admin/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2025-12-07 20:06:24 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
8f7aa3d3c7323f4ca2768a9e74ebbe359c4f8f88
linux/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst
Eric Dumazet ecfea98b7d tcp: add net.ipv4.tcp_rcvbuf_low_rtt 
This is a follow up of commit aa251c8463 ("tcp: fix too slow
tcp_rcvbuf_grow() action") which brought again the issue that I tried
to fix in commit 65c5287892 ("tcp: fix sk_rcvbuf overshoot")

We also recently increased tcp_rmem[2] to 32 MB in commit 572be9bf9d
("tcp: increase tcp_rmem[2] to 32 MB")

Idea of this patch is to not let tcp_rcvbuf_grow() grow sk->sk_rcvbuf
too fast for small RTT flows. If sk->sk_rcvbuf is too big, this can
force NIC driver to not recycle pages from their page pool, and also
can cause cache evictions for DDIO enabled cpus/NIC, as receivers
are usually slower than senders.

Add net.ipv4.tcp_rcvbuf_low_rtt sysctl, set by default to 1000 usec (1 ms)

If RTT if smaller than the sysctl value, use the RTT/tcp_rcvbuf_low_rtt
ratio to control sk_rcvbuf inflation.

Tested:

Pair of hosts with a 200Gbit IDPF NIC. Using netperf/netserver

Client initiates 8 TCP bulk flows, asking netserver to use CPU #10 only.

super_netperf 8 -H server -T,10 -l 30

On server, use perf -e tcp:tcp_rcvbuf_grow while test is running.

Before:

