KVM testing on Debian 10 via the Phoronix Test Suite.
n2d-standard-16 Processor: AMD EPYC 7B12 (8 Cores / 16 Threads), Motherboard: Google Compute Engine n2d-standard-16, Memory: 64GB, Disk: 32GB PersistentDisk
OS: Debian 10, Kernel: 4.19.0-13-cloud-amd64 (x86_64), Compiler: GCC 8.3.0, File-System: ext4, System Layer: KVM
Kernel Notes: scsi_mod.use_blk_mq=Y - Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / discard,errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: CPU Microcode: 0x1000065Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-post-Debian-1deb10u2)Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
benchmark-n2d OpenBenchmarking.org Phoronix Test Suite AMD EPYC 7B12 (8 Cores / 16 Threads) Google Compute Engine n2d-standard-16 64GB 32GB PersistentDisk Debian 10 4.19.0-13-cloud-amd64 (x86_64) GCC 8.3.0 ext4 KVM Processor Motherboard Memory Disk OS Kernel Compiler File-System System Layer Benchmark-n2d Performance System Logs - scsi_mod.use_blk_mq=Y - Transparent Huge Pages: always - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v - NONE / discard,errors=remount-ro,relatime,rw / Block Size: 4096 - CPU Microcode: 0x1000065 - OpenJDK Runtime Environment (build 11.0.9.1+1-post-Debian-1deb10u2) - Python 2.7.16 + Python 3.7.3 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
benchmark-n2d compilebench: Compile compilebench: Initial Create compilebench: Read Compiled Tree ior: 8MB - Default Test Directory stress-ng: MMAP stress-ng: NUMA stress-ng: MEMFD stress-ng: Atomic stress-ng: Crypto ior: 64MB - Default Test Directory stress-ng: Malloc stress-ng: Forking stress-ng: SENDFILE stress-ng: CPU Cache stress-ng: CPU Stress stress-ng: Semaphores stress-ng: Matrix Math ior: 32MB - Default Test Directory ior: 16MB - Default Test Directory ior: 4MB - Default Test Directory stress-ng: Vector Math stress-ng: Memory Copying stress-ng: Socket Activity stress-ng: Context Switching stress-ng: Glibc C String Functions stress-ng: Glibc Qsort Data Sorting stress-ng: System V Message Passing sockperf: Throughput sockperf: Latency Ping Pong ior: 2MB - Default Test Directory sockperf: Latency Under Load ramspeed: Add - Integer ramspeed: Copy - Integer ramspeed: Scale - Integer ramspeed: Triad - Integer ramspeed: Average - Integer ramspeed: Add - Floating Point ramspeed: Copy - Floating Point ramspeed: Scale - Floating Point ramspeed: Triad - Floating Point ramspeed: Average - Floating Point hint: FLOAT multichase: 4MB Array, 64 Byte Stride multichase: 1GB Array, 256 Byte Stride multichase: 256MB Array, 256 Byte Stride multichase: 1GB Array, 256 Byte Stride, 2 Threads multichase: 1GB Array, 256 Byte Stride, 4 Threads dbench: 12 Clients fio: Rand Read - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Rand Read - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Rand Read - Linux AIO - No - Yes - 4KB - Default Test Directory fio: Rand Read - Linux AIO - No - Yes - 4KB - Default Test Directory fio: Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Rand Write - Linux AIO - No - Yes - 4KB - Default Test Directory fio: Rand Write - Linux AIO - No - Yes - 4KB - Default Test Directory fio: Seq Read - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Seq Read - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Seq Read - Linux AIO - No - Yes - 4KB - Default Test Directory fio: Seq Read - Linux AIO - No - Yes - 4KB - Default Test Directory fio: Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Seq Write - Linux AIO - No - Yes - 4KB - Default Test Directory fio: Seq Write - Linux AIO - No - Yes - 4KB - Default Test Directory osbench: Create Files osbench: Create Threads osbench: Launch Programs osbench: Create Processes osbench: Memory Allocations pmbench: 1 - 50% pmbench: 2 - 50% pmbench: 4 - 50% pmbench: 8 - 50% pmbench: 16 - 50% pmbench: 1 - 100% Reads pmbench: 2 - 100% Reads pmbench: 4 - 100% Reads pmbench: 8 - 100% Reads pmbench: 1 - 100% Writes pmbench: 16 - 100% Reads pmbench: 2 - 100% Writes pmbench: 4 - 100% Writes pmbench: 8 - 100% Writes pmbench: 16 - 100% Writes pmbench: 1 - 80% Reads 20% Writes pmbench: 2 - 80% Reads 20% Writes pmbench: 4 - 80% Reads 20% Writes pmbench: 8 - 80% Reads 20% Writes pmbench: 16 - 80% Reads 20% Writes coremark: CoreMark Size 666 - Iterations Per Second build-apache: Time To Compile compress-7zip: Compress Speed Test build-linux-kernel: Time To Compile x264: H.264 Video Encoding openssl: RSA 4096-bit Performance redis: LPOP redis: SADD redis: LPUSH redis: GET redis: SET sqlite: 1 sqlite-speedtest: Timed Time - Size 1,000 n2d-standard-16 1600.42 394.84 2615.09 12.92 222.59 2086.06 584.57 381866.99 1695.33 11.82 73559568.13 15912.69 124211.30 34.78 2256.90 925452.74 36305.86 11.84 11.98 14.63 56129.04 9269.32 5963.48 3275655.88 780364.64 88.92 5909219.14 585573 13.660 17.46 33.200 41452.57 41988.18 36105.67 43509.16 40777.73 43638.75 41079.97 39649.72 42899.76 41409.79 269367383.13479 8.192 94.491 94.082 94.748 96.403 325.791 16.0 5 0.302 72 14.5 5 0.699 171 11.9 3 11.5 3052 14.9 5 11.2 3056 17.192537 24.369240 60.500622 37.851731 91.470639 0.1022 0.1080 0.1106 0.1219 0.1218 0.0594 0.0545 0.0544 0.0542 0.0707 0.0570 0.0712 0.0669 0.0604 0.0787 0.1289 0.1560 0.1437 0.1441 0.1541 282525.767448 24.613 44274 84.936 64.19 1804.4 1636222.29 1292686.00 985310.29 1504492.63 1124629.87 33.654 83.964 OpenBenchmarking.org
Compile Bench Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile n2d-standard-16 300 600 900 1200 1500 SE +/- 29.77, N = 9 1600.42
IOR IOR is a parallel I/O storage benchmark making use of MPI with a particular focus on HPC (High Performance Computing) systems. IOR is developed at the Lawrence Livermore National Laboratory (LLNL). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better IOR 3.3.0 Block Size: 8MB - Disk Target: Default Test Directory n2d-standard-16 3 6 9 12 15 SE +/- 0.17, N = 9 12.92 MIN: 11.33 / MAX: 137.23 1. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: NUMA n2d-standard-16 400 800 1200 1600 2000 SE +/- 19.64, N = 3 2086.06 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MEMFD n2d-standard-16 130 260 390 520 650 SE +/- 3.51, N = 3 584.57 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic n2d-standard-16 80K 160K 240K 320K 400K SE +/- 1202.90, N = 3 381866.99 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto n2d-standard-16 400 800 1200 1600 2000 SE +/- 0.35, N = 3 1695.33 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
IOR IOR is a parallel I/O storage benchmark making use of MPI with a particular focus on HPC (High Performance Computing) systems. IOR is developed at the Lawrence Livermore National Laboratory (LLNL). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better IOR 3.3.0 Block Size: 64MB - Disk Target: Default Test Directory n2d-standard-16 3 6 9 12 15 SE +/- 0.01, N = 3 11.82 MIN: 9.88 / MAX: 16.05 1. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Forking n2d-standard-16 3K 6K 9K 12K 15K SE +/- 73.46, N = 3 15912.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE n2d-standard-16 30K 60K 90K 120K 150K SE +/- 213.15, N = 3 124211.30 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Cache n2d-standard-16 8 16 24 32 40 SE +/- 0.63, N = 15 34.78 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress n2d-standard-16 500 1000 1500 2000 2500 SE +/- 1.91, N = 3 2256.90 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores n2d-standard-16 200K 400K 600K 800K 1000K SE +/- 1313.80, N = 3 925452.74 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Matrix Math n2d-standard-16 8K 16K 24K 32K 40K SE +/- 22.40, N = 3 36305.86 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
IOR IOR is a parallel I/O storage benchmark making use of MPI with a particular focus on HPC (High Performance Computing) systems. IOR is developed at the Lawrence Livermore National Laboratory (LLNL). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better IOR 3.3.0 Block Size: 32MB - Disk Target: Default Test Directory n2d-standard-16 3 6 9 12 15 SE +/- 0.03, N = 3 11.84 MIN: 11.47 / MAX: 24.74 1. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.org MB/s, More Is Better IOR 3.3.0 Block Size: 16MB - Disk Target: Default Test Directory n2d-standard-16 3 6 9 12 15 SE +/- 0.12, N = 9 11.98 MIN: 11.42 / MAX: 128.46 1. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.org MB/s, More Is Better IOR 3.3.0 Block Size: 4MB - Disk Target: Default Test Directory n2d-standard-16 4 8 12 16 20 SE +/- 0.28, N = 9 14.63 MIN: 11.1 / MAX: 234.43 1. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Memory Copying n2d-standard-16 2K 4K 6K 8K 10K SE +/- 14.51, N = 3 9269.32 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity n2d-standard-16 1300 2600 3900 5200 6500 SE +/- 60.33, N = 3 5963.48 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching n2d-standard-16 700K 1400K 2100K 2800K 3500K SE +/- 15624.04, N = 3 3275655.88 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc C String Functions n2d-standard-16 200K 400K 600K 800K 1000K SE +/- 3322.92, N = 3 780364.64 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc Qsort Data Sorting n2d-standard-16 20 40 60 80 100 SE +/- 1.35, N = 15 88.92 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing n2d-standard-16 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 77069.46, N = 15 5909219.14 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc
OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Ping Pong n2d-standard-16 4 8 12 16 20 SE +/- 0.20, N = 25 13.66 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
IOR IOR is a parallel I/O storage benchmark making use of MPI with a particular focus on HPC (High Performance Computing) systems. IOR is developed at the Lawrence Livermore National Laboratory (LLNL). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better IOR 3.3.0 Block Size: 2MB - Disk Target: Default Test Directory n2d-standard-16 4 8 12 16 20 SE +/- 0.58, N = 12 17.46 MIN: 10.26 / MAX: 356.52 1. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Floating Point n2d-standard-16 9K 18K 27K 36K 45K SE +/- 440.57, N = 15 43638.75 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Floating Point n2d-standard-16 9K 18K 27K 36K 45K SE +/- 451.48, N = 3 41079.97 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Floating Point n2d-standard-16 8K 16K 24K 32K 40K SE +/- 426.91, N = 5 39649.72 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Floating Point n2d-standard-16 9K 18K 27K 36K 45K SE +/- 561.19, N = 15 42899.76 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Floating Point n2d-standard-16 9K 18K 27K 36K 45K SE +/- 294.04, N = 3 41409.79 1. (CC) gcc options: -O3 -march=native
Flexible IO Tester FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory n2d-standard-16 4 8 12 16 20 SE +/- 5.02, N = 15 16.0 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory n2d-standard-16 1.125 2.25 3.375 4.5 5.625 SE +/- 2.47, N = 15 5 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory n2d-standard-16 0.068 0.136 0.204 0.272 0.34 SE +/- 0.000, N = 3 0.302 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory n2d-standard-16 16 32 48 64 80 72 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory n2d-standard-16 4 8 12 16 20 SE +/- 0.27, N = 15 14.5 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory n2d-standard-16 1.125 2.25 3.375 4.5 5.625 SE +/- 0.16, N = 15 5 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory n2d-standard-16 0.1573 0.3146 0.4719 0.6292 0.7865 SE +/- 0.015, N = 14 0.699 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory n2d-standard-16 40 80 120 160 200 SE +/- 3.62, N = 14 171 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory n2d-standard-16 3 6 9 12 15 SE +/- 0.00, N = 3 11.9 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory n2d-standard-16 0.675 1.35 2.025 2.7 3.375 3 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory n2d-standard-16 3 6 9 12 15 SE +/- 0.12, N = 15 11.5 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory n2d-standard-16 700 1400 2100 2800 3500 SE +/- 2.08, N = 15 3052 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory n2d-standard-16 4 8 12 16 20 SE +/- 0.36, N = 15 14.9 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory n2d-standard-16 1.125 2.25 3.375 4.5 5.625 5 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory n2d-standard-16 3 6 9 12 15 SE +/- 0.11, N = 15 11.2 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory n2d-standard-16 700 1400 2100 2800 3500 SE +/- 2.76, N = 15 3056 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OSBench OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files n2d-standard-16 4 8 12 16 20 SE +/- 0.01, N = 3 17.19 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads n2d-standard-16 6 12 18 24 30 SE +/- 0.44, N = 15 24.37 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs n2d-standard-16 14 28 42 56 70 SE +/- 0.80, N = 15 60.50 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes n2d-standard-16 9 18 27 36 45 SE +/- 1.59, N = 12 37.85 1. (CC) gcc options: -lm
OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations n2d-standard-16 20 40 60 80 100 SE +/- 0.15, N = 3 91.47 1. (CC) gcc options: -lm
pmbench Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 50% n2d-standard-16 0.023 0.046 0.069 0.092 0.115 SE +/- 0.0001, N = 3 0.1022 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 50% n2d-standard-16 0.0243 0.0486 0.0729 0.0972 0.1215 SE +/- 0.0006, N = 3 0.1080 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 50% n2d-standard-16 0.0249 0.0498 0.0747 0.0996 0.1245 SE +/- 0.0001, N = 3 0.1106 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 50% n2d-standard-16 0.0274 0.0548 0.0822 0.1096 0.137 SE +/- 0.0045, N = 15 0.1219 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 16 - Read-Write Ratio: 50% n2d-standard-16 0.0274 0.0548 0.0822 0.1096 0.137 SE +/- 0.0010, N = 9 0.1218 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Reads n2d-standard-16 0.0134 0.0268 0.0402 0.0536 0.067 SE +/- 0.0032, N = 15 0.0594 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Reads n2d-standard-16 0.0123 0.0246 0.0369 0.0492 0.0615 SE +/- 0.0000, N = 3 0.0545 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Reads n2d-standard-16 0.0122 0.0244 0.0366 0.0488 0.061 SE +/- 0.0000, N = 3 0.0544 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Reads n2d-standard-16 0.0122 0.0244 0.0366 0.0488 0.061 SE +/- 0.0001, N = 3 0.0542 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Writes n2d-standard-16 0.0159 0.0318 0.0477 0.0636 0.0795 SE +/- 0.0041, N = 15 0.0707 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 16 - Read-Write Ratio: 100% Reads n2d-standard-16 0.0128 0.0256 0.0384 0.0512 0.064 SE +/- 0.0003, N = 3 0.0570 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Writes n2d-standard-16 0.016 0.032 0.048 0.064 0.08 SE +/- 0.0041, N = 15 0.0712 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Writes n2d-standard-16 0.0151 0.0302 0.0453 0.0604 0.0755 SE +/- 0.0035, N = 15 0.0669 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Writes n2d-standard-16 0.0136 0.0272 0.0408 0.0544 0.068 SE +/- 0.0008, N = 14 0.0604 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 16 - Read-Write Ratio: 100% Writes n2d-standard-16 0.0177 0.0354 0.0531 0.0708 0.0885 SE +/- 0.0001, N = 3 0.0787 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 80% Reads 20% Writes n2d-standard-16 0.029 0.058 0.087 0.116 0.145 SE +/- 0.0001, N = 3 0.1289 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 80% Reads 20% Writes n2d-standard-16 0.0351 0.0702 0.1053 0.1404 0.1755 SE +/- 0.0046, N = 15 0.1560 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 80% Reads 20% Writes n2d-standard-16 0.0323 0.0646 0.0969 0.1292 0.1615 SE +/- 0.0004, N = 3 0.1437 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 80% Reads 20% Writes n2d-standard-16 0.0324 0.0648 0.0972 0.1296 0.162 SE +/- 0.0002, N = 3 0.1441 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 16 - Read-Write Ratio: 80% Reads 20% Writes n2d-standard-16 0.0347 0.0694 0.1041 0.1388 0.1735 SE +/- 0.0032, N = 15 0.1541 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance n2d-standard-16 400 800 1200 1600 2000 SE +/- 1.62, N = 3 1804.4 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SADD n2d-standard-16 300K 600K 900K 1200K 1500K SE +/- 6400.27, N = 3 1292686.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: LPUSH n2d-standard-16 200K 400K 600K 800K 1000K SE +/- 6487.50, N = 15 985310.29 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: GET n2d-standard-16 300K 600K 900K 1200K 1500K SE +/- 9075.94, N = 3 1504492.63 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SET n2d-standard-16 200K 400K 600K 800K 1000K SE +/- 6923.76, N = 3 1124629.87 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
n2d-standard-16 Processor: AMD EPYC 7B12 (8 Cores / 16 Threads), Motherboard: Google Compute Engine n2d-standard-16, Memory: 64GB, Disk: 32GB PersistentDisk
OS: Debian 10, Kernel: 4.19.0-13-cloud-amd64 (x86_64), Compiler: GCC 8.3.0, File-System: ext4, System Layer: KVM
Kernel Notes: scsi_mod.use_blk_mq=Y - Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / discard,errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: CPU Microcode: 0x1000065Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-post-Debian-1deb10u2)Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 February 2021 16:19 by user rajat.ga.