net: increase SOMAXCONN to 4096
Subsystems (4)
PATCH 1/1 net: increase SOMAXCONN to 4096
SOMAXCONN is /proc/sys/net/core/somaxconn default value.
It has been defined as 128 more than 20 years ago.
Since it caps the listen() backlog values, the very small value has caused numerous problems over the years, and many people had to raise it on their hosts after beeing hit by problems.
Google has been using 1024 for at least 15 years, and we increased this to 4096 after TCP listener rework has been completed, more than 4 years ago. We got no complain of this change breaking any legacy application.
Many applications indeed setup a TCP listener with listen(fd, -1); meaning they let the system select the backlog.
Raising SOMAXCONN lowers chance of the port being unavailable under even small SYNFLOOD attack, and reduces possibilities of side channel vulnerabilities.
--- Documentation/networking/ip-sysctl.txt | 4 ++-- include/linux/socket.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-)
Documentation/networking/ip-sysctl.txt +2 -2
@@ -207,8 +207,8 @@ TCP variables: somaxconn - INTEGER Limit of socket listen() backlog, known in userspace as SOMAXCONN. - Defaults to 128. See also tcp_max_syn_backlog for additional tuning - for TCP sockets. + Defaults to 4096. (Was 128 before linux-5.4) + See also tcp_max_syn_backlog for additional tuning for TCP sockets. tcp_abort_on_overflow - BOOLEAN If listening service is too slow to accept new connections,
include/linux/socket.h +1 -1
@@ -263,7 +263,7 @@ struct ucred {#define PF_MAX AF_MAX/* Maximum queue length specifiable by listen. */ -#define SOMAXCONN 128 +#define SOMAXCONN 4096/* Flags we can use with send/ and recv. Added those for 1003.1g not all are supported yet
Signature · 1 line
2.24.0.rc0.303.g954a862665-goog
Quoted 13 lines · Eric Dumazet
SOMAXCONN is
/proc/sys/net/core/somaxconndefault value.It has been defined as 128 more than 20 years ago.
Since it caps the
listen()backlog values, the very small value has caused numerous problems over the years, and many people had to raise it on their hosts after beeing hit by problems.Google has been using 1024 for at least 15 years, and we increased this to 4096 after TCP listener rework has been completed, more than 4 years ago. We got no complain of this change breaking any legacy application.
Quoted 6 lines
Many applications indeed setup a TCP listener with
listen(fd, -1); meaning they let the system select the backlog.Raising SOMAXCONN lowers chance of the port being unavailable under even small SYNFLOOD attack, and reduces possibilities of side channel vulnerabilities.
Just a quick question, I remember that when somaxconn is greater than tcp_max_syn_backlog, SYN cookies are never emitted, but I think it recently changed and there's no such constraint anymore. Do you confirm it's no more needed, or should we also increase this latter one accordingly ?
Willy
Quoted 22 lines · Willy Tarreau
Quoted 13 lines · Eric Dumazet
SOMAXCONN is
/proc/sys/net/core/somaxconndefault value.It has been defined as 128 more than 20 years ago.
Since it caps the
listen()backlog values, the very small value has caused numerous problems over the years, and many people had to raise it on their hosts after beeing hit by problems.Google has been using 1024 for at least 15 years, and we increased this to 4096 after TCP listener rework has been completed, more than 4 years ago. We got no complain of this change breaking any legacy application.
Quoted 6 lines
Many applications indeed setup a TCP listener with
listen(fd, -1); meaning they let the system select the backlog.Raising SOMAXCONN lowers chance of the port being unavailable under even small SYNFLOOD attack, and reduces possibilities of side channel vulnerabilities.
Quoted 6 lines
Just a quick question, I remember that when somaxconn is greater than
tcp_max_syn_backlog, SYN cookies are never emitted, but I think it recently changed and there's no such constraint anymore. Do you confirm it's no more needed, or should we also increase this latter one accordingly ?
There is no relationship like that.
The only place somaxconn is use is in __sys_listen() to cap the user-provided backlog.
somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; if ((unsigned int)backlog > somaxconn)
backlog = somaxconn;
There is a second place in fastopen_queue_tune() but this is not relevant for this discussion.
Quoted 8 lines · Eric Dumazet
Quoted 6 lines · Willy Tarreau
Just a quick question, I remember that when somaxconn is greater than
tcp_max_syn_backlog, SYN cookies are never emitted, but I think it recently changed and there's no such constraint anymore. Do you confirm it's no more needed, or should we also increase this latter one accordingly ?
Quoted 8 lines
There is no relationship like that.
The only place somaxconn is use is in
__sys_listen()to cap the user-provided backlog.somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; if ((unsigned int)backlog > somaxconn)
backlog = somaxconn;
OK, thanks for checking.
Willy
From: Eric Dumazet <[email protected]>
Date: Wed, 30 Oct 2019 09:36:20 -0700
Quoted 13 lines
SOMAXCONN is
/proc/sys/net/core/somaxconndefault value.It has been defined as 128 more than 20 years ago.
Since it caps the
listen()backlog values, the very small value has caused numerous problems over the years, and many people had to raise it on their hosts after beeing hit by problems.Google has been using 1024 for at least 15 years, and we increased this to 4096 after TCP listener rework has been completed, more than 4 years ago. We got no complain of this change breaking any legacy application.
Quoted 8 lines
Many applications indeed setup a TCP listener with
listen(fd, -1); meaning they let the system select the backlog.Raising SOMAXCONN lowers chance of the port being unavailable under even small SYNFLOOD attack, and reduces possibilities of side channel vulnerabilities.
Signed-off-by Eric Dumazet <[email protected]>
Applied.