Btrfs Mount Options On Ubuntu Linux Testing various Btrfs file-system mount options from an early Linux 3.7 development kernel. Benchmarking for a future article on Phoronix.com by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/1210138-RA-BTRFSMOUN28&sor .
Btrfs Mount Options On Ubuntu Linux Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Stock nodatacow nobarrier compress=zlib compress=lzo discard nospace_cache clear_cache inode_cache noatime Intel Core i7 720Q @ 1.60GHz (8 Cores) LENOVO 4318CTO Intel Core DMI 2 x 2048 MB DDR3-1066MHz M471B5673FH0-CF8 160GB INTEL SSDSA2M160 NVIDIA Quadro FX 880M (405/324MHz) Conexant CX20585 Intel 82577LM Gigabit Connection + Intel Centrino Ultimate-N 6300 Ubuntu 12.10 3.6.0-999-generic (x86_64) Unity 6.8.0 X Server 1.13.0 nouveau 1.0.2 3.0 Mesa 9.0-devel Gallium 0.4 GCC 4.7 btrfs 1600x900 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-arch-32=i686 --with-tune=generic -v Disk Details - Stock: DEADLINE / relatime,rw,space_cache,ssd - nodatacow: DEADLINE / nodatacow,nodatasum,relatime,rw,space_cache,ssd - nobarrier: DEADLINE / nobarrier,relatime,rw,space_cache,ssd - compress=zlib: DEADLINE / compress=zlib,relatime,rw,space_cache,ssd - compress=lzo: DEADLINE / compress=lzo,relatime,rw,space_cache,ssd - discard: DEADLINE / discard,relatime,rw,space_cache,ssd - nospace_cache: DEADLINE / nospace_cache,relatime,rw,ssd - clear_cache: DEADLINE / clear_cache,relatime,rw,space_cache,ssd - inode_cache: DEADLINE / inode_cache,relatime,rw,space_cache,ssd - noatime: DEADLINE / noatime,rw,space_cache,ssd System Details - Disk Scheduler: DEADLINE. Python 2.7.3. Compiz was running on this system.
Btrfs Mount Options On Ubuntu Linux fio: Intel IOMeter File Server Access Pattern fs-mark: 1000 Files, 1MB Size fs-mark: 5000 Files, 1MB Size, 4 Threads fs-mark: 4000 Files, 32 Sub Dirs, 1MB Size dbench: 1 iozone: 1MB - 8GB - Read Performance iozone: 4Kb - 8GB - Read Performance iozone: 1MB - 8GB - Write Performance iozone: 4Kb - 8GB - Write Performance iozone: 64Kb - 8GB - Read Performance iozone: 64Kb - 8GB - Write Performance tiobench: Rand Write - 32MB - 4 tiobench: Rand Write - 32MB - 8 tiobench: Rand Write - 64MB - 4 tiobench: Rand Write - 64MB - 8 compilebench: Compile compilebench: Initial Create unpack-linux: linux-2.6.32.tar.bz2 postmark: Disk Transaction Performance Stock nodatacow nobarrier compress=zlib compress=lzo discard nospace_cache clear_cache inode_cache noatime 724.41 65.37 93.23 64.00 170.36 292.69 286.04 102.44 102.30 294.92 102.86 75.10 75.00 74.26 77.23 96.76 59.11 16.07 1594 661.77 86.23 99.10 76.80 193.99 278.89 274.59 103.05 102.97 275.35 103.19 97.25 96.21 93.61 93.33 95.50 56.48 15.73 2318 715.79 70.83 93.87 68.97 181.87 288.37 285.02 103.01 102.48 292.75 102.68 67.72 78.74 71.64 78.33 