diff mbox

[rdma-next,3/5] RDMA/hns: Increase checking CMQ status timeout value

Message ID 1526544173-106587-4-git-send-email-xavier.huwei@huawei.com (mailing list archive)
State Superseded
Headers show

Commit Message

Wei Hu (Xavier) May 17, 2018, 8:02 a.m. UTC
This patch increases checking CMQ status timeout value and
uses the same value with NIC driver to avoid deficiency of
time.

Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
---
 drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Comments

Leon Romanovsky May 23, 2018, 5:49 a.m. UTC | #1
On Thu, May 17, 2018 at 04:02:51PM +0800, Wei Hu (Xavier) wrote:
> This patch increases checking CMQ status timeout value and
> uses the same value with NIC driver to avoid deficiency of
> time.
>
> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
> ---
>  drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
> index 182b672..f16df1b 100644
> --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
> +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
> @@ -76,7 +76,7 @@
>  #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
>  #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
>  #define HNS_ROCE_INVALID_LKEY			0x100
> -#define HNS_ROCE_CMQ_TX_TIMEOUT			200
> +#define HNS_ROCE_CMQ_TX_TIMEOUT			30000

Don't you think that loop of 30 seconds too much?

Thanks

>
>  #define HNS_ROCE_CONTEXT_HOP_NUM		1
>  #define HNS_ROCE_MTT_HOP_NUM			1
> --
> 1.9.1
>
Wei Hu (Xavier) May 23, 2018, 6:09 a.m. UTC | #2
On 2018/5/23 13:49, Leon Romanovsky wrote:
> On Thu, May 17, 2018 at 04:02:51PM +0800, Wei Hu (Xavier) wrote:
>> This patch increases checking CMQ status timeout value and
>> uses the same value with NIC driver to avoid deficiency of
>> time.
>>
>> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
>> ---
>>  drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 +-
>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
>> index 182b672..f16df1b 100644
>> --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
>> +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
>> @@ -76,7 +76,7 @@
>>  #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
>>  #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
>>  #define HNS_ROCE_INVALID_LKEY			0x100
>> -#define HNS_ROCE_CMQ_TX_TIMEOUT			200
>> +#define HNS_ROCE_CMQ_TX_TIMEOUT			30000
> Don't you think that loop of 30 seconds too much?
>
> Thanks
Leon, 30ms
>
>>  #define HNS_ROCE_CONTEXT_HOP_NUM		1
>>  #define HNS_ROCE_MTT_HOP_NUM			1
>> --
>> 1.9.1
>>


--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Wei Hu (Xavier) May 23, 2018, 6:15 a.m. UTC | #3
On 2018/5/23 14:09, Wei Hu (Xavier) wrote:
>
> On 2018/5/23 13:49, Leon Romanovsky wrote:
>> On Thu, May 17, 2018 at 04:02:51PM +0800, Wei Hu (Xavier) wrote:
>>> This patch increases checking CMQ status timeout value and
>>> uses the same value with NIC driver to avoid deficiency of
>>> time.
>>>
>>> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
>>> ---
>>>  drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 +-
>>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>>
>>> diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
>>> index 182b672..f16df1b 100644
>>> --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
>>> +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
>>> @@ -76,7 +76,7 @@
>>>  #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
>>>  #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
>>>  #define HNS_ROCE_INVALID_LKEY			0x100
>>> -#define HNS_ROCE_CMQ_TX_TIMEOUT			200
>>> +#define HNS_ROCE_CMQ_TX_TIMEOUT			30000
>> Don't you think that loop of 30 seconds too much?
>>
>> Thanks
> Leon, 30ms
Because firmware take turns excuting NIC and RoCE command.
Although RoCE command does not  take so long,  we still use
the same timeout value with NIC driver.
Thanks
>>>  #define HNS_ROCE_CONTEXT_HOP_NUM		1
>>>  #define HNS_ROCE_MTT_HOP_NUM			1
>>> --
>>> 1.9.1
>>>
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>
> .
>


--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Leon Romanovsky May 23, 2018, 6:23 a.m. UTC | #4
On Wed, May 23, 2018 at 02:15:48PM +0800, Wei Hu (Xavier) wrote:
>
>
> On 2018/5/23 14:09, Wei Hu (Xavier) wrote:
> >
> > On 2018/5/23 13:49, Leon Romanovsky wrote:
> >> On Thu, May 17, 2018 at 04:02:51PM +0800, Wei Hu (Xavier) wrote:
> >>> This patch increases checking CMQ status timeout value and
> >>> uses the same value with NIC driver to avoid deficiency of
> >>> time.
> >>>
> >>> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
> >>> ---
> >>>  drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 +-
> >>>  1 file changed, 1 insertion(+), 1 deletion(-)
> >>>
> >>> diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
> >>> index 182b672..f16df1b 100644
> >>> --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
> >>> +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
> >>> @@ -76,7 +76,7 @@
> >>>  #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
> >>>  #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
> >>>  #define HNS_ROCE_INVALID_LKEY			0x100
> >>> -#define HNS_ROCE_CMQ_TX_TIMEOUT			200
> >>> +#define HNS_ROCE_CMQ_TX_TIMEOUT			30000
> >> Don't you think that loop of 30 seconds too much?
> >>
> >> Thanks
> > Leon, 30ms
> Because firmware take turns excuting NIC and RoCE command.
> Although RoCE command does not  take so long,  we still use
> the same timeout value with NIC driver.

Sorry, you are right it is 30ms and not 30s.

Thanks,
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
diff mbox

Patch

diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index 182b672..f16df1b 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -76,7 +76,7 @@ 
 #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
 #define HNS_ROCE_INVALID_LKEY			0x100
-#define HNS_ROCE_CMQ_TX_TIMEOUT			200
+#define HNS_ROCE_CMQ_TX_TIMEOUT			30000
 
 #define HNS_ROCE_CONTEXT_HOP_NUM		1
 #define HNS_ROCE_MTT_HOP_NUM			1