Solarflare Solarflare XtremeScale series, Руководство пользователя, Страница: 317 / 400

Solarflare Server Adapter User Guide
Solarflare Adapters on FreeBSD
Issue 20 © Solarflare Communications 2017 310
ifconfig_sfxge<n>="inet <IPv4 address> netmask <netmask> lro"
NOTE: LRO should NOT be enabled when using the host to forward packets from
one interface to another. For example, if the host is performing IP routing.
TCP Protocol Tuning
TCP Performance can also be improved by tuning kernel TCP settings. Settings
include adjusting send and receive buffer sizes, connection backlog, congestion
control, etc.
Initial buffering settings should provide good performance. However for certain
applications, tuning buffer settings can significantly benefit throughput. To change
buffer settings, adjust the
tcp_rmem
and
tcp_wmem
using the
sysctl
command:
• Receive buffering:
sysctl net.ipv4.tcp_rmem="<min> <default> <max>"
• Transmit buffering:
sysctl net.ipv4.tcp_wmem="<min> <default> <max>"
(
tcp_rmem
and
tcp_wmem
can also be adjusted for IPV6 and globally with the
net.ipv6 and net.core variable prefixes respectively).
Typically it is sufficient to tune just the max buffer value. It defines the largest size
the buffer can grow to. Suggested alternate values are max=500000 (1/2 Mbyte).
Factors such as link latency, packet loss and CPU cache size all influence the affect of
the max buffer size values. The minimum and default values can be left at their
defaults minimum=4096 and default=87380.
See https://wiki.freebsd.org/NetworkPerformanceTuning for more details.
Receive Side Scaling (RSS)
Solarflare adapters support Receive Side Scaling (RSS). RSS enables packet receive ‐
processing to scale with the number of available CPU cores. RSS requires a platform
that supports MSI ‐ X interrupts.
When RSS is enabled the controller uses multiple receive queues to deliver incoming
packets. The receive queue selected for an incoming packet is chosen to ensure that
packets within a TCP stream are all sent to the same receive queue – this ensures
that packet ‐ ordering within each stream is maintained. Each receive queue has its
own dedicated MSI ‐ X interrupt which ideally should be tied to a dedicated CPU core.
This allows the receive side TCP processing to be distributed amongst the available
CPU cores, providing a considerable performance advantage over a conventional
adapter architecture in which all received packets for a given interface are processed
by just one CPU core.
By default the driver enables RSS and configures one RSS Receive queue per CPU
core. The number of RSS Receive queues is changed using
kenv
to modify the kernel
environment variable
hw.sfxge.<n>.max_rss_channels
. The driver must be
reloaded after the change using the
kldload
command.