sysctl -w net.ipv4.tcp_rcvbuf_low_rtt=1
perf record -a -e tcp:tcp_rcvbuf_grow sleep 30 ; perf script|tail -20|cut -c30-230
 1153.051201: tcp:tcp_rcvbuf_grow: time=398 rtt_us=382 copied=6905856 inq=180224 space=6115328 ooo=0 scaling_ratio=240 rcvbuf=27666235 rcv_ssthresh=25878235 window_clamp=25937095 rcv_wnd=25600000 famil
 1153.138752: tcp:tcp_rcvbuf_grow: time=446 rtt_us=413 copied=5529600 inq=180224 space=4505600 ooo=0 scaling_ratio=240 rcvbuf=23068672 rcv_ssthresh=21571860 window_clamp=21626880 rcv_wnd=21286912 famil
 1153.361484: tcp:tcp_rcvbuf_grow: time=415 rtt_us=380 copied=7061504 inq=204800 space=6725632 ooo=0 scaling_ratio=240 rcvbuf=27666235 rcv_ssthresh=25878235 window_clamp=25937095 rcv_wnd=25600000 famil
 1153.457642: tcp:tcp_rcvbuf_grow: time=483 rtt_us=421 copied=5885952 inq=720896 space=4407296 ooo=0 scaling_ratio=240 rcvbuf=23763511 rcv_ssthresh=22223271 window_clamp=22278291 rcv_wnd=21430272 famil
 1153.466002: tcp:tcp_rcvbuf_grow: time=308 rtt_us=281 copied=3244032 inq=180224 space=2883584 ooo=0 scaling_ratio=240 rcvbuf=44854314 rcv_ssthresh=41992059 window_clamp=42050919 rcv_wnd=41713664 famil
 1153.747792: tcp:tcp_rcvbuf_grow: time=394 rtt_us=332 copied=4460544 inq=585728 space=3063808 ooo=0 scaling_ratio=240 rcvbuf=44854314 rcv_ssthresh=41992059 window_clamp=42050919 rcv_wnd=41373696 famil
 1154.260747: tcp:tcp_rcvbuf_grow: time=652 rtt_us=226 copied=10977280 inq=737280 space=9486336 ooo=0 scaling_ratio=240 rcvbuf=31165538 rcv_ssthresh=29197743 window_clamp=29217691 rcv_wnd=28368896 fami
 1154.375019: tcp:tcp_rcvbuf_grow: time=461 rtt_us=443 copied=7573504 inq=507904 space=6856704 ooo=0 scaling_ratio=240 rcvbuf=27666235 rcv_ssthresh=25878235 window_clamp=25937095 rcv_wnd=25288704 famil
 1154.463072: tcp:tcp_rcvbuf_grow: time=494 rtt_us=408 copied=7983104 inq=200704 space=7065600 ooo=0 scaling_ratio=240 rcvbuf=27666235 rcv_ssthresh=25878235 window_clamp=25937095 rcv_wnd=25579520 famil
 1154.474658: tcp:tcp_rcvbuf_grow: time=507 rtt_us=459 copied=5586944 inq=540672 space=4718592 ooo=0 scaling_ratio=240 rcvbuf=17852266 rcv_ssthresh=16692999 window_clamp=16736499 rcv_wnd=16056320 famil
 1154.584657: tcp:tcp_rcvbuf_grow: time=494 rtt_us=427 copied=8126464 inq=204800 space=7782400 ooo=0 scaling_ratio=240 rcvbuf=27666235 rcv_ssthresh=25878235 window_clamp=25937095 rcv_wnd=25600000 famil
 1154.702117: tcp:tcp_rcvbuf_grow: time=480 rtt_us=406 copied=5734400 inq=180224 space=5349376 ooo=0 scaling_ratio=240 rcvbuf=23068672 rcv_ssthresh=21571860 window_clamp=21626880 rcv_wnd=21286912 famil
 1155.941595: tcp:tcp_rcvbuf_grow: time=717 rtt_us=670 copied=11042816 inq=3784704 space=7159808 ooo=0 scaling_ratio=240 rcvbuf=19581357 rcv_ssthresh=18333222 window_clamp=18357522 rcv_wnd=14614528 fam
 1156.384735: tcp:tcp_rcvbuf_grow: time=529 rtt_us=473 copied=9011200 inq=180224 space=7258112 ooo=0 scaling_ratio=240 rcvbuf=19581357 rcv_ssthresh=18333222 window_clamp=18357522 rcv_wnd=18018304 famil
 1157.821676: tcp:tcp_rcvbuf_grow: time=529 rtt_us=272 copied=8224768 inq=602112 space=6545408 ooo=0 scaling_ratio=240 rcvbuf=67000000 rcv_ssthresh=62793576 window_clamp=62812500 rcv_wnd=62115840 famil
 1158.906379: tcp:tcp_rcvbuf_grow: time=710 rtt_us=445 copied=11845632 inq=540672 space=10240000 ooo=0 scaling_ratio=240 rcvbuf=31165538 rcv_ssthresh=29205935 window_clamp=29217691 rcv_wnd=28536832 fam
 1164.600160: tcp:tcp_rcvbuf_grow: time=841 rtt_us=430 copied=12976128 inq=1290240 space=11304960 ooo=0 scaling_ratio=240 rcvbuf=31165538 rcv_ssthresh=29212591 window_clamp=29217691 rcv_wnd=27856896 fa
 1165.163572: tcp:tcp_rcvbuf_grow: time=845 rtt_us=800 copied=12632064 inq=540672 space=7921664 ooo=0 scaling_ratio=240 rcvbuf=27666235 rcv_ssthresh=25912795 window_clamp=25937095 rcv_wnd=25260032 fami
 1165.653464: tcp:tcp_rcvbuf_grow: time=388 rtt_us=309 copied=4493312 inq=180224 space=3874816 ooo=0 scaling_ratio=240 rcvbuf=44854314 rcv_ssthresh=41995899 window_clamp=42050919 rcv_wnd=41713664 famil
 1166.651211: tcp:tcp_rcvbuf_grow: time=556 rtt_us=553 copied=6328320 inq=540672 space=5554176 ooo=0 scaling_ratio=240 rcvbuf=23068672 rcv_ssthresh=21571860 window_clamp=21626880 rcv_wnd=20946944 famil