95.61 64.22 15.94 1562 721.72 101.13 237.93 99.07 169.11 1072.39 309.67 313.89 193.81 1048.39 326.80 63.16 62.57 63.34 57.46 210.26 51.70 27.05 713.95 188.13 832.43 185.60 187.59 1018.11 322.96 1285.86 212.67 1029.06 1291.38 63.92 69.41 58.12 57.60 705.81 70.21 19.15 2003 816.52 59.40 70.52 54.93 148.72 310.42 300.61 102.83 101.42 320.97 102.15 75.62 75.53 68.89 60.66 98.50 51.46 17.27 1597 722.57 66.03 93.83 63.80 170.64 302.79 287.20 102.61 102.57 291.59 102.88 72.54 77.34 69.56 79.95 96.67 65.73 15.84 1597 721.05 65.50 93.57 63.90 169.72 287.90 292.42 102.63 102.82 294.81 102.79 73.31 82.24 72.94 73.71 96.58 61.87 16.21 1562 715.86 66.20 93.57 63.90 191.24 289.47 285.79 102.43 102.61 298.31 102.79 70.14 81.62 68.66 68.78 93.44 59.44 16.05 1562 713.06 65.97 93.90 63.20 168.49 259.74 220.49 100.85 97.56 232.97 101.20 59.66 73.41 68.82 79.89 91.84 62.97 16.09 1607 OpenBenchmarking.org
Flexible IO Tester Test: Intel IOMeter File Server Access Pattern OpenBenchmarking.org Seconds (Run Time), Fewer Is Better Flexible IO Tester 1.57 Test: Intel IOMeter File Server Access Pattern nodatacow noatime compress=lzo nobarrier inode_cache clear_cache compress=zlib nospace_cache Stock discard 200 400 600 800 1000 SE +/- 2.46, N = 3 SE +/- 0.76, N = 3 SE +/- 3.76, N = 3 SE +/- 4.02, N = 3 SE +/- 2.99, N = 3 SE +/- 2.17, N = 3 SE +/- 2.47, N = 3 SE +/- 4.88, N = 3 SE +/- 2.45, N = 3 SE +/- 8.49, N = 3 661.77 713.06 713.95 715.79 715.86 721.05 721.72 722.57 724.41 816.52
FS-Mark Test: 1000 Files, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size compress=lzo compress=zlib nodatacow nobarrier inode_cache nospace_cache noatime clear_cache Stock discard 40 80 120 160 200 SE +/- 0.67, N = 3 SE +/- 0.15, N = 3 SE +/- 0.32, N = 3 SE +/- 0.87, N = 3 SE +/- 0.42, N = 3 SE +/- 0.46, N = 3 SE +/- 0.28, N = 3 SE +/- 0.35, N = 3 SE +/- 0.47, N = 3 SE +/- 2.45, N = 6 188.13 101.13 86.23 70.83 66.20 66.03 65.97 65.50 65.37 59.40 1. (CC) gcc options: -static
FS-Mark Test: 5000 Files, 1MB Size, 4 Threads OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 5000 Files, 1MB Size, 4 Threads compress=lzo compress=zlib nodatacow noatime nobarrier nospace_cache inode_cache clear_cache Stock discard 200 400 600 800 1000 SE +/- 13.89, N = 3 SE +/- 0.27, N = 3 SE +/- 0.25, N = 3 SE +/- 0.55, N = 3 SE +/- 0.58, N = 3 SE +/- 0.52, N = 3 SE +/- 0.70, N = 3 SE +/- 0.74, N = 3 SE +/- 0.62, N = 3 SE +/- 0.94, N = 6 832.43 237.93 99.10 93.90 93.87 93.83 93.57 93.57 93.23 70.52 1. (CC) gcc options: -static
FS-Mark Test: 4000 Files, 32 Sub Dirs, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size compress=lzo compress=zlib nodatacow nobarrier Stock inode_cache clear_cache nospace_cache noatime discard 40 80 120 160 200 SE +/- 0.92, N = 3 SE +/- 0.15, N = 3 SE +/- 0.40, N = 3 SE +/- 0.34, N = 3 SE +/- 0.26, N = 3 SE +/- 0.20, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.20, N = 3 SE +/- 1.43, N = 6 185.60 99.07 76.80 68.97 64.00 63.90 63.90 63.80 63.20 54.93 1. (CC) gcc options: -static
