2020-06-12 06:32:11

by Oded Gabbay

Subject: [PATCH] habanalabs: increase GAUDI QMAN ARB WDT timeout

The current timeout is too low for some of the workloads and we see false
errors as a result.

Signed-off-by: Oded Gabbay <[email protected]>
---
drivers/misc/habanalabs/gaudi/gaudi.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 211547d4f8a7..69317d2ebdfa 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -96,7 +96,7 @@

#define GAUDI_NUM_OF_QM_ARB_ERR_CAUSE 3

-#define GAUDI_ARB_WDT_TIMEOUT 0x400000
+#define GAUDI_ARB_WDT_TIMEOUT 0x1000000

static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = {
"gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3",
--
2.17.1

2020-06-12 08:35:08

by Tomer Tayar

Subject: RE: [PATCH] habanalabs: increase GAUDI QMAN ARB WDT timeout

On Fri, Jun 12, 2020 at 9:28 AM, Oded Gabbay <[email protected]> wrote:
> The current timeout is too low for some of the workloads and we see false
> errors as a result.
>
> Signed-off-by: Oded Gabbay <[email protected]>

Reviewed-by: Tomer Tayar <[email protected]>