"Fossies" - the Fresh Open Source Software Archive

Member "stress-ng-0.09.56/example-jobs/filesystem.job" (15 Mar 2019, 14616 Bytes) of package /linux/privat/stress-ng-0.09.56.tar.xz:


As a special service "Fossies" has tried to format the requested text file into HTML format (style: standard) with prefixed line numbers. Alternatively you can here view or download the uninterpreted source code file.

    1 #
    2 # filesystem class stressors:
    3 #   various options have been commented out, one can remove the
    4 #   proceeding comment to enable these options if required.
    5 
    6 #
    7 # run the following tests in parallel or sequentially
    8 #
    9 run sequential
   10 # run parallel
   11 
   12 #
   13 # aggressive:
   14 #   enables more file, cache and memory aggressive options. This may
   15 #   slow tests down, increase latencies and  reduce  the  number  of
   16 #   bogo  ops as well as changing the balance of user time vs system
   17 #   time used depending on the type of stressor being used.
   18 #
   19 # aggressive
   20 
   21 #
   22 # ignite-cpu:
   23 #   alter kernel controls to try and maximize the CPU. This requires
   24 #   root  privilege  to alter various /sys interface controls.  Cur‐
   25 #   rently this only works for Intel P-State enabled x86 systems  on
   26 #   Linux.
   27 #
   28 # ignite-cpu
   29 
   30 #
   31 # keep-name:
   32 #   by  default,  stress-ng  will  attempt to change the name of the
   33 #   stress processes according to their functionality;  this  option
   34 #   disables  this and keeps the process names to be the name of the
   35 #   parent process, that is, stress-ng.
   36 #
   37 # keep-name
   38 
   39 #
   40 # metrics-brief:
   41 #   enable metrics and only output metrics that are non-zero.
   42 #
   43 metrics-brief
   44 
   45 #
   46 # verbose
   47 #   show all debug, warnings and normal information output.
   48 #
   49 verbose
   50 
   51 #
   52 # run each of the tests for 60 seconds
   53 #  stop stress test after N seconds. One can also specify the units
   54 #  of time in seconds, minutes, hours, days or years with the  suf‐
   55 #  fix s, m, h, d or y.
   56 #
   57 timeout 60s
   58 
   59 #
   60 # per stressor options start here
   61 #
   62 
   63 # bind-mount stressor options:
   64 #   start  N workers that repeatedly bind mount / to / inside a user
   65 #   namespace. This can consume resources rapidly,  forcing  out  of
   66 #   memory  situations.  Do not use this stressor unless you want to
   67 #   risk hanging your machine.
   68 #
   69 bind-mount 0		# 0 means 1 stressor per CPU
   70 # bind-mount-ops 1000000 # stop after 1000000 bogo ops
   71 
   72 #
   73 # chdir stressor options:
   74 #   start N workers that change directory between directories  using
   75 #   chdir(2)
   76 #
   77 chdir 0			# 0 means 1 stressor per CPU
   78 # chdir-ops 1000000	# stop after 1000000 bogo ops
   79 # chdir-dirs 8192	# create 8192 directories
   80 
   81 #
   82 # chmod stressor options:
   83 #   start N workers that change the file mode bits via chmod(2)  and
   84 #   fchmod(2) on the same file. The greater the value for N then the
   85 #   more contention on the single  file.   The  stressor  will  work
   86 #   through all the combination of mode bits.
   87 #
   88 chmod 0			# 0 means 1 stressor per CPU
   89 # chmod-ops 1000000	# stop after 1000000 bogo ops
   90 
   91 #
   92 # chown stressor options:
   93 #   start  N  workers  that  exercise chown(2) on the same file. The
   94 #   greater the value for N then the more contention on  the  single
   95 #   file.
