fio.git
15 years agonet engine: accept both upper and lowercase tcp/udp.
Jens Axboe [Fri, 16 Jan 2009 12:22:26 +0000 (13:22 +0100)]
net engine: accept both upper and lowercase tcp/udp.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agonet engine: add UDP support
Jens Axboe [Fri, 16 Jan 2009 12:21:15 +0000 (13:21 +0100)]
net engine: add UDP support

The filename= option now accepts a third parameter designating the
protocol type, udp or tcp.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd platform section to README
Jens Axboe [Wed, 7 Jan 2009 09:05:14 +0000 (10:05 +0100)]
Add platform section to README

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoOS includes need errno.h
Jens Axboe [Tue, 6 Jan 2009 13:22:30 +0000 (14:22 +0100)]
OS includes need errno.h

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agosmalloc: get rid of MP_SAFE define and lock checks
Jens Axboe [Tue, 6 Jan 2009 10:30:08 +0000 (11:30 +0100)]
smalloc: get rid of MP_SAFE define and lock checks

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoSome more pthread_* call mishandled errors
Jens Axboe [Mon, 5 Jan 2009 18:07:13 +0000 (19:07 +0100)]
Some more pthread_* call mishandled errors

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd --debug=mutex
Jens Axboe [Mon, 5 Jan 2009 18:06:39 +0000 (19:06 +0100)]
Add --debug=mutex

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoMake sure os mutex define is visible in mutex.c
Jens Axboe [Mon, 5 Jan 2009 18:04:15 +0000 (19:04 +0100)]
Make sure os mutex define is visible in mutex.c

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoOnly use process shared mutexes on support platforms
Jens Axboe [Mon, 5 Jan 2009 08:56:29 +0000 (09:56 +0100)]
Only use process shared mutexes on support platforms

On FreeBSD, suggest the use of threads instead.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFixup handling of pthread_mutex*() error returns
Jens Axboe [Mon, 5 Jan 2009 08:45:13 +0000 (09:45 +0100)]
Fixup handling of pthread_mutex*() error returns

They return the errno, not 0/-1. Thanks to
Fabio Checconi <fabio@gandalf.sssup.it>
for noticing this.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd fio_cpuset_exit() empty handler for platforms that don't support affinity
Jens Axboe [Mon, 5 Jan 2009 08:40:13 +0000 (09:40 +0100)]
Add fio_cpuset_exit() empty handler for platforms that don't support affinity

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoInclude crc32c and crc32c-intel checksums in FreeBSD/Solaris
Jens Axboe [Mon, 22 Dec 2008 10:29:50 +0000 (11:29 +0100)]
Include crc32c and crc32c-intel checksums in FreeBSD/Solaris

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoSolaris pset fixes
Jens Axboe [Mon, 22 Dec 2008 10:28:26 +0000 (11:28 +0100)]
Solaris pset fixes

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoSolaris compilation fix
Jens Axboe [Fri, 12 Dec 2008 19:54:15 +0000 (20:54 +0100)]
Solaris compilation fix

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoCPU set creation and destruction can fail on some platforms
Jens Axboe [Fri, 12 Dec 2008 19:51:40 +0000 (20:51 +0100)]
CPU set creation and destruction can fail on some platforms

Check for that and error out if necessary.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoSupport for CPU binding in Solaris
Jens Axboe [Fri, 12 Dec 2008 19:42:26 +0000 (20:42 +0100)]
Support for CPU binding in Solaris

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd a cpuset exit function
Jens Axboe [Fri, 12 Dec 2008 19:40:27 +0000 (20:40 +0100)]
Add a cpuset exit function

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoPrepare for support for CPU binding on other platforms
Jens Axboe [Fri, 12 Dec 2008 19:02:58 +0000 (20:02 +0100)]
Prepare for support for CPU binding on other platforms

The interface was Linux/glibc centric, since that is what got there first.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years ago__usec_sleep() really just spins, rename it
Jens Axboe [Wed, 10 Dec 2008 12:24:12 +0000 (13:24 +0100)]
__usec_sleep() really just spins, rename it

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoLong line style fix + comment
Jens Axboe [Tue, 9 Dec 2008 07:04:29 +0000 (08:04 +0100)]
Long line style fix + comment

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoDon't allow higher CPU counts than what the system has
Jens Axboe [Mon, 8 Dec 2008 19:31:43 +0000 (20:31 +0100)]
Don't allow higher CPU counts than what the system has

Basically just catch the condition before setting up the job, job files,
etc.

