[PATCH v1] app/mldev: fix error reporting on IO failure
Srikanth Yalavarthi
syalavarthi at marvell.com
Mon Jun 12 20:00:19 CEST 2023
Application is reporting the test output as success when a
failure occurs in writing the output. Fix incorrect error
reporting on failure to write output files.
Fixes: da6793390596 ("app/mldev: support inference validation")
Signed-off-by: Srikanth Yalavarthi <syalavarthi at marvell.com>
---
app/test-mldev/test_inference_common.c | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/app/test-mldev/test_inference_common.c b/app/test-mldev/test_inference_common.c
index 7c62726761..418bf38be4 100644
--- a/app/test-mldev/test_inference_common.c
+++ b/app/test-mldev/test_inference_common.c
@@ -867,9 +867,6 @@ ml_inference_validation(struct ml_test *test, struct ml_request *req)
goto next_output;
}
done:
- if (match)
- t->nb_valid++;
-
return match;
}
@@ -892,10 +889,8 @@ ml_request_finish(struct rte_mempool *mp, void *opaque, void *obj, unsigned int
rte_ml_io_dequantize(t->cmn.opt->dev_id, model->id, t->model[req->fid].nb_batches,
req->output, model->output);
- if (model->reference == NULL) {
- t->nb_valid++;
+ if (model->reference == NULL)
goto dump_output_pass;
- }
if (!ml_inference_validation(opaque, req))
goto dump_output_fail;
@@ -920,6 +915,7 @@ ml_request_finish(struct rte_mempool *mp, void *opaque, void *obj, unsigned int
if (error)
return;
}
+ t->nb_valid++;
return;
--
2.17.1
More information about the dev
mailing list