fio.git
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 years agoRevert "Add spinlocks"
Jens Axboe [Fri, 13 Jun 2008 06:38:40 +0000 (08:38 +0200)]
Revert "Add spinlocks"

This reverts commit 69ebbd397e80b23ec4281c99e9f7242a089cc771.

12 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.

12 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.

12 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.

12 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.

12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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

12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 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>
12 years agoDon't print 100% done, when we don't have a time estimate yet
Jens Axboe [Thu, 5 Jun 2008 07:03:05 +0000 (09:03 +0200)]
Don't print 100% done, when we don't have a time estimate yet

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoMAP_ANON requires fd == -1
Jens Axboe [Wed, 4 Jun 2008 18:37:18 +0000 (20:37 +0200)]
MAP_ANON requires fd == -1

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoAdd OS agnostic RAND_MAX
Jens Axboe [Wed, 4 Jun 2008 18:13:04 +0000 (20:13 +0200)]
Add OS agnostic RAND_MAX

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoCompile warning for non-signal driven solaris asynch io
Jens Axboe [Wed, 4 Jun 2008 17:57:47 +0000 (19:57 +0200)]
Compile warning for non-signal driven solaris asynch io

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoSolaris: support for proper random functions
Jens Axboe [Wed, 4 Jun 2008 17:55:58 +0000 (19:55 +0200)]
Solaris: support for proper random functions

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoAdd directio support to Solaris
Jens Axboe [Wed, 4 Jun 2008 13:14:24 +0000 (15:14 +0200)]
Add directio support to Solaris

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoWe need to grab and mark the file open before jumping to an error path
Jens Axboe [Wed, 4 Jun 2008 13:13:02 +0000 (15:13 +0200)]
We need to grab and mark the file open before jumping to an error path

The error path will close the file.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoKill useless undef's
Jens Axboe [Wed, 4 Jun 2008 12:49:27 +0000 (14:49 +0200)]
Kill useless undef's

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoAdd missing splice syscall numbers for alpha and s390
Jens Axboe [Wed, 4 Jun 2008 12:48:29 +0000 (14:48 +0200)]
Add missing splice syscall numbers for alpha and s390

All archs now verified as compiling.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoAdd write barriers
Jens Axboe [Wed, 4 Jun 2008 12:31:25 +0000 (14:31 +0200)]
Add write barriers

And enable them in solarisaio, then it should be safe to use the
signal driven IO "interrupts".

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoFio 1.21-rc7 fio-1.21-rc7
Jens Axboe [Wed, 4 Jun 2008 08:47:08 +0000 (10:47 +0200)]
Fio 1.21-rc7

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoMissing time store in rwmix switch
Jens Axboe [Wed, 4 Jun 2008 08:35:25 +0000 (10:35 +0200)]
Missing time store in rwmix switch

Caused missing display of either read or write direction for a mixed
workload.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoBase FreeBSD Makefile on Linux, but insist on gmake usage
Jens Axboe [Mon, 2 Jun 2008 14:15:59 +0000 (16:15 +0200)]
Base FreeBSD Makefile on Linux, but insist on gmake usage

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoMakefile update
Jens Axboe [Mon, 2 Jun 2008 13:57:45 +0000 (15:57 +0200)]
Makefile update

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoRemove comment wrt sigaction() usage, it's deprecated
Jens Axboe [Mon, 2 Jun 2008 13:02:46 +0000 (15:02 +0200)]
Remove comment wrt sigaction() usage, it's deprecated

We already use sigaction(), so no difference between *BSD/Solaris
and Linux.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agosolarisaio: support signal driven async IO
Jens Axboe [Mon, 2 Jun 2008 13:01:16 +0000 (15:01 +0200)]
solarisaio: support signal driven async IO

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agosolarisaio: aiowait() can return (void *) -1 for error
Jens Axboe [Mon, 2 Jun 2008 12:18:23 +0000 (14:18 +0200)]
solarisaio: aiowait() can return (void *) -1 for error

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoMove fls.h in with the other lib helpers
Jens Axboe [Mon, 2 Jun 2008 11:31:26 +0000 (13:31 +0200)]
Move fls.h in with the other lib helpers

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoInclude solarisaio in README
Jens Axboe [Mon, 2 Jun 2008 11:28:21 +0000 (13:28 +0200)]
Include solarisaio in README

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agosolarisaio: IO depth constrained by MAXASYNCHIO
Jens Axboe [Mon, 2 Jun 2008 11:23:34 +0000 (13:23 +0200)]
solarisaio: IO depth constrained by MAXASYNCHIO

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoFio 1.21-rc6 fio-1.21-rc6
Jens Axboe [Mon, 2 Jun 2008 10:55:14 +0000 (12:55 +0200)]
Fio 1.21-rc6

Stupid Linux compile error in -rc5

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoMissed fls() -> __fls() conversion
Jens Axboe [Mon, 2 Jun 2008 10:55:03 +0000 (12:55 +0200)]
Missed fls() -> __fls() conversion

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoFio 1.21-rc5 fio-1.21-rc5
Jens Axboe [Mon, 2 Jun 2008 10:52:56 +0000 (12:52 +0200)]
Fio 1.21-rc5

Getting close to 1.21, all three supported platforms (Linux, Solaris,
and FreeBSD) now compile and work fine.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoFreeBSD Makefile update
Jens Axboe [Mon, 2 Jun 2008 10:51:42 +0000 (12:51 +0200)]
FreeBSD Makefile update

Don't ask...

