Jens Axboe [Sat, 2 Feb 2013 09:05:07 +0000 (10:05 +0100)]
clock: hardwire tsc as unreliable on Solaris for now
Need to double check the cpuid test, it probably only is reliable
on Intel. Need to check the CPU vendor and flags appropriately.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Sat, 2 Feb 2013 08:56:23 +0000 (09:56 +0100)]
parse: use MIN/MAXDOUBLE instead of some representation of NAN
Doesn't always work for C99.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Vincent Kang Fu [Sat, 2 Feb 2013 08:28:55 +0000 (09:28 +0100)]
Fix percentile_list option
Commit
802ad4a8 broke the parsing of the percentile list,
by neglecting to change the parser type fo a fio_fp64_t.
Also get rid of the def_percentile_list, just set the
default percentile list as the option default.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 1 Feb 2013 14:51:23 +0000 (15:51 +0100)]
Makefile: fixup dependency problem for files in sub dirs
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Neto, Antonio Jose Rodrigues [Fri, 1 Feb 2013 07:30:38 +0000 (08:30 +0100)]
README: how to compile fio on Windows 64 bits
Signed-off-by: Jens Axboe <axboe@kernel.dk>
David M. Lee [Thu, 31 Jan 2013 17:37:41 +0000 (18:37 +0100)]
Allow override of CFLAGS
If you attempt to specify your own CFLAGS on the command line (such as
make CFLAGS="--whatever"), this would prevent -DFIO_VERSION from being
added to CFLAGS. This patch uses the override directive to allow the
flag to be appended to CFLAGS.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 31 Jan 2013 14:24:34 +0000 (15:24 +0100)]
Only disable stdout ETA output if results are going to stdout
If they are being redirected to a file with --output, then
we can still use the normal runtime ETA output on stdout.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 31 Jan 2013 12:33:45 +0000 (13:33 +0100)]
net: 'nodelay' HOWTO/man page update
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 31 Jan 2013 09:19:51 +0000 (10:19 +0100)]
configure: add TCP_NODELAY check
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 31 Jan 2013 08:58:22 +0000 (09:58 +0100)]
windows: fix typo in <netinet/tcp.h> header
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ken Raeburn [Wed, 30 Jan 2013 21:31:09 +0000 (22:31 +0100)]
Fix bugs in [v]snprintf usage
When calling snprintf, supply the full buffer size instead of
one byte less.
When using the returned length from vsnprintf for logging, don't write
more than the actual buffer size (minus one for the trailing \0), in
case the formatted string was truncated.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 30 Jan 2013 20:54:58 +0000 (21:54 +0100)]
Add empty <netinet/tcp.h> for Windows
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 30 Jan 2013 20:52:37 +0000 (21:52 +0100)]
net: fix compile warning on Windows (and others)
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Steven Noonan [Wed, 28 Nov 2012 22:52:36 +0000 (14:52 -0800)]
net engine: implement option "nodelay" for TCP sockets
With disks, O_DIRECT effectively bypasses all buffering/caching mechanisms and
ensures that the I/O is going directly to the disk. Since TCP is a streaming
protocol (like disk I/O), it also has a buffering mechanism. As with disks, it
is sometimes desirable to bypass buffering. To that end, we can use
TCP_NODELAY, which transmits the packet as soon as data is assembled,
regardless of whether it occupies a full frame.
Signed-off-by: Steven Noonan <snoonan@amazon.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 30 Jan 2013 13:08:00 +0000 (14:08 +0100)]
idletime: style cleanups
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 30 Jan 2013 12:58:58 +0000 (13:58 +0100)]
configure: add SCHED_IDLE check
We can't consider it always available on Linux. It fails on
Debian 6.x, for instance.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Huadong Liu [Wed, 30 Jan 2013 12:22:24 +0000 (13:22 +0100)]
Add support for idletime profiling
Idletime profiling allows a benchmark to run while filling the
idle cycles on the server, hence giving you some metric of how
much pressure the system is under. This is useful to be able
to profile and compare changes in a setup or driver, for instance.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 30 Jan 2013 11:56:23 +0000 (12:56 +0100)]
Add unified_rw_reporting option
If this is set, then fio will sum and display just a single set
of statistics for any IO type. By default, fio accounts and reports
each data direction separately.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 30 Jan 2013 11:53:55 +0000 (12:53 +0100)]
HOWTO: indentation fix
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 29 Jan 2013 21:29:09 +0000 (22:29 +0100)]
smalloc: alloc failure cleanups
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 29 Jan 2013 19:53:52 +0000 (20:53 +0100)]
client/server: fixup missing TRIM conversions
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ken Raeburn [Tue, 29 Jan 2013 09:18:13 +0000 (10:18 +0100)]
Fix crash with absurdly but not impossibly deeply nested device stacks
Use the proper PATH_MAX for the max path for disk util, and use
snprintf() to avoid potentially overwriting it.