   96 #
   97 chown 0			# 0 means 1 stressor per CPU
   98 # chown-ops 1000000	# stop after 1000000 bogo ops
   99 
  100 # copy-file stressor options:
  101 #   start   N   stressors   that   copy   a  file  using  the  Linux
  102 #   copy_file_range(2) system call. 2MB chunks of data  are  copyied
  103 #   from  random  locations  from  one file to random locations to a
  104 #   destination file.  By default, the files are  256  MB  in  size.
  105 #   Data  is  sync'd to the filesystem after each copy_file_range(2)
  106 #   call.
  107 #
  108 copy-file 0		# 0 means 1 stressor per CPU
  109 # copy-file-ops 1000000 # stop after 1000000 bogo ops
  110 # copy-file-bytes 256M	# size of the copy file (256MB)
  111 
  112 #
  113 # dentry stressor options:
  114 #   start  N workers that create and remove directory entries.  This
  115 #   should create file system  meta  data  activity.  The  directory
  116 #   entry names are suffixed by a gray-code encoded number to try to
  117 #   mix up the hashing of the namespace.
  118 #
  119 dentry 0		# 0 means 1 stressor per CPU
  120 # dentry-ops 1000000	# stop after 1000000 bogo ops
  121 # dentry-order forward	# forward order dentry unlinking,
  122 			# can be forward, reverse, stride or random
  123 # dentries 2048		# create 2048 dentries per stress iteration
  124 
  125 
  126 #
  127 # dir stressor options:
  128 #   start N workers that create and remove directories  using  mkdir
  129 #   and rmdir.
  130 #
  131 dir 0			# 0 means 1 stressor per CPU
  132 # dir-ops 1000000	# stop after 1000000 bogo ops
  133 # dir-dirs 8192		# exercise 8192 directories per stressor
  134 
  135 #
  136 # dirdeep stressor options:
  137 #   start N workers that create multiple levels of directories to  a
  138 #   maximum depth as limited by PATH_MAX or ENAMETOOLONG (which ever
  139 #   occurs first)
  140 #
  141 dirdeep 0		# 0 means 1 stressor per CPU
  142 # dirdeep-ops 1000000	# stop after 1000000 bogo ops
  143 
  144 #
  145 # dnotify stressor options:
  146 #   start N workers performing file system activities such  as  mak‐
  147 #   ing/deleting  files/directories,  renaming files, etc. to stress
  148 #   exercise the various dnotify events (Linux only).
  149 #
  150 dnotify 0		# 0 means 1 stressor per CPU
  151 # dnotify-ops 1000000	# stop after 1000000 bogo ops
  152 
  153 #
  154 # dup stressor options:
  155 #   start N workers that perform dup(2) and then close(2) operations
  156 #   on  /dev/zero.  The maximum opens at one time is system defined,
  157 #   so the test will run up to this  maximum,  or  65536  open  file
  158 #   descriptors, which ever comes first.
  159 #
  160 dup 0		# 0 means 1 stressor per CPU
  161 # dup-ops 1000000	# stop after 1000000 bogo ops
  162 
  163 #
  164 # eventfd stressor options:
  165 #   start  N parent and child worker processes that read and write 8
  166 #   byte event messages  between  them  via  the  eventfd  mechanism
  167 #   (Linux only).
  168 #
  169 eventfd 0		# 0 means 1 stressor per CPU
  170 # eventfd-ops 1000000	# stop after 1000000 bogo ops
  171 
  172 #
  173 # fallocate stressor options:
  174 #   start N  workers  continually  fallocating  (preallocating  file
  175 #   space) and ftuncating (file truncating) temporary files.  If the
  176 #   file is larger than the free space, fallocate  will  produce  an
  177 #   ENOSPC error which is ignored by this stressor.
