HP DL380p Gen8 4 disk RAID5 vs RAID1+0 Benchmarking the difference between RAID 5 and RAID 1+0 on a HP ProLiant DL380p Gen8, using a P420i (revision B, firmware 6.00) card with 1GB cache (90% write cache), strip size of 256KB and 4 x 1.2TB 10K SFF SAS hard drives. The OS, a fresh CentOS 6.6 installation, was installed on a separate RAID1 array.
HTML result view exported from: https://openbenchmarking.org/result/1411187-REZZ-HPDL38097&sro .
HP DL380p Gen8 4 disk RAID5 vs RAID1+0 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Display Driver Compiler File-System RAID5 RAID1+0 Intel Xeon E5-2620 v2 @ 2.10GHz (12 Cores) HP ProLiant DL380p Gen8 Intel Xeon E7 v2/Xeon 16384MB 300GB LOGICAL VOLUME + 3601GB LOGICAL VOLUME Matrox s MGA G200EH Smart Cable Broadcom NetXtreme BCM5719 Gigabit PCIe CentOS 6.6 2.6.32-504.1.3.el6.x86_64 (x86_64) modesetting 0.8.0 GCC 4.4.7 20120313 ext4 OpenBenchmarking.org Compiler Details - --build=x86_64-redhat-linux --disable-dssi --disable-libjava-multilib --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-gnu-unique-object --enable-java-awt=gtk --enable-java-maintainer-mode --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-libgcj-multifile --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-cloog --with-ppl --with-tune=generic Disk Details - CFQ / barrier=1,data=ordered,relatime,rw,stripe=64 Processor Details - Scaling Governor: pcc-cpufreq userspace System Details - Disk Scheduler: CFQ. Python 2.6.6.
HP DL380p Gen8 4 disk RAID5 vs RAID1+0 aio-stress: Rand Write sqlite: 12,500 INSERTs fs-mark: 1000 Files, 1MB Size dbench: 12 Clients dbench: 48 Clients dbench: 128 Clients dbench: 1 Clients iozone: 8GB Read Performance iozone: 8GB Write Performance tiobench: 64MB Rand Read - 32 Threads tiobench: 64MB Rand Write - 32 Threads compilebench: Compile compilebench: Initial Create compilebench: Read Compiled Tree unpack-linux: linux-2.6.32.tar.bz2 postmark: Disk Transaction Performance compress-gzip: 2GB File Compression pgbench: TPC-B Transactions Per Second apache: Static Web Page Serving RAID5 RAID1+0 2422.77 6.60 637.68 2481.36 3207.28 2909.55 605.90 6252.36 545.22 6044.46 100.82 774.83 181.40 1216.16 12.02 3750 17.91 6993.46 17539.74 2402.77 6.46 659.80 2495.30 3217.17 2920.24 606.33 6284.78 376.69 5588.19 378.58 727.67 188.38 1194.60 12.04 3750 17.92 7377.05 17420.15 OpenBenchmarking.org
AIO-Stress Random Write OpenBenchmarking.org MB/s, More Is Better AIO-Stress 0.21 Random Write RAID1+0 RAID5 500 1000 1500 2000 2500 SE +/- 2.11, N = 3 SE +/- 7.68, N = 3 2402.77 2422.77 1. (CC) gcc options: -pthread -laio
SQLite 12,500 INSERTs OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.7.3 12,500 INSERTs RAID1+0 RAID5 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.10, N = 5 6.46 6.60 1. (CC) gcc options: -O2 -lreadline -lcurses -ldl -lpthread
FS-Mark 1000 Files, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 1000 Files, 1MB Size RAID1+0 RAID5 140 280 420 560 700 SE +/- 23.26, N = 6 SE +/- 23.26, N = 6 659.80 637.68 1. (CC) gcc options: -static
Dbench 12 Clients OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 12 Clients RAID1+0 RAID5 500 1000 1500 2000 2500 SE +/- 1.09, N = 3 SE +/- 2.43, N = 3 2495.30 2481.36 1. (CC) gcc options: -lpopt -O2
