X-Git-Url: https://git.kernel.dk/?p=fio.git;a=blobdiff_plain;f=README;h=72ff465ed7ebe68c11960619733bf600c9394016;hp=8db962b625aaf8b2eb7cad1f27bafbd7edce9fd4;hb=493dd6c153bc169e1b52757e496d64ea596f165d;hpb=8079cb463d0934ef458788030922923ce4be1ac0 diff --git a/README b/README index 8db962b6..72ff465e 100644 --- a/README +++ b/README @@ -1,321 +1,234 @@ -fio ---- - -fio is a tool that will spawn a number of threads or processes doing a -particular type of io action as specified by the user. fio takes a -number of global parameters, each inherited by the thread unless -otherwise parameters given to them overriding that setting is given. -The typical use of fio is to write a job file matching the io load -one wants to simulate. +Overview and history +-------------------- + +Fio was originally written to save me the hassle of writing special test case +programs when I wanted to test a specific workload, either for performance +reasons or to find/reproduce a bug. The process of writing such a test app can +be tiresome, especially if you have to do it often. Hence I needed a tool that +would be able to simulate a given I/O workload without resorting to writing a +tailored test case again and again. + +A test work load is difficult to define, though. There can be any number of +processes or threads involved, and they can each be using their own way of +generating I/O. You could have someone dirtying large amounts of memory in an +memory mapped file, or maybe several threads issuing reads using asynchronous +I/O. fio needed to be flexible enough to simulate both of these cases, and many +more. + +Fio spawns a number of threads or processes doing a particular type of I/O +action as specified by the user. fio takes a number of global parameters, each +inherited by the thread unless otherwise parameters given to them overriding +that setting is given. The typical use of fio is to write a job file matching +the I/O load one wants to simulate. Source ------ -fio resides in a git repo, the canonical place is: - -git://git.kernel.dk/fio.git - -If you are inside a corporate firewall, git:// may not always work for -you. In that case you can use the http protocol, path is the same: +Fio resides in a git repo, the canonical place is: -http://git.kernel.dk/fio.git + git://git.kernel.dk/fio.git -Snapshots are frequently generated and they include the git meta data as -well. You can download them here: +When inside a corporate firewall, git:// URL sometimes does not work. +If git:// does not work, use the http protocol instead: -http://brick.kernel.dk/snaps/ + http://git.kernel.dk/fio.git +Snapshots are frequently generated and :file:`fio-git-*.tar.gz` include the git +meta data as well. Other tarballs are archives of official fio releases. +Snapshots can download from: -Binary packages ---------------- + http://brick.kernel.dk/snaps/ -Debian: -Starting with Debian "Squeeze", fio packages are part of the official -Debian repository. http://packages.debian.org/search?keywords=fio +There are also two official mirrors. Both of these are automatically synced with +the main repository, when changes are pushed. If the main repo is down for some +reason, either one of these is safe to use as a backup: -Ubuntu: -Starting with Ubuntu 10.04 LTS (aka "Lucid Lynx"), fio packages are part -of the Ubuntu "universe" repository. -http://packages.ubuntu.com/search?keywords=fio + git://git.kernel.org/pub/scm/linux/kernel/git/axboe/fio.git -Red Hat, CentOS & Co: -Dag Wieërs has RPMs for Red Hat related distros, find them here: -http://dag.wieers.com/rpm/packages/fio/ + https://git.kernel.org/pub/scm/linux/kernel/git/axboe/fio.git -Mandriva: -Mandriva has integrated fio into their package repository, so installing -on that distro should be as easy as typing 'urpmi fio'. +or -Solaris: -Packages for Solaris are available from OpenCSW. Install their pkgutil -tool (http://www.opencsw.org/get-it/pkgutil/) and then install fio via -'pkgutil -i fio'. + git://github.com/axboe/fio.git -Windows: -Bruce Cran has fio packages for Windows at -http://www.bluestop.org/fio/ . + https://github.com/axboe/fio.git Mailing list ------------ -There's a mailing list associated with fio. It's meant for general -discussion, bug reporting, questions, and development - basically anything -that has to do with fio. An automated mail detailing recent commits is -automatically sent to the list at most daily. The list address is -fio@vger.kernel.org, subscribe by