Previous patch added a TCP_RTO_MAX_MS socket option
to tune a TCP socket max RTO value.
Many setups prefer to change a per netns sysctl.
This patch adds /proc/sys/net/ipv4/tcp_rto_max_ms
Its initial value is 120000 (120 seconds).
Keep in mind that a decrease of tcp_rto_max_ms
means shorter overall timeouts, unless tcp_retries2
sysctl is increased.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Today we have a hardcoded delay of 1 sec before a TIME-WAIT socket can be
reused by reopening a connection. This is a safe choice based on an
assumption that the other TCP timestamp clock frequency, which is unknown
to us, may be as low as 1 Hz (RFC 7323, section 5.4).
However, this means that in the presence of short lived connections with an
RTT of couple of milliseconds, the time during which a 4-tuple is blocked
from reuse can be orders of magnitude longer that the connection lifetime.
Combined with a reduced pool of ephemeral ports, when using
IP_LOCAL_PORT_RANGE to share an egress IP address between hosts [1], the
long TIME-WAIT reuse delay can lead to port exhaustion, where all available
4-tuples are tied up in TIME-WAIT state.
Turn the reuse delay into a per-netns setting so that sysadmins can make
more aggressive assumptions about remote TCP timestamp clock frequency and
shorten the delay in order to allow connections to reincarnate faster.
Note that applications can completely bypass the TIME-WAIT delay protection
already today by locking the local port with bind() before connecting. Such
immediate connection reuse may result in PAWS failing to detect old
duplicate segments, leaving us with just the sequence number check as a
safety net.
This new configurable offers a trade off where the sysadmin can balance
between the risk of PAWS detection failing to act versus exhausting ports
by having sockets tied up in TIME-WAIT state for too long.
[1] https://lpc.events/event/16/contributions/1349/
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20241209-jakub-krn-909-poc-msec-tw-tstamp-v2-2-66aca0eed03e@cloudflare.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
sysctl_tcp_l3mdev_accept is read from TCP receive fast path from
tcp_v6_early_demux(),
__inet6_lookup_established,
inet_request_bound_dev_if().
Move it to netns_ipv4_read_rx.
Remove the '#ifdef CONFIG_NET_L3_MASTER_DEV' that was guarding
its definition.
Note this adds a hole of three bytes that could be filled later.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Cc: Wei Wang <weiwan@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Link: https://patch.msgid.link/20241010034100.320832-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The doc pages under /networking/net_cachelines are unreadable because
they lack .rst formatting for the tabular text.
Add simple table markup and tidy up the table contents:
- remove dashes that represent empty cells because they render
as bullets and are not needed
- replace 'struct_*' with 'struct *' in the first column so that
sphinx can render links for any structs that appear in the docs
Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20241008165329.45647-1-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Analyzed a few structs in the networking stack by looking at variables
within them that are used in the TCP/IP fast path.
Fast path is defined as TCP path where data is transferred from sender to
receiver unidirectionally. It doesn't include phases other than
TCP_ESTABLISHED, nor does it look at error paths.
We hope to re-organizing variables that span many cachelines whose fast
path variables are also spread out, and this document can help future
developers keep networking fast path cachelines small.
Optimized_cacheline field is computed as
(Fastpath_Bytes/L3_cacheline_size_x86), and not the actual organized
results (see patches to come for these).
Investigation is done on 6.5
Name Struct_Cachelines Cur_fastpath_cache Fastpath_Bytes Optimized_cacheline
tcp_sock 42 (2664 Bytes) 12 396 8
net_device 39 (2240 bytes) 12 234 4
inet_sock 15 (960 bytes) 14 922 14
Inet_connection_sock 22 (1368 bytes) 18 1166 18
Netns_ipv4 (sysctls) 12 (768 bytes) 4 77 2
linux_mib 16 (1060) 6 104 2
Note how there isn't much improvement space for inet_sock and
Inet_connection_sock because sk and icsk_inet respectively takes up so
much of the struct that rest of the variables become a small portion of
the struct size.
So, we decided to reorganize tcp_sock, net_device, netns_ipv4
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Coco Li <lixiaoyan@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
