net: Add sysctl to toggle early demux for tcp and udp
Certain system process significant unconnected UDP workload.
It would be preferrable to disable UDP early demux for those systems
and enable it for TCP only.
By disabling UDP demux, we see these slight gains on an ARM64 system-
782 -> 788Mbps unconnected single stream UDPv4
633 -> 654Mbps unconnected UDPv4 different sources
The performance impact can change based on CPU architecure and cache
sizes. There will not much difference seen if entire UDP hash table
is in cache.
Both sysctls are enabled by default to preserve existing behavior.
v1->v2: Change function pointer instead of adding conditional as
suggested by Stephen.
v2->v3: Read once in callers to avoid issues due to compiler
optimizations. Also update commit message with the tests.
v3->v4: Store and use read once result instead of querying pointer
again incorrectly.
v4->v5: Refactor to avoid errors due to compilation with IPV6={m,n}
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Suggested-by: Eric Dumazet <edumazet@google.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Tom Herbert <tom@herbertland.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index eaee2c8..b1c6500 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -856,12 +856,21 @@
ip_early_demux - BOOLEAN
Optimize input packet processing down to one demux for
certain kinds of local sockets. Currently we only do this
- for established TCP sockets.
+ for established TCP and connected UDP sockets.
It may add an additional cost for pure routing workloads that
reduces overall throughput, in such case you should disable it.
Default: 1
+tcp_early_demux - BOOLEAN
+ Enable early demux for established TCP sockets.
+ Default: 1
+
+udp_early_demux - BOOLEAN
+ Enable early demux for connected UDP sockets. Disable this if
+ your system could experience more unconnected load.
+ Default: 1
+
icmp_echo_ignore_all - BOOLEAN
If set non-zero, then the kernel will ignore all ICMP ECHO
requests sent to it.