fio.git
22 months agoFio 3.1 fio-3.1
Jens Axboe [Thu, 28 Sep 2017 10:23:20 +0000 (04:23 -0600)]
Fio 3.1

Signed-off-by: Jens Axboe <axboe@kernel.dk>
22 months agoRemove old exp/README.md file
Jens Axboe [Tue, 26 Sep 2017 19:38:38 +0000 (13:38 -0600)]
Remove old exp/README.md file

Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoinit: typo in help output
Jens Axboe [Thu, 21 Sep 2017 04:21:35 +0000 (22:21 -0600)]
init: typo in help output

Reported-by: Rebecca Cran <rebecca@bluestop.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoadd fio_set_directio() error message for platforms without direct I/O
Tomohiro Kusumi [Mon, 18 Sep 2017 18:42:50 +0000 (21:42 +0300)]
add fio_set_directio() error message for platforms without direct I/O

This lets platforms without dio (e.g. OpenBSD) fail with an explicit
message, otherwise they fail without a clue about dio even with
--debug=all enabled.

The message modified based on comments from Jens.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoadd "invalid block size" to "first direct IO errored." message
Tomohiro Kusumi [Mon, 18 Sep 2017 18:23:54 +0000 (21:23 +0300)]
add "invalid block size" to "first direct IO errored." message

It could fail due to bs not multiple of sector size.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agofix strncpy(3) copy length
Tomohiro Kusumi [Mon, 18 Sep 2017 17:53:50 +0000 (20:53 +0300)]
fix strncpy(3) copy length

0 terminate the last byte, and copy at most size-1.
(or 0 terminate the last byte after copying upto size bytes)

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agolib/memalign: don't malloc size twice
Tomohiro Kusumi [Mon, 18 Sep 2017 17:53:49 +0000 (20:53 +0300)]
lib/memalign: don't malloc size twice

The footer offset (diff between malloc'd address and aligned address)
is (alignment-1) at most, and footer appears `size' bytes after the
aligned address, thus required size is (alignment-1 + size + sizeof(*f)).

The existing code seems to allocate extra unused `size' bytes.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoMerge branch 'doc-patches' of https://github.com/vincentkfu/fio
Jens Axboe [Thu, 14 Sep 2017 17:37:34 +0000 (11:37 -0600)]
Merge branch 'doc-patches' of https://github.com/vincentkfu/fio

23 months agostat: some bool conversions
Jens Axboe [Thu, 14 Sep 2017 14:54:34 +0000 (08:54 -0600)]
stat: some bool conversions

Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoAdd support for doing total latency percentiles
Jens Axboe [Thu, 14 Sep 2017 04:07:31 +0000 (22:07 -0600)]
Add support for doing total latency percentiles

By default, fio does completion latency percentiles. Sometimes
what you want is total IO latency percentiles, including the
submission part as well. If that's your thing, then set

lat_percentiles=1

and get that instead of the default completion latency percentiles.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoinit: fixup_options() cleanup
Jens Axboe [Thu, 14 Sep 2017 03:53:47 +0000 (21:53 -0600)]
init: fixup_options() cleanup

We have o = &td->o, use it everywhere.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agodoc: provide some documentation for the json output format
Vincent Fu [Wed, 30 Aug 2017 19:44:27 +0000 (15:44 -0400)]
doc: provide some documentation for the json output format

Provide basic documentation for the json output format, including unit information for 'runtime' and 'bw' values.

23 months agodoc: provide more detail regarding the --status-interval option
Vincent Fu [Wed, 30 Aug 2017 19:42:52 +0000 (15:42 -0400)]
doc: provide more detail regarding the --status-interval option

There has been some confusion regarding what the --status-interval option provides. Modify the HOWTO and man page to emphasize that --status-interval provides cumulative instead of per-period values.

23 months agotime: use bool for ramp time
Jens Axboe [Wed, 13 Sep 2017 15:07:25 +0000 (09:07 -0600)]
time: use bool for ramp time

Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agotime: ensure that offload mode switches parent out of ramp
Jens Axboe [Wed, 13 Sep 2017 15:03:20 +0000 (09:03 -0600)]
time: ensure that offload mode switches parent out of ramp

If we have worker threads submitting IO for the jobs AND using
ramp time, then we need to ensure that the parent job is switched out of
ramp mode. This normally happens as part of IO submission, but since
we have worker threads doing that for us, it never happens for the
parent.

Fixes: https://github.com/axboe/fio/issues/459
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoio_u: fix trimming of mixed block size randommap
Jens Axboe [Tue, 12 Sep 2017 20:02:34 +0000 (14:02 -0600)]
io_u: fix trimming of mixed block size randommap

If you run something ala:

fio --name=test --filename=/dev/sda --rw=randread --size=1M --bs=128k,64k --ioengine=libaio --io_submit_mode=offload

where the you have different block sizes for reads and writes, we can
get into a situation where we have to trim IO size for a read
(128k bs), but we use the general minimum block size, which is 64k
That results in a case where we incorrectly reset the IO size to
0, resulting in an invalid IO.

Fixes: https://github.com/axboe/fio/issues/458
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoMerge branch 'solaris-clock-setaffinity' of https://github.com/szaydel/fio
Jens Axboe [Mon, 11 Sep 2017 20:26:01 +0000 (14:26 -0600)]
Merge branch 'solaris-clock-setaffinity' of https://github.com/szaydel/fio

23 months agoFix clock setaffinity failed error which occurs on Solaris and Solaris derivatives...
Sam Zaydel [Mon, 11 Sep 2017 19:48:00 +0000 (12:48 -0700)]
Fix clock setaffinity failed error which occurs on Solaris and Solaris derivatives such as Illumos.

23 months agoMerge branch 'verify_trigger' of https://github.com/sitsofe/fio
Jens Axboe [Mon, 11 Sep 2017 14:29:41 +0000 (08:29 -0600)]
Merge branch 'verify_trigger' of https://github.com/sitsofe/fio

23 months agoMerge branch 'windows_io_hint' of https://github.com/sitsofe/fio
Jens Axboe [Tue, 5 Sep 2017 21:37:36 +0000 (15:37 -0600)]
Merge branch 'windows_io_hint' of https://github.com/sitsofe/fio

23 months agoMerge branch 'travis_32bit' of https://github.com/sitsofe/fio
Jens Axboe [Tue, 5 Sep 2017 14:49:42 +0000 (08:49 -0600)]
Merge branch 'travis_32bit' of https://github.com/sitsofe/fio

23 months agoMerge branch 'gluster_printf' of https://github.com/sitsofe/fio
Jens Axboe [Tue, 5 Sep 2017 14:49:10 +0000 (08:49 -0600)]
Merge branch 'gluster_printf' of https://github.com/sitsofe/fio

23 months agofilesetup: revert O_DIRECT for layout mess
Jens Axboe [Tue, 5 Sep 2017 14:43:28 +0000 (08:43 -0600)]
filesetup: revert O_DIRECT for layout mess