Also fixes a big with cpumask, it set the wrong part.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoMake sure that the given CPU range is within the bounds of the OS
Jens Axboe [Mon, 8 Dec 2008 14:03:12 +0000 (15:03 +0100)]
Make sure that the given CPU range is within the bounds of the OS

glibc provides CPU_SETSIZE as the maximum CPU count.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd gtod_cpu option for pinning gettimeofday() to a single CPU
Jens Axboe [Mon, 8 Dec 2008 13:10:52 +0000 (14:10 +0100)]
Add gtod_cpu option for pinning gettimeofday() to a single CPU

Similar to what real life products sometimes do, offload gettimeofday()
calls to a single CPU and have that update the current time into a shared
memory location. This option pins a specific CPU for that job, and excludes
it from participating in any of the IO jobs.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoProperly strip end-of-option blanks
Jens Axboe [Mon, 8 Dec 2008 13:06:42 +0000 (14:06 +0100)]
Properly strip end-of-option blanks

We don't want to fail with

option_foo = 0

when

option_foo=0

works.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAllow ranges of CPUs in cpus_allowed option
Jens Axboe [Mon, 8 Dec 2008 10:37:01 +0000 (11:37 +0100)]
Allow ranges of CPUs in cpus_allowed option

For a larger number of CPUs, it's a bit of a bother having to set
each one individually. Plus, you typically want to bind to a range of
CPUs, to keep the job core local (or whatever your preference). So extend
cpus_allowed to take ranges of CPU numbers as well. Now you can do:

cpus_allowed=0-7

and have your job confined to CPUs 0 through 7.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFix bogus 'may be used uninitialized' warning from older gcc versions
Jens Axboe [Fri, 5 Dec 2008 12:17:16 +0000 (13:17 +0100)]
Fix bogus 'may be used uninitialized' warning from older gcc versions

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd comment on cpumask not working with a CPU count > 32
Jens Axboe [Fri, 5 Dec 2008 11:57:11 +0000 (12:57 +0100)]
Add comment on cpumask not working with a CPU count > 32

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agosmalloc: pool->file is only used in add_pool(), so make it local
Jens Axboe [Thu, 4 Dec 2008 13:33:41 +0000 (14:33 +0100)]
smalloc: pool->file is only used in add_pool(), so make it local

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agosmalloc: unlink pool file in add_pool()
Jens Axboe [Thu, 4 Dec 2008 13:30:13 +0000 (14:30 +0100)]
smalloc: unlink pool file in add_pool()

Don't defer until cleanup time, since we may not clean up if fio
crashes or is killed in other ways.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoUse frame pointer
Jens Axboe [Thu, 20 Nov 2008 08:13:23 +0000 (09:13 +0100)]
Use frame pointer

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoMake log writing append
Jens Axboe [Thu, 20 Nov 2008 08:13:04 +0000 (09:13 +0100)]
Make log writing append

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd support for giving bw/clat/slat log prefixes
Jens Axboe [Wed, 19 Nov 2008 18:57:52 +0000 (19:57 +0100)]
Add support for giving bw/clat/slat log prefixes

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFix bug in parser that causes a crash with a bad option
Jens Axboe [Wed, 19 Nov 2008 11:31:43 +0000 (12:31 +0100)]
Fix bug in parser that causes a crash with a bad option

The priority sorting would crash if it failed to lookup both
of the passed in options.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFio 1.23 fio-1.23
Jens Axboe [Tue, 18 Nov 2008 18:22:31 +0000 (19:22 +0100)]
Fio 1.23

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoHandle ctrl-c properly with threads
Jens Axboe [Tue, 18 Nov 2008 18:10:21 +0000 (19:10 +0100)]
Handle ctrl-c properly with threads