sending an email to -majordomo@vger.kernel.org with +The fio project mailing list is meant for anything related to fio including +general discussion, bug reporting, questions, and development. For bug reporting, +see REPORTING-BUGS. -subscribe fio +An automated mail detailing recent commits is automatically sent to the list at +most daily. The list address is fio@vger.kernel.org, subscribe by sending an +email to majordomo@vger.kernel.org with + + subscribe fio in the body of the email. Archives can be found here: -http://www.spinics.net/lists/fio/ + http://www.spinics.net/lists/fio/ and archives for the old list can be found here: -http://maillist.kernel.dk/fio-devel/ + http://maillist.kernel.dk/fio-devel/ -Building --------- - -Just type 'make' and 'make install'. +Author +------ -Note that GNU make is required. On BSD it's available from devel/gmake; -on Solaris it's in the SUNWgmake package. On platforms where GNU make -isn't the default, type 'gmake' instead of 'make'. +Fio was written by Jens Axboe to enable flexible testing of +the Linux I/O subsystem and schedulers. He got tired of writing specific test +applications to simulate a given workload, and found that the existing I/O +benchmark/test tools out there weren't flexible enough to do what he wanted. -If your compile fails with an error like this: +Jens Axboe 20060905 - CC gettime.o -In file included from fio.h:23, - from gettime.c:8: -os/os.h:15:20: error: libaio.h: No such file or directory -In file included from gettime.c:8: -fio.h:119: error: field 'iocb' has incomplete type -make: *** [gettime.o] Error 1 -Check that you have the libaio development package installed. On RPM -based distros, it's typically called libaio-devel. +Binary packages +--------------- +Debian: + Starting with Debian "Squeeze", fio packages are part of the official + Debian repository. http://packages.debian.org/search?keywords=fio . -Windows -------- +Ubuntu: + Starting with Ubuntu 10.04 LTS (aka "Lucid Lynx"), fio packages are part + of the Ubuntu "universe" repository. + http://packages.ubuntu.com/search?keywords=fio . -On Windows Cygwin (http://www.cygwin.com/) is required in order to -build fio. To create an MSI installer package install WiX 3.7 from -http://wixtoolset.org and run dobuild.cmd from the -os/windows directory. +Red Hat, Fedora, CentOS & Co: + Starting with Fedora 9/Extra Packages for Enterprise Linux 4, fio + packages are part of the Fedora/EPEL repositories. + https://apps.fedoraproject.org/packages/fio . -How to compile FIO on 64-bit Windows: +Mandriva: + Mandriva has integrated fio into their package repository, so installing + on that distro should be as easy as typing ``urpmi fio``. - 1. Install Cygwin (http://www.cygwin.com/setup.exe). Install 'make' and all - packages starting with 'mingw64-i686' and 'mingw64-x86_64'. - 2. Download ftp://sourceware.org/pub/pthreads-win32/prebuilt-dll-2-9-1-release/dll/x64/pthreadGC2.dll - and copy to the fio source directory. - 3. Open the Cygwin Terminal. - 4. Go to the fio directory (source files). - 5. Run 'make clean'. - 6. Run 'make'. +Arch Linux: + An Arch Linux package is provided under the Community sub-repository: + https://www.archlinux.org/packages/?sort=&q=fio -To build fio on 32-bit Windows, download x86/pthreadGC2.dll instead and do -'./configure --build-32bit-win=yes' before 'make'. +Solaris: + Packages for Solaris are available from OpenCSW. Install their pkgutil + tool (http://www.opencsw.org/get-it/pkgutil/) and then install fio via + ``pkgutil -i fio``. -It's recommended that once built or installed, fio be run in a Command Prompt -or other 'native' console such as console2, since there are known to be display -and signal issues when running it under a Cygwin shell -(see http://code.google.com/p/mintty/issues/detail?id=56 for details). +Windows: + Rebecca Cran has fio packages for Windows at + http://www.bluestop.org/fio/ . +BSDs: + Packages for BSDs may be available from their binary package repositories. + Look for a package "fio" using their binary package managers. -Command line ------------- -$ fio - --debug Enable some debugging options (see below) - --parse-only Parse options only, don't start any IO - --output Write output to file - --runtime Runtime in seconds - --latency-log Generate per-job latency logs - --bandwidth-log Generate per-job bandwidth logs - --minimal Minimal (terse) output - --output-format=type Output format (terse,json,normal) - --terse-version=type