This commit essentially reverts the following fives commits:

d33db728d ("fix regression by 8c43ba62('filesetup: align layout buffer')")
47534cda0 ("filesetup: add non O_DIRECT direct I/O support for initial layout setup")
6c3169f9c ("filesetup: add direct=1 failure warning to layout")
8c43ba625 ("filesetup: align layout buffer")
6e344dc34 ("filesetup: keep OS_O_DIRECT flag when pre-allocating file")

in reverse order, since we keep having issues with the basic idea of
using O_DIRECT for file layout or extensions, if the job file has
asked for O_DIRECT.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agowindowsaio: obey sequential/random I/O hinting
Sitsofe Wheeler [Mon, 4 Sep 2017 06:21:23 +0000 (07:21 +0100)]
windowsaio: obey sequential/random I/O hinting

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
23 months agoglusterfs: silence printf specifier warnings
Sitsofe Wheeler [Sun, 3 Sep 2017 21:59:30 +0000 (22:59 +0100)]
glusterfs: silence printf specifier warnings

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
23 months agotravis: add 32 bit build, minor updates and cleanups
Sitsofe Wheeler [Sun, 3 Sep 2017 09:02:41 +0000 (10:02 +0100)]
travis: add 32 bit build, minor updates and cleanups

- Rejig the Travis file so it does a 32 bit Linux build (albeit on a 64
  bit system). GlusterFS is only installed on 64 bit Linux because the
  32 bit deb tries to pull in psmisc:i386 which conflicts with the
  regular (64 bit) psmisc. The clang 32 bit build works fine but only
  the gcc 32 bit build is done to reduce the number of builds for now.
- Minor reformatting to make it a bit easier to read the shell script
  (but behind the scenes it's still all squashed on to one line).
- Stop apt from installing/upgrading non-essential packages so as to
  reduce build time.
- Make OSX build use a newer Xcode.

23 months agoMerge branch 'shifted_logging' of https://github.com/sitsofe/fio
Jens Axboe [Sat, 2 Sep 2017 23:00:24 +0000 (17:00 -0600)]
Merge branch 'shifted_logging' of https://github.com/sitsofe/fio

23 months agostat: fix shifted windowed logging when using multiple directions
Sitsofe Wheeler [Wed, 30 Aug 2017 19:08:00 +0000 (20:08 +0100)]
stat: fix shifted windowed logging when using multiple directions

When using log_avg_msec and multiple I/O directions, the results
recorded for the directions other than the first are attributed to the
wrong time. This is demonstrated by the following:

sudo modprobe null_blk completion_nsec=100000000 irqmode=2
sudo ./fio --bs=4k --direct=1 --ioengine=libaio --log_avg_msec=1000 \
 --runtime=2s --disable_lat=1 --disable_bw_measurement=1 \
 --filename=/dev/nullb0 --write_iops_log=shiftedlog --rw=rw \
 --name=shiftedlog

results in this:
cat shiftedlog_iops.1.log
1000, 5, 0, 0
2000, 6, 0, 0
2000, 4, 1, 0
2256, 4, 1, 0

shiftedlog_iops.1.log is missing an entry at 1000ms for for the write
direction (1) because the sample has been misattributed to 2000ms (the
third row) due to iolog->avg_last being shared by all directions.

Fix the shifting by turning iolog->avg_last into an array indexed by
direction and only update the windowed stats for the current direction
from add_log_sample().

Fixes https://github.com/axboe/fio/issues/410 .

Reported-by: Kris Davis <shimrot@gmail.com>
Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
23 months agorevert/rework 81647a9a('fix load_ioengine() not to support no "external:" prefix')
Tomohiro Kusumi [Fri, 1 Sep 2017 19:54:12 +0000 (22:54 +0300)]
revert/rework 81647a9a('fix load_ioengine() not to support no "external:" prefix')

We have decided to revert 81647a9a, which disallowed loading an external
ioengine without using (explicitly documented)"external:" prefix.

[PATCH 4/5] fix load_ioengine() not to support no "external:" prefix
http://www.spinics.net/lists/fio/msg06241.html

> The current implementation (i.e. do 2 if 1 failed) happened to have
> been able to load an external ioengine with below syntax without
> "external:" prefix, but this is a bug rather than a feature.

This commit reverts what 81647a9a does, while keeping a commit made
on top of it. See below for details, which is also available in above
mailing list thread. Lines marked with \ are comments by Jens.

--
  >>>>>>> People have already started depending on the "wrong" behaviour e.g.
  >>>>>>> ioengine=libfio_ceph_objectstore.so # must be found in your LD_LIBRARY_PATH
  >>>>>>> from https://github.com/ceph/ceph/blob/master/src/test/fio/ceph-bluestore.fio
  >>>>>>> . Because they're external it's hard to find out just how prevalent
  >>>>>>> this behaviour is.
  >>>>>>
  >>>>>> Then they can add "external:".
  >>>>>> If it has ever been official (in docs/etc), then the program should
  >>>>>> maintain such behavior, like fio keeps kb_base=1024 by default.
  >>>>>>
  >>>>>> This isn't the first time fio broke external ioengines to begin with,
  >>>>>> and fio doesn't guarantee external ioengines.
  >>>>>> e.g. this commit more than a year ago broke ABI.
  >>>>>> 565e784df05c2529479eed8a38701a33b01894bd
  >>>>>>
  >>>>>> It's essentially the same as non mainline'd kernel modules are on
  >>>>>> their own to be uptodate with upstream.
  >>>>>
 \>>>>> No, those two are VERY different. Fio doesn't make any guarantees wrt
 \>>>>> keeping the same ABI (or API, even) for external engines. If they break,
 \>>>>> then you get to keep the pieces and glue them back together. We have
 \>>>>> the engine version number as well to guard against those kinds of
 \>>>>> changes.
 \>>>>>
 \>>>>> But we don't break job files, at least not knowingly, and definitely
 \>>>>> not just in the name of a cleanup.
  >>>>
  >>>> Yes, but you took this patch which breaks job files *wrongly* using
  >>>> external engine option syntax.
  >>>
 \>>> Right, but it's not in a release yet, so it's not impossible to just
 \>>> revert it.
  >>>
  >>>> By "job files wrongly using", I mean job files somehow found
  >>>> unofficial (i.e. undocumented, not intended) way to dlopen it.
  >>>
 \>>> This case is a bit difficult, since it isn't black and white. I took a
 \>>> look at some of the older documentation, and we have been documenting
 \>>> the need for 'external' for a long time (forever?). So I'd be inclined
 \>>> to let this one stay in.
  >>>
  >>>> If breaking this case is not okay, shouldn't this commit be reverted
  >>>> or the design be expand to allow both with/without prefix ?
  >>>
 \>>> The design (or intent, at least) has always been that if you do:
 \>>>
 \>>> ioengine=something
 \>>>
 \>>> then we first try and load 'something' as an internal engine. If that
 \>>> fails, we look for an external engine of that name. That makes sense to
 \>>> me, since it means you don't have to do anything special to load an
 \>>> external engine. I think we should try and retain that behavior, if we
 \>>> can.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agofix regression by 8c43ba62('filesetup: align layout buffer')
Tomohiro Kusumi [Fri, 1 Sep 2017 12:24:23 +0000 (15:24 +0300)]
fix regression by 8c43ba62('filesetup: align layout buffer')

8c43ba62('filesetup: align layout buffer') needs to use the same size
for fio_memalign() and fio_memfree().

