/share/doc/papers/diskperf/tests.ms

https://bitbucket.org/freebsd/freebsd-head/ · Unknown · 109 lines · 108 code · 1 blank · 0 comment · 0 complexity · e2f9be541027c2905e339f048983afe2 MD5 · raw file

  1. .\" Copyright (c) 1983 The Regents of the University of California.
  2. .\" All rights reserved.
  3. .\"
  4. .\" Redistribution and use in source and binary forms, with or without
  5. .\" modification, are permitted provided that the following conditions
  6. .\" are met:
  7. .\" 1. Redistributions of source code must retain the above copyright
  8. .\" notice, this list of conditions and the following disclaimer.
  9. .\" 2. Redistributions in binary form must reproduce the above copyright
  10. .\" notice, this list of conditions and the following disclaimer in the
  11. .\" documentation and/or other materials provided with the distribution.
  12. .\" 3. All advertising materials mentioning features or use of this software
  13. .\" must display the following acknowledgement:
  14. .\" This product includes software developed by the University of
  15. .\" California, Berkeley and its contributors.
  16. .\" 4. Neither the name of the University nor the names of its contributors
  17. .\" may be used to endorse or promote products derived from this software
  18. .\" without specific prior written permission.
  19. .\"
  20. .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  21. .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  22. .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  23. .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  24. .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  25. .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  26. .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  27. .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  28. .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  29. .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  30. .\" SUCH DAMAGE.
  31. .\"
  32. .\" @(#)tests.ms 6.2 (Berkeley) 4/16/91
  33. .\" $FreeBSD$
  34. .\"
  35. .ds RH Tests
  36. .NH
  37. Tests
  38. .PP
  39. Our battery of tests consists of four programs,
  40. read_8192, write_8192, write_4096
  41. and rewrite_8192 originally written by [McKusick83]
  42. to evaluate the performance of the new file system in 4.2BSD.
  43. These programs all follow the same model and are typified by
  44. read_8192 shown here.
  45. .DS
  46. #define BUFSIZ 8192
  47. main( argc, argv)
  48. char **argv;
  49. {
  50. char buf[BUFSIZ];
  51. int i, j;
  52. j = open(argv[1], 0);
  53. for (i = 0; i < 1024; i++)
  54. read(j, buf, BUFSIZ);
  55. }
  56. .DE
  57. The remaining programs are included in appendix A.
  58. .PP
  59. These programs read, write with two different blocking factors,
  60. and rewrite logical files in structured file system on the disk
  61. under test.
  62. The write programs create new files while the rewrite program
  63. overwrites an existing file.
  64. Each of these programs represents an important segment of the
  65. typical UNIX file system activity with the read program
  66. representing by far the largest class and the rewrite the smallest.
  67. .PP
  68. A blocking factor of 8192 is used by all programs except write_4096.
  69. This is typical of most 4.2BSD user programs since a standard set of
  70. I/O support routines is commonly used and these routines buffer
  71. data in similar block sizes.
  72. .PP
  73. For each test run, an empty eight Kilobyte block
  74. file system was created in the target
  75. storage system.
  76. Then each of the four tests was run and timed.
  77. Each test was run three times;
  78. the first to clear out any useful data in the cache,
  79. and the second two to insure that the experiment
  80. had stablized and was repeatable.
  81. Each test operated on eight Megabytes of data to
  82. insure that the cache did not overly influence the results.
  83. Another file system was then initialized using a
  84. basic blocking factor of four Kilobytes and the same tests
  85. were run again and timed.
  86. A command script for a run appears as follows:
  87. .DS
  88. #!/bin/csh
  89. set time=2
  90. echo "8K/1K file system"
  91. newfs /dev/rhp0g eagle
  92. mount /dev/hp0g /mnt0
  93. mkdir /mnt0/foo
  94. echo "write_8192 /mnt0/foo/tst2"
  95. rm -f /mnt0/foo/tst2
  96. write_8192 /mnt0/foo/tst2
  97. rm -f /mnt0/foo/tst2
  98. write_8192 /mnt0/foo/tst2
  99. rm -f /mnt0/foo/tst2
  100. write_8192 /mnt0/foo/tst2
  101. echo "read_8192 /mnt0/foo/tst2"
  102. read_8192 /mnt0/foo/tst2
  103. read_8192 /mnt0/foo/tst2
  104. read_8192 /mnt0/foo/tst2
  105. umount /dev/hp0g
  106. .DE
  107. .ds RH Results
  108. .bp