diff options
author | Eric Dumazet <edumazet@google.com> | 2023-09-11 20:05:31 +0300 |
---|---|---|
committer | Paolo Abeni <pabeni@redhat.com> | 2023-09-12 20:10:01 +0300 |
commit | 133c4c0d37175f510a10fa9bed51e223936073fc (patch) | |
tree | 987f1ac9958a489af0b4bfd4726fb91ce94f028d /Documentation/networking/ip-sysctl.rst | |
parent | 4505dc2a522826975167823f64f0896bac1323fb (diff) | |
download | linux-133c4c0d37175f510a10fa9bed51e223936073fc.tar.xz |
tcp: defer regular ACK while processing socket backlog
This idea came after a particular workload requested
the quickack attribute set on routes, and a performance
drop was noticed for large bulk transfers.
For high throughput flows, it is best to use one cpu
running the user thread issuing socket system calls,
and a separate cpu to process incoming packets from BH context.
(With TSO/GRO, bottleneck is usually the 'user' cpu)
Problem is the user thread can spend a lot of time while holding
the socket lock, forcing BH handler to queue most of incoming
packets in the socket backlog.
Whenever the user thread releases the socket lock, it must first
process all accumulated packets in the backlog, potentially
adding latency spikes. Due to flood mitigation, having too many
packets in the backlog increases chance of unexpected drops.
Backlog processing unfortunately shifts a fair amount of cpu cycles
from the BH cpu to the 'user' cpu, thus reducing max throughput.
This patch takes advantage of the backlog processing,
and the fact that ACK are mostly cumulative.
The idea is to detect we are in the backlog processing
and defer all eligible ACK into a single one,
sent from tcp_release_cb().
This saves cpu cycles on both sides, and network resources.
Performance of a single TCP flow on a 200Gbit NIC:
- Throughput is increased by 20% (100Gbit -> 120Gbit).
- Number of generated ACK per second shrinks from 240,000 to 40,000.
- Number of backlog drops per second shrinks from 230 to 0.
Benchmark context:
- Regular netperf TCP_STREAM (no zerocopy)
- Intel(R) Xeon(R) Platinum 8481C (Saphire Rapids)
- MAX_SKB_FRAGS = 17 (~60KB per GRO packet)
This feature is guarded by a new sysctl, and enabled by default:
/proc/sys/net/ipv4/tcp_backlog_ack_defer
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Dave Taht <dave.taht@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Diffstat (limited to 'Documentation/networking/ip-sysctl.rst')
-rw-r--r-- | Documentation/networking/ip-sysctl.rst | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index a66054d0763a..5bfa1837968c 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -745,6 +745,13 @@ tcp_comp_sack_nr - INTEGER Default : 44 +tcp_backlog_ack_defer - BOOLEAN + If set, user thread processing socket backlog tries sending + one ACK for the whole queue. This helps to avoid potential + long latencies at end of a TCP socket syscall. + + Default : true + tcp_slow_start_after_idle - BOOLEAN If set, provide RFC2861 behavior and time out the congestion window after an idle period. An idle period is defined at |