Dbench 48 Clients OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 48 Clients RAID1+0 RAID5 700 1400 2100 2800 3500 SE +/- 0.73, N = 3 SE +/- 3.31, N = 3 3217.17 3207.28 1. (CC) gcc options: -lpopt -O2
Dbench 128 Clients OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 128 Clients RAID1+0 RAID5 600 1200 1800 2400 3000 SE +/- 18.78, N = 3 SE +/- 5.02, N = 3 2920.24 2909.55 1. (CC) gcc options: -lpopt -O2
Dbench 1 Clients OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 1 Clients RAID1+0 RAID5 130 260 390 520 650 SE +/- 2.10, N = 3 SE +/- 2.89, N = 3 606.33 605.90 1. (CC) gcc options: -lpopt -O2
IOzone 8GB Read Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.405 8GB Read Performance RAID1+0 RAID5 1300 2600 3900 5200 6500 SE +/- 15.57, N = 3 SE +/- 65.15, N = 3 6284.78 6252.36 1. (CC) gcc options: -O3
IOzone 8GB Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.405 8GB Write Performance RAID1+0 RAID5 120 240 360 480 600 SE +/- 0.86, N = 3 SE +/- 1.04, N = 3 376.69 545.22 1. (CC) gcc options: -O3
Threaded I/O Tester 64MB Random Read - 32 Threads OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 0.3.3 64MB Random Read - 32 Threads RAID1+0 RAID5 1300 2600 3900 5200 6500 SE +/- 5.82, N = 3 SE +/- 47.49, N = 3 5588.19 6044.46
Threaded I/O Tester 64MB Random Write - 32 Threads OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 0.3.3 64MB Random Write - 32 Threads RAID1+0 RAID5 80 160 240 320 400 SE +/- 4.28, N = 3 SE +/- 60.32, N = 6 378.58 100.82
Compile Bench Test: Compile OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile RAID1+0 RAID5 200 400 600 800 1000 SE +/- 14.64, N = 6 SE +/- 42.16, N = 6 727.67 774.83
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create RAID1+0 RAID5 40 80 120 160 200 SE +/- 2.32, N = 3 SE +/- 7.52, N = 3 188.38 181.40
Compile Bench Test: Read Compiled Tree OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree RAID1+0 RAID5 300 600 900 1200 1500 SE +/- 3.67, N = 3 SE +/- 1.65, N = 3 1194.60 1216.16
Unpacking The Linux Kernel linux-2.6.32.tar.bz2 OpenBenchmarking.org Seconds, Fewer Is Better Unpacking The Linux Kernel linux-2.6.32.tar.bz2 RAID1+0 RAID5 3 6 9 12 15 SE +/- 0.20, N = 4 SE +/- 0.20, N = 4 12.04 12.02
PostMark Disk Transaction Performance OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance RAID1+0 RAID5 800 1600 2400 3200 4000 SE +/- 18.67, N = 3 SE +/- 18.67, N = 3 3750 3750 1. (CC) gcc options: -O3
Gzip Compression 2GB File Compression OpenBenchmarking.org Seconds, Fewer Is Better Gzip Compression 2GB File Compression RAID1+0 RAID5 4 8 12 16 20 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 17.92 17.91
PostgreSQL pgbench TPC-B Transactions Per Second OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 8.4.11 TPC-B Transactions Per Second RAID1+0 RAID5 1600 3200 4800 6400 8000 SE +/- 18.37, N = 3 SE +/- 105.20, N = 6 7377.05 6993.46 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 2.4.7 Static Web Page Serving RAID1+0 RAID5 4K 8K 12K 16K 20K SE +/- 102.33, N = 3 SE +/- 50.73, N = 3 17420.15 17539.74 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Phoronix Test Suite v10.8.4