After:

sysctl -w net.ipv4.tcp_rcvbuf_low_rtt=1000
perf record -a -e tcp:tcp_rcvbuf_grow sleep 30 ; perf script|tail -20|cut -c30-230
 1457.053149: tcp:tcp_rcvbuf_grow: time=128 rtt_us=24 copied=1441792 inq=40960 space=1269760 ooo=0 scaling_ratio=240 rcvbuf=2960741 rcv_ssthresh=2605474 window_clamp=2775694 rcv_wnd=2568192 family=AF_I
 1458.000778: tcp:tcp_rcvbuf_grow: time=128 rtt_us=31 copied=1441792 inq=24576 space=1400832 ooo=0 scaling_ratio=240 rcvbuf=3060163 rcv_ssthresh=2810042 window_clamp=2868902 rcv_wnd=2674688 family=AF_I
 1458.088059: tcp:tcp_rcvbuf_grow: time=190 rtt_us=110 copied=3227648 inq=385024 space=2781184 ooo=0 scaling_ratio=240 rcvbuf=6728240 rcv_ssthresh=6252705 window_clamp=6307725 rcv_wnd=5799936 family=AF
 1458.148549: tcp:tcp_rcvbuf_grow: time=232 rtt_us=129 copied=3956736 inq=237568 space=2842624 ooo=0 scaling_ratio=240 rcvbuf=6731333 rcv_ssthresh=6252705 window_clamp=6310624 rcv_wnd=5918720 family=AF
 1458.466861: tcp:tcp_rcvbuf_grow: time=193 rtt_us=83 copied=2949120 inq=180224 space=2457600 ooo=0 scaling_ratio=240 rcvbuf=5751438 rcv_ssthresh=5357689 window_clamp=5391973 rcv_wnd=5054464 family=AF_
 1458.775476: tcp:tcp_rcvbuf_grow: time=257 rtt_us=127 copied=4304896 inq=352256 space=3346432 ooo=0 scaling_ratio=240 rcvbuf=8067131 rcv_ssthresh=7523275 window_clamp=7562935 rcv_wnd=7061504 family=AF
 1458.776631: tcp:tcp_rcvbuf_grow: time=200 rtt_us=96 copied=3260416 inq=143360 space=2768896 ooo=0 scaling_ratio=240 rcvbuf=6397256 rcv_ssthresh=5938567 window_clamp=5997427 rcv_wnd=5828608 family=AF_
 1459.707973: tcp:tcp_rcvbuf_grow: time=215 rtt_us=96 copied=2506752 inq=163840 space=1388544 ooo=0 scaling_ratio=240 rcvbuf=3068867 rcv_ssthresh=2768282 window_clamp=2877062 rcv_wnd=2555904 family=AF_
 1460.246494: tcp:tcp_rcvbuf_grow: time=231 rtt_us=80 copied=3756032 inq=204800 space=3117056 ooo=0 scaling_ratio=240 rcvbuf=7288091 rcv_ssthresh=6773725 window_clamp=6832585 rcv_wnd=6471680 family=AF_
 1460.714596: tcp:tcp_rcvbuf_grow: time=270 rtt_us=110 copied=4714496 inq=311296 space=3719168 ooo=0 scaling_ratio=240 rcvbuf=8957739 rcv_ssthresh=8339020 window_clamp=8397880 rcv_wnd=7933952 family=AF