A stupid bug, the main process should just ignore its own SIGQUIT.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFix leaks with using get_opt_postfix()
Jens Axboe [Fri, 14 Nov 2008 12:06:06 +0000 (13:06 +0100)]
Fix leaks with using get_opt_postfix()

It returns a strdup(), so remember to free() the result when done.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd gtod_reduce option
Jens Axboe [Fri, 14 Nov 2008 12:04:53 +0000 (13:04 +0100)]
Add gtod_reduce option

This cuts down even more on gtod() calls. While the three disable_X
options halved the gettimeofday() call count, this can reduce it to
less than 1 percent of what it otherwise would have been.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFix backwards clock on tsc source with Linux
Jens Axboe [Thu, 13 Nov 2008 11:07:20 +0000 (12:07 +0100)]
Fix backwards clock on tsc source with Linux

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoIssue time fixup for guasi/libaio
Jens Axboe [Thu, 16 Oct 2008 19:26:10 +0000 (21:26 +0200)]
Issue time fixup for guasi/libaio

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd options for disabling slat/clat/bw measurements
Jens Axboe [Thu, 16 Oct 2008 19:03:27 +0000 (21:03 +0200)]
Add options for disabling slat/clat/bw measurements

Useful for cutting down on the number of gettimeofday calls in
situations where that does impact performance. This is mostly for
really high IOPS rates.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoKill io_u timeout handling
Jens Axboe [Thu, 16 Oct 2008 18:36:51 +0000 (20:36 +0200)]
Kill io_u timeout handling

It has never been enabled, get rid of it.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoOnly memcpy last issue time when using iolog replay
Jens Axboe [Thu, 16 Oct 2008 18:33:51 +0000 (20:33 +0200)]
Only memcpy last issue time when using iolog replay

Part of a series that'll allow switching off various time measurements
to avoid impacting system performance too much.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFio 1.22 fio-1.22
Jens Axboe [Fri, 10 Oct 2008 11:49:50 +0000 (13:49 +0200)]
Fio 1.22

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFio 1.22-rc3 fio-1.22-rc3
Jens Axboe [Tue, 7 Oct 2008 09:33:21 +0000 (11:33 +0200)]
Fio 1.22-rc3

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoWarning fixes
Jens Axboe [Tue, 7 Oct 2008 09:33:00 +0000 (11:33 +0200)]
Warning fixes

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoDocument environment variable expansion
Aaron Carroll [Tue, 7 Oct 2008 09:25:38 +0000 (11:25 +0200)]
Document environment variable expansion

Add environment variable expansion documentation to HOWTO, and fix
a few nearby typo's while we're at it.

Signed-off-by: Aaron Carroll <aaronc@gelato.unsw.edu.au>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd environment-variable substitution to config options
Aaron Carroll [Tue, 7 Oct 2008 09:25:20 +0000 (11:25 +0200)]
Add environment-variable substitution to config options

Strings of the form ${VARNAME} in config option strings are substituted with
the value of the environment variable VARNAME.  Only the right hand side of
an option assignment undergoes substitution.  If VARNAME is empty or
undefined, the empty string is substituted.

Signed-off-by: Aaron Carroll <aaronc@gelato.unsw.edu.au>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoUpdate README for new mailing list info
Jens Axboe [Wed, 1 Oct 2008 07:04:28 +0000 (09:04 +0200)]
Update README for new mailing list info

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFix missing initialization of merge/io counts
Jens Axboe [Tue, 30 Sep 2008 06:39:17 +0000 (08:39 +0200)]
Fix missing initialization of merge/io counts

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAggregate slave device stats into the stats for master.
Shehjar Tikoo [Tue, 30 Sep 2008 01:11:35 +0000 (11:11 +1000)]
Aggregate slave device stats into the stats for 

But do so by adding new fields in the stats line.
We dont want the existing output format to get clobbered.
The new fields in master device line which contain
aggregated stats start with "aggr".

Signed-off-by: Shehjar Tikoo <shehjart@gelato.unsw.edu.au>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd support to display slave device stats for software RAIDs.
Shehjar Tikoo [Tue, 30 Sep 2008 00:35:44 +0000 (10:35 +1000)]
Add support to display slave device stats for software RAIDs.