Dbench Client Count: 1 OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 1 nodatacow inode_cache compress=lzo nobarrier nospace_cache Stock clear_cache compress=zlib noatime discard 40 80 120 160 200 SE +/- 0.24, N = 3 SE +/- 1.30, N = 3 SE +/- 0.49, N = 3 SE +/- 0.31, N = 3 SE +/- 0.26, N = 3 SE +/- 0.24, N = 3 SE +/- 0.63, N = 3 SE +/- 1.88, N = 3 SE +/- 0.83, N = 3 SE +/- 0.14, N = 3 193.99 191.24 187.59 181.87 170.64 170.36 169.72 169.11 168.49 148.72 1. (CC) gcc options: -lpopt
IOzone Record Size: 1MB - File Size: 8GB - Disk Test: Read Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.405 Record Size: 1MB - File Size: 8GB - Disk Test: Read Performance compress=zlib compress=lzo discard nospace_cache Stock inode_cache nobarrier clear_cache nodatacow noatime 200 400 600 800 1000 SE +/- 18.51, N = 4 SE +/- 11.23, N = 3 SE +/- 5.51, N = 6 SE +/- 8.22, N = 6 SE +/- 4.39, N = 5 SE +/- 5.64, N = 3 SE +/- 5.71, N = 3 SE +/- 5.48, N = 3 SE +/- 0.93, N = 3 SE +/- 9.94, N = 6 1072.39 1018.11 310.42 302.79 292.69 289.47 288.37 287.90 278.89 259.74 1. (CC) gcc options: -O3
IOzone Record Size: 4Kb - File Size: 8GB - Disk Test: Read Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.405 Record Size: 4Kb - File Size: 8GB - Disk Test: Read Performance compress=lzo compress=zlib discard clear_cache nospace_cache Stock inode_cache nobarrier nodatacow noatime 70 140 210 280 350 SE +/- 5.86, N = 3 SE +/- 6.50, N = 6 SE +/- 4.70, N = 3 SE +/- 3.61, N = 3 SE +/- 2.24, N = 3 SE +/- 2.42, N = 3 SE +/- 1.30, N = 3 SE +/- 1.78, N = 3 SE +/- 0.97, N = 3 SE +/- 3.14, N = 3 322.96 309.67 300.61 292.42 287.20 286.04 285.79 285.02 274.59 220.49 1. (CC) gcc options: -O3
IOzone Record Size: 1MB - File Size: 8GB - Disk Test: Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.405 Record Size: 1MB - File Size: 8GB - Disk Test: Write Performance compress=lzo compress=zlib nodatacow nobarrier discard clear_cache nospace_cache Stock inode_cache noatime 300 600 900 1200 1500 SE +/- 39.86, N = 6 SE +/- 14.31, N = 6 SE +/- 0.30, N = 3 SE +/- 0.26, N = 3 SE +/- 0.37, N = 3 SE +/- 0.05, N = 3 SE +/- 0.50, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.38, N = 3 1285.86 313.89 103.05 103.01 102.83 102.63 102.61 102.44 102.43 100.85 1. (CC) gcc options: -O3