  178 #
  179 fallocate 0		# 0 means 1 stressor per CPU
  180 # fallocate-ops 1000000	# stop after 1000000 bogo ops
  181 # fallocate-bytes 1G	# allocated file size, 1GB
  182 #
  183 
  184 #
  185 # fanotify stressor options:
  186 #   start N workers performing file system activities such as creat‐
  187 #   ing, opening, writing, reading and unlinking files  to  exercise
  188 #   the  fanotify  event  monitoring  interface  (Linux only).  Each
  189 #   stressor runs a child process to generate file events and a par‐
  190 #   ent process to read file events using fanotify.
  191 #
  192 fanotify 0		# 0 means 1 stressor per CPU
  193 # fanotify-ops 1000000	# stop after 1000000 bogo ops
  194 
  195 #
  196 # fcntl stressor options:
  197 #   start  N  workers  that perform fcntl(2) calls with various com‐
  198 #   mands.  The exercised  commands  (if  available)  are:  F_DUPFD,
  199 #   F_DUPFD_CLOEXEC,  F_GETFD,  F_SETFD, F_GETFL, F_SETFL, F_GETOWN,
  200 #   F_SETOWN, F_GETOWN_EX, F_SETOWN_EX, F_GETSIG, F_SETSIG, F_GETLK,
  201 #   F_SETLK, F_SETLKW, F_OFD_GETLK, F_OFD_SETLK and F_OFD_SETLKW.
  202 #
  203 fcntl 0		# 0 means 1 stressor per CPU
  204 # fcntl-ops 1000000	# stop after 1000000 bogo ops
  205 
  206 #
  207 # fiemap stressor options:
  208 #   start  N  workers  that  each  create  a file with many randomly
  209 #   changing extents and has  4  child  processes  per  worker  that
  210 #   gather the extent information using the FS_IOC_FIEMAP ioctl(2).
  211 #
  212 fiemap 0		# 0 means 1 stressor per CPU
  213 # fiemap-ops 1000000	# stop after 1000000 bogo ops
  214 # fiemap-bytes 1G	# allocated file size, 1GB
  215 
  216 #
  217 # filename stressor options:
  218 #   start N workers that exercise file creation using various length
  219 #   filenames containing a range  of  allower  filename  characters.
  220 #   This  will  try  to see if it can exceed the file system allowed
  221 #   filename length  was  well  as  test  various  filename  lengths
  222 #   between 1 and the maximum allowed by the file system.
  223 #
  224 filename 0		# 0 means 1 stressor per CPU
  225 # filename-ops 1000000	# stop after 1000000 bogo ops
  226 # filename-opts probe	# probe for valid filename characters,
  227 			# can also use posix and ext
  228 #
  229 # flock stressor options:
  230 #   start N workers locking on a single file.
  231 #
  232 flock 0			# 0 means 1 stressor per CPU
  233 # flock-ops 1000000	# stop after 1000000 bogo ops
  234 
  235 #
  236 # fstat stressor options:
  237 #   start  N  workers  fstat'ing  files  in  a directory (default is
  238 #   /dev).
  239 #
  240 fstat 0			# 0 means 1 stressor per CPU
  241 # fstat-ops 1000000	# stop after 1000000 bogo ops
  242 # fstat-dir /path	# fstat on the directory named '/path'
  243 
  244 #
  245 # getdent stressor options:
  246 #   start  N workers that recursively read directories /proc, /dev/,
  247 #   /tmp, /sys and /run using getdents and getdents64 (Linux only)
  248 #
  249 getdent 0		# 0 means 1 stressor per CPU
  250 # getdent-ops 1000000	# stop after 1000000 bogo ops
  251 
  252 #
  253 # handle stressor options:
  254 #   start N  workers  that  exercise  the  name_to_handle_at(2)  and
  255 #   open_by_handle_at(2) system calls. (Linux only).
  256 #
  257 handle 0		# 0 means 1 stressor per CPU
  258 # handle-ops 1000000	# stop after 1000000 bogo ops
  259 
  260 #
  261 # inotify stressor options:
  262 #   start N workers performing file system activities such  as  mak‐
  263 #   ing/deleting  files/directories,  moving  files,  etc. to stress
  264 #   exercise the various inotify events (Linux only).
