diff mbox series

[rdma-next] RDMA/ipoib: Use the networking stack default for txqueuelen

Message ID cc97764b5a8def4ea879b371549a5867fe75c756.1728555243.git.leon@kernel.org (mailing list archive)
State Accepted
Headers show
Series [rdma-next] RDMA/ipoib: Use the networking stack default for txqueuelen | expand

Commit Message

Leon Romanovsky Oct. 10, 2024, 10:16 a.m. UTC 
From: Gal Pressman <gal@nvidia.com>

There is no need for a special txqueuelen value for IPoIB.
This value represents the qdisc size which is not related to the SQ
size, and the default value provided by the stack (DEFAULT_TX_QUEUE_LEN)
is sufficient for typical use cases.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/ulp/ipoib/ipoib_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

Comments

Leon Romanovsky Oct. 28, 2024, 8:23 a.m. UTC | #1 
On Thu, 10 Oct 2024 13:16:19 +0300, Leon Romanovsky wrote:
> There is no need for a special txqueuelen value for IPoIB.
> This value represents the qdisc size which is not related to the SQ
> size, and the default value provided by the stack (DEFAULT_TX_QUEUE_LEN)
> is sufficient for typical use cases.
> 
> 

Applied, thanks!

[1/1] RDMA/ipoib: Use the networking stack default for txqueuelen
      https://git.kernel.org/rdma/rdma/c/c11db1bf0ddc3c

Best regards,
diff mbox series

Patch

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 4e31bb0b6466..3b463db8ce39 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -49,6 +49,7 @@ 
 #include <linux/jhash.h>
 #include <net/arp.h>
 #include <net/addrconf.h>
+#include <net/pkt_sched.h>
 #include <linux/inetdevice.h>
 #include <rdma/ib_cache.h>
 
@@ -2145,7 +2146,7 @@  void ipoib_setup_common(struct net_device *dev)
 	dev->hard_header_len	 = IPOIB_HARD_LEN;
 	dev->addr_len		 = INFINIBAND_ALEN;
 	dev->type		 = ARPHRD_INFINIBAND;
-	dev->tx_queue_len	 = ipoib_sendq_size * 2;
+	dev->tx_queue_len	 = DEFAULT_TX_QUEUE_LEN;
 	dev->features		 = (NETIF_F_VLAN_CHALLENGED	|
 				    NETIF_F_HIGHDMA);
 	netif_keep_dst(dev);