IOzone Record Size: 4Kb - File Size: 8GB - Disk Test: Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.405 Record Size: 4Kb - File Size: 8GB - Disk Test: Write Performance compress=lzo compress=zlib nodatacow clear_cache inode_cache nospace_cache nobarrier Stock discard noatime 50 100 150 200 250 SE +/- 38.65, N = 6 SE +/- 29.60, N = 6 SE +/- 0.21, N = 3 SE +/- 0.23, N = 3 SE +/- 0.18, N = 3 SE +/- 0.10, N = 3 SE +/- 0.28, N = 3 SE +/- 0.09, N = 3 SE +/- 0.18, N = 3 SE +/- 1.57, N = 3 212.67 193.81 102.97 102.82 102.61 102.57 102.48 102.30 101.42 97.56 1. (CC) gcc options: -O3
IOzone Record Size: 64Kb - File Size: 8GB - Disk Test: Read Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.405 Record Size: 64Kb - File Size: 8GB - Disk Test: Read Performance compress=zlib compress=lzo discard inode_cache Stock clear_cache nobarrier nospace_cache nodatacow noatime 200 400 600 800 1000 SE +/- 7.62, N = 3 SE +/- 9.95, N = 3 SE +/- 4.88, N = 5 SE +/- 3.62, N = 3 SE +/- 5.74, N = 3 SE +/- 1.17, N = 3 SE +/- 1.53, N = 3 SE +/- 5.60, N = 3 SE +/- 4.63, N = 6 SE +/- 8.86, N = 6 1048.39 1029.06 320.97 298.31 294.92 294.81 292.75 291.59 275.35 232.97 1. (CC) gcc options: -O3
IOzone Record Size: 64Kb - File Size: 8GB - Disk Test: Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.405 Record Size: 64Kb - File Size: 8GB - Disk Test: Write Performance compress=lzo compress=zlib nodatacow nospace_cache Stock inode_cache clear_cache nobarrier discard noatime 300 600 900 1200 1500 SE +/- 3.96, N = 3 SE +/- 0.70, N = 3 SE +/- 0.05, N = 3 SE +/- 0.38, N = 3 SE +/- 0.20, N = 3 SE +/- 0.12, N = 3 SE +/- 0.33, N = 3 SE +/- 0.19, N = 3 SE +/- 0.24, N = 3 SE +/- 0.28, N = 3 1291.38 326.80 103.19 102.88 102.86 102.79 102.79 102.68 102.15 101.20 1. (CC) gcc options: -O3
Threaded I/O Tester Test: Random Write - Size Per Thread: 32MB - Thread Count: 4 OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 0.3.3 Test: Random Write - Size Per Thread: 32MB - Thread Count: 4 nodatacow discard Stock clear_cache nospace_cache inode_cache nobarrier compress=lzo compress=zlib noatime 20 40 60 80 100 SE +/- 0.55, N = 4 SE +/- 2.30, N = 8 SE +/- 1.22, N = 8 SE +/- 1.78, N = 8 SE +/- 2.27, N = 8 SE +/- 3.19, N = 8 SE +/- 5.25, N = 8 SE +/- 1.86, N = 8 SE +/- 1.31, N = 8 SE +/- 7.10, N = 8 97.25 75.62 75.10 73.31 72.54 70.14 67.72 63.92 63.16 59.66
Threaded I/O Tester Test: Random Write - Size Per Thread: 32MB - Thread Count: 8 OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 0.3.3 Test: Random Write - Size Per Thread: 32MB - Thread Count: 8 nodatacow clear_cache inode_cache nobarrier nospace_cache discard Stock noatime compress=lzo compress=zlib 20 40 60 80 100 SE +/- 0.56, N = 4 SE +/- 2.92, N = 8 SE +/- 0.57, N = 4 SE +/- 3.20, N = 8 SE +/- 2.51, N = 8 SE +/- 3.12, N = 8 SE +/- 3.03, N = 8 SE +/- 5.10, N = 8 SE +/- 1.85, N = 8 SE +/- 3.11, N = 8 96.21 82.24 81.62 78.74 77.34 75.53 75.00 73.41 69.41 62.57
