VM Comparison Virtualization Comparison
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1302140-RA-VMCOMPARI29 Baremetal Disk Notes: CFQ / barrier=1,data=ordered,errors=remount-ro,relatime,rw,user_xattrProcessor Notes: Scaling Governor: ondemandSystem Notes: Disk Scheduler: CFQ. Python 2.7.3.
Baremetal (Performance) Processor: 2 x Intel Xeon E5440 @ 2.83GHz (8 Cores), Motherboard: Dell 0TT740, Chipset: Intel 5000X MCH, Memory: 16384MB, Disk: 1000GB PERC 6/i, Graphics: AMD ATI ES1000 128MB, Network: Broadcom NetXtreme II BCM5708 Gigabit
OS: Ubuntu 12.04, Kernel: 3.2.0-37-generic (x86_64), Compiler: GCC 4.6, File-System: ext4, Screen Resolution: 1024x768
Disk Notes: CFQ / barrier=1,data=ordered,errors=remount-ro,relatime,rw,user_xattrProcessor Notes: Scaling Governor: performanceSystem Notes: Disk Scheduler: CFQ. Python 2.7.3.
VM Comparison OpenBenchmarking.org Phoronix Test Suite 2 x Intel Xeon E5440 @ 2.83GHz (8 Cores) Dell 0TT740 Intel 5000X MCH 16384MB 1000GB PERC 6/i AMD ATI ES1000 128MB Broadcom NetXtreme II BCM5708 Gigabit Ubuntu 12.04 3.2.0-37-generic (x86_64) GCC 4.6 ext4 1024x768 Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Compiler File-System Screen Resolution VM Comparison Benchmarks System Logs - CFQ / barrier=1,data=ordered,errors=remount-ro,relatime,rw,user_xattr - Baremetal: Scaling Governor: ondemand - Baremetal (Performance): Scaling Governor: performance - Disk Scheduler: CFQ. Python 2.7.3.
Baremetal vs. Baremetal (Performance) Comparison Phoronix Test Suite Baseline +4.9% +4.9% +9.8% +9.8% +14.7% +14.7% 19.4% P.P.A.B S.W.P.S 13.3% D.T.D 8.2% Rand Write - 2 MB - 32 - 4 k Block Size - Total 64 MB 3.1% Timed MrBayes Analysis Apache Benchmark SQLite Threaded I/O Tester Baremetal Baremetal (Performance)
VM Comparison fio: Intel IOMeter File Server Access Pattern sqlite: Default Test Directory fs-mark: 1000 Files, 1MB Size fs-mark: 1000 Files, 1MB Size, No Sync/FSync blogbench: Read hdparm-read: /dev/sda iozone: 1MB - 32GB - Read Performance iozone: 1MB - 8GB - Write Performance iozone: 64kB - 32GB - Read Performance iozone: 64kB - 8GB - Write Performance tiobench: Seq Read - 1.024 MB - 32 - 64 k Block Size - Total 32 GB tiobench: Rand Read - 128 MB - 32 - 4 k Block Size - Total 4 GB tiobench: Rand Write - 2 MB - 32 - 4 k Block Size - Total 64 MB tiobench: Rand Write - 64 MB - 16 - 4 k Block Size - Total 1 GB tiobench: Seq Write - 128 MB - 32 - 4 k Block Size - Total 4 GB compilebench: Compile postmark: NetApp Disk Transaction Performance ramspeed: Triad - Integer ramspeed: Triad - Floating Point ffte: N=64, 1D Complex FFT Routine mrbayes: Primate Phylogeny Analysis (Bayes) cachebench: Read / Modify / Write john-the-ripper: Blowfish build-linux-kernel: Time To Compile c-ray: Raytracing, 1600x1200, 16 Threads, 8xAA compress-pbzip2: 256MB File Compression compress-gzip: 2GB File Compression encode-flac: WAV To FLAC encode-mp3: WAV To MP3 gnupg: 1GB File Encryption mencoder: AVI To LAVC pybench: Python Benchmark Suite phpbench: PHP Benchmark Suite cyclictest: POSIX Timer, Interval 500 ms, 100000 Loops cyclictest: POSIX Timer, Interval 10000 ms, 10000 Loops cyclictest: clock_nanosleep TIME_ABSTIME, Interval 500 ms, 100000 Loops cyclictest: clock_nanosleep TIME_ABSTIME, Interval 10000 ms, 10000 Loops openssl: RSA 4096-bit Performance pgbench: TPC-B Transactions Per Second nginx: Static Web Page Serving apache: Static Web Page Serving pgbench: PostgreSQL TPC-B Transactions Per Second cyclictest: POSIX Timer, Interval 500 ms, 100000 Loops cyclictest: POSIX Timer, Interval 10000 ms, 10000 Loops cyclictest: clock_nanosleep TIME_ABSTIME, Interval 500 ms, 100000 Loops cyclictest: clock_nanosleep TIME_ABSTIME, Interval 10000 ms, 10000 Loops Baremetal Baremetal (Performance) 2571.17 10.65 134.38 945.67 344940 128.83 139.47 128.03 139.23 128.53 91.70 4248.86 853.29 7.27 126.83 353.40 2395 5157.28 5317.75 3614.78 23.67 14219.27 6219 86.43 37.33 6.69 15.90 10.30 23.37 12.20 37.31 2956 60426 7 10 6 8 61.70 2541.71 14187.48 14486.26 2592.09 11.52 135.63 928.23 345025 128.85 137.92 128.30 138.92 128.70 91.89 4222.69 827.64 7.33 125.90 353.87 2403 5156.48 5321.30 3603.48 19.83 14225.03 6240 85.25 37.26 6.71 15.77 10.29 23.35 12.21 37.37 2938 60369 61.50 14174.44 12787.70 2596.37 6 8 5 7 OpenBenchmarking.org
PostMark This is a test of NetApp's PostMark benchmark designed to simulate small-file testing similar to the tasks endured by web and mail servers. This test profile will set PostMark to perform 25,000 transactions with 500 files simultaneously with the file sizes ranging between 5 and 512 kilobytes. Learn more via the OpenBenchmarking.org test page.