Terse version output format (default 3, or 2 or 4). - --version Print version info and exit - --help Print this page - --cpuclock-test Perform test/validation of CPU clock - --cmdhelp=cmd Print command help, "all" for all of them - --enghelp=engine Print ioengine help, or list available ioengines - --enghelp=engine,cmd Print help for an ioengine cmd - --showcmd Turn a job file into command line options - --readonly Turn on safety read-only checks, preventing - writes - --eta=when When ETA estimate should be printed - May be "always", "never" or "auto" - --eta-newline=time Force a new line for every 'time' period passed - --section=name Only run specified section in job file. - Multiple sections can be specified. - --alloc-size=kb Set smalloc pool to this size in kb (def 1024) - --warnings-fatal Fio parser warnings are fatal - --max-jobs Maximum number of threads/processes to support - --server=args Start backend server. See Client/Server section. - --client=host Connect to specified backend. - --idle-prof=option Report cpu idleness on a system or percpu basis - (option=system,percpu) or run unit work - calibration only (option=calibrate). - - -Any parameters following the options will be assumed to be job files, -unless they match a job file parameter. You can add as many as you want, -each job file will be regarded as a separate group and fio will stonewall -its execution. - -The --readonly switch is an extra safety guard to prevent accidentally -turning on a write setting when that is not desired. Fio will only write -if rw=write/randwrite/rw/randrw is given, but this extra safety net can -be used as an extra precaution. It will also enable a write check in the -io engine core to prevent an accidental write due to a fio bug. - -The debug switch allows adding options that trigger certain logging -options in fio. Currently the options are: - - process Dump info related to processes - file Dump info related to file actions - io Dump info related to IO queuing - mem Dump info related to memory allocations - blktrace Dump info related to blktrace setup - verify Dump info related to IO verification - all Enable all debug options - random Dump info related to random offset generation - parse Dump info related to option matching and parsing - diskutil Dump info related to disk utilization updates - job:x Dump info only related to job number x - mutex Dump info only related to mutex up/down ops - profile Dump info related to profile extensions - time Dump info related to internal time keeping - ? or help Show available debug options. - -You can specify as many as you want, eg --debug=file,mem will enable -file and memory debugging. - -The section switch is meant to make it easier to ship a bigger job file -instead of several smaller ones. Say you define a job file with light, -moderate, and heavy parts. Then you can ask fio to run the given part -only by giving it a --section=heavy command line option. The section -option only applies to job sections, the reserved 'global' section is -always parsed and taken into account. - -Fio has an internal allocator for shared memory called smalloc. It -allocates shared structures from this pool. The pool defaults to 1024k -in size, and can grow to 128 pools. If running large jobs with randommap -enabled it can run out of memory, in which case the --alloc-size switch -is handy for starting with a larger pool size. The backing store is -files in /tmp. Fio cleans up after itself, while it is running you -may see .fio_smalloc.* files in /tmp. - - -Job file +Building -------- -See the HOWTO file for a more detailed description of parameters and what -they mean. This file contains the terse version. You can describe big and -complex setups with the command line, but generally it's a lot easier to -just write a simple job file to describe the workload. The job file format -is in the ini style format, as that is easy to read and write for the user. - -The HOWTO or man page has a full list of all options, along with -descriptions, etc. The --cmdhelp option also lists all options. If -used with an option argument, it will detail that particular option. +Just type:: + $ ./configure + $ make + $ make install -Client/server ------------- - -Normally you would run fio as a stand-alone application on the machine -where the IO workload should be generated. However, it is also possible to -run the frontend and backend of fio separately. This makes it possible to -have a fio