Threaded I/O Tester Test: Random Write - Size Per Thread: 64MB - Thread Count: 4 OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 0.3.3 Test: Random Write - Size Per Thread: 64MB - Thread Count: 4 nodatacow Stock clear_cache nobarrier nospace_cache discard noatime inode_cache compress=zlib compress=lzo 20 40 60 80 100 SE +/- 0.59, N = 4 SE +/- 0.86, N = 4 SE +/- 2.51, N = 8 SE +/- 0.96, N = 4 SE +/- 0.96, N = 5 SE +/- 1.77, N = 8 SE +/- 0.91, N = 4 SE +/- 0.25, N = 4 SE +/- 0.96, N = 4 SE +/- 4.92, N = 8 93.61 74.26 72.94 71.64 69.56 68.89 68.82 68.66 63.34 58.12
Threaded I/O Tester Test: Random Write - Size Per Thread: 64MB - Thread Count: 8 OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 0.3.3 Test: Random Write - Size Per Thread: 64MB - Thread Count: 8 nodatacow nospace_cache noatime nobarrier Stock clear_cache inode_cache discard compress=lzo compress=zlib 20 40 60 80 100 SE +/- 1.45, N = 4 SE +/- 0.39, N = 4 SE +/- 3.52, N = 8 SE +/- 3.24, N = 8 SE +/- 2.20, N = 8 SE +/- 1.99, N = 8 SE +/- 5.13, N = 8 SE +/- 8.00, N = 8 SE +/- 0.92, N = 4 SE +/- 3.72, N = 8 93.33 79.95 79.89 78.33 77.23 73.71 68.78 60.66 57.60 57.46
Compile Bench Test: Compile OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile compress=lzo compress=zlib discard Stock nospace_cache clear_cache nobarrier nodatacow inode_cache noatime 150 300 450 600 750 SE +/- 2.51, N = 3 SE +/- 0.51, N = 3 SE +/- 0.19, N = 3 SE +/- 0.30, N = 3 SE +/- 0.27, N = 3 SE +/- 0.33, N = 3 SE +/- 0.06, N = 3 SE +/- 0.33, N = 3 SE +/- 1.56, N = 4 SE +/- 0.46, N = 3 705.81 210.26 98.50 96.76 96.67 96.58 95.61 95.50 93.44 91.84
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create compress=lzo nospace_cache nobarrier noatime clear_cache inode_cache Stock nodatacow compress=zlib discard 16 32 48 64 80 SE +/- 1.18, N = 3 SE +/- 1.95, N = 3 SE +/- 1.36, N = 3 SE +/- 0.93, N = 3 SE +/- 3.14, N = 3 SE +/- 2.15, N = 4 SE +/- 1.11, N = 3 SE +/- 1.41, N = 3 SE +/- 0.61, N = 3 SE +/- 2.06, N = 3 70.21 65.73 64.22 62.97 61.87 59.44 59.11 56.48 51.70 51.46
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 nodatacow nospace_cache nobarrier inode_cache Stock noatime clear_cache discard compress=lzo compress=zlib 6 12 18 24 30 SE +/- 0.15, N = 4 SE +/- 0.07, N = 4 SE +/- 0.19, N = 4 SE +/- 0.11, N = 4 SE +/- 0.18, N = 4 SE +/- 0.19, N = 4 SE +/- 0.26, N = 4 SE +/- 0.25, N = 4 SE +/- 0.13, N = 4 SE +/- 0.05, N = 4 15.73 15.84 15.94 16.05 16.07 16.09 16.21 17.27 19.15 27.05
PostMark Disk Transaction Performance OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance nodatacow compress=lzo noatime nospace_cache discard Stock inode_cache clear_cache nobarrier 500 1000 1500 2000 2500 SE +/- 30.40, N = 10 SE +/- 26.67, N = 10 SE +/- 21.01, N = 7 SE +/- 21.93, N = 6 SE +/- 21.93, N = 6 SE +/- 21.40, N = 10 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 2318 2003 1607 1597 1597 1594 1562 1562 1562
Phoronix Test Suite v10.8.4