  265 #
  266 inotify 0		# 0 means 1 stressor per CPU
  267 # inotify-ops 1000000	# stop after 1000000 bogo ops
  268 
  269 #
  270 # io stressor options:
  271 #   start N workers continuously calling sync(2)  to  commit  buffer
  272 #   cache  to  disk.  This can be used in conjunction with the --hdd
  273 #   options.
  274 #
  275 io 0			# 0 means 1 stressor per CPU
  276 # io-ops 1000000	# stop after 1000000 bogo ops
  277 
  278 #
  279 # iomix stressor options:
  280 #   start N workers that perform a mix  of  sequential,  random  and
  281 #   memory  mapped  read/write operations as well as forced sync'ing
  282 #   and (if run as root) cache dropping.  Multiple  child  processes
  283 #   are spawned to all share a single file and perform different I/O
  284 #   operations on the same file.
  285 #
  286 iomix 0			# 0 means 1 stressor per CPU
  287 # iomix-ops 1000000	# stop after 1000000 bogo ops
  288 # iomix-bytes 1G	# iomix file size (1GB)
  289 
  290 #
  291 # ioprio stressor options:
  292 #   start   N   workers   that   exercise   the   ioprio_get(2)  and
  293 #   ioprio_set(2) system calls (Linux only).
  294 #
  295 ioprio 0		# 0 means 1 stressor per CPU
  296 # ioprio-ops 1000000	# stop after 1000000 bogo ops
  297 
  298 #
  299 # lease stressor options:
  300 #   start  N  workers locking, unlocking and breaking leases via the
  301 #   fcntl(2) F_SETLEASE operation. The parent processes  continually
  302 #   lock and unlock a lease on a file while a user selectable number
  303 #   of child processes open the file with  a  non-blocking  open  to
  304 #   generate SIGIO lease breaking notifications to the parent.  This
  305 #   stressor is only available if F_SETLEASE,  F_WRLCK  and  F_UNLCK
  306 #   support is provided by fcntl(2).
  307 #
  308 lease 0			# 0 means 1 stressor per CPU
  309 # lease-ops 1000000	# stop after 1000000 bogo ops
  310 # lease-breakers 4	# start 4 lease breaker child processors
  311 			# per stressor
  312 #
  313 # link stressor options:
  314 #   start N workers creating and removing hardlinks.
  315 #
  316 link 0			# 0 means 1 stressor per CPU
  317 # link-ops 1000000	# stop after 1000000 bogo ops
  318 
  319 #
  320 # locka stressor options:
  321 #   start N workers that randomly lock and unlock regions of a  file
  322 #   using  the  POSIX  advisory  locking  mechanism  (see  fcntl(2),
  323 #   F_SETLK, F_GETLK). Each  worker  creates  a  1024  KB  file  and
  324 #   attempts to hold a maximum of 1024 concurrent locks with a child
  325 #   process that also tries to hold 1024 concurrent locks. Old locks
  326 #   are unlocked in a first-in, first-out basis.
  327 #
  328 locka 0			# 0 means 1 stressor per CPU
  329 # locka-ops 1000000	# stop after 1000000 bogo ops
  330 
  331 #
  332 # lockf stressor options:
  333 #   start  N workers that randomly lock and unlock regions of a file
  334 #   using the POSIX lockf(3) locking mechanism. Each worker  creates
  335 #   a  64  KB file and attempts to hold a maximum of 1024 concurrent
  336 #   locks with a child process that also tries to hold 1024  concur‐
  337 #   rent  locks.  Old  locks  are  unlocked in a first-in, first-out
  338 #   basis.