Modified by Jens to return NULL instead of exiting.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 29 Jan 2013 09:06:30 +0000 (10:06 +0100)]
configure: enable --extra-cflags for Windows
Add configure help as well.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 29 Jan 2013 08:26:07 +0000 (09:26 +0100)]
configure: add --extra-cflags
And ensure that -D_GNU_SOURCE is being set for configure test
programs too.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Bruce Cran [Mon, 28 Jan 2013 16:07:15 +0000 (16:07 +0000)]
Fix Windows build by defining clock sources and adding include file.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Sat, 26 Jan 2013 16:28:23 +0000 (09:28 -0700)]
Always fsync if asked to
Currently we don't fsync() is direct IO is issued. But if the
user asked for fsync(), he should get an fsync. So remove this
restriction.
Reported-by: Stefan Hajnoczi <stefanha@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 25 Jan 2013 21:36:46 +0000 (14:36 -0700)]
Fix getopt def check
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 25 Jan 2013 21:35:27 +0000 (14:35 -0700)]
configure: HPUX warning for empty CC
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 25 Jan 2013 15:52:43 +0000 (08:52 -0700)]
Makefile: remove config-host.ld
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 25 Jan 2013 15:52:28 +0000 (08:52 -0700)]
configure: add configure header to config-host.h
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 25 Jan 2013 06:07:55 +0000 (23:07 -0700)]
configure: auto-generate a config-host.h
Don't have all these special cases to convert a .mak to a .h define,
just generate it from the configure script instead.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 22:38:37 +0000 (15:38 -0700)]
Drop EXTFLAG and lib references
They are picked up automatically now.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 22:35:17 +0000 (15:35 -0700)]
configure: kill windows FIO_HAVE_FDATASYNC
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 22:33:33 +0000 (15:33 -0700)]
configure: solaris and windowsaio fixups
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 22:29:58 +0000 (15:29 -0700)]
options: add help to experimental_verify
Option help is required...
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 22:27:40 +0000 (15:27 -0700)]
configure: fix more old FIO_HAVE_ checks
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 22:22:20 +0000 (15:22 -0700)]
NAN: use __builtin_nanf() if not available
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 22:21:04 +0000 (15:21 -0700)]
hash: make 64-bit type ULL
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 22:00:25 +0000 (15:00 -0700)]
Correct ifdef checks for posix and linux fallocate
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 21:53:47 +0000 (14:53 -0700)]
configure: add that windows has RUSGE_THREAD
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 21:20:09 +0000 (14:20 -0700)]
Add lib/getrusage.c
Abstract out the SELF/THREAD complication.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Huadong Liu [Thu, 24 Jan 2013 21:07:20 +0000 (14:07 -0700)]
Use RUSAGE_THREAD, if available
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 01:11:48 +0000 (18:11 -0700)]
init: complain on unrecognized option with builtin getopt_long_only()
It returns '?' for a bad option, whereas the glibc one does
not. Catch that so we behave identically.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 24 Jan 2013 00:21:41 +0000 (17:21 -0700)]
Fix compile warnings on Windows
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 23:28:24 +0000 (16:28 -0700)]
windows: don't provide strsep(), fio already has one
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 23:26:12 +0000 (16:26 -0700)]
configure: add default compiler on Windows
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 23:23:48 +0000 (16:23 -0700)]
configure: fixup Windows
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 22:42:16 +0000 (15:42 -0700)]
configure: add endian check
Will remove guesswork and manual hacking in the OS headers.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 22:29:59 +0000 (15:29 -0700)]
Kill now unneeded clock definitions
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 21:02:23 +0000 (14:02 -0700)]
OSX: Fixup warnings and clock_gettime() bug
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 20:51:39 +0000 (13:51 -0700)]
configure: remember to output CC for windows
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 20:47:54 +0000 (13:47 -0700)]
configure: add --cc= option to script
Get rid of uname -o usage for Windows, and specifically require
CC=bla ./configure or ./configure --cc=bla to set something else
than gcc.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 20:35:14 +0000 (13:35 -0700)]
Fix 32-bit compile warning in should_check_rate()
Introduced with the change from unsigned long -> uint64_T
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 18:02:07 +0000 (11:02 -0700)]
t/axmap: update to catch recent bugs
Also properly include axmap.h and don't declare our own prototypes.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 18:01:09 +0000 (11:01 -0700)]
axmap: ensure that we never return a value that is larger than the map size
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 17:33:20 +0000 (10:33 -0700)]
axmap: improve axmap_find_first_free()
Add a ret variable, saves a branch on return.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 17:15:57 +0000 (10:15 -0700)]
verify: stop on actual number of bytes needed to be verified
If we don't use LFSR or a random map, we don't get told when
to stop by the random generator or map. So track it on the
side, using the same mechanism as do_io().
