| Message ID | 1572003721-26368-1-git-send-email-dag.moxnes@oracle.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | [rdma-next] RDMA/cma: Use ACK timeout for RoCE packetLifeTime | expand |
On Fri, Oct 25, 2019 at 01:42:01PM +0200, Dag Moxnes wrote: > The cma is currently using a hard-coded value, CMA_IBOE_PACKET_LIFETIME, > for the PacketLifeTime, as it can not be determined from the network. > This value might not be optimal for all networks. > > The cma module supports the function rdma_set_ack_timeout to set the > ACK timeout for a QP associated with a connection. As per IBTA 12.7.34 > local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). > Assuming a negligible local ACK delay, we can use > PacketLifeTime = local ACK timeout/2 > as a reasonable approximation for RoCE networks. > > Signed-off-by: Dag Moxnes <dag.moxnes@oracle.com> > Change-Id: I200eda9d54829184e556c3c55d6a8869558d76b2 Please don't send Change-Id to the public lists. Run checkpatch before sending. Otherwise this seems reasonable to me.. Jason
Hi Jason, Den 29.10.2019 20:51, skrev Jason Gunthorpe: > On Fri, Oct 25, 2019 at 01:42:01PM +0200, Dag Moxnes wrote: >> The cma is currently using a hard-coded value, CMA_IBOE_PACKET_LIFETIME, >> for the PacketLifeTime, as it can not be determined from the network. >> This value might not be optimal for all networks. >> >> The cma module supports the function rdma_set_ack_timeout to set the >> ACK timeout for a QP associated with a connection. As per IBTA 12.7.34 >> local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). >> Assuming a negligible local ACK delay, we can use >> PacketLifeTime = local ACK timeout/2 >> as a reasonable approximation for RoCE networks. >> >> Signed-off-by: Dag Moxnes <dag.moxnes@oracle.com> >> Change-Id: I200eda9d54829184e556c3c55d6a8869558d76b2 > Please don't send Change-Id to the public lists. Run checkpatch before > sending. > > Otherwise this seems reasonable to me.. Thanks for the review. Sorry about the Change-Id. I will send a v2 patch without it. Regards, -Dag > > Jason
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index c8566a4237..2c1b08bde2 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2530,7 +2530,9 @@ EXPORT_SYMBOL(rdma_set_service_type); * This function should be called before rdma_connect() on active side, * and on passive side before rdma_accept(). It is applicable to primary * path only. The timeout will affect the local side of the QP, it is not - * negotiated with remote side and zero disables the timer. + * negotiated with remote side and zero disables the timer. In case it is + * set before rdma_resolve_route, the value will also be used to determine + * PacketLifeTime for RoCE. * * Return: 0 for success */ @@ -2939,7 +2941,16 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) route->path_rec->rate = iboe_get_rate(ndev); dev_put(ndev); route->path_rec->packet_life_time_selector = IB_SA_EQ; - route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME; + /* In case ACK timeout is set, use this value to calculate + * PacketLifeTime. As per IBTA 12.7.34, + * local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). + * Assuming a negligible local ACK delay, we can use + * PacketLifeTime = local ACK timeout/2 + * as a reasonable approximation for RoCE networks. + */ + route->path_rec->packet_life_time = id_priv->timeout_set ? + id_priv->timeout - 1 : CMA_IBOE_PACKET_LIFETIME; + if (!route->path_rec->mtu) { ret = -EINVAL; goto err2;
The cma is currently using a hard-coded value, CMA_IBOE_PACKET_LIFETIME, for the PacketLifeTime, as it can not be determined from the network. This value might not be optimal for all networks. The cma module supports the function rdma_set_ack_timeout to set the ACK timeout for a QP associated with a connection. As per IBTA 12.7.34 local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). Assuming a negligible local ACK delay, we can use PacketLifeTime = local ACK timeout/2 as a reasonable approximation for RoCE networks. Signed-off-by: Dag Moxnes <dag.moxnes@oracle.com> Change-Id: I200eda9d54829184e556c3c55d6a8869558d76b2 --- drivers/infiniband/core/cma.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)