When running tests on a device created using mdadm, the relevant
disk statistics must also come from the individual
disks that constitute the RAID, because the software RAID device
is just a virtual device.

This patch goes through the 'slaves' directory in the software
RAID device's directory in /sys/block, gets a list of all the
slave devices and creates a master-slave relationship between
the virtual device and the actual disks.

The individual slave disks' stats are displayed along with the
master's disk stats at the end of the test.

Signed-off-by: Shehjar Tikoo <shehjart@gelato.unsw.edu.au>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoHOWTO: add comment on terse and --minimal
Jens Axboe [Sat, 27 Sep 2008 10:33:53 +0000 (12:33 +0200)]
HOWTO: add comment on terse and --minimal

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFio 1.22-rc2 fio-1.22-rc2
Jens Axboe [Thu, 18 Sep 2008 01:01:34 +0000 (18:01 -0700)]
Fio 1.22-rc2

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoDon't compile crc32c-intel on non-x86 platforms
Aaron Carroll [Fri, 12 Sep 2008 08:57:13 +0000 (10:57 +0200)]
Don't compile crc32c-intel on non-x86 platforms

crc32c_intel() doesn't make sense on platforms without SSE, so alias it
to crc32c() on such machines.

Signed-off-by: Aaron Carroll <aaronc@gelato.unsw.edu.au>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoUpdate ramp_time
Jens Axboe [Thu, 11 Sep 2008 08:17:26 +0000 (10:17 +0200)]
Update ramp_time

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoUpdate options
Jens Axboe [Thu, 11 Sep 2008 07:27:15 +0000 (09:27 +0200)]
Update options

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFio 1.22-rc1 fio-1.22-rc1
Jens Axboe [Wed, 10 Sep 2008 07:48:11 +0000 (09:48 +0200)]
Fio 1.22-rc1

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd ramp_time option
Jens Axboe [Wed, 10 Sep 2008 07:46:16 +0000 (09:46 +0200)]
Add ramp_time option

Sometimes it's useful to let a job settle for a little while
before taking any measurements on latency and throughput, since
the initial rate on eg a write workload may be much higher than
the longer sustained rate.

So add a ramp_time option that allows the user to specify a lead
ramp time that must have passed before fio takes any performance
numbers into account.

Suggested by "Jenkins, Lee" <Lee.Jenkins@hp.com>

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoeta: fix bugs withe fill_device and exitall_on_terminate
Shaozhi Shawn Ye [Wed, 10 Sep 2008 07:09:37 +0000 (09:09 +0200)]
eta: fix bugs withe fill_device and exitall_on_terminate

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agofilehash: check for NULL ->file_name in hash lookup
Jens Axboe [Wed, 10 Sep 2008 07:07:55 +0000 (09:07 +0200)]
filehash: check for NULL ->file_name in hash lookup

Original patch from Shaozhi Shawn Ye <yeshao@google.com>, modified
by me to continue the lookup and just skip the file instead of
returning NULL.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agofilehash: Filehash should be removed after the file is closed
Shaozhi Shawn Ye [Wed, 10 Sep 2008 07:05:17 +0000 (09:05 +0200)]
filehash: Filehash should be removed after the file is closed

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agofilesetup: When terse_output is set, The 'laying out' message should not be displayed.
Shaozhi Shawn Ye [Wed, 10 Sep 2008 07:04:18 +0000 (09:04 +0200)]
filesetup: When terse_output is set, The 'laying out' message should not be displayed.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agosmalloc: Remove read/write lock race condition which will result in segmentation...
Shaozhi Shawn Ye [Wed, 10 Sep 2008 07:02:51 +0000 (09:02 +0200)]
smalloc: Remove read/write lock race condition which will result in segmentation fault

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAllow fio headers to be included by a C++ build
Daniel Rall [Wed, 10 Sep 2008 06:56:01 +0000 (08:56 +0200)]
Allow fio headers to be included by a C++ build

The attached patch allows fio 1.17.2 header files to be included by a
C++ build without generating compile errors due to C-ism.
Specifically, due to:
- use of the keyword "new" as a parameter name
- a cast of a return value to void *, when the function signature
returns a different type

