Advertisement
Conchubair

Untitled

Dec 6th, 2016
68
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 6.85 KB | None | 0 0
  1.  
  2. STRESS TESTING YOUR COMPUTER
  3.  
  4. BACKGROUND
  5. ----------
  6.  
  7. Today's computers are not perfect. Even brand new systems from major
  8. manufacturers can have hidden flaws. If any of several key components such
  9. as CPU, memory, cooling, etc. are not up to spec, it can lead to incorrect
  10. calculations and/or unexplained system crashes.
  11.  
  12. Overclocking is the practice of increasing the speed of the CPU and/or
  13. memory to make a machine faster at little cost. Typically, overclocking
  14. involves pushing a machine past its limits and then backing off just a
  15. little bit.
  16.  
  17. For these reasons, both non-overclockers and overclockers need programs
  18. that test the stability of their computers. This is done by running
  19. programs that put a heavy load on the computer. Though not originally
  20. designed for this purpose, this program is one of a few programs that
  21. are excellent at stress testing a computer.
  22.  
  23.  
  24. RESOURCES
  25. ---------
  26.  
  27. This program is a good stress test for the CPU, memory, L1 and L2 caches,
  28. CPU cooling, and case cooling. The torture test runs continuously, comparing
  29. your computer's results to results that are known to be correct. Any
  30. mismatch and you've got a problem! Note that the torture test sometimes
  31. reads from and writes to disk but cannot be considered a stress test for
  32. hard drives.
  33.  
  34. You'll need other programs to stress video cards, PCI bus, disk access,
  35. networking and other important components. In addition, this is only one
  36. of several good programs that are freely available. Some people report
  37. finding problems only when running two or more stress test programs
  38. concurrently. You may need to raise prime95's priority when running two
  39. stress test programs so that each gets about 50% of the CPU time.
  40.  
  41. Forums are a great place to learn about available stability test programs
  42. and to get advice on what to do when a problem is found.
  43.  
  44. The currently popular stability test programs are (sorry, I don't have
  45. web addresses for these):
  46. Prime95 (this program's torture test)
  47. 3DMark2001
  48. CPU Stability test
  49. Sisoft sandra
  50. Quake and other games
  51. Folding@Home
  52. Seti@home
  53. Genome@home
  54.  
  55. Several useful websites for help (look for overclocking community or forum):
  56. http://www.overclockers.com
  57. http://www.arstechnica.com
  58. http://www.hardocp.com
  59. http://www.anandtech.com
  60. http://www.tomshardware.com
  61. http://www.sharkyextreme.com
  62. Also try the alt.comp.hardware.overclocking Usenet newsgroup.
  63.  
  64. Utility programs you may find useful (I'm sure there are others - look around):
  65. Motherboard monitor from http://mbm.livewiredev.com
  66. Memtest86 from http://www.memtest86.com
  67. Cpuburn by redelm: http://pages.sbcglobal.net/redelm/
  68. TaskInfo2002 from http://www.iarsn.com/
  69.  
  70.  
  71. WHAT TO DO IF A PROBLEM IS FOUND?
  72. ---------------------------------
  73.  
  74. The exact cause of a hardware problem can be very hard to find.
  75.  
  76. If you are not overclocking, the most likely cause is an overheating CPU
  77. or memory DIMMs that are not quite up to spec. Another possibility is
  78. you might need a better power supply. Try running MotherBoard monitor
  79. and browse the forums above to see if your CPU is running too hot.
  80. If so, make sure the heat sink is properly attached, fans are operational,
  81. and air flow inside the case is good. For isolating memory problems, try
  82. swapping memory DIMMs with a co-worker's or friend's machine. If the errors
  83. go away, then you can be fairly confidant that memory was the cause of
  84. the trouble. A power supply problem can often be identified by a significant
  85. drop in the voltages when prime95 starts running. Once again the overclocker
  86. forums are a good resource for what voltages are acceptable.
  87.  
  88. If you are overclocking then try increasing the core voltage, reduce the
  89. CPU speed, reduce the front side bus speed, or change the memory timings
  90. (CAS latency). Also try asking for help in one of the forums above - they
  91. may have other ideas to try.
  92.  
  93.  
  94. CAN I IGNORE THE PROBLEM?
  95. -------------------------
  96.  
  97. Ignoring the problem is a matter of personal preference. There are
  98. two schools of thought on this subject.
  99.  
  100. Most programs you run will not stress your computer enough to cause a
  101. wrong result or system crash. If you ignore the problem, then video games
  102. may stress your machine resulting in a system crash. Also, stay away from
  103. distributed computing projects where an incorrect calculation might cause
  104. you to return wrong results. Bad data will not help these projects!
  105. In conclusion, if you are comfortable with a small risk of an occasional
  106. system crash then feel free to live a little dangerously! Keep in mind
  107. that the faster prime95 finds a hardware error the more likely it is that
  108. other programs will experience problems.
  109.  
  110. The second school of thought is, "Why run a stress test if you are going
  111. to ignore the results?" These people want a guaranteed 100% rock solid
  112. machine. Passing these stability tests gives them the ability to run
  113. CPU intensive programs with confidence.
  114.  
  115.  
  116. FREQUENTLY ASKED QUESTIONS
  117. --------------------------
  118.  
  119. Q) My machine is not overclocked. If I'm getting an error, then there must
  120. be a bug in the program, right?
  121.  
  122. A) The torture test is comparing your machines results against
  123. KNOWN CORRECT RESULTS. If your machine cannot generate correct
  124. results, you have a hardware problem. HOWEVER, if you are failing
  125. the torture test in the SAME SPOT with the SAME ERROR MESSAGE
  126. every time, then ask for help at http://mersenneforum.org - it is
  127. possible that a recent change to the torture test code may have
  128. introduced a software bug.
  129.  
  130. Q) How long should I run the torture test?
  131.  
  132. A) I recommend running it for somewhere between 6 and 24 hours.
  133. The program has been known to fail only after several hours and in
  134. some cases several weeks of operation. In most cases though, it will
  135. fail within a few minutes on a flaky machine.
  136.  
  137. Q) Prime95 reports errors during the torture test, but other stability
  138. tests don't. Do I have a problem?
  139.  
  140. A) Yes, you've reached the point where your machine has been
  141. pushed just beyond its limits. Follow the recommendations above
  142. to make your machine 100% stable or decide to live with a
  143. machine that could have problems in rare circumstances.
  144.  
  145. Q) A forum member said "Don't bother with prime95, it always pukes on me,
  146. and my system is stable!. What do you make of that?"
  147.  
  148. or
  149.  
  150. "We had a server at work that ran for 2 MONTHS straight, without a reboot
  151. I installed Prime95 on it and ran it - a couple minutes later I get an error.
  152. You are going to tell me that the server wasn't stable?"
  153.  
  154. A) These users obviously do not subscribe to the 100% rock solid
  155. school of thought. THEIR MACHINES DO HAVE HARDWARE PROBLEMS.
  156. But since they are not presently running any programs that reveal
  157. the hardware problem, the machines are quite stable. As long as
  158. these machines never run a program that uncovers the hardware problem,
  159. then the machines will continue to be stable.
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement