3a35845f7756a8a86b420650bff41267192dce22 |
|
15-Apr-2014 |
Jens Axboe <axboe@fb.com> |
sg/binject: only restore file flags if they have been set Signed-off-by: Jens Axboe <axboe@fb.com>
/external/fio/libfio.c
|
4a851614cfdbebddeb78de04ac89a39d26f25459 |
|
14-Apr-2014 |
Jens Axboe <axboe@fb.com> |
Error check fcntl() calls Add a helper to mark an fd as non-blocking, so we can check and complain in one place. Signed-off-by: Jens Axboe <axboe@fb.com>
/external/fio/libfio.c
|
046395d7ab181288d14737c1d0041e98328f473f |
|
09-Apr-2014 |
Jens Axboe <axboe@fb.com> |
Add exit_on_io_done option to the CPU IO engine The CPU IO engine is most often used to saturate the system, while running an IO load on it. As such, it's useful to have CPU engine threads exit automatically, when IO has completed. Add exit_on_io_done as a CPU IO engine option for that purpose. Signed-off-by: Jens Axboe <axboe@fb.com>
/external/fio/libfio.c
|
243bfe190245a10e9d0981bf2a7c722edc4c43d4 |
|
02-Apr-2014 |
Jens Axboe <axboe@fb.com> |
iolog: don't serialize the writing of all logs Serialize based on filename, so that independent logs can be written at the same time. If the logs are big, this can take a while to flush to disk. It's silly to have all jobs waiting on each other, when they could write their own logs independently. Signed-off-by: Jens Axboe <axboe@fb.com>
/external/fio/libfio.c
|
8edd973d57a311d4c590d7385796bbdf111ed04c |
|
01-Mar-2014 |
Jens Axboe <axboe@fb.com> |
Add runstate swap helpers Signed-off-by: Jens Axboe <axboe@fb.com>
/external/fio/libfio.c
|
6bb58215842760895071d9f331da4dc2dfc16f30 |
|
21-Feb-2014 |
Jens Axboe <axboe@fb.com> |
Improve latency_target runs Reset the stats when we have found our target, and then do another latency_window run with those settings so that the final results reflect the probed values. Signed-off-by: Jens Axboe <axboe@fb.com>
/external/fio/libfio.c
|
da0a7bd224bb9331f27bb4b20394dd5c8fa3acb0 |
|
17-Sep-2013 |
Juan Casse <jcasse@chromium.org> |
Adds check for numberio during verify phase. Currently, fio checks the block offset number in a block's header during the verify phase. We add a check for the io number (numberio) to detect stale blocks. This check is performed only on workloads that write data, as those workloads know what numberio was written to each block. td->io_issues[ddir] = 0; was removed so that numberio does not get reset at each iteration; we want numberio to keep incrementing to reflect how many times the same data was written. Signed-off-by: Juan Casse <jcasse@chromium.org> Reviewed-by: Grant Grundler <grundler@chromium.org> Fixed typo. Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
1c7eaa7b2e8d06e56fc1db3f9e0a48293e96b27f |
|
30-Dec-2013 |
Jens Axboe <axboe@kernel.dk> |
libfio: add missing OS's to fio_os_strings[] Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
3e260a46ea9a8de224c3d0a29a608da3440f284a |
|
09-Dec-2013 |
Jens Axboe <axboe@kernel.dk> |
Add options to have fio latency profile a device This adds three new options: - latency_target. This defines a specific latency target, in usec. - latency_window. This defines the period over which fio samples. - latency_percentile. This defines the percentage of IOs that must meet the criteria specified by latency_target/latency_window. With these options set, fio will run the described workload and vary the queue depth between 1 and iodepth= to find the best performing spot that meets the criteria specified by the three options. A sample job file is also added to demonstrate how to use this. Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
3a5f6bde1d14faa9e60cde1c8b45c101bc462f34 |
|
11-Apr-2013 |
Jens Axboe <axboe@kernel.dk> |
Make nr_thread/nr_process private to backend No need export that knowledge. Merge from gfio. Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
a569b45f68ebaa93fbbaca424dc827f4bbc5d655 |
|
11-Apr-2013 |
Jens Axboe <axboe@kernel.dk> |
Move init code to libfio More merge from gfio. Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
5b3faae6f26beb2572ebeae7caf8cd7d693bb818 |
|
07-Mar-2013 |
SEOKYOUNG KO <seokyoung.ko@samsung.com> |
Fix rate iops with ramp time When the ramp time is over, fio resets the ->io_issues[] counters, but not the rwmix counters. This causes a problem for mixed read/write workloads that are rate limited and include a ramp time. Fix it by resetting rwmix_issues with the regular issues. Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
bcd5abfa9f230bbe4365dad1289fdea1f5509f74 |
|
23-Jan-2013 |
Jens Axboe <axboe@kernel.dk> |
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>
/external/fio/libfio.c
|
44cbc6daaae3674ea5d0a113b66596ca24f372e0 |
|
21-Jan-2013 |
Jens Axboe <axboe@kernel.dk> |
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>
/external/fio/libfio.c
|
36d80bc7c7f7fbc2612941b7dd7ceaf645798c7f |
|
30-Nov-2012 |
Jens Axboe <axboe@kernel.dk> |
Wire up SIGUSR2 to kill blocking threads Get rid of io engine ops SIGTERM flag, it didn't really work. Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
41fa20ec4b70d727128b0aa72640e53817d12cda |
|
29-Nov-2012 |
Jens Axboe <axboe@kernel.dk> |
libfio: don't sent KILL signal to own process from signal handler Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
2caefeecf95c2e01ccffc3e286d17a84b12f4dc1 |
|
15-Nov-2012 |
Jens Axboe <axboe@kernel.dk> |
server: properly reset stat_number in fio_reset_state() Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
6eaf09d6e9ca1f8accb057cdb18620b7e53ae33f |
|
14-Sep-2012 |
Shaohua Li <shli@fusionio.com> |
Add support for trim as a workload type This only works on Linux so far, and it's always sync given what the interface to the kernel looks like. Also restricted to pure block devices. Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
59dfce577869f0a6668d682ad06874b3398a4b93 |
|
15-Feb-2012 |
Jens Axboe <axboe@kernel.dk> |
Fixup includes Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
a3efc919b0dcc27d65a6e84edca209b91cee173d |
|
09-Feb-2012 |
Jens Axboe <axboe@kernel.dk> |
Move variables to backend, fix up line spaces Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|
2e1df07d1ea30e0304cc65370f3ed161a6f22cd4 |
|
09-Feb-2012 |
Jens Axboe <axboe@kernel.dk> |
Move some code around to better separate front/backend Signed-off-by: Jens Axboe <axboe@kernel.dk>
/external/fio/libfio.c
|