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd SIGILL signal handler
Jens Axboe [Mon, 4 Aug 2008 19:43:55 +0000 (21:43 +0200)]
Add SIGILL signal handler

If crc32c-intel is used and the opcode isn't supported by the CPU,
we'll display a nice warning instead of just dying.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoRemember to add crc32c_intel option check
Jens Axboe [Mon, 4 Aug 2008 13:40:35 +0000 (15:40 +0200)]
Remember to add crc32c_intel option check

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd intel hardware assisted crc32c support
Jens Axboe [Mon, 4 Aug 2008 13:35:26 +0000 (15:35 +0200)]
Add intel hardware assisted crc32c support

Not tested, since I don't have the hardware.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoDetect and complain on smalloc failures
Jens Axboe [Thu, 31 Jul 2008 17:55:02 +0000 (19:55 +0200)]
Detect and complain on smalloc failures

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agosmalloc: default to 128 pools instead of 4
Jens Axboe [Thu, 31 Jul 2008 17:50:54 +0000 (19:50 +0200)]
smalloc: default to 128 pools instead of 4

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoPrevent filetype disappearing
Aaron Carroll [Wed, 25 Jun 2008 07:20:37 +0000 (09:20 +0200)]
Prevent filetype disappearing

fio_file->filetype is set in add_file(), but for duplicated files
fio-file->file_name is already set so add_file() is not called.
This patch copies the filetype at the same time as file_name so
it remains valid for dup'd files.

Signed-off-by: Aaron Carroll <aaronc@gelato.unsw.edu.au>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd uninitialized_var() to silence bogus compiler warnings
Jens Axboe [Fri, 13 Jun 2008 08:27:05 +0000 (10:27 +0200)]
Add uninitialized_var() to silence bogus compiler warnings

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoeta overflow fix
Gurudas Pai [Fri, 13 Jun 2008 06:40:11 +0000 (08:40 +0200)]
eta overflow fix

Sometime I get eta's like "eta 4294967286m:4294967266s" , just an overflow
issue. The following patch fixes the issue.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoRevert "Add spinlocks"
Jens Axboe [Fri, 13 Jun 2008 06:38:40 +0000 (08:38 +0200)]
Revert "Add spinlocks"

This reverts commit 69ebbd397e80b23ec4281c99e9f7242a089cc771.

15 years agoRevert "Add spinlock wrapper helpers"
Jens Axboe [Fri, 13 Jun 2008 06:38:35 +0000 (08:38 +0200)]
Revert "Add spinlock wrapper helpers"

This reverts commit 8b4a7c860d004ea8dffc11f6232124b574fe6cd7.

15 years agoRevert "smalloc: convert to spinlocks"
Jens Axboe [Fri, 13 Jun 2008 06:38:31 +0000 (08:38 +0200)]
Revert "smalloc: convert to spinlocks"

This reverts commit 3f1959101ed6a935ff3e2aec0fe7f5828f23fbcb.

15 years agoRevert "Convert file hash lock to spinlocks"
Jens Axboe [Fri, 13 Jun 2008 06:38:25 +0000 (08:38 +0200)]
Revert "Convert file hash lock to spinlocks"

This reverts commit 0ec7b3c9a0926e6377bd145206bb9f6a70be610d.

15 years agoRevert "Remove unused define"
Jens Axboe [Fri, 13 Jun 2008 06:38:20 +0000 (08:38 +0200)]
Revert "Remove unused define"

This reverts commit edf2c6cf5adc82ee43c81e033cf2215eb9ffdb16.

