest - Phoronix Test Suite Linux 4.19 + New Microcode: Bare Metal vs. KVM Guest Tests for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1808277-RA-MICROCODE34&grs&sor .
Processor Motherboard Chipset Memory Disk Graphics Monitor Network Audio OS Kernel Desktop Display Server Display Driver Compiler File-System Screen Resolution System Layer Stock New Microcode Bare Metal VM Guest Bare Metal VM Guest 2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads) TYAN S7106 (V1.01 BIOS) Intel Sky Lake-E DMI3 Registers 96256MB 256GB Samsung SSD 850 + 2000GB Seagate ST2000DM006-2DM1 + 2 x 120GB TOSHIBA-TR150 ASPEED ASPEED Family VE228 Intel I210 Gigabit Connection Ubuntu 18.04 4.18.0-999-generic (x86_64) 20180824 GNOME Shell 3.28.2 X Server 1.19.6 modesetting 1.19.6 GCC 7.3.0 ext4 1920x1080 64 x Intel Xeon (Skylake IBRS) @ 2.00GHz (64 Cores) QEMU Standard PC (i440FX + PIIX 1996) (1.10.2-1ubuntu1 BIOS) Intel 440FX- 82441FX PMC 47104MB 162GB Red Hat QXL paravirtual graphic card QEMU Generic Red Hat Virtio device 1024x768 KVM 2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads) TYAN S7106 (V1.01 BIOS) Intel Sky Lake-E DMI3 Registers 96256MB 256GB Samsung SSD 850 + 2000GB Seagate ST2000DM006-2DM1 + 2 x 120GB TOSHIBA-TR150 ASPEED ASPEED Family VE228 Intel I210 Gigabit Connection 1920x1080 64 x Intel Xeon (Skylake IBRS) @ 2.00GHz (64 Cores) QEMU Standard PC (i440FX + PIIX 1996) (1.10.2-1ubuntu1 BIOS) Intel 440FX- 82441FX PMC 47104MB 162GB Red Hat QXL paravirtual graphic card QEMU Generic Red Hat Virtio device 1024x768 KVM OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-as=/usr/bin/x86_64-linux-gnu-as --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-ld=/usr/bin/x86_64-linux-gnu-ld --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Disk Details - Stock: Bare Metal: CFQ / errors=remount-ro,relatime,rw - Stock: VM Guest: NONE / errors=remount-ro,relatime,rw - New Microcode: Bare Metal: CFQ / errors=remount-ro,relatime,rw - New Microcode: VM Guest: NONE / errors=remount-ro,relatime,rw Processor Details - Stock: Bare Metal, New Microcode: Bare Metal: Scaling Governor: intel_pstate powersave Python Details - Python 2.7.15rc1 + Python 3.6.5 Security Details - Stock: Bare Metal: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + PTE Inversion; VMX: conditional cache flushes SMT vulnerable Protection - Stock: VM Guest: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + PTE Inversion Protection - New Microcode: Bare Metal: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable Protection - New Microcode: VM Guest: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + PTE Inversion Protection
stress-ng: Semaphores primesieve: 1e12 Prime Number Generation mysqlslap: 32 pgbench: Buffer Test - Normal Load - Read Only build-llvm: Time To Compile compilebench: Compile sysbench: CPU blender: Barbershop - CPU-Only sysbench: Memory ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping compilebench: Initial Create compilebench: Read Compiled Tree x265: H.265 Video Encoding nginx: Static Web Page Serving stress-ng: System V Message Passing stress-ng: Context Switching stress-ng: Socket Activity redis: SET redis: GET hackbench: 32 - Process build-linux-kernel: Time To Compile Stock New Microcode Bare Metal VM Guest Bare Metal VM Guest 1831962.43 8.62 246 585224.79 169.53 1712.79 58755.65 374.05 11764465.11 742.68 501.79 2469.93 10.31 24591.86 7053890.14 22234776.32 3454.63 1656081.46 2142971.11 35.73 33.70 600043.13 24.62 131 384280.70 208.78 1467.65 51676.09 423.31 10796572.79 673.74 460.82 2351.28 10.36 27078.58 11422458.91 12704770.93 14127.95 1455207.36 1999876.29 71.54 37.21 1890399.79 8.64 221 588527.68 171.02 1698.50 59370.55 373.98 11803679.99 731.60 487.43 2478.36 10.32 23745.74 7163233.31 22976365.08 3313.12 1688379.92 2059062.25 36.73 33.40 602511.28 24.41 152 377789.35 208.59 1489.48 51662.13 420.12 10580279.09 668.11 460.99 2281.89 10.43 27448.91 12196067.33 12082482.71 13024.27 1393755.40 1997504.97 73.79 36.90 OpenBenchmarking.org
