On Wed, Feb 05 2014, Grant Grundler wrote:
> On Wed, Feb 5, 2014 at 10:27 AM, Jens Axboe <[email protected]> wrote:
> > On Tue, Feb 04 2014, Puthikorn Voravootivat wrote:
> >> I tried to run the same test with fio 2.1.3 and saw the same error.
> >> This error always occurs when rw=read or randread and verify_backlog=1
> >>
> >> Here is an example job file and error message.
> >>
> >> Job file:
> >> [md5-sync-1-0-1-1-1]
> >> filename=test213/fio/md5-sync-1-0-1-1-1
> >> loops=1
> >> direct=0
> >> iodepth=1
> >> ioengine=sync
> >> verify=md5
> >> size=1m
> >> bs=4k
> >> rw=read
> >> verifysort=1
> >> verify_backlog=1
> >>
> >> Error message:
> >> verify: bad magic header 869, wanted acca at file
> >> test213/fio/md5-sync-1-0-1-1-1 offset 585728, length 2290190
> >
> > This is indeed breakage between 2.1.2 and 2.1.3. I ran a bisect on it,
> > it reveals:
> >
> > 20876c53b5d32f2da9049af5e7fb102133946981 is the first bad commit
> > commit 20876c53b5d32f2da9049af5e7fb102133946981
> > Author: Juan Casse <[email protected]>
> > Date: Mon Sep 16 09:22:10 2013 -0700
> >
> > Add condition to stop issuing io in do_io().
>
> I think Puthik has a fix related to this but I haven't reviewed his
> next patch yet. We've been talking about this behavior though.
>
> I'll take another look at this patch to see what it's changing.
The below should take care of it. Juan's fix didn't account for verify
exceeding size=.
diff --git a/backend.c b/backend.c
index bf9d066e012a..3ac72e771cb9 100644
--- a/backend.c
+++ b/backend.c
@@ -642,7 +642,7 @@ static uint64_t do_io(struct thread_data *td)
uint64_t bytes_done[DDIR_RWDIR_CNT] = { 0, 0, 0 };
unsigned int i;
int ret = 0;
- uint64_t bytes_issued = 0;
+ uint64_t total_bytes, bytes_issued = 0;
if (in_ramp_time(td))
td_set_runstate(td, TD_RAMP);
@@ -651,6 +651,10 @@ static uint64_t do_io(struct thread_data *td)
lat_target_init(td);
+ total_bytes = td->o.size;
+ if (td->o.verify != VERIFY_NONE && td_write(td))
+ total_bytes += td->o.size;
+
while ((td->o.read_iolog_file && !flist_empty(&td->io_log_list)) ||
(!flist_empty(&td->trim_list)) || !io_bytes_exceeded(td) ||
td->o.time_based) {
@@ -678,7 +682,7 @@ static uint64_t do_io(struct thread_data *td)
if (flow_threshold_exceeded(td))
continue;
- if (bytes_issued >= (uint64_t) td->o.size)
+ if (bytes_issued >= total_bytes)
break;
io_u = get_io_u(td);
--
Jens Axboe
--
To unsubscribe from this list: send the line "unsubscribe fio" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