Timed Linux Kernel Compilation
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Raytracing, 1600x1200, 16 Threads, 8xAA Baremetal (Performance) Baremetal 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 37.26 37.33 1. (CC) gcc options: -lm -lpthread -O3
Result Confidence
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Raytracing, 1600x1200, 16 Threads, 8xAA Baremetal (Performance) Baremetal 8 16 24 32 40 Min: 37.23 / Avg: 37.26 / Max: 37.3 Min: 37.29 / Avg: 37.33 / Max: 37.38 1. (CC) gcc options: -lm -lpthread -O3
Parallel BZIP2 Compression
OpenBenchmarking.org ms Average, Fewer Is Better Cyclictest 0.84 Test Case: POSIX Timer, Interval 10000 ms, 10000 Loops Baremetal 3 6 9 12 15 SE +/- 0.17, N = 6 10 1. (CC) gcc options: -O2 -lrt -lpthread -lrttest
OpenBenchmarking.org ms Average, Fewer Is Better Cyclictest 0.84 Test Case: clock_nanosleep TIME_ABSTIME, Interval 500 ms, 100000 Loops Baremetal 2 4 6 8 10 SE +/- 0.00, N = 3 6 1. (CC) gcc options: -O2 -lrt -lpthread -lrttest
OpenBenchmarking.org ms Average, Fewer Is Better Cyclictest 0.84 Test Case: clock_nanosleep TIME_ABSTIME, Interval 10000 ms, 10000 Loops Baremetal 2 4 6 8 10 SE +/- 0.00, N = 3 8 1. (CC) gcc options: -O2 -lrt -lpthread -lrttest
PostgreSQL pgbench OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 8.4.11 TPC-B Transactions Per Second Baremetal 500 1000 1500 2000 2500 SE +/- 22.76, N = 3 2541.71 1. (CC) gcc options: -O2 -fno-strict-aliasing -fwrapv -lpgport -lpq -lcrypt -ldl -lm
PostgreSQL pgbench OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 8.4.11 PostgreSQL TPC-B Transactions Per Second Baremetal (Performance) 600 1200 1800 2400 3000 SE +/- 35.61, N = 3 2596.37 1. (CC) gcc options: -O2 -fno-strict-aliasing -fwrapv -lpgport -lpq -lcrypt -ldl -lm
OpenBenchmarking.org ms Average, Fewer Is Better Cyclictest 0.84 Kernel Latency: POSIX Timer, Interval 10000 ms, 10000 Loops Baremetal (Performance) 2 4 6 8 10 SE +/- 0.00, N = 3 8 1. (CC) gcc options: -O2 -lrt -lpthread -lrttest
OpenBenchmarking.org ms Average, Fewer Is Better Cyclictest 0.84 Kernel Latency: clock_nanosleep TIME_ABSTIME, Interval 500 ms, 100000 Loops Baremetal (Performance) 1.125 2.25 3.375 4.5 5.625 SE +/- 0.00, N = 3 5 1. (CC) gcc options: -O2 -lrt -lpthread -lrttest
OpenBenchmarking.org ms Average, Fewer Is Better Cyclictest 0.84 Kernel Latency: clock_nanosleep TIME_ABSTIME, Interval 10000 ms, 10000 Loops Baremetal (Performance) 2 4 6 8 10 SE +/- 0.00, N = 3 7 1. (CC) gcc options: -O2 -lrt -lpthread -lrttest
Baremetal Disk Notes: CFQ / barrier=1,data=ordered,errors=remount-ro,relatime,rw,user_xattrProcessor Notes: Scaling Governor: ondemandSystem Notes: Disk Scheduler: CFQ. Python 2.7.3.
Testing initiated at 13 February 2013 10:41 by user torben.
Baremetal (Performance) Processor: 2 x Intel Xeon E5440 @ 2.83GHz (8 Cores), Motherboard: Dell 0TT740, Chipset: Intel 5000X MCH, Memory: 16384MB, Disk: 1000GB PERC 6/i, Graphics: AMD ATI ES1000 128MB, Network: Broadcom NetXtreme II BCM5708 Gigabit
OS: Ubuntu 12.04, Kernel: 3.2.0-37-generic (x86_64), Compiler: GCC 4.6, File-System: ext4, Screen Resolution: 1024x768
Disk Notes: CFQ / barrier=1,data=ordered,errors=remount-ro,relatime,rw,user_xattrProcessor Notes: Scaling Governor: performanceSystem Notes: Disk Scheduler: CFQ. Python 2.7.3.
Testing initiated at 13 February 2013 20:24 by user torben.