If the size `bs' gets decreased while in the write(2) loop, the size
for freeing is smaller than it should be, and results in segfault
by dereferencing ->offset of the footer via irrelevant address somewhere
in user data.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoadd __load_ioengine() to separate ioengine loading from td context
Tomohiro Kusumi [Thu, 31 Aug 2017 20:13:08 +0000 (23:13 +0300)]
add __load_ioengine() to separate ioengine loading from td context

Add a sub function __load_ioengine(), which only takes name argument,
to be called from load_ioengine(). No functional changes.

This lets fio_show_ioengine_help() get rid of a local variable td
which only existed to call load_ioengine(&td, ...) while this td had
no actual thread context thus unneeded.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agofix load_ioengine() not to support no "external:" prefix
Tomohiro Kusumi [Thu, 31 Aug 2017 20:13:07 +0000 (23:13 +0300)]
fix load_ioengine() not to support no "external:" prefix

To load ioengines, it should be done by either
 1) find the ioengine from the existing (static linked) ioengines or
 2) dlopen the path in case of external ioengine,

but not to do 2 if 1 failed, as fio doesn't expect an ioengine to be
dynamically loaded unless with "external:" prefix by design.

The current implementation (i.e. do 2 if 1 failed) happened to have
been able to load an external ioengine with below syntax without
"external:" prefix, but this is a bug rather than a feature.

(--)ioengine=./engines/skeleton_external.so

The design of the external ioengine option since below commits in 2007
 7b395ca5('Prefix external io engine loading with 'external'')
 8a7bd877('Document loading external io engines')
is to use "external:/path/to/so" syntax.

This commit fixes above bug, which also potentially avoids the case
where "/path/to/so" within the given "external:/path/to/so" happens
to match the existing name, though this is normally unlikely to happen.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agocleanup ioengine_load() (for the next commit)
Tomohiro Kusumi [Thu, 31 Aug 2017 20:13:06 +0000 (23:13 +0300)]
cleanup ioengine_load() (for the next commit)

This commit removes name argument from ioengine_load(), as both
ioengine name and path are self contained in td.
No functional changes.

This makes the next commit's diff more clear by separating non
functional noise.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agofix broken external ioengine option
Tomohiro Kusumi [Thu, 31 Aug 2017 20:13:05 +0000 (23:13 +0300)]
fix broken external ioengine option

get_engine_name() function added to support external ioengine option
via "external:" prefix in below commits in 2007 has been broken.
 7b395ca5('Prefix external io engine loading with 'external'')
 8a7bd877('Document loading external io engines')

It seems to have been broken since below commit in 2011 which made
__handle_option() strip ':' and after while parsing the option.
 c44b1ff5('Add sub-option support (sort-of) and convert libaio_userspace_reap')

Above change made fio dlopen "external" instead of the path located
after "external:", since the path had already been stripped by
__handle_option() by the time get_engine_name() was called. This commit
fixes it by adding ->ioengine_so_path pointer to keep the path while
parsing using sub-option callback.

Note that removing get_engine_name() doesn't affect non "external:"
ioengine options, as the option parser also strips while parsing.

-- before this commit
 # ./fio --name=xxx --ioengine=external:./engines/skeleton_external.so
 fio: engine external not loadable
 fio: failed to load engine external
 fio: file:ioengines.c:91, func=dlopen, error=external: cannot open shared object file: No such file or directory

-- with this commit
 # ./fio --name=xxx --ioengine=external:./engines/skeleton_external.so
 xxx: (g=0): rw=read, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=engine_name, iodepth=1
 fio-3.0-32-g68f6f
 Starting 1 process
 xxx: you need to specify size=
 fio: pid=0, err=22/file:filesetup.c:973, func=total_file_size, error=Invalid argument

 Run status group 0 (all jobs):

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoskeleton: add option example
Tomohiro Kusumi [Thu, 31 Aug 2017 20:13:04 +0000 (23:13 +0300)]
skeleton: add option example

Add an example of ioengine specific options, which can/should exist
within each ioengine code. Also fix/add documentation.

Also see e59b9e11('move skip_bad= option to engines/mtd.c').

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agot/axmap: we don't need smalloc/sfree wrappers
Jens Axboe [Thu, 31 Aug 2017 14:34:27 +0000 (08:34 -0600)]
t/axmap: we don't need smalloc/sfree wrappers

Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoMerge branch 'verify_warn' of https://github.com/sitsofe/fio
Jens Axboe [Thu, 31 Aug 2017 14:21:48 +0000 (08:21 -0600)]
Merge branch 'verify_warn' of https://github.com/sitsofe/fio

23 months agolib/axmap: a few fixes/cleanups
Jens Axboe [Wed, 30 Aug 2017 19:03:26 +0000 (13:03 -0600)]
lib/axmap: a few fixes/cleanups

- If we clear a bit and it's lower than the first free cache,
  update the cache.

- Mark bit_masks[] as const.

- Clean up logic in axmap_first_free()

Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoMerge branch 'asmfix' of https://github.com/oohal/fio
Jens Axboe [Tue, 29 Aug 2017 21:35:49 +0000 (15:35 -0600)]
Merge branch 'asmfix' of https://github.com/oohal/fio

23 months agochange os_trim() prototype not to use int fd
Tomohiro Kusumi [Tue, 29 Aug 2017 21:12:16 +0000 (00:12 +0300)]
change os_trim() prototype not to use int fd

This is the same as the previous commit. The offset and length are
universal regardless of platforms, but int fd is not, thus it should
take struct fio_file*.

In fact, other fd related functions under os/ don't take int fd for
portability even if some of them work fine with int fd at the moment.

(OS headers basically (should)have no dependencies on fio functions
and structures, but struct fio_file is the only exception.)

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agochange fio_set_odirect() prototype not to use int fd
Tomohiro Kusumi [Tue, 29 Aug 2017 21:12:15 +0000 (00:12 +0300)]
change fio_set_odirect() prototype not to use int fd

This function should take struct fio_file*, since the idea of integer
fd in unix likes isn't necessarily usable on other platforms (Windows).

In fact, other fd related functions under os/ don't take int fd for
portability even if some of them work fine with int fd at the moment.

(OS headers basically (should)have no dependencies on fio functions
and structures, but struct fio_file is the only exception.)

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agofilesetup: add non O_DIRECT direct I/O support for initial layout setup
Tomohiro Kusumi [Tue, 29 Aug 2017 21:12:14 +0000 (00:12 +0300)]
filesetup: add non O_DIRECT direct I/O support for initial layout setup

8c43ba62('filesetup: align layout buffer') and
6e344dc3('filesetup: keep OS_O_DIRECT flag when pre-allocating file')
only consider OS with open(O_DIRECT).

This commit adds fio_set_directio() since now OS specific direct I/O
initialization is needed by both real ->fd and temporary ->fd while in
extend_file() to equally support the feature.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoadd ifdef __sun__ for Solaris specific code
Tomohiro Kusumi [Tue, 29 Aug 2017 21:12:13 +0000 (00:12 +0300)]
add ifdef __sun__ for Solaris specific code

ENOTTY on direct I/O setup failure via directio(3C) is Solaris (ZFS)
specific (as also mentioned in ZoL commit[1]).

