d/freebsd-skq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update to reflect the fact that net.inet.tcp.rfc1323 is on by default.

Browse Source
This commit is contained in:
Jonathan Lemon 2001-09-17 03:49:51 +00:00
parent a4c7cc9f12
commit 0d5d2695c0
1 changed files with 7 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
share/man/man7/tuning.7
View File

@ -313,18 +313,14 @@ bandwidth limitations in order to ensure that they are not charged for
using too much bandwidth.
.Pp
Setting the send or receive TCP buffer to values larger then 65535 will result
in a marginal performance improvement at best due to limitations within
the TCP protocol itself.
These limitations can prevent certain types of network links (specifically,
gigabit WAN links and high-latency satellite links) from reaching
their maximum level of performance. For such cases we first recommend that
you simply set the TCP buffer size to 65535 and stick with that if the
performance is acceptable. In extreme cases you may have to turn on the
in a marginal performance improvement unless both hosts support the window
scaling extension of the TCP protocol, which is controlled by the
.Em net.inet.tcp.rfc1323
sysctl and increase the buffer size to values greater then 65535. This option
turns on the window sizing extension to the TCP protocol. We do not recommend
that you use this option unless you absolutely have to because many hosts on
the internet can't handle the feature and may cause connections to freeze up.
sysctl.
These extensions should be enabled and the TCP buffer size should be set
to a value larger than 65536 in order to obtain good performance out of
certain types of network links; specifically, gigabit WAN links and
high-latency satellite links.
.Pp
We recommend that you turn on (set to 1) and leave on the
.Em net.inet.tcp.always_keepalive