server running on the machine(s) where the IO workload should -be running, while controlling it from another machine. +Note that GNU make is required. On BSDs it's available from devel/gmake within +ports directory; on Solaris it's in the SUNWgmake package. On platforms where +GNU make isn't the default, type ``gmake`` instead of ``make``. -To start the server, you would do: +Configure will print the enabled options. Note that on Linux based platforms, +the libaio development packages must be installed to use the libaio +engine. Depending on distro, it is usually called libaio-devel or libaio-dev. -fio --server=args +For gfio, gtk 2.18 (or newer), associated glib threads, and cairo are required +to be installed. gfio isn't built automatically and can be enabled with a +``--enable-gfio`` option to configure. -on that machine, where args defines what fio listens to. The arguments -are of the form 'type,hostname or IP,port'. 'type' is either 'ip' (or ip4) -for TCP/IP v4, 'ip6' for TCP/IP v6, or 'sock' for a local unix domain socket. -'hostname' is either a hostname or IP address, and 'port' is the port to -listen to (only valid for TCP/IP, not a local socket). Some examples: +To build fio with a cross-compiler:: -1) fio --server + $ make clean + $ make CROSS_COMPILE=/path/to/toolchain/prefix - Start a fio server, listening on all interfaces on the default port (8765). +Configure will attempt to determine the target platform automatically. -2) fio --server=ip:hostname,4444 +It's possible to build fio for ESX as well, use the ``--esx`` switch to +configure. - Start a fio server, listening on IP belonging to hostname and on port 4444. -3) fio --server=ip6:::1,4444 - - Start a fio server, listening on IPv6 localhost ::1 and on port 4444. - -4) fio --server=,4444 +Windows +~~~~~~~ - Start a fio server, listening on all interfaces on port 4444. +On Windows, Cygwin (http://www.cygwin.com/) is required in order to build +fio. To create an MSI installer package install WiX 3.8 from +http://wixtoolset.org and run :file:`dobuild.cmd` from the :file:`os/windows` +directory. -5) fio --server=1.2.3.4 +How to compile fio on 64-bit Windows: - Start a fio server, listening on IP 1.2.3.4 on the default port. + 1. Install Cygwin (http://www.cygwin.com/). Install **make** and all + packages starting with **mingw64-i686** and **mingw64-x86_64**. + 2. Open the Cygwin Terminal. + 3. Go to the fio directory (source files). + 4. Run ``make clean && make -j``. -6) fio --server=sock:/tmp/fio.sock +To build fio on 32-bit Windows, run ``./configure --build-32bit-win`` before +``make``. - Start a fio server, listening on the local socket /tmp/fio.sock. +It's recommended that once built or installed, fio be run in a Command Prompt or +other 'native' console such as console2, since there are known to be display and +signal issues when running it under a Cygwin shell (see +https://github.com/mintty/mintty/issues/56 and +https://github.com/mintty/mintty/wiki/Tips#inputoutput-interaction-with-alien-programs +for details). -When a server is running, you can connect to it from a client. The client -is run with: -fio --local-args --client=server --remote-args +Documentation +~~~~~~~~~~~~~ -where --local-args are arguments that are local to the client where it is -running, 'server' is the connect string, and --remote-args and -are sent to the server. The 'server' string follows the same format as it -does on the server side, to allow IP/hostname/socket and port strings. -You can connect to multiple clients as well, to do that you could run: +Fio uses Sphinx_ to generate documentation from the reStructuredText_ files. +To build HTML formatted documentation run ``make -C doc html`` and direct your +browser to :file:`./doc/output/html/index.html`. To build manual page run +``make -C doc man`` and then ``man doc/output/man/fio.1``. To see what other +output formats are supported run ``make -C doc help``. -fio --client=server2 --client=server2 +.. _reStructuredText: http://www.sphinx-doc.org/rest.html +.. _Sphinx: http://www.sphinx-doc.org Platforms --------- -Fio works on (at least) Linux, Solaris, AIX, HP-UX, OSX, NetBSD, Windows -and FreeBSD. Some features and/or options may only be available on some of -the platforms, typically because those features only apply to that platform -(like the solarisaio engine, or the splice engine on Linux). +Fio works on (at least) Linux, Solaris, AIX, HP-UX, OSX, NetBSD, OpenBSD, +Windows, FreeBSD, and