Linux and many others which support O_DIRECT never come here, but
others supporting direct I/O via OS specific way don't necessarily
have the same ENOTTY behavior or ZFS itself.

This commit brings back the original log before 42f1ee68 for others.

[1] https://github.com/zfsonlinux/zfs/commit/a08c76a8ad63c28384ead72b53a3d7ef73f39357

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoHOWTO: add OpenBSD to direct I/O unsupported platform
Tomohiro Kusumi [Tue, 29 Aug 2017 21:12:12 +0000 (00:12 +0300)]
HOWTO: add OpenBSD to direct I/O unsupported platform

OpenBSD has neither open(O_DIRECT) nor its kernel specific way.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agocleanup NetBSD/OpenBSD header
Tomohiro Kusumi [Tue, 29 Aug 2017 21:12:11 +0000 (00:12 +0300)]
cleanup NetBSD/OpenBSD header

* NetBSD's <sys/rb.h> was renamed to <sys/rbtree.h> 7 years ago.
* Drop unneeded undefs.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoarch/ppc: Fix get_cpu_clock asm clobber list
Oliver O'Halloran [Thu, 6 Jul 2017 08:47:10 +0000 (18:47 +1000)]
arch/ppc: Fix get_cpu_clock asm clobber list

Mark condition register 0 (cr0) as being clobbered by the inline asm in
get_cpu_clock(). Not doing this results in strange behaviour due to GCC
optimising away some checking. For example e.g:

  $ ./fio examples/null.fio --output-format=json
  time     5500  cycles_start=8085227422910      <--- bad!
  {
    "fio version" : "fio-2.21-89-gb034",
    <snip>

The extra output is due to the flag checking in dprint being removed
at higher optimisation levels.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
23 months agoMerge branch 'direct_layout_fix' of https://github.com/sitsofe/fio
Jens Axboe [Mon, 28 Aug 2017 15:57:30 +0000 (09:57 -0600)]
Merge branch 'direct_layout_fix' of https://github.com/sitsofe/fio

23 months agofilesetup: add direct=1 failure warning to layout
Sitsofe Wheeler [Mon, 21 Aug 2017 21:15:00 +0000 (22:15 +0100)]
filesetup: add direct=1 failure warning to layout

Add warning about the filesystem not liking direct=1/buffered=0 to
initial layout code.

v2:
- Update warning to include /buffered=0 so it matches other EINVAL
  warnings
- Minor commit message update

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
23 months agofilesetup: align layout buffer
Sitsofe Wheeler [Mon, 21 Aug 2017 21:15:00 +0000 (22:15 +0100)]
filesetup: align layout buffer

Since commit 6e344dc3445bfec0583072e82bea728ab8d54d58 ("filesetup: keep
OS_O_DIRECT flag when pre-allocating file") when direct=1 fio will set
the OS_O_DIRECT flag during file layout. Unfortunately this makes the
following job fail with due to an "Invalid argument" on Linux:

$ rm -f fiodirect.tmp; ./fio --direct=1 --bs=4k --filename=fiodirect.tmp \
 --size=16k --name=directtest
directtest: (g=0): rw=read, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=psync, iodepth=1
fio-3.0-9-gb427
Starting 1 process
directtest: Laying out IO file (1 file / 0MiB)
fio: pid=35410, err=22/file:filesetup.c:227, func=write, error=Invalid argument

(where fiodirect.tmp is on a filesystem that supports O_DIRECT such as
ext4 and the job used to succeed)

The open(2) man page for Linux says:

"Under Linux 2.4, transfer sizes, and the alignment of the user buffer
and the file offset must all be multiples of the logical block size of
the filesystem.  Since Linux 2.6.0, alignment to the logical block size
of the underlying storage (typically 512 bytes) suffices."

The above is cryptic but suggests that on Linux 2.6 and above kernels
the transfer size, the *memory alignment of the user buffer* and the
file offset must all be multiples of the underlying logical block size
when using O_DIRECT.

This commit forces the memory of fio's layout I/O buffer to be aligned
to the system's page size in an attempt to meet the memory alignment
requirement. Altough approximate, this should handle all but the most
unusual setups for the near future and matches what init_io_u() does in
backend.c.

v2:
- Align buffer pointer to page size rather than maximum block size
- Update commit message, include example

Fixes https://github.com/axboe/fio/issues/429 .

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
23 months agoengines/windowsaio: kill useless forward declarations
Jens Axboe [Sun, 27 Aug 2017 21:21:26 +0000 (15:21 -0600)]
engines/windowsaio: kill useless forward declarations

Signed-off-by: Jens Axboe <axboe@kernel.dk>
23 months agoMerge branch 'doc_runtime' of https://github.com/sitsofe/fio
Jens Axboe [Sun, 27 Aug 2017 16:04:28 +0000 (10:04 -0600)]
Merge branch 'doc_runtime' of https://github.com/sitsofe/fio

23 months agoMerge branch 'fixes' of https://github.com/sitsofe/fio
Jens Axboe [Sun, 27 Aug 2017 16:03:38 +0000 (10:03 -0600)]
Merge branch 'fixes' of https://github.com/sitsofe/fio

23 months agobackend: verify-trigger fixes
Sitsofe Wheeler [Sat, 26 Aug 2017 07:38:11 +0000 (08:38 +0100)]
backend: verify-trigger fixes

Clear the trigger_timeout after we have found it has been exceeded in
trigger_timedout() to stop us repeatedly firing the trigger again and
again in the future.

When --trigger-remote is unset, the server winds up with the remote
trigger command represented by buf[] being zero length rather than buf
being NULL in handle_trigger_cmd(). Cope with this by returning right
away if we find the cmd string is NULL or empty in exec_trigger().

Make server mode fio terminate after sending the verify state back to
the client so it goes on behave the same way as standalone fio. This
stops the while loop in thread_main() restating and in turn prevents
state being cleared away by clear_io_state().

Make keep_running() return false if td->terminate has been set Just In
Case.

The below would trigger the above problem before this patch:

cat <<EOF > trigger.fio
[global]
ioengine=null
time_based=1
runtime=10s
size=1M
bs=4k
rate=4k

[trigtest]
EOF
./fio --server &
./fio --trigger-timeout=2s --trigger='hostname' --client=localhost \
 --debug=net trigger.fio

Fixes https://github.com/axboe/fio/issues/431 ("fio intermittently fails
to perform IO when --trigger-timeout, --trigger is specified").

Reported-by: saurabhbpl <saurabh.shiva@gmail.com>
Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
23 months agoMerge branch 'stat_base_overflow' of https://github.com/football1222/fio
Jens Axboe [Wed, 23 Aug 2017 14:34:37 +0000 (08:34 -0600)]
Merge branch 'stat_base_overflow' of https://github.com/football1222/fio

23 months agostat: increase the size of base to avoid overflow
Richard Liu [Wed, 23 Aug 2017 10:49:58 +0000 (18:49 +0800)]
stat: increase the size of base to avoid overflow

plat_idx_to_val() in stat.c has a variable base that is defined as an
unsigned int but it was designed to fit old settings where
FIO_IO_U_PLAT_GROUP_NR = 19.
With the alteration from usec to nsec in commit
d6bb626ef37d3905221ade2887b422717a07af09(nanosecond: update completion
latency recording and normal, json output to use nanoseconds)
FIO_IO_U_PLAT_GROUP_NR is now 29 and the range of latency changed from
uint32_t to uint64_t. This means in plat_idx_to_val(), variable base
can easily exceed a 32-bit range and overflow after error_bits reaches 26.