 1462.029977: tcp:tcp_rcvbuf_grow: time=101 rtt_us=19 copied=1105920 inq=40960 space=1036288 ooo=0 scaling_ratio=240 rcvbuf=2338970 rcv_ssthresh=2091684 window_clamp=2192784 rcv_wnd=1986560 family=AF_I
 1462.802385: tcp:tcp_rcvbuf_grow: time=89 rtt_us=45 copied=1069056 inq=0 space=1064960 ooo=0 scaling_ratio=240 rcvbuf=2338970 rcv_ssthresh=2091684 window_clamp=2192784 rcv_wnd=2035712 family=AF_INET6
 1462.918648: tcp:tcp_rcvbuf_grow: time=105 rtt_us=33 copied=1441792 inq=180224 space=1069056 ooo=0 scaling_ratio=240 rcvbuf=2383282 rcv_ssthresh=2091684 window_clamp=2234326 rcv_wnd=1896448 family=AF_
 1463.222533: tcp:tcp_rcvbuf_grow: time=273 rtt_us=144 copied=4603904 inq=385024 space=3469312 ooo=0 scaling_ratio=240 rcvbuf=8422564 rcv_ssthresh=7891053 window_clamp=7896153 rcv_wnd=7409664 family=AF
 1466.519312: tcp:tcp_rcvbuf_grow: time=130 rtt_us=23 copied=1343488 inq=0 space=1261568 ooo=0 scaling_ratio=240 rcvbuf=2780158 rcv_ssthresh=2493778 window_clamp=2606398 rcv_wnd=2494464 family=AF_INET6
 1466.681003: tcp:tcp_rcvbuf_grow: time=128 rtt_us=21 copied=1441792 inq=12288 space=1343488 ooo=0 scaling_ratio=240 rcvbuf=2932027 rcv_ssthresh=2578555 window_clamp=2748775 rcv_wnd=2568192 family=AF_I
 1470.689959: tcp:tcp_rcvbuf_grow: time=255 rtt_us=122 copied=3932160 inq=204800 space=3551232 ooo=0 scaling_ratio=240 rcvbuf=8182038 rcv_ssthresh=7647384 window_clamp=7670660 rcv_wnd=7442432 family=AF
 1471.754154: tcp:tcp_rcvbuf_grow: time=188 rtt_us=95 copied=2138112 inq=577536 space=1429504 ooo=0 scaling_ratio=240 rcvbuf=3113650 rcv_ssthresh=2806426 window_clamp=2919046 rcv_wnd=2248704 family=AF_
 1476.813542: tcp:tcp_rcvbuf_grow: time=269 rtt_us=99 copied=3088384 inq=180224 space=2564096 ooo=0 scaling_ratio=240 rcvbuf=6219470 rcv_ssthresh=5771893 window_clamp=5830753 rcv_wnd=5509120 family=AF_
 1477.738309: tcp:tcp_rcvbuf_grow: time=166 rtt_us=54 copied=1777664 inq=180224 space=1417216 ooo=0 scaling_ratio=240 rcvbuf=3117118 rcv_ssthresh=2874958 window_clamp=2922298 rcv_wnd=2613248 family=AF_