Stress-NG Test: Semaphores New Microcode Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores Bare Metal VM Guest 400K 800K 1200K 1600K 2000K SE +/- 26014.39, N = 6 SE +/- 2331.55, N = 3 SE +/- 29092.76, N = 3 SE +/- 925.56, N = 3 1890399.79 602511.28 1831962.43 600043.13 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Primesieve 1e12 Prime Number Generation Stock New Microcode OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.1 1e12 Prime Number Generation Bare Metal VM Guest 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.02, N = 3 SE +/- 0.25, N = 3 8.62 24.62 8.64 24.41 1. (CXX) g++ options: -O3 -lpthread
MariaDB Clients: 32 Stock New Microcode OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.3.8 Clients: 32 Bare Metal VM Guest 50 100 150 200 250 SE +/- 1.96, N = 3 SE +/- 0.75, N = 3 SE +/- 2.85, N = 3 SE +/- 0.67, N = 3 246 131 221 152 1. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -laio -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only New Microcode Stock OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only Bare Metal VM Guest 130K 260K 390K 520K 650K SE +/- 823.94, N = 3 SE +/- 3308.21, N = 3 SE +/- 2323.77, N = 3 SE +/- 2865.20, N = 3 588527.68 377789.35 585224.79 384280.70 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Timed LLVM Compilation Time To Compile Stock New Microcode OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 6.0.1 Time To Compile Bare Metal VM Guest 50 100 150 200 250 169.53 208.78 171.02 208.59
Compile Bench Test: Compile Stock New Microcode OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile Bare Metal VM Guest 400 800 1200 1600 2000 SE +/- 8.67, N = 3 SE +/- 11.24, N = 3 SE +/- 2.32, N = 3 SE +/- 4.45, N = 3 1712.79 1467.65 1698.50 1489.48
Sysbench Test: CPU New Microcode Stock OpenBenchmarking.org Events Per Second, More Is Better Sysbench 2018-07-28 Test: CPU Bare Metal VM Guest 13K 26K 39K 52K 65K SE +/- 296.24, N = 3 SE +/- 11.32, N = 3 SE +/- 583.55, N = 3 SE +/- 5.72, N = 3 59370.55 51662.13 58755.65 51676.09 1. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=core2 -rdynamic -ldl -laio -lm
Blender Blend File: Barbershop - Compute: CPU-Only New Microcode Stock OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: Barbershop - Compute: CPU-Only Bare Metal VM Guest 90 180 270 360 450 373.98 420.12 374.05 423.31
Sysbench Test: Memory New Microcode Stock OpenBenchmarking.org Events Per Second, More Is Better Sysbench 2018-07-28 Test: Memory Bare Metal VM Guest 3M 6M 9M 12M 15M SE +/- 188626.26, N = 3 SE +/- 113244.97, N = 3 SE +/- 132541.95, N = 12 SE +/- 139878.10, N = 3 11803679.99 10580279.09 11764465.11 10796572.79 1. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=core2 -rdynamic -ldl -laio -lm
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping Stock New Microcode OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping Bare Metal VM Guest 160 320 480 640 800 SE +/- 10.35, N = 3 SE +/- 6.63, N = 3 SE +/- 6.67, N = 3 SE +/- 3.91, N = 3 742.68 673.74 731.60 668.11 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