Eg.
Group MSB #discarded range of #buckets
error_bits value
27 32 26 [42949672968589934591]     64
base = 1 << (error_bits + FIO_IO_U_PLAT_BITS);
(1 << 32) will overflow
if change to:
base = ((unsigned long long) 1) << (error_bits + FIO_IO_U_PLAT_BITS);
base itself will still overflow
so base should be unsigned long long

23 months agoMerge branch 'timespec_add_msec_overflow' of https://github.com/sitsofe/fio
Jens Axboe [Tue, 22 Aug 2017 16:32:18 +0000 (10:32 -0600)]
Merge branch 'timespec_add_msec_overflow' of https://github.com/sitsofe/fio

23 months agotime: fix overflow in timespec_add_msec
Sitsofe Wheeler [Tue, 22 Aug 2017 05:19:29 +0000 (06:19 +0100)]
time: fix overflow in timespec_add_msec

Commit 8b6a404cdd2c40715885e562416c3db039912773 ("nanosecond: initial
commit changing timeval to timespec") introduced a change to
timespec_add_msec that decreased the time to (unsigned) overflow of
adj_nsec leading to strange values in the write_*_log files when using
log_avg_msec. The following fio job reproduces the problem:

./fio --ioengine=null --size=2G --time_based --runtime=11s \
 --ramp_time=5s --write_iops_log=overflow --log_avg_msec=5000 \
 --name=overflow

cat overflow_iops.1.log shows the following:
5000, 997853, 0, 0
10640, 141323, 0, 0

Compiling fio with clang's undefined behaviour
sanitizer with unsigned wraparound detection turned on by using

CC=clang ./configure --extra-cflags="-fsanitize=undefined,integer"

and running the previous job produces a lot of false positives but also
flags up this:

time.c:11:35: runtime error: unsigned integer overflow: 1000000 * 5000 cannot be represented in type 'unsigned int'

Fix this by forcing the type of the integer literal to ensure that a 64
bit multiplication takes place. Further, force the result variables to
be uint64_t allowing us to remove UL from other literals. Finally adjust
some spacing while we're here.

Fixes https://github.com/axboe/fio/issues/426 (which was also reported
on the mailing list - http://www.spinics.net/lists/fio/msg06190.html ).

Reported-by: Joseph R Gruher <joseph.r.gruher@intel.com>
Suggested-by: Vincent Fu <vincent.fu@wdc.com>
Suggested-by: Jeff Furlong <jeff.furlong@wdc.com>
Reviewed-by: Vincent Fu <vincent.fu@wdc.com>
Tested-by: Joseph R Gruher <joseph.r.gruher@intel.com>
Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoREADME: update/add mintty issue links
Sitsofe Wheeler [Fri, 18 Aug 2017 21:07:15 +0000 (22:07 +0100)]
README: update/add mintty issue links

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoconfigure: clean up libverbs configure test
Sitsofe Wheeler [Thu, 17 Aug 2017 21:45:03 +0000 (22:45 +0100)]
configure: clean up libverbs configure test

Compiling the libverbs configure test generated warnings which would
cause libverbs to be detected as unavailable when using -Werror. Fix
this by changing an include to infiniband/verbs.h and eliminate the
unused stdio.h include while we're here.

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agofio: implement 64 bit network/big endian byte swapping macros
Sitsofe Wheeler [Thu, 17 Aug 2017 06:37:01 +0000 (07:37 +0100)]
fio: implement 64 bit network/big endian byte swapping macros

Add cpu_to_be64/be64_to_cpu and make the RDMA ioengine use them so it no
longer needs to include infiniband/arch.h (which generates obsolete
warnings at compile time) or ntohll (which generates deprecation
warnings at compile time).

Tested-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agodoc: remove '--runtime' command line option
Sitsofe Wheeler [Sun, 13 Aug 2017 07:06:15 +0000 (08:06 +0100)]
doc: remove '--runtime' command line option

Commit 5bba8b3acee1bf1359470a82cac030942018405a ("Remove '--runtime'
command line option") removed the --runtime option from the fio tool and
its internal help. This commit removes it from the documentation files
too.

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agodoc: latency log unit is nsec
Vincent Fu [Thu, 17 Aug 2017 18:05:33 +0000 (14:05 -0400)]
doc: latency log unit is nsec

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agotravis: install additional development libraries
Sitsofe Wheeler [Wed, 16 Aug 2017 06:34:01 +0000 (07:34 +0100)]
travis: install additional development libraries

Change the travis configuration to install development libraries and
headers for librbd (Ceph/rados), glusterfs, libibverbs and librdmacm on
Linux CI builds so we can check the related engines continue to build.

This reverses commit ff56a4e2e0a87e4e3b1cc1e74547d55b295967a6 ("travis:
don't enable rbd") because the previous commit now prevents the rbd
engine being built when the librbd found is too old.

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoconfigure: fail rbd configure check on wrong rados_create2 signature
Sitsofe Wheeler [Wed, 16 Aug 2017 20:45:35 +0000 (21:45 +0100)]
configure: fail rbd configure check on wrong rados_create2 signature

Alter the rbd/rados/ceph configure check so it will fail if the
rados_create2() signature is incorrect or if the function is
unavailable. Completes the suggestion in commit
ff56a4e2e0a87e4e3b1cc1e74547d55b295967a6 ("travis: don't enable rbd").

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agofio2gnuplot: minor man page heading fix
Sitsofe Wheeler [Wed, 16 Aug 2017 06:29:50 +0000 (07:29 +0100)]
fio2gnuplot: minor man page heading fix

Fix the man page heading to specify the section and change the date to
be "month year" in English.

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agorbd: fixup format specifier
Sitsofe Wheeler [Wed, 16 Aug 2017 06:14:02 +0000 (07:14 +0100)]
rbd: fixup format specifier

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoFio 3.0 fio-3.0
Jens Axboe [Wed, 16 Aug 2017 20:12:33 +0000 (14:12 -0600)]
Fio 3.0

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoHOWTO: fix wrong kb_base= description
Tomohiro Kusumi [Wed, 16 Aug 2017 20:09:30 +0000 (23:09 +0300)]
HOWTO: fix wrong kb_base= description

Definition of [KMGTP] and [KMGTP]i for kb_base=1000 are opposite.
It instead describes how it works when kb_base=1024 which is default.

