perf-report.txt 1.5 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566
  1. perf-report(1)
  2. ==============
  3. NAME
  4. ----
  5. perf-report - Read perf.data (created by perf record) and display the profile
  6. SYNOPSIS
  7. --------
  8. [verse]
  9. 'perf report' [-i <file> | --input=file]
  10. DESCRIPTION
  11. -----------
  12. This command displays the performance counter profile information recorded
  13. via perf record.
  14. OPTIONS
  15. -------
  16. -i::
  17. --input=::
  18. Input file name. (default: perf.data)
  19. -d::
  20. --dsos=::
  21. Only consider symbols in these dsos. CSV that understands
  22. file://filename entries.
  23. -n
  24. --show-nr-samples
  25. Show the number of samples for each symbol
  26. -T
  27. --threads
  28. Show per-thread event counters
  29. -C::
  30. --comms=::
  31. Only consider symbols in these comms. CSV that understands
  32. file://filename entries.
  33. -S::
  34. --symbols=::
  35. Only consider these symbols. CSV that understands
  36. file://filename entries.
  37. -w::
  38. --field-width=::
  39. Force each column width to the provided list, for large terminal
  40. readability.
  41. -t::
  42. --field-separator=::
  43. Use a special separator character and don't pad with spaces, replacing
  44. all occurances of this separator in symbol names (and other output)
  45. with a '.' character, that thus it's the only non valid separator.
  46. -g [type,min]::
  47. --call-graph::
  48. Display callchains using type and min percent threshold.
  49. type can be either:
  50. - flat: single column, linear exposure of callchains.
  51. - graph: use a graph tree, displaying absolute overhead rates.
  52. - fractal: like graph, but displays relative rates. Each branch of
  53. the tree is considered as a new profiled object. +
  54. Default: fractal,0.5.
  55. SEE ALSO
  56. --------
  57. linkperf:perf-stat[1]