ext4 Liqid HHHL AMD Ryzen Threadripper 2990WX 32-Core testing with a Gigabyte X399 AORUS XTREME-CF (F5c BIOS) and AMD Radeon Pro WX 7100 8GB on ManjaroLinux 18.0.4 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/1903308-SK-1903265SK05&grr&sor .
ext4 Liqid HHHL Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution ext4 xfs xfs run 2 AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads) Gigabyte X399 AORUS XTREME-CF (F5c BIOS) AMD Family 17h 64512MB 16GB USB DISK 3.0 + 4 x 400GB KXG50ZNV512G TOSHIBA + Samsung SSD 960 PRO 512GB AMD Radeon Pro WX 7100 8GB (1243/1750MHz) Realtek ALC1220 554K Intel I210 Gigabit Connection + Intel Wireless 8265 / 8275 ManjaroLinux 18.0.4 4.19.30-1-MANJARO (x86_64) GNOME Shell 3.30.2 X Server 1.20.4 amdgpu 19.0.0 4.5 Mesa 18.3.4 (LLVM 7.0.1) GCC 8.2.1 20181127 ext4 3840x2160 xfs OpenBenchmarking.org Compiler Details - --disable-libssp --disable-libstdcxx-pch --disable-libunwind-exceptions --disable-werror --enable-__cxa_atexit --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-install-libiberty --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++ --enable-libmpx --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-isl --with-linker-hash-style=gnu Disk Details - NONE / noatime,rw Processor Details - Scaling Governor: acpi-cpufreq schedutil Python Details - Python 3.7.2 Security Details - __user pointer sanitization + Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + SSB disabled via prctl and seccomp
ext4 Liqid HHHL pgbench: On-Disk - Normal Load - Read Write pgbench: On-Disk - Normal Load - Read Only dbench: 48 Clients dbench: 12 Clients dbench: 1 Clients dbench: 128 Clients tiobench: 64MB Rand Read - 32 Threads iozone: 4Kb - 8GB - Write Performance iozone: 4Kb - 8GB - Read Performance tiobench: 64MB Rand Write - 32 Threads fio: Seq Write - Linux AIO - Yes - No - 8MB - Default Test Directory apache: Static Web Page Serving fs-mark: 1000 Files, 1MB Size pgbench: compress-gzip: Linux Source Tree Archiving To .tar.gz postmark: Disk Transaction Performance fio: Seq Read - Linux AIO - Yes - No - 8MB - Default Test Directory fio: Rand Read - Linux AIO - Yes - No - 8MB - Default Test Directory fio: Rand Write - Linux AIO - Yes - No - 8MB - Default Test Directory compilebench: Compile sqlite: Timed SQLite Insertions unpack-linux: linux-4.15.tar.xz aio-stress: Rand Write compilebench: Read Compiled Tree compilebench: Initial Create ext4 xfs xfs run 2 2958 161075 2201 910 213 3391 341896 1090 9721 657 4318 17553 120 49.63 36.73 6199 7322 7435 4321 1790 22.69 5.74 2744 2969 466 2294 162301 2324 1089 251 3711 377752 546 8042 484 5093 138 36.36 7654 7618 7535 5366 2608 20.20 6.05 4157 2972 403 2399 160050 2067 1014 238 3436 359755 301 7841 477 5028 21610 68.67 129.28 36.26 7501 7053 7030 5092 2568 21.36 6.05 4009 2919 395 OpenBenchmarking.org
PostgreSQL pgbench Scaling: On-Disk - Test: Normal Load - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: On-Disk - Test: Normal Load - Mode: Read Write ext4 xfs run 2 xfs 600 1200 1800 2400 3000 SE +/- 106.86, N = 3 SE +/- 54.39, N = 3 SE +/- 65.92, N = 3 2958 2399 2294 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: On-Disk - Test: Normal Load - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: On-Disk - Test: Normal Load - Mode: Read Only xfs ext4 xfs run 2 30K 60K 90K 120K 150K SE +/- 1207.36, N = 3 SE +/- 3359.35, N = 3 SE +/- 674.57, N = 3 162301 161075 160050 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Dbench 48 Clients OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 48 Clients xfs ext4 xfs run 2 500 1000 1500 2000 2500 SE +/- 11.63, N = 3 SE +/- 76.37, N = 9 SE +/- 6.86, N = 3 2324 2201 2067 1. (CC) gcc options: -lpopt -O2
Dbench 12 Clients OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 12 Clients xfs xfs run 2 ext4 200 400 600 800 1000 SE +/- 4.06, N = 3 SE +/- 2.26, N = 3 SE +/- 12.20, N = 6 1089 1014 910 1. (CC) gcc options: -lpopt -O2
Dbench 1 Clients OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 1 Clients xfs xfs run 2 ext4 50 100 150 200 250 SE +/- 0.40, N = 3 SE +/- 1.27, N = 3 SE +/- 3.13, N = 4 251 238 213 1. (CC) gcc options: -lpopt -O2
Dbench 128 Clients OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 128 Clients xfs xfs run 2 ext4 800 1600 2400 3200 4000 SE +/- 22.16, N = 3 SE +/- 7.06, N = 3 SE +/- 17.42, N = 3 3711 3436 3391 1. (CC) gcc options: -lpopt -O2
Threaded I/O Tester 64MB Random Read - 32 Threads OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 20170503 64MB Random Read - 32 Threads xfs xfs run 2 ext4 80K 160K 240K 320K 400K SE +/- 11731.90, N = 12 SE +/- 17896.72, N = 12 SE +/- 6133.57, N = 3 377752 359755 341896 1. (CC) gcc options: -O2
IOzone Record Size: 4Kb - File Size: 8GB - Disk Test: Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 4Kb - File Size: 8GB - Disk Test: Write Performance ext4 xfs xfs run 2 200 400 600 800 1000 SE +/- 2.66, N = 3 SE +/- 111.16, N = 12 SE +/- 50.77, N = 9 1090 546 301 1. (CC) gcc options: -O3
IOzone Record Size: 4Kb - File Size: 8GB - Disk Test: Read Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 4Kb - File Size: 8GB - Disk Test: Read Performance ext4 xfs xfs run 2 2K 4K 6K 8K 10K SE +/- 36.77, N = 3 SE +/- 228.44, N = 12 SE +/- 194.22, N = 12 9721 8042 7841 1. (CC) gcc options: -O3
Threaded I/O Tester 64MB Random Write - 32 Threads OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 20170503 64MB Random Write - 32 Threads ext4 xfs xfs run 2 140 280 420 560 700 SE +/- 4.87, N = 3 SE +/- 4.16, N = 3 SE +/- 2.25, N = 3 657 484 477 1. (CC) gcc options: -O2
Flexible IO Tester Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory xfs xfs run 2 ext4 1100 2200 3300 4400 5500 SE +/- 69.06, N = 3 SE +/- 52.47, N = 3 SE +/- 52.32, N = 12 5093 5028 4318 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lrt -laio -lz -lm -lpthread -ldl
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving xfs run 2 ext4 5K 10K 15K 20K 25K SE +/- 100.71, N = 3 SE +/- 13.90, N = 3 21610 17553 1. (CC) gcc options: -shared -fPIC -O2 -pthread
FS-Mark 1000 Files, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 1000 Files, 1MB Size xfs ext4 xfs run 2 30 60 90 120 150 SE +/- 1.96, N = 12 SE +/- 8.27, N = 9 SE +/- 1.82, N = 12 138.00 120.00 68.67 1. (CC) gcc options: -static
PostgreSQL pgbench OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 xfs run 2 ext4 30 60 90 120 150 129.28 49.63 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Gzip Compression Linux Source Tree Archiving To .tar.gz OpenBenchmarking.org Seconds, Fewer Is Better Gzip Compression Linux Source Tree Archiving To .tar.gz xfs run 2 xfs ext4 8 16 24 32 40 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 36.26 36.36 36.73
PostMark Disk Transaction Performance OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance xfs xfs run 2 ext4 1600 3200 4800 6400 8000 SE +/- 79.00, N = 3 SE +/- 74.33, N = 3 SE +/- 51.00, N = 3 7654 7501 6199 1. (CC) gcc options: -O3
Flexible IO Tester Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory xfs ext4 xfs run 2 1600 3200 4800 6400 8000 SE +/- 46.84, N = 3 SE +/- 98.53, N = 3 SE +/- 122.58, N = 4 7618 7322 7053 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory xfs ext4 xfs run 2 1600 3200 4800 6400 8000 SE +/- 39.07, N = 3 SE +/- 14.85, N = 3 SE +/- 74.10, N = 3 7535 7435 7030 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 8MB - Disk Target: Default Test Directory xfs xfs run 2 ext4 1200 2400 3600 4800 6000 SE +/- 17.62, N = 3 SE +/- 32.98, N = 3 SE +/- 71.14, N = 3 5366 5092 4321 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lrt -laio -lz -lm -lpthread -ldl
Compile Bench Test: Compile OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile xfs xfs run 2 ext4 600 1200 1800 2400 3000 SE +/- 12.38, N = 3 SE +/- 19.52, N = 3 SE +/- 9.61, N = 3 2608 2568 1790
SQLite Timed SQLite Insertions OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.22 Timed SQLite Insertions xfs xfs run 2 ext4 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.20, N = 3 SE +/- 0.17, N = 3 20.20 21.36 22.69 1. (CC) gcc options: -O2 -ledit -ltinfo -lz -ldl -lpthread
Unpacking The Linux Kernel linux-4.15.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking The Linux Kernel linux-4.15.tar.xz ext4 xfs xfs run 2 2 4 6 8 10 SE +/- 0.01, N = 4 SE +/- 0.09, N = 4 SE +/- 0.07, N = 4 5.74 6.05 6.05
AIO-Stress Random Write OpenBenchmarking.org MB/s, More Is Better AIO-Stress 0.21 Random Write xfs xfs run 2 ext4 900 1800 2700 3600 4500 SE +/- 13.29, N = 3 SE +/- 22.61, N = 3 SE +/- 53.48, N = 3 4157 4009 2744 1. (CC) gcc options: -pthread -laio
Compile Bench Test: Read Compiled Tree OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree xfs ext4 xfs run 2 600 1200 1800 2400 3000 SE +/- 9.50, N = 3 SE +/- 26.70, N = 3 SE +/- 0.00, N = 3 2972 2969 2919
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create ext4 xfs xfs run 2 100 200 300 400 500 SE +/- 2.76, N = 3 SE +/- 1.28, N = 3 SE +/- 1.82, N = 3 466 403 395
Phoronix Test Suite v10.8.5