DragonFly. Some features and/or options may only be +available on some of the platforms, typically because those features only apply +to that platform (like the solarisaio engine, or the splice engine on Linux). Some features are not available on FreeBSD/Solaris even if they could be -implemented, I'd be happy to take patches for that. An example of that is -disk utility statistics and (I think) huge page support, support for that -does exist in FreeBSD/Solaris. - -Fio uses pthread mutexes for signalling and locking and FreeBSD does not -support process shared pthread mutexes. As a result, only threads are -supported on FreeBSD. This could be fixed with sysv ipc locking or -other locking alternatives. - -Other *BSD platforms are untested, but fio should work there almost out -of the box. Since I don't do test runs or even compiles on those platforms, -your mileage may vary. Sending me patches for other platforms is greatly +implemented, I'd be happy to take patches for that. An example of that is disk +utility statistics and (I think) huge page support, support for that does exist +in FreeBSD/Solaris. + +Fio uses pthread mutexes for signalling and locking and some platforms do not +support process shared pthread mutexes. As a result, on such platforms only +threads are supported. This could be fixed with sysv ipc locking or other +locking alternatives. + +Other \*BSD platforms are untested, but fio should work there almost out of the +box. Since I don't do test runs or even compiles on those platforms, your +mileage may vary. Sending me patches for other platforms is greatly appreciated. There's a lot of value in having the same test/benchmark tool available on all platforms. -Note that POSIX aio is not enabled by default on AIX. If you get messages like: +Note that POSIX aio is not enabled by default on AIX. Messages like these:: Symbol resolution failed for /usr/lib/libc.a(posix_aio.o) because: Symbol _posix_kaio_rdwr (number 2) is not exported from dependent module /unix. -you need to enable POSIX aio. Run the following commands as root: +indicate one needs to enable POSIX aio. Run the following commands as root:: # lsdev -C -l posix_aio0 posix_aio0 Defined Posix Asynchronous I/O @@ -323,20 +236,41 @@ you need to enable POSIX aio. Run the following commands as root: # lsdev -C -l posix_aio0 posix_aio0 Available Posix Asynchronous I/O -POSIX aio should work now. To make the change permanent: +POSIX aio should work now. To make the change permanent:: # chdev -l posix_aio0 -P -a autoconfig='available' posix_aio0 changed -Author ------- +Running fio +----------- -Fio was written by Jens Axboe to enable flexible testing -of the Linux IO subsystem and schedulers. He got tired of writing -specific test applications to simulate a given workload, and found that -the existing io benchmark/test tools out there weren't flexible enough -to do what he wanted. +Running fio is normally the easiest part - you just give it the job file +(or job files) as parameters:: -Jens Axboe 20060905 + $ fio [options] [jobfile] ... + +and it will start doing what the *jobfile* tells it to do. You can give more +than one job file on the command line, fio will serialize the running of those +files. Internally that is the same as using the :option:`stonewall` parameter +described in the parameter section. + +If the job file contains only one job, you may as well just give the parameters +on the command line. The command line parameters are identical to the job +parameters, with a few extra that control global parameters. For example, for +the job file parameter :option:`iodepth=2 `, the mirror command line +option would be :option:`--iodepth 2 ` or :option:`--iodepth=2 +`. You can also use the command line for giving more than one job +entry. For each :option:`--name ` option that fio sees, it will start a +new job with that name. Command line entries following a +:option:`--name ` entry will apply to that job, until there are no more +entries or a new :option:`--name ` entry is seen. This is similar to the +job file options, where each option applies to the current job until a new [] +job entry is seen. + +fio does not need to run as root, except if the files or devices specified in +the job section requires that. Some other options may also be restricted, such +as memory locking, I/O scheduler switching, and decreasing the nice value. +If *jobfile* is specified as ``-``, the job file will be read from standard +input.