We can see sk_rcvbuf values are much smaller, and that rtt_us (estimation of rtt
from a receiver point of view) is kept small, instead of being bloated.

No difference in throughput.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Tested-by: Paolo Abeni <pabeni@redhat.com>
Link: https://patch.msgid.link/20251119084813.3684576-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-11-20 17:44:23 -08:00

164 lines
13 KiB
ReStructuredText
Raw Blame History

.. SPDX-License-Identifier: GPL-2.0
.. Copyright (C) 2023 Google LLC
===========================================
netns_ipv4 struct fast path usage breakdown
===========================================
=============================== ============================================ =================== =================== =================================================
Type Name fastpath_tx_access fastpath_rx_access comment
=============================== ============================================ =================== =================== =================================================
struct_inet_timewait_death_row tcp_death_row
struct_udp_table* udp_table
struct_ctl_table_header* forw_hdr
struct_ctl_table_header* frags_hdr
struct_ctl_table_header* ipv4_hdr
struct_ctl_table_header* route_hdr
struct_ctl_table_header* xfrm4_hdr
struct_ipv4_devconf* devconf_all
struct_ipv4_devconf* devconf_dflt
struct_ip_ra_chain ra_chain
struct_mutex ra_mutex
struct_fib_rules_ops* rules_ops
struct_fib_table fib_main
struct_fib_table fib_default
unsigned_int fib_rules_require_fldissect
bool fib_has_custom_rules
bool fib_has_custom_local_routes
bool fib_offload_disabled
atomic_t fib_num_tclassid_users
struct_hlist_head* fib_table_hash
struct_sock* fibnl
struct_sock* mc_autojoin_sk
struct_inet_peer_base* peers
struct_fqdir* fqdir
u8 sysctl_icmp_echo_ignore_all
u8 sysctl_icmp_echo_enable_probe
u8 sysctl_icmp_echo_ignore_broadcasts
u8 sysctl_icmp_ignore_bogus_error_responses
u8 sysctl_icmp_errors_use_inbound_ifaddr
int sysctl_icmp_ratelimit
int sysctl_icmp_ratemask
u32 ip_rt_min_pmtu
int ip_rt_mtu_expires
int ip_rt_min_advmss
struct_local_ports ip_local_ports
u8 sysctl_tcp_ecn
u8 sysctl_tcp_ecn_fallback
u8 sysctl_ip_default_ttl ip4_dst_hoplimit/ip_select_ttl
u8 sysctl_ip_no_pmtu_disc
u8 sysctl_ip_fwd_use_pmtu read_mostly ip_dst_mtu_maybe_forward/ip_skb_dst_mtu
u8 sysctl_ip_fwd_update_priority ip_forward
u8 sysctl_ip_nonlocal_bind
u8 sysctl_ip_autobind_reuse
u8 sysctl_ip_dynaddr
u8 sysctl_ip_early_demux read_mostly ip(6)_rcv_finish_core
u8 sysctl_raw_l3mdev_accept
u8 sysctl_tcp_early_demux read_mostly ip(6)_rcv_finish_core
u8 sysctl_udp_early_demux
u8 sysctl_nexthop_compat_mode
u8 sysctl_fwmark_reflect
u8 sysctl_tcp_fwmark_accept
u8 sysctl_tcp_l3mdev_accept read_mostly __inet6_lookup_established/inet_request_bound_dev_if
u8 sysctl_tcp_mtu_probing
int sysctl_tcp_mtu_probe_floor
int sysctl_tcp_base_mss
int sysctl_tcp_min_snd_mss read_mostly __tcp_mtu_to_mss(tcp_write_xmit)
int sysctl_tcp_probe_threshold tcp_mtu_probe(tcp_write_xmit)
u32 sysctl_tcp_probe_interval tcp_mtu_check_reprobe(tcp_write_xmit)
int sysctl_tcp_keepalive_time
int sysctl_tcp_keepalive_intvl
u8 sysctl_tcp_keepalive_probes
u8 sysctl_tcp_syn_retries
u8 sysctl_tcp_synack_retries
u8 sysctl_tcp_syncookies generated_on_syn
u8 sysctl_tcp_migrate_req reuseport
u8 sysctl_tcp_comp_sack_nr __tcp_ack_snd_check
int sysctl_tcp_reordering read_mostly tcp_may_raise_cwnd/tcp_cong_control
u8 sysctl_tcp_retries1
u8 sysctl_tcp_retries2
u8 sysctl_tcp_orphan_retries
u8 sysctl_tcp_tw_reuse timewait_sock_ops
unsigned_int sysctl_tcp_tw_reuse_delay timewait_sock_ops
int sysctl_tcp_fin_timeout TCP_LAST_ACK/tcp_rcv_state_process