This was originally spotted by Mikhail Terekhov in the mailing list
(in a related thread about a week ago, and the patch hasn't been sent).
http://www.spinics.net/lists/fio/msg06151.html

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agogfio: update copyright
Jens Axboe [Wed, 16 Aug 2017 15:10:12 +0000 (09:10 -0600)]
gfio: update copyright

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoprinting: use bigger on-stack buffer
Jens Axboe [Wed, 16 Aug 2017 15:08:27 +0000 (09:08 -0600)]
printing: use bigger on-stack buffer

We might be writing more than 20 bytes, bump up the size to
be safe.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoman: update description of normal output latencies
Vincent Fu [Mon, 14 Aug 2017 18:59:44 +0000 (14:59 -0400)]
man: update description of normal output latencies

1) Describe lat (min, max, avg, stddev) line
2) Use IO latencies description for lat (nsec/usec/msec) lines
3) Fix IO latency description

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoHOWTO: minor fixes and backports from man page
Tomohiro Kusumi [Mon, 14 Aug 2017 15:30:26 +0000 (18:30 +0300)]
HOWTO: minor fixes and backports from man page

These are minor fixes not worth separating into different commits,
which are partly backports from the previous 3 commits, and partly
its own minor fixes.

 * Use proper argument name (option -> command).
 * Use proper quotation (``).
 * Add missing :option:`` directives.
 * Add missing :file:`` directive (stat.h).
 * Add indentation.
 * Add missing alias (mem_align=).
 * Add missing period.
 * Add $ for fio command line examples
 * Cleanup ordering of some ioengine specific options.
 * Change inconsistent quotations for "1..N" and "N" to always use ``.
 * Avoid mixing of whitespace and tab indentation within the same section/block.
 * Correct fio commands' name (fio-genzipf, fio_generate_plots)
 * Correct typos ("used,where", "See disable_slat" in disable_slat)
 * Change "IO" to "I/O" which has been corrected in the past commits as well,
   except for "IO" in the output of fio itself.
 * Mention verification trigger (using magic sysrq) is Linux specific.
 * Mention "Disk stats" output (using sysfs) is Linux specific.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoman: minor fixes for sections before "JOB PARAMETERS" for consistency
Tomohiro Kusumi [Mon, 14 Aug 2017 15:30:25 +0000 (18:30 +0300)]
man: minor fixes for sections before "JOB PARAMETERS" for consistency

This is the continuation of below series of patches as well as the
previous 2 commits to sync the man page with HOWTO.

[PATCH 0/7] Sync fio(1) man page with HOWTO
http://www.spinics.net/lists/fio/msg06008.html

This commit consists of minor fixes to sync formats in the earlier
sections (made by above series of pathches) with the previous 2 commits.
The contents remain the same.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoman: sync "OUTPUT" section and after with HOWTO
Tomohiro Kusumi [Mon, 14 Aug 2017 15:30:24 +0000 (18:30 +0300)]
man: sync "OUTPUT" section and after with HOWTO

This is the continuation of below series of patches as well as the
previous commit to sync the man page with HOWTO. This commit covers the
rest of the sections.

[PATCH 0/7] Sync fio(1) man page with HOWTO
http://www.spinics.net/lists/fio/msg06008.html

This commit syncs the man page with HOWTO. It does not create new contents
that didn't exist in HOWTO, however formats (indentations, directives,
quotations, etc) are modified for some sections so that the entire man
page has consistent style.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoman: sync "JOB PARAMETERS" section with HOWTO
Tomohiro Kusumi [Mon, 14 Aug 2017 15:30:23 +0000 (18:30 +0300)]
man: sync "JOB PARAMETERS" section with HOWTO

This is the continuation of below series of patches to sync the man page
with HOWTO. This commit covers the entire job parameters section.

[PATCH 0/7] Sync fio(1) man page with HOWTO
http://www.spinics.net/lists/fio/msg06008.html

This commit syncs the man page with HOWTO. It does not create new contents
that didn't exist in HOWTO, however formats (indentations, directives,
quotations, etc) are modified for some sections so that the entire man
page has consistent style.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoHOWTO: update and clarify description of latencies in normal output
Vincent Fu [Mon, 14 Aug 2017 18:59:43 +0000 (14:59 -0400)]
HOWTO: update and clarify description of latencies in normal output

1) Add a description for the lat (min, max, avg, stddev) line
2) Use the old 'IO latencies' description for the lat (nsec/usec/msec) section
3) Fix the description of the 'IO latency' section

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agostat: change indentation of the lat (nsec/usec/msec) section in the normal output
Vincent Fu [Mon, 14 Aug 2017 18:59:42 +0000 (14:59 -0400)]
stat: change indentation of the lat (nsec/usec/msec) section in the normal output

With mixed IO the normal output looks like:

$ ./fio --name=test --ioengine=null --time_based --runtime=5s --size=1G --rw=randrw

test: (g=0): rw=randrw, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=null, iodepth=1
fio-2.21-14-ge22fd-dirty
Starting 1 process
Jobs: 1 (f=1): [m(1)][100.0%][r=5749MiB/s,w=5748MiB/s][r=1472k,w=1472k IOPS][eta 00m:00s]
test: (groupid=0, jobs=1): err= 0: pid=16555: Tue Jun 20 16:08:00 2017
   read: IOPS=1488k, BW=5814MiB/s (6096MB/s)(28.4GiB/5001msec)
...
  write: IOPS=1488k, BW=5812MiB/s (6094MB/s)(28.4GiB/5001msec)
...
    lat (nsec) : 20=15.47%, 50=83.90%, 100=0.49%, 250=0.11%, 500=0.02%
    lat (nsec) : 750=0.01%, 1000=0.01%
    lat (usec) : 2=0.01%, 4=0.01%, 10=0.01%, 20=0.01%, 50=0.01%
    lat (usec) : 100=0.01%, 250=0.01%, 500=0.01%
  cpu          : usr=99.84%, sys=0.00%, ctx=181, majf=0, minf=7
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwt: total=7443094,7440426,0, short=0,0,0, dropped=0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1
...

The 'lat (nsec) : 20=15.47%...' section is indented inside the 'write' block,
giving the impression that these describe only write latencies when they are
actually latencies for all of the IOs in the job.

With this patch the normal output looks like:

$ ./fio --name=test --ioengine=null --time_based --runtime=5s --size=1G --rw=randrw

