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State | Superseded |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