15 years agoRemove unused define
Jens Axboe [Thu, 12 Jun 2008 18:05:33 +0000 (20:05 +0200)]
Remove unused define

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoConvert file hash lock to spinlocks
Jens Axboe [Thu, 12 Jun 2008 09:53:57 +0000 (11:53 +0200)]
Convert file hash lock to spinlocks

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agosmalloc: convert to spinlocks
Jens Axboe [Thu, 12 Jun 2008 09:50:47 +0000 (11:50 +0200)]
smalloc: convert to spinlocks

Makes the allocator 10-20% faster.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd spinlock wrapper helpers
Jens Axboe [Thu, 12 Jun 2008 09:49:46 +0000 (11:49 +0200)]
Add spinlock wrapper helpers

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd spinlocks
Jens Axboe [Thu, 12 Jun 2008 09:26:26 +0000 (11:26 +0200)]
Add spinlocks

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agofio.1: Correct terse (--minimal) output - page faults
Carl Henrik Lunde [Thu, 12 Jun 2008 07:17:46 +0000 (09:17 +0200)]
fio.1: Correct terse (--minimal) output - page faults

Major and minor page faults were added in commit e7823a941468e

Signed-off-by: Carl Henrik Lunde <chlunde@ping.uio.no>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoMerge branch 'master' of ssh://git.kernel.dk/data/git/fio
Jens Axboe [Wed, 11 Jun 2008 18:46:29 +0000 (20:46 +0200)]
Merge branch 'master' of ssh://git.kernel.dk/data/git/fio

15 years agoAdd crc32c checksum
Jens Axboe [Wed, 11 Jun 2008 18:46:19 +0000 (20:46 +0200)]
Add crc32c checksum

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agocrc32 is uint32_t, not unsigned long
Jens Axboe [Wed, 11 Jun 2008 18:44:57 +0000 (20:44 +0200)]
crc32 is uint32_t, not unsigned long

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoImprove bsrange buflen generations
Jens Axboe [Wed, 11 Jun 2008 13:37:32 +0000 (15:37 +0200)]
Improve bsrange buflen generations

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoDon't include headers in depend target
Jens Axboe [Wed, 11 Jun 2008 11:18:30 +0000 (13:18 +0200)]
Don't include headers in depend target

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoClear num_opts early
Jens Axboe [Wed, 11 Jun 2008 09:47:56 +0000 (11:47 +0200)]
Clear num_opts early

If we error out, it could be garbage.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoOlder Linux versions do not have O_NOATIME
Jens Axboe [Wed, 11 Jun 2008 08:21:43 +0000 (10:21 +0200)]
Older Linux versions do not have O_NOATIME

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoRemember to free **opts as well
Jens Axboe [Tue, 10 Jun 2008 18:26:06 +0000 (20:26 +0200)]
Remember to free **opts as well

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd option priorities
Jens Axboe [Tue, 10 Jun 2008 17:46:23 +0000 (19:46 +0200)]
Add option priorities

For instance, filename= must come after directory= or things will
go wrong. So add a priority value to each option, so that the parser
will take that into account.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agosplice: if splicing fails with EINVAL, it's most likely missing fs support
Jens Axboe [Mon, 9 Jun 2008 17:25:49 +0000 (19:25 +0200)]
splice: if splicing fails with EINVAL, it's most likely missing fs support

So tell the user in more direct terms.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFio 1.21 fio-1.21
Jens Axboe [Fri, 6 Jun 2008 10:21:38 +0000 (12:21 +0200)]
Fio 1.21

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoLinux sysfs change broke fio disk lookup
Jens Axboe [Fri, 6 Jun 2008 10:08:04 +0000 (12:08 +0200)]
Linux sysfs change broke fio disk lookup

/sys/block/<dev> is now a sym link to the real path, which
broke our disk lookup. Fix it.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoETA fix
Jens Axboe [Thu, 5 Jun 2008 23:17:03 +0000 (01:17 +0200)]
ETA fix

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoFio 1.21-rc8 fio-1.21-rc8
Jens Axboe [Thu, 5 Jun 2008 09:59:42 +0000 (11:59 +0200)]
Fio 1.21-rc8

Should be the last -rc, not aware of any pending issues.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoHOWTO spelling
Jens Axboe [Thu, 5 Jun 2008 09:53:08 +0000 (11:53 +0200)]
HOWTO spelling

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoHelp entry typos
Jens Axboe [Thu, 5 Jun 2008 09:48:22 +0000 (11:48 +0200)]
Help entry typos

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
15 years agoAdd iodepth_batch_complete control
Jens Axboe [Thu, 5 Jun 2008 07:03:30 +0000 (09:03 +0200)]
Add iodepth_batch_complete control

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>