diff options
| author | Eric Dumazet <edumazet@google.com> | 2023-07-17 15:29:17 +0000 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2023-07-18 18:41:18 -0700 |
| commit | dfa2f0483360d4d6f2324405464c9f281156bd87 (patch) | |
| tree | 5aa4cb885109efde347b21e9669be75ff8175bf9 /include/linux/tcp.h | |
| parent | 63c8778d9149d5df86e3a5dd192103d42d74cc93 (diff) | |
tcp: get rid of sysctl_tcp_adv_win_scale
With modern NIC drivers shifting to full page allocations per
received frame, we face the following issue:
TCP has one per-netns sysctl used to tweak how to translate
a memory use into an expected payload (RWIN), in RX path.
tcp_win_from_space() implementation is limited to few cases.
For hosts dealing with various MSS, we either under estimate
or over estimate the RWIN we send to the remote peers.
For instance with the default sysctl_tcp_adv_win_scale value,
we expect to store 50% of payload per allocated chunk of memory.
For the typical use of MTU=1500 traffic, and order-0 pages allocations
by NIC drivers, we are sending too big RWIN, leading to potential
tcp collapse operations, which are extremely expensive and source
of latency spikes.
This patch makes sysctl_tcp_adv_win_scale obsolete, and instead
uses a per socket scaling factor, so that we can precisely
adjust the RWIN based on effective skb->len/skb->truesize ratio.
This patch alone can double TCP receive performance when receivers
are too slow to drain their receive queue, or by allowing
a bigger RWIN when MSS is close to PAGE_SIZE.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Link: https://lore.kernel.org/r/20230717152917.751987-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'include/linux/tcp.h')
| -rw-r--r-- | include/linux/tcp.h | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b4c08ac86983..fbcb0ce13171 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -172,6 +172,8 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) return (struct tcp_request_sock *)req; } +#define TCP_RMEM_TO_WIN_SCALE 8 + struct tcp_sock { /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; @@ -238,7 +240,7 @@ struct tcp_sock { u32 window_clamp; /* Maximal window to advertise */ u32 rcv_ssthresh; /* Current window clamp */ - + u8 scaling_ratio; /* see tcp_win_from_space() */ /* Information of the most recently (s)acked skb */ struct tcp_rack { u64 mstamp; /* (Re)sent time of the skb */ |