Compile Bench Test: Initial Create Stock New Microcode OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create Bare Metal VM Guest 110 220 330 440 550 SE +/- 3.51, N = 3 SE +/- 15.44, N = 3 SE +/- 1.19, N = 3 SE +/- 5.36, N = 3 501.79 460.82 487.43 460.99
Compile Bench Test: Read Compiled Tree New Microcode Stock OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree Bare Metal VM Guest 500 1000 1500 2000 2500 SE +/- 27.68, N = 3 SE +/- 35.39, N = 3 SE +/- 12.91, N = 3 SE +/- 12.12, N = 3 2478.36 2281.89 2469.93 2351.28
Tinymembench Standard Memset Stock New Microcode OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset Bare Metal VM Guest 2K 4K 6K 8K 10K 9298.20 8980.20 9151.70 1. (CC) gcc options: -O2 -lm
x265 H.265 Video Encoding New Microcode Stock OpenBenchmarking.org Frames Per Second, More Is Better x265 2.8 H.265 Video Encoding VM Guest Bare Metal 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 10.43 10.32 10.36 10.31 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
NGINX Benchmark Static Web Page Serving New Microcode Stock OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving VM Guest Bare Metal 6K 12K 18K 24K 30K SE +/- 83.37, N = 3 SE +/- 114.41, N = 3 SE +/- 1495.37, N = 3 SE +/- 140.64, N = 3 27448.91 23745.74 27078.58 24591.86 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
Stress-NG Test: System V Message Passing New Microcode Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: System V Message Passing VM Guest Bare Metal 3M 6M 9M 12M 15M SE +/- 55318.04, N = 3 SE +/- 457349.76, N = 9 SE +/- 87029.51, N = 3 SE +/- 342053.14, N = 12 12196067.33 7163233.31 11422458.91 7053890.14 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Stress-NG Test: Context Switching New Microcode Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching Bare Metal VM Guest 5M 10M 15M 20M 25M SE +/- 550387.69, N = 12 SE +/- 69768.14, N = 3 SE +/- 858271.57, N = 12 SE +/- 57576.83, N = 3 22976365.08 12082482.71 22234776.32 12704770.93 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Stress-NG Test: Socket Activity Stock New Microcode OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity VM Guest Bare Metal 3K 6K 9K 12K 15K SE +/- 151.62, N = 3 SE +/- 853.24, N = 12 SE +/- 207.14, N = 3 SE +/- 943.03, N = 12 14127.95 3454.63 13024.27 3313.12 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Redis Test: SET New Microcode Stock OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SET Bare Metal VM Guest 400K 800K 1200K 1600K 2000K SE +/- 10888.60, N = 3 SE +/- 60085.02, N = 12 SE +/- 19253.77, N = 3 SE +/- 51445.85, N = 12 1688379.92 1393755.40 1656081.46 1455207.36 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Redis Test: GET Stock New Microcode OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: GET Bare Metal VM Guest 500K 1000K 1500K 2000K 2500K SE +/- 42615.86, N = 12 SE +/- 67289.89, N = 12 SE +/- 6166.42, N = 3 SE +/- 51272.68, N = 12 2142971.11 1999876.29 2059062.25 1997504.97 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Hackbench Count: 32 - Type: Process Stock New Microcode OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process Bare Metal VM Guest 16 32 48 64 80 SE +/- 0.99, N = 12 SE +/- 0.25, N = 3 SE +/- 0.69, N = 3 SE +/- 0.53, N = 3 35.73 71.54 36.73 73.79 1. (CC) gcc options: -lpthread
Timed Linux Kernel Compilation Time To Compile New Microcode Stock OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 4.18 Time To Compile Bare Metal VM Guest 9 18 27 36 45 SE +/- 0.50, N = 12 SE +/- 0.41, N = 12 SE +/- 1.08, N = 12 SE +/- 0.41, N = 12 33.40 36.90 33.70 37.21
Phoronix Test Suite v10.8.4