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 17:15:05 +0000 (10:15 -0700)]
axmap: fix bug in axmap_find_first_free()
If the map is completely full, we could return an invalid value
for the first free bit. So check if we actually found a match,
return failure if we didn't.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 16:27:25 +0000 (09:27 -0700)]
Make experimental_verify=1 handle all cases properly
- Don't track written bytes, just replay the workload by resetting
all the random generators. This should work for any mixture of IO.
- Handle trims for verify.
- Ensure that rwmix is replayed properly for verify.
- Fixup logging for replay.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 16:26:53 +0000 (09:26 -0700)]
Ensure all random seeds are repeatable for randrepeat=1
Currently we only do the offset.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 23 Jan 2013 15:40:11 +0000 (08:40 -0700)]
eta: improve accuracy for rwmix workloads and verify
We assume 50/50 for mixed workloads. That's silly, use the actual
number specified instead.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 21 Jan 2013 19:30:34 +0000 (12:30 -0700)]
Use unsigned long long for the uint64_t type
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 21 Jan 2013 19:28:42 +0000 (12:28 -0700)]
windows: use hweight64(), it's a 64-bit type
Courtesy of Bruce.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 21 Jan 2013 19:28:23 +0000 (12:28 -0700)]
Add hweight64()
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Bruce Cran [Mon, 21 Jan 2013 17:57:59 +0000 (10:57 -0700)]
Fix _SC_NPROCESSORS_ONLN on Windows
_SC_NPROCESSORS_ONLN was returning the wrong value on Windows because
GetLogicalProcessorInformation() returns data about caches, nodes and
packages in addition to processors.
Modified by Jens to use hweight32()
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 21 Jan 2013 17:55:02 +0000 (10:55 -0700)]
Add generic hweight helpers
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 21 Jan 2013 16:47:03 +0000 (09:47 -0700)]
verify: add new experimental mode that requires no meta data
Should work fine, but we need to account and track trims to know
which blocks NOT to verify (or verify as zero).
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 21 Jan 2013 16:46:06 +0000 (09:46 -0700)]
Re-seed random generator when a file is reset
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 21 Jan 2013 16:43:30 +0000 (09:43 -0700)]
axmap: clear map->first_free when we reset it
Otherwise it could be left at an invalid value. When we clear the map,
we know the first free bit is 0.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 21 Jan 2013 16:42:49 +0000 (09:42 -0700)]
lfsr: add lfsr_reset()
This enables us to restart a sequence.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 21 Jan 2013 12:38:22 +0000 (05:38 -0700)]
gettime: use proper uint64_t types where needed
Windows has 32-bit longs even on 64-bit, so we risk overflowing.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 18 Jan 2013 19:13:45 +0000 (20:13 +0100)]
Add info log on whether tsc is reliable or not for --cpuclock-test
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Bruce Cran [Fri, 18 Jan 2013 13:13:13 +0000 (13:13 +0000)]
Windows: fix off-by-one error in fio_cpu_set and add affinity error messages.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Shaohua Li [Thu, 17 Jan 2013 12:28:15 +0000 (13:28 +0100)]
Make hugetlbfs maping work
If it's a file mapping, flags must be MAP_HARED; If it's an anonymous
mapping, flags must be MAP_PRIVATE|MAP_ANONYMOUS|MAP_HUGETLB (can be
shared, but doesn't matter here).
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 14 Jan 2013 18:33:40 +0000 (19:33 +0100)]
fusion-aw: make configure and compile actually work
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 14 Jan 2013 18:22:15 +0000 (19:22 +0100)]
fusion-aw: fixes
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 14 Jan 2013 18:21:55 +0000 (19:21 +0100)]
configure: use exit 0 instead of just exit
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Bruce Cran [Sun, 13 Jan 2013 17:21:58 +0000 (17:21 +0000)]
Fix typo (READ/DDIR_READ).
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Bruce Cran [Sun, 13 Jan 2013 17:10:25 +0000 (17:10 +0000)]
Fix configure script for 64-bit Windows.
Hard-code config options when building using MinGW-w64 on Windows.
For 32-bit builds, CC and CONFIG_32BIT/CONFIG_64BIT will need to be
updated manually.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Bruce Cran [Sun, 13 Jan 2013 17:09:22 +0000 (17:09 +0000)]
Add CONFIG_64BIT_LLP64, CONFIG_POSIX_FALLOCATE and CONFIG_LINUX_FALLOCATE to Makefile.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Sun, 13 Jan 2013 16:16:46 +0000 (17:16 +0100)]
Improve documentation for end_fsync
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Sat, 12 Jan 2013 09:27:53 +0000 (10:27 +0100)]
configure: enable e4defrag engine regardless of MOVE_EXTENT compile test
It may exist in the running kernel, even if the defines
and structures haven't bubbled back into userspace yet.
