On 08/26/2013 03:22 PM, Juan Casse wrote: > We check numberio to detect stale blocks. > > Signed-off-by: Juan Casse <jcasse@xxxxxxxxxxxx> > Reviewed-by: Grant Grundler <grundler@xxxxxxxxxxxx> > --- > HOWTO | 7 +++++++ > init.c | 33 +++++++++++++++++++++++++++++++++ > ioengine.h | 1 + > iolog.c | 1 + > iolog.h | 1 + > libfio.c | 3 ++- > options.c | 9 +++++++++ > thread_options.h | 2 ++ > verify.c | 10 ++++++++-- > 9 files changed, 64 insertions(+), 3 deletions(-) > > diff --git a/HOWTO b/HOWTO > index 005dac2..14ff8b5 100644 > --- a/HOWTO > +++ b/HOWTO > @@ -657,6 +657,13 @@ ioengine=str Defines how the job issues io to the file. The following > filename, eg ioengine=external:/tmp/foo.o > to load ioengine foo.o in /tmp. > > +data_integrity_check > + If this option is given, fio will check the i/o number of > + each block read back during the verification phase. Fio > + checks numberio to detect stale blocks. Currently, this > + option requires synchronous i/o, and equal-sized read and > + write blocks. This option requires workloads that write data. I think this use case is just too narrow. Why does it require sync IO and equal read/write sizes? Can't you just replay and re-generate and compare? -- Jens Axboe -- To unsubscribe from this list: send the line "unsubscribe fio" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