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agomutex: only regard less-than-zero return as error
Jens Axboe [Mon, 2 Jun 2008 10:50:10 +0000 (12:50 +0200)]
mutex: only regard less-than-zero return as error

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agonet engine: missing includes
Jens Axboe [Mon, 2 Jun 2008 10:30:06 +0000 (12:30 +0200)]
net engine: missing includes

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoposixaio: not all platforms have aio_fsync()
Jens Axboe [Mon, 2 Jun 2008 10:28:02 +0000 (12:28 +0200)]
posixaio: not all platforms have aio_fsync()

FreeBSD is (again) the odd man out...

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoposixaio: need fcntl.h
Jens Axboe [Mon, 2 Jun 2008 10:25:12 +0000 (12:25 +0200)]
posixaio: need fcntl.h

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoGuard posix_fallocate() behind OS define
Jens Axboe [Mon, 2 Jun 2008 10:23:40 +0000 (12:23 +0200)]
Guard posix_fallocate() behind OS define

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoRename fls() to __fls()
Jens Axboe [Mon, 2 Jun 2008 10:22:30 +0000 (12:22 +0200)]
Rename fls() to __fls()

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoNot all platforms have ENODATA
Jens Axboe [Mon, 2 Jun 2008 10:19:50 +0000 (12:19 +0200)]
Not all platforms have ENODATA

So use EIO instead.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoRename list_* function and file to flist_ to avoid conflict with FreeBSD
Jens Axboe [Mon, 2 Jun 2008 10:19:19 +0000 (12:19 +0200)]
Rename list_* function and file to flist_ to avoid conflict with FreeBSD

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoAdd Solaris native aio engine
Jens Axboe [Mon, 2 Jun 2008 09:59:30 +0000 (11:59 +0200)]
Add Solaris native aio engine

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoDon't make posix_fallocate() set td->verror
Jens Axboe [Mon, 2 Jun 2008 08:37:36 +0000 (10:37 +0200)]
Don't make posix_fallocate() set td->verror

It's supposed to be an error log, not stop the job.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoFio 1.21-rc4 fio-1.21-rc4
Jens Axboe [Mon, 2 Jun 2008 08:17:12 +0000 (10:17 +0200)]
Fio 1.21-rc4

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoDo at least one block if randommap fails us
Jens Axboe [Mon, 2 Jun 2008 08:15:48 +0000 (10:15 +0200)]
Do at least one block if randommap fails us

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoInc block in mark_random_map()
Jens Axboe [Mon, 2 Jun 2008 08:09:43 +0000 (10:09 +0200)]
Inc block in mark_random_map()

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agosmalloc: use optimized ffz()
Jens Axboe [Mon, 2 Jun 2008 07:59:32 +0000 (09:59 +0200)]
smalloc: use optimized ffz()

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoBe sure to use internal __ffs, not glibc variant
Jens Axboe [Mon, 2 Jun 2008 07:57:41 +0000 (09:57 +0200)]
Be sure to use internal __ffs, not glibc variant

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoSpeedup mark_random_map()
Jens Axboe [Mon, 2 Jun 2008 07:53:05 +0000 (09:53 +0200)]
Speedup mark_random_map()

Do each int at the time, not each bit.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agox86-64: enable arch ffz again
Jens Axboe [Mon, 2 Jun 2008 07:43:29 +0000 (09:43 +0200)]
x86-64: enable arch ffz again

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agox86-64: ffz need only search the first 32-bits
Jens Axboe [Mon, 2 Jun 2008 07:41:51 +0000 (09:41 +0200)]
x86-64: ffz need only search the first 32-bits

So use bsfl, not bsfq.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoFix off-by-one in generic ffz
Jens Axboe [Mon, 2 Jun 2008 07:41:29 +0000 (09:41 +0200)]
Fix off-by-one in generic ffz

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoAdd missing lib/ffz.h file
Jens Axboe [Mon, 2 Jun 2008 07:19:37 +0000 (09:19 +0200)]
Add missing lib/ffz.h file

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoReadd the arch ffz functions
Jens Axboe [Sun, 1 Jun 2008 17:45:10 +0000 (19:45 +0200)]
Readd the arch ffz functions

May as well use the single op version if we have them, it's
generally a lot faster than the generic_ffz()

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoffz() takes ints, so change the file_map to being int based
Jens Axboe [Fri, 30 May 2008 22:21:12 +0000 (00:21 +0200)]
ffz() takes ints, so change the file_map to being int based

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoAdd sparc and sparc64 support
Jens Axboe [Fri, 30 May 2008 22:04:45 +0000 (00:04 +0200)]
Add sparc and sparc64 support

Also get rid of the arch private ffz functions, the generic
one is just fine.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoSeperate status timer setup from disk util timer
Jens Axboe [Fri, 30 May 2008 21:18:00 +0000 (23:18 +0200)]
Seperate status timer setup from disk util timer

It's still the same timer and shared, but move it out of
diskutil so we get proper status reporting on non-Linux.

We also need to rearm the signal handlers on each signal.
Move this to sigaction() next.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
12 years agoFixup posix_fallocate() usage
Jens Axboe [Fri, 30 May 2008 20:58:37 +0000 (22:58 +0200)]
Fixup posix_fallocate() usage

It returns the error directly, not through errno. Also make
it non-fatal, Solaris seems to complain about it.

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