The engine carries it's own check and structure define
for that case.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Sat, 12 Jan 2013 08:44:15 +0000 (01:44 -0700)]
Pre-load and sort random blocks for pure read verify workloads
If fio is run with a write phase before a read phase and the
IO type is random, the end read verify phase will get sorted
blocks to read back. But if fio is asked to verify something
that was previously randomly written, it will generate the
same random offsets in random order and verify those. This is
usually much slower than a sorted read back.
So add a verifysort_nr option that allows the user to specify
a number of random offsets to pre-generate and sort, before
reading them and verifying the contents. This greatly speeds
up pure read verify workloads.
Default to 1024, and put a max of 64K entries on the option.
We do a merge list sort on the entries, so we don't want a
huge amount of backlog.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 11 Jan 2013 13:03:25 +0000 (14:03 +0100)]
lfsr: ensure we don't generate an offset + buflen that exceeds the max size
Currently we check for the max value, but that doesn't always
work since it may not fit the minimum block size (even if it
is guaranteed to be smaller than the max offset). Pass in the
last valid block.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 11 Jan 2013 13:03:05 +0000 (14:03 +0100)]
filesetup: limit rand map to the actual IO size, if needed
No need allocating a larger map than we need.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jianpeng Ma [Fri, 11 Jan 2013 07:52:55 +0000 (08:52 +0100)]
Add a check avoid segfault
If new_size was zero or realloc failed, it would be segment fault.
So add a check.
Signed-off-by: Jianpeng Ma <majianpeng@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jianpeng Ma [Thu, 10 Jan 2013 12:20:02 +0000 (13:20 +0100)]
Remove repeated --readonly options in documentation
Signed-off-by: Jianpeng Ma <majianpeng@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jianpeng Ma [Thu, 10 Jan 2013 12:19:27 +0000 (13:19 +0100)]
Fix a potential integer overflow
Because nr_files and new_size are not same types.It can cause new_size
less than zero.Then realloc will be failed.
Signed-off-by: Jianpeng Ma <majianpeng@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 10 Jan 2013 10:23:19 +0000 (11:23 +0100)]
Add configure script
Get rid of all the fragile guessing and checking of features,
and roll a configure script instead.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 9 Jan 2013 10:46:01 +0000 (11:46 +0100)]
Fix variable type warning
Bruce reports:
With 2.0.13 on FreeBSD there's also a warning from client.c:
client.c:24:18: warning: field 'eta' with variable sized type 'struct
jobs_eta' not at the end of a struct or class is a GNU extension [-Wgnu]
struct jobs_eta eta;
Re-order ->eta and ->pending.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 9 Jan 2013 10:01:55 +0000 (11:01 +0100)]
Fio 2.0.13
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 8 Jan 2013 20:02:14 +0000 (21:02 +0100)]
Fix potential null pointer dereference on verify and requeue events
We clear io_u to NULL, but later we derefence io_u to check
the data direction. Do as we do in the main IO loop - store
the data direction in a local variable, and use that after
the main switch.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 8 Jan 2013 12:43:14 +0000 (13:43 +0100)]
server: move fio_net_cmd to the end of fio_net_int_cmd
fio_net_cmd is variably sized. We don't use any transfer space
for the internal command, but the compiler might complain about
this (since it has no way to know this fact). Move fio_net_cmd
to the end of the internal command to both avoid a warning on
clang and to make this more idiot proof.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 8 Jan 2013 12:42:41 +0000 (13:42 +0100)]
Use variable[] instead of GCC variable[0] syntax
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 8 Jan 2013 12:41:35 +0000 (13:41 +0100)]
Enable -ffast-math
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 4 Jan 2013 12:24:52 +0000 (13:24 +0100)]
time: convert to uint64_t
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 4 Jan 2013 12:21:23 +0000 (13:21 +0100)]
Use uintptr_t for engine data
Gets rid of a warning on 32-bit builds on Linux.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 4 Jan 2013 12:16:54 +0000 (13:16 +0100)]
Start of transition from unsigned long long to uint64_t
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 4 Jan 2013 12:09:29 +0000 (13:09 +0100)]
zipf/pareto: use min of file size and io size for init
It is valid to use size=foo, where foo is larger than the size
of the file or device. For that case, we don't want offsets
larger than the size of the file. So use the minimum of the
real or given size.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 4 Jan 2013 07:27:06 +0000 (08:27 +0100)]
Merge branch 'master' of ssh://brick.kernel.dk/data/git/fio