unsigned_int sysctl_tcp_notsent_lowat read_mostly tcp_notsent_lowat/tcp_stream_memory_free
u8 sysctl_tcp_sack tcp_syn_options
u8 sysctl_tcp_window_scaling tcp_syn_options,tcp_parse_options
u8 sysctl_tcp_timestamps
u8 sysctl_tcp_early_retrans read_mostly tcp_schedule_loss_probe(tcp_write_xmit)
u32 sysctl_tcp_rto_max_ms
u8 sysctl_tcp_recovery tcp_fastretrans_alert
u8 sysctl_tcp_thin_linear_timeouts tcp_retrans_timer(on_thin_streams)
u8 sysctl_tcp_slow_start_after_idle unlikely(tcp_cwnd_validate-network-not-starved)
u8 sysctl_tcp_retrans_collapse
u8 sysctl_tcp_stdurg unlikely(tcp_check_urg)
u8 sysctl_tcp_rfc1337
u8 sysctl_tcp_abort_on_overflow
u8 sysctl_tcp_fack
int sysctl_tcp_max_reordering tcp_check_sack_reordering
int sysctl_tcp_adv_win_scale tcp_init_buffer_space
u8 sysctl_tcp_dsack partial_packet_or_retrans_in_tcp_data_queue
u8 sysctl_tcp_app_win tcp_win_from_space
u8 sysctl_tcp_frto tcp_enter_loss
u8 sysctl_tcp_nometrics_save TCP_LAST_ACK/tcp_update_metrics
u8 sysctl_tcp_no_ssthresh_metrics_save TCP_LAST_ACK/tcp_(update/init)_metrics
u8 sysctl_tcp_moderate_rcvbuf read_mostly tcp_rcvbuf_grow()
u32 sysctl_tcp_rcvbuf_low_rtt read_mostly tcp_rcvbuf_grow()
u8 sysctl_tcp_tso_win_divisor read_mostly tcp_tso_should_defer(tcp_write_xmit)
u8 sysctl_tcp_workaround_signed_windows tcp_select_window
int sysctl_tcp_limit_output_bytes read_mostly tcp_small_queue_check(tcp_write_xmit)
int sysctl_tcp_challenge_ack_limit
int sysctl_tcp_min_rtt_wlen read_mostly tcp_ack_update_rtt
u8 sysctl_tcp_min_tso_segs unlikely(icsk_ca_ops-written)
u8 sysctl_tcp_tso_rtt_log read_mostly tcp_tso_autosize
u8 sysctl_tcp_autocorking read_mostly tcp_push/tcp_should_autocork
u8 sysctl_tcp_reflect_tos tcp_v(4/6)_send_synack
int sysctl_tcp_invalid_ratelimit
int sysctl_tcp_pacing_ss_ratio default_cong_cont(tcp_update_pacing_rate)
int sysctl_tcp_pacing_ca_ratio default_cong_cont(tcp_update_pacing_rate)
int sysctl_tcp_wmem[3] read_mostly tcp_wmem_schedule(sendmsg/sendpage)
int sysctl_tcp_rmem[3] read_mostly __tcp_grow_window(tx),tcp_rcv_space_adjust(rx)
unsigned_int sysctl_tcp_child_ehash_entries
unsigned_long sysctl_tcp_comp_sack_delay_ns __tcp_ack_snd_check
unsigned_long sysctl_tcp_comp_sack_slack_ns __tcp_ack_snd_check
int sysctl_max_syn_backlog
int sysctl_tcp_fastopen
struct_tcp_congestion_ops tcp_congestion_control init_cc
struct_tcp_fastopen_context tcp_fastopen_ctx
unsigned_int sysctl_tcp_fastopen_blackhole_timeout
atomic_t tfo_active_disable_times
unsigned_long tfo_active_disable_stamp
u32 tcp_challenge_timestamp
u32 tcp_challenge_count
u8 sysctl_tcp_plb_enabled
u8 sysctl_tcp_plb_idle_rehash_rounds
u8 sysctl_tcp_plb_rehash_rounds
u8 sysctl_tcp_plb_suspend_rto_sec
int sysctl_tcp_plb_cong_thresh
int sysctl_udp_wmem_min
int sysctl_udp_rmem_min
u8 sysctl_fib_notify_on_flag_change
u8 sysctl_udp_l3mdev_accept
u8 sysctl_igmp_llm_reports
int sysctl_igmp_max_memberships
int sysctl_igmp_max_msf
int sysctl_igmp_qrv
struct_ping_group_range ping_group_range
atomic_t dev_addr_genid
unsigned_int sysctl_udp_child_hash_entries
unsigned_long* sysctl_local_reserved_ports
int sysctl_ip_prot_sock
struct_mr_table* mrt
struct_list_head mr_tables
struct_fib_rules_ops* mr_rules_ops
u32 sysctl_fib_multipath_hash_fields
u8 sysctl_fib_multipath_use_neigh
u8 sysctl_fib_multipath_hash_policy
struct_fib_notifier_ops* notifier_ops
unsigned_int fib_seq
struct_fib_notifier_ops* ipmr_notifier_ops
unsigned_int ipmr_seq
atomic_t rt_genid
siphash_key_t ip_id_key
=============================== ============================================ =================== =================== =================================================
Reference in New Issue View Git Blame Copy Permalink