ocdcephbenchmarks

SSD directly attached to the system (type='raw' cache='none' io='native'), Micron 5100 MAX 1.92TB

HTML result view exported from: https://openbenchmarking.org/result/1805287-FO-OCDCEPHBE12.

ocdcephbenchmarksProcessorMotherboardMemoryDiskGraphicsOSKernelCompilerFile-SystemScreen ResolutionSystem Layerlocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none8 x QEMU Virtual 2.5+ @ 2.19GHz (8 Cores)Red Hat KVM (1.11.0-2.el7 BIOS)2 x 16384 MB RAM28GBcirrusdrmfbCentOS Linux 73.10.0-862.3.2.el7.x86_64 (x86_64)GCC 4.8.5 20150623xfs1024x768KVM QEMU1024GB1788GBOpenBenchmarking.orgCompiler Details- --build=x86_64-redhat-linux --disable-libgcj --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,objc,obj-c++,java,fortran,ada,go,lto --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-linker-hash-style=gnu --with-tune=generic Disk Mount Options Details- attr2,inode64,noquota,relatime,rw,seclabelPython Details- Python 2.7.5Security Details- SELinux + KPTI + Load fences + Retpoline without IBPB Protection

ocdcephbenchmarksaio-stress: Rand Writesqlite: Timed SQLite Insertionsfs-mark: 1000 Files, 1MB Sizedbench: 12 Clientsdbench: 48 Clientsdbench: 128 Clientsdbench: 1 Clientstiobench: 64MB Rand Read - 32 Threadstiobench: 64MB Rand Write - 32 Threadsunpack-linux: linux-4.15.tar.xzpostmark: Disk Transaction Performancecompress-gzip: Linux Source Tree Archiving To .tar.gzapache: Static Web Page Servingpgbench: On-Disk - Normal Load - Read Writelocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none1478.3820.61152.131285.75812.43959.00179.0260691.53958.9614.45240971.337307.721721.8252.7587.98683.49968.60965.1782.85107041.83337.0015.41214973.377336.671802.6617.29159.03800.771220.011336.95197.93115753.71555.5414.71229969.397272.343642.91OpenBenchmarking.org

AIO-Stress

Random Write

OpenBenchmarking.orgMB/s, More Is BetterAIO-Stress 0.21Random Writelocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none400800120016002000SE +/- 73.02, N = 6SE +/- 25.85, N = 3SE +/- 55.02, N = 61478.381721.821802.661. (CC) gcc options: -pthread -laio

SQLite

Timed SQLite Insertions

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.22Timed SQLite Insertionslocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none1224364860SE +/- 0.06, N = 3SE +/- 0.77, N = 4SE +/- 0.28, N = 620.6152.7517.291. (CC) gcc options: -O2 -ldl -lpthread

FS-Mark

1000 Files, 1MB Size

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.31000 Files, 1MB Sizelocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none4080120160200SE +/- 4.84, N = 6SE +/- 1.36, N = 5SE +/- 1.29, N = 3152.1387.98159.031. (CC) gcc options: -static

Dbench

12 Clients

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.012 Clientslocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none30060090012001500SE +/- 4.49, N = 3SE +/- 1.93, N = 3SE +/- 7.08, N = 31285.75683.49800.771. (CC) gcc options: -lpopt -O2

Dbench

48 Clients

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.048 Clientslocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none30060090012001500SE +/- 98.18, N = 6SE +/- 7.36, N = 3SE +/- 2.82, N = 3812.43968.601220.011. (CC) gcc options: -lpopt -O2

Dbench

128 Clients

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0128 Clientslocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none30060090012001500SE +/- 10.43, N = 3SE +/- 11.71, N = 3SE +/- 6.02, N = 3959.00965.171336.951. (CC) gcc options: -lpopt -O2

Dbench

1 Clients

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.01 Clientslocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none4080120160200SE +/- 2.91, N = 3SE +/- 0.76, N = 3SE +/- 1.04, N = 3179.0282.85197.931. (CC) gcc options: -lpopt -O2

Threaded I/O Tester

64MB Random Read - 32 Threads

OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 2017050364MB Random Read - 32 Threadslocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none20K40K60K80K100KSE +/- 3323.01, N = 6SE +/- 1303.43, N = 3SE +/- 1990.78, N = 660691.53107041.83115753.711. (CC) gcc options: -O2

Threaded I/O Tester

64MB Random Write - 32 Threads

OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 2017050364MB Random Write - 32 Threadslocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none2004006008001000SE +/- 27.51, N = 6SE +/- 5.79, N = 3SE +/- 10.53, N = 3958.96337.00555.541. (CC) gcc options: -O2

Unpacking The Linux Kernel

linux-4.15.tar.xz

OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking The Linux Kernellinux-4.15.tar.xzlocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none48121620SE +/- 0.07, N = 4SE +/- 0.19, N = 8SE +/- 0.19, N = 714.4515.4114.71

PostMark

Disk Transaction Performance

OpenBenchmarking.orgTPS, More Is BetterPostMark 1.51Disk Transaction Performancelocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none5001000150020002500SE +/- 53.62, N = 6SE +/- 16.19, N = 3SE +/- 35.31, N = 52409214922991. (CC) gcc options: -O3

Gzip Compression

Linux Source Tree Archiving To .tar.gz

OpenBenchmarking.orgSeconds, Fewer Is BetterGzip CompressionLinux Source Tree Archiving To .tar.gzlocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none1632486480SE +/- 2.64, N = 6SE +/- 1.77, N = 6SE +/- 2.46, N = 671.3373.3769.39

Apache Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page Servinglocal filesystemCEPH Jewel 3 OSDsDirect SSD io=native cache=none16003200480064008000SE +/- 37.64, N = 3SE +/- 99.52, N = 6SE +/- 125.92, N = 47307.727336.677272.341. (CC) gcc options: -shared -fPIC -O2 -pthread

PostgreSQL pgbench

Scaling: On-Disk - Test: Normal Load - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: On-Disk - Test: Normal Load - Mode: Read WriteDirect SSD io=native cache=none8001600240032004000SE +/- 14.08, N = 33642.911. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Phoronix Test Suite v10.8.4