test: (g=0): rw=randrw, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=null, iodepth=1
fio-2.21-14-g4ed22a-dirty
Starting 1 process
Jobs: 1 (f=1): [m(1)][100.0%][r=5879MiB/s,w=5880MiB/s][r=1505k,w=1505k IOPS][eta 00m:00s]
test: (groupid=0, jobs=1): err= 0: pid=16686: Tue Jun 20 16:12:43 2017
   read: IOPS=1523k, BW=5950MiB/s (6239MB/s)(29.1GiB/5001msec)
    clat (nsec): min=15, max=114599, avg=25.38, stdev=139.48
     lat (nsec): min=47, max=257952, avg=58.18, stdev=269.48
    clat percentiles (nsec):
     |  1.00th=[   18],  5.00th=[   19], 10.00th=[   20], 20.00th=[   21],
     | 30.00th=[   22], 40.00th=[   23], 50.00th=[   23], 60.00th=[   24],
     | 70.00th=[   26], 80.00th=[   27], 90.00th=[   27], 95.00th=[   28],
     | 99.00th=[   42], 99.50th=[   45], 99.90th=[  101], 99.95th=[  165],
     | 99.99th=[ 6368]
   bw (  MiB/s): min= 5722, max= 6081, per=0.10%, avg=5950.14, stdev=126.61
  write: IOPS=1523k, BW=5948MiB/s (6236MB/s)(29.0GiB/5001msec)
    clat (nsec): min=15, max=127752, avg=25.56, stdev=158.32
     lat (nsec): min=63, max=230121, avg=79.84, stdev=317.00
    clat percentiles (nsec):
     |  1.00th=[   18],  5.00th=[   19], 10.00th=[   20], 20.00th=[   21],
     | 30.00th=[   22], 40.00th=[   23], 50.00th=[   23], 60.00th=[   25],
     | 70.00th=[   26], 80.00th=[   27], 90.00th=[   27], 95.00th=[   28],
     | 99.00th=[   42], 99.50th=[   46], 99.90th=[  105], 99.95th=[  175],
     | 99.99th=[ 6624]
   bw (  MiB/s): min= 5727, max= 6079, per=0.10%, avg=5947.07, stdev=125.05
  lat (nsec)   : 20=9.40%, 50=90.27%, 100=0.22%, 250=0.08%, 500=0.01%
  lat (nsec)   : 750=0.01%, 1000=0.01%
  lat (usec)   : 2=0.01%, 4=0.01%, 10=0.01%, 20=0.01%, 50=0.01%
  lat (usec)   : 100=0.01%, 250=0.01%
  cpu          : usr=99.84%, sys=0.00%, ctx=150, majf=0, minf=7
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwt: total=7617184,7614394,0, short=0,0,0, dropped=0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: bw=5950MiB/s (6239MB/s), 5950MiB/s-5950MiB/s (6239MB/s-6239MB/s), io=29.1GiB (31.2GB), run=5001-5001msec
  WRITE: bw=5948MiB/s (6236MB/s), 5948MiB/s-5948MiB/s (6236MB/s-6236MB/s), io=29.0GiB (31.2GB), run=5001-5001msec

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoMerge branch 'ci' of https://github.com/sitsofe/fio
Jens Axboe [Mon, 14 Aug 2017 14:32:56 +0000 (08:32 -0600)]
Merge branch 'ci' of https://github.com/sitsofe/fio

2 years agobackend: cleanup overlap submission logic
Jens Axboe [Mon, 14 Aug 2017 14:28:54 +0000 (08:28 -0600)]
backend: cleanup overlap submission logic

Move it into a helper, since we're calling it from two places.
Only check if depth is > 1, since the current io_u is already
accounted as one.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoMerge branch 'serialize_overlap' of https://github.com/sitsofe/fio
Jens Axboe [Mon, 14 Aug 2017 14:24:12 +0000 (08:24 -0600)]
Merge branch 'serialize_overlap' of https://github.com/sitsofe/fio

2 years agoiolog: tidy up log_io_piece() conditional
Sitsofe Wheeler [Wed, 10 May 2017 05:33:31 +0000 (06:33 +0100)]
iolog: tidy up log_io_piece() conditional

Code inspection shows there are currently guards in the call sites of
log_io_piece() that prevent log_io_piece() being called when
td->o.verify == VERIFY_NONE so skip checking it within log_io_piece().

Tested-by: Jeff Furlong <jeff.furlong@wdc.com>
Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoiolog: remove random layout verification optimisation
Sitsofe Wheeler [Thu, 27 Apr 2017 06:22:26 +0000 (07:22 +0100)]
iolog: remove random layout verification optimisation

Running the following fio jobs unexpectedly reports a verification
failure:
rm /tmp/tmp.fio; ./fio --iodepth=1 \
 --verify=pattern --verify_fatal=1 --size=100M --bsrange=512-128k \
 --rw=randwrite --verify_backlog=128 --filename=/tmp/tmp.fio \
 --verify_pattern="%o" --name=spuriousmismatch1

rm /tmp/tmp.fio; ./fio --iodepth=1 \
 --verify=crc32c --verify_fatal=1 --size=100M --bs=4k \
 --rw=randwrite --verify_backlog=20 --filename=/tmp/tmp.fio \
 --percentage_random=50 --randseed=86 --name=spuriousmismatch2

In the case of the first job, using a bsrange where the start and end
are different can cause random write I/O to overlap an already written
region making the original data unverifiable.

For the second job, when percentage_random is between 1 and 99 the same
offset can be generated multiple times but only the last write to that
offset should be verified.

Rather than special casing the growing number of random jobs that might
generate overlaps while still having a randommap, and given preallocation
during layout is the default where possible, just remove the overwrite=0
optimisation thus forcing all random jobs to be checked for overlaps. It
is still possible to force the old behaviour by setting verifysort=0.

Fixes https://github.com/axboe/fio/issues/335 and
https://github.com/axboe/fio/issues/344 .

Tested-by: Jeff Furlong <jeff.furlong@wdc.com>
Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoiolog: fix double free when verified I/O overlaps
Sitsofe Wheeler [Thu, 27 Apr 2017 06:29:56 +0000 (07:29 +0100)]
iolog: fix double free when verified I/O overlaps

When running
valgrind ./fio --randseed=1 --ioengine=libaio --thread --rw=randrw \
 --random_distribution=zipf:1.4 --filename=/tmp/fiofile --io_limit=50M \
 --verify=crc32c --name=verifyfree --iodepth=32 --bsrange=512-1M --size=100M

valgrind reports:
==29301== Invalid read of size 4
==29301==    at 0x44ADFC: io_completed (io_u.c:1835)
==29301==    by 0x44B215: ios_completed (io_u.c:1924)
==29301==    by 0x44B683: io_u_queued_complete (io_u.c:1983)
==29301==    by 0x46FA6F: wait_for_completions (backend.c:455)
==29301==    by 0x471568: do_io (backend.c:1046)
==29301==    by 0x474405: thread_main (backend.c:1746)
==29301==    by 0x576E6B9: start_thread (pthread_create.c:333)
==29301==    by 0x5C8E82C: clone (clone.S:109)
==29301==  Address 0x62cf988 is 72 bytes inside a block of size 88 free'd
==29301==    at 0x4C2EDEB: free (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)

When the __ipo is still in-flight we shouldn't free it when it overlaps
because it will be used at I/O completion time. Fixes
https://github.com/axboe/fio/issues/336 .

Tested-by: Jeff Furlong <jeff.furlong@wdc.com>
Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agofio: add serialize_overlap option
Sitsofe Wheeler [Sun, 23 Apr 2017 21:54:54 +0000 (22:54 +0100)]
fio: add serialize_overlap option

If this isn't set (the default) fio can submit write I/Os that overlap
other in-flight I/Os leading to potential data races. For example the
following job frequently fails at the verification stage:

./fio --random_distribution=zipf:1.6 --direct=1 --filename \
 /tmp/fiofile --ioengine=posixaio --iodepth=32 --size=20M --bs=4k \
 --rw=randwrite --verify=crc32c --name=verifyoverlap

When serialize_overlap=1 fio avoids creating such races.

Thanks to Rachel Lunnon (StorMagic) for helping me debug the initial
version of this!

Fixes: https://github.com/axboe/fio/issues/335

v2: Fix merge conflict and add missing conversion.
v3: Add man page, fix serialize_overlap disabling, improve commit
    message.

Tested-by: Jeff Furlong <jeff.furlong@wdc.com>
Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoverify: warn when verify pass won't be run
Sitsofe Wheeler [Thu, 9 Feb 2017 06:30:04 +0000 (06:30 +0000)]
verify: warn when verify pass won't be run

Put up a warning when the user sets write + verify + runtime +
time_based together because the runtime is completely used by the write
phase but skip the warning if the user is doing verifies "inline" within
the write phase via verify_backlog or they are doing a mixed read/write
workload where the reads might be verifying.

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoverify: make overwriting verified blocks warning more specific
Sitsofe Wheeler [Fri, 17 Feb 2017 07:34:05 +0000 (07:34 +0000)]
verify: make overwriting verified blocks warning more specific

Try to avoid warning when it looks like the filename used is being
auto-generated in a unique fashion and make the start of the warning
more consistent with other fio warnings.

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoci: make CI builds fail on compilation warnings
Sitsofe Wheeler [Sun, 13 Aug 2017 08:03:46 +0000 (09:03 +0100)]
ci: make CI builds fail on compilation warnings

Fio currently builds without warnings using its default options on at
least the platforms where CI is run (Linux, macOS, Windows).
Unfortunately it's easy to overlook changes that start generating
warnings on a platform you don't use regularly. Make this problem more
visible by changing appveyor/travis CI builds to fail when compilation
warnings are produced (but don't make this change for normal manual
builds).

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoMakefile: modify make test to use a filesystem file
Sitsofe Wheeler [Sun, 13 Aug 2017 07:47:40 +0000 (08:47 +0100)]
Makefile: modify make test to use a filesystem file

Change the second job done by "make test" to a use a real file on the
filesystem where fio is built to help highlight problems (like the one
introduced by commit 2c3e17be).

Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
2 years agoHOWTO: fix unit type suffix in "Parameter types" section to upper case
Tomohiro Kusumi [Wed, 9 Aug 2017 13:44:34 +0000 (16:44 +0300)]
HOWTO: fix unit type suffix in "Parameter types" section to upper case

Redo 9ff84231('HOWTO: fix unit type suffix in "Parameter types" section').

> These should be all in lower case or all in upper case, but not both.
> The man page already has these in lower case.

Change above to all upper case based on below comment, instead of all
in lower. Fix the man page (which originally had in lower) as well.

RE: [PATCH 2/4] HOWTO: fix unit type suffix in "Parameter types" section
http://www.spinics.net/lists/fio/msg06146.html
Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoAdd ability to keep memory-mapped files
Stephen Bates [Tue, 8 Aug 2017 20:26:56 +0000 (14:26 -0600)]
Add ability to keep memory-mapped files

By default file backed memory mappings are unlink()'ed after use. This
patch keeps the files if they already existed. We don't check for
errors on access() since we will catch them on the open().

Discovered this when doing p2pmem testing and fio kept deleting the
/dev/p2pmem0 files...

Changes since v1
  Altered based on feedback from Jens to avoid using an option and
  test for file existance instead.

Signed-off-by: Stephen Bates <sbates@raithlin.com>
Changed by me to use a td->flags flag, instead of adding a new
member to thread options.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoMerge branch 'fio-jsonplus-patches' of https://github.com/vincentkfu/fio
Jens Axboe [Mon, 7 Aug 2017 19:44:01 +0000 (13:44 -0600)]
Merge branch 'fio-jsonplus-patches' of https://github.com/vincentkfu/fio

2 years agoman: add section describing json+ output format
Vincent Fu [Mon, 7 Aug 2017 19:05:32 +0000 (15:05 -0400)]
man: add section describing json+ output format

2 years agoHOWTO: add section providing details about json+ output format
Vincent Fu [Thu, 27 Jul 2017 17:57:11 +0000 (13:57 -0400)]
HOWTO: add section providing details about json+ output format

2 years agotools: add fio_jsonplus_clat2csv
Vincent Fu [Wed, 28 Jun 2017 15:47:28 +0000 (11:47 -0400)]
tools: add fio_jsonplus_clat2csv

tools/fio_jsonplus_clat2csv converts JSON+ completion latency data to CSV
format

e6200d822f0d2b9da5600ad2429be0e9e140e125 eliminated an earlier script that
carried out a similar conversion for the original JSON+ format. I assumed
that the new JSON+ format would have no use for a similar script, but I was
wrong.

2 years agomove skip_bad= option to engines/mtd.c
Tomohiro Kusumi [Mon, 7 Aug 2017 17:37:54 +0000 (20:37 +0300)]
move skip_bad= option to engines/mtd.c

This is ioengine specific, thus should be defined in engines/mtd.c.

This option is useless unless engines/mtd.c is enabled.
It could be conditionally compiled using CONFIG_MTD, but all
other ioengines define their own option structure in their code.

The only functional difference is that now .category is changed
to FIO_OPT_C_ENGINE. This is also something done by all other
ioengine specific options, though ->category isn't really used
for anything meaningfull.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoHOWTO: use proper (or drop wrong usage of) option type =bool
Tomohiro Kusumi [Mon, 7 Aug 2017 17:37:53 +0000 (20:37 +0300)]
HOWTO: use proper (or drop wrong usage of) option type =bool

There are options whose .type field are FIO_OPT_BOOL, but not using
=bool for arg type. Likewise there are options whose .type field
are not FIO_OPT_BOOL, but using =bool for arg type.

The options without explicit arg types in HOWTO seem to be for
FIO_OPT_STR_SET, which is not the same as FIO_OPT_BOOL.

The man page also has these, but not the same as the ones in HOWTO.
Also fix a typo "(mtd)skipbad=bool" in the man page which should be
"(mtd)skip_bad=bool".

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoHOWTO: fix unit type suffix in "Parameter types" section
Tomohiro Kusumi [Mon, 7 Aug 2017 17:37:52 +0000 (20:37 +0300)]
HOWTO: fix unit type suffix in "Parameter types" section

These should be all in lower case or all in upper case, but not both.
Given the examples of these are mostly in lower case, this commit
uses lower.

The man page already has these in lower case.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoman: add proper indentation to "PARAMETER TYPES" section
Tomohiro Kusumi [Mon, 7 Aug 2017 17:37:51 +0000 (20:37 +0300)]
man: add proper indentation to "PARAMETER TYPES" section

This commit fixes "int" subsection of "PARAMETER TYPES" section
which had no indentation, while other sections normally do have
proper indentation.

The corresponding section in HOWTO also has indentation.

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoHOWTO: minor fix and backport from man page
Tomohiro Kusumi [Tue, 1 Aug 2017 19:49:28 +0000 (22:49 +0300)]
HOWTO: minor fix and backport from man page

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2 years agoHOWTO: fix wrong "here follows the complete list of fio job parameters" position
Tomohiro Kusumi [Tue, 1 Aug 2017 19:49:27 +0000 (22:49 +0300)]
HOWTO: fix wrong "here follows the complete list of fio job parameters" position

f80dba8d('Convert documentation to reStructured text.')
made this sentence appear in the wrong place.
It should appear before "Units" job parameter section.

The man page has this right as it's not synced (will be soon).

Signed-off-by: Tomohiro Kusumi <tkusumi@tuxera.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>