| Message ID | 20230522201552.3585421-1-ziweixiao@google.com (mailing list archive) |
|---|---|
| State | Accepted |
| Commit | a695641c8eaac268ad7e373c7e33c00b88b2bcbf |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [net-next] gve: Support IPv6 Big TCP on DQ | expand |
On Mon, May 22, 2023 at 01:15:52PM -0700, Ziwei Xiao wrote: > From: Coco Li <lixiaoyan@google.com> > > Add support for using IPv6 Big TCP on DQ which can handle large TSO/GRO > packets. See https://lwn.net/Articles/895398/. This can improve the > throughput and CPU usage. > > Perf test result: > ip -d link show $DEV > gso_max_size 185000 gso_max_segs 65535 tso_max_size 262143 tso_max_segs 65535 gro_max_size 185000 > > For performance, tested with neper using 9k MTU on hardware that supports 200Gb/s line rate. > > In single streams when line rate is not saturated, we expect throughput improvements. > When the networking is performing at line rate, we expect cpu usage improvements. > > Tcp_stream (unidirectional stream test, T=thread, F=flow): > skb=180kb, T=1, F=1, no zerocopy: throughput average=64576.88 Mb/s, sender stime=8.3, receiver stime=10.68 > skb=64kb, T=1, F=1, no zerocopy: throughput average=64862.54 Mb/s, sender stime=9.96, receiver stime=12.67 > skb=180kb, T=1, F=1, yes zerocopy: throughput average=146604.97 Mb/s, sender stime=10.61, receiver stime=5.52 > skb=64kb, T=1, F=1, yes zerocopy: throughput average=131357.78 Mb/s, sender stime=12.11, receiver stime=12.25 > > skb=180kb, T=20, F=100, no zerocopy: throughput average=182411.37 Mb/s, sender stime=41.62, receiver stime=79.4 > skb=64kb, T=20, F=100, no zerocopy: throughput average=182892.02 Mb/s, sender stime=57.39, receiver stime=72.69 > skb=180kb, T=20, F=100, yes zerocopy: throughput average=182337.65 Mb/s, sender stime=27.94, receiver stime=39.7 > skb=64kb, T=20, F=100, yes zerocopy: throughput average=182144.20 Mb/s, sender stime=47.06, receiver stime=39.01 > > Signed-off-by: Ziwei Xiao <ziweixiao@google.com> > Signed-off-by: Coco Li <lixiaoyan@google.com> Reviewed-by: Simon Horman <simon.horman@corigine.com>
Hello: This patch was applied to netdev/net-next.git (main) by Jakub Kicinski <kuba@kernel.org>: On Mon, 22 May 2023 13:15:52 -0700 you wrote: > From: Coco Li <lixiaoyan@google.com> > > Add support for using IPv6 Big TCP on DQ which can handle large TSO/GRO > packets. See https://lwn.net/Articles/895398/. This can improve the > throughput and CPU usage. > > Perf test result: > ip -d link show $DEV > gso_max_size 185000 gso_max_segs 65535 tso_max_size 262143 tso_max_segs 65535 gro_max_size 185000 > > [...] Here is the summary with links: - [net-next] gve: Support IPv6 Big TCP on DQ https://git.kernel.org/netdev/net-next/c/a695641c8eaa You are awesome, thank you!
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index caa00c72aeeb..8fb70db63b8b 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -31,6 +31,7 @@ // Minimum amount of time between queue kicks in msec (10 seconds) #define MIN_TX_TIMEOUT_GAP (1000 * 10) +#define DQO_TX_MAX 0x3FFFF const char gve_version_str[] = GVE_VERSION; static const char gve_version_prefix[] = GVE_VERSION_PREFIX; @@ -2047,6 +2048,10 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) goto err; } + /* Big TCP is only supported on DQ*/ + if (!gve_is_gqi(priv)) + netif_set_tso_max_size(priv->dev, DQO_TX_MAX); + priv->num_registered_pages = 0; priv->rx_copybreak = GVE_DEFAULT_RX_COPYBREAK; /* gvnic has one Notification Block per MSI-x vector, except for the diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index b76143bfd594..3c09e66ba1ab 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -8,6 +8,7 @@ #include "gve_adminq.h" #include "gve_utils.h" #include "gve_dqo.h" +#include <net/ip.h> #include <linux/tcp.h> #include <linux/slab.h> #include <linux/skbuff.h> @@ -646,6 +647,9 @@ static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx, goto drop; } + if (unlikely(ipv6_hopopt_jumbo_remove(skb))) + goto drop; + num_buffer_descs = gve_num_buffer_descs_needed(skb); } else { num_buffer_descs = gve_num_buffer_descs_needed(skb);