  339 #
  340 lockf 0			# 0 means 1 stressor per CPU
  341 # lockf-ops 1000000	# stop after 1000000 bogo ops
  342 # lockf-nonblock	# use non-blocking F_TLOCK and retry unlocks
  343 
  344 #
  345 # lockofd stressor options:
  346 #   start N workers that randomly lock and unlock regions of a  file
  347 #   using  the  Linux  open  file  description  locks (see fcntl(2),
  348 #   F_OFD_SETLK, F_OFD_GETLK).  Each worker creates a 1024  KB  file
  349 #   and  attempts  to hold a maximum of 1024 concurrent locks with a
  350 #   child process that also tries to hold 1024 concurrent locks. Old
  351 #   locks are unlocked in a first-in, first-out basis.
  352 #
  353 lockofd 0		# 0 means 1 stressor per CPU
  354 # lockofd-ops 1000000	# stop after 1000000 bogo ops
  355 
  356 #
  357 # mknod stressor options:
  358 #   start N workers that create and remove fifos,  empty  files  and
  359 #   named sockets using mknod and unlink.
  360 #
  361 mknod 0			# 0 means 1 stressor per CPU
  362 # mknod-ops 1000000	# stop after 1000000 bogo ops
  363 
  364 #
  365 # open stressor options:
  366 #   start N workers that perform open(2) and  then  close(2)  opera‐
  367 #   tions  on  /dev/zero.  The  maximum  opens at one time is system
  368 #   defined, so the test will run up to this maximum, or 65536  open
  369 #   file descriptors, which ever comes first.
  370 #
  371 open 0			# 0 means 1 stressor per CPU
  372 # open-ops 1000000	# stop after 1000000 bogo ops
  373 
  374 #
  375 # procfs stressor options:
  376 #   start  N workers that read files from /proc and recursively read
  377 #   files from /proc/self (Linux only).
  378 #
  379 procfs 0		# 0 means 1 stressor per CPU
  380 # procfs-ops 1000000	# stop after 1000000 bogo ops
  381 
  382 #
  383 # rename stressor options:
  384 #   start N workers that each create  a  file  and  then  repeatedly
  385 #   rename it.
  386 #
  387 rename 0		# 0 means 1 stressor per CPU
  388 # rename-ops 1000000	# stop after 1000000 bogo ops
  389 
  390 #
  391 # symlink stressor options:
  392 #   start N workers creating and removing symbolic links.
  393 #
  394 symlink 0		# 0 means 1 stressor per CPU
  395 # symlink-ops 1000000	# stop after 1000000 bogo ops
  396 
  397 #
  398 # sync-file stressor options:
  399 #   start N workers that perform a range of data syncs across a file
  400 #   using sync_file_range(2).  Three mixes of syncs  are  performed,
  401 #   from  start to the end of the file,  from end of the file to the
  402 #   start, and a random mix. A random selection of valid sync  types
  403 #   are     used,    covering    the    SYNC_FILE_RANGE_WAIT_BEFORE,
  404 #   SYNC_FILE_RANGE_WRITE and SYNC_FILE_RANGE_WAIT_AFTER flag bits
  405 #
  406 sync-file 0		# 0 means 1 stressor per CPU
  407 # sync-file-ops 1000000	# stop after 1000000 bogo ops
  408 # sync-file-bytes 1G	# allocated file size, 1GB
  409 
  410 #
  411 # utime stressor options:
  412 #   start  N  workers  updating  file timestamps. This is mainly CPU
  413 #   bound when the default is used as the  system  flushes  metadata
  414 #   changes only periodically.
  415 #
  416 utime 0			# 0 means 1 stressor per CPU
  417 # utime-ops 1000000	# stop after 1000000 bogo ops
  418 # utime-fsync		# force flush metadata to disk
  419 
  420 #
  421 # xattr stressor options:
  422 #   start  N  workers  that  create,  update  and  delete batches of
  423 #   extended attributes on a file.
  424 #
  425 xattr 0			# 0 means 1 stressor per CPU
  426 # xattr-ops 1000000	# stop after 1000000 bogo ops