Differential D52872

tcp: bump max snd buffer size for autoscaling
AcceptedPublic
Actions

Authored by tuexen on Thu, Oct 2, 7:30 PM.

Tags

None

Referenced Files

	F131971911: D52872.diff
	Sun, Oct 12, 3:02 PM

	Unknown Object (File)
	Sat, Oct 11, 3:28 PM

	Unknown Object (File)
	Thu, Oct 9, 11:56 AM

	Unknown Object (File)
	Thu, Oct 9, 11:55 AM

	Unknown Object (File)
	Thu, Oct 9, 11:40 AM

	Unknown Object (File)
	Fri, Oct 3, 8:21 AM

	Unknown Object (File)
	Thu, Oct 2, 10:39 PM

	Unknown Object (File)
	Thu, Oct 2, 9:53 PM

View All 11 Files

Subscribers

Details

Reviewers

rgrimes
rscheff
cc
glebius
nickbanks_netflix.com
peter.lei_ieee.org
lstewart
jtl
thj
rrs

Group Reviewers

Summary

Bump it to 16 MB to allow higher throughput with default configurations.

Diff Detail

Repository

rG FreeBSD src repository

Lint

Lint Skipped

Unit

Tests Skipped

Event Timeline

tuexen created this revision.Thu, Oct 2, 7:30 PM

Herald added a reviewer: transport. · View Herald TranscriptThu, Oct 2, 7:30 PM

Herald added subscribers: melifaro, imp. · View Herald Transcript

tuexen requested review of this revision.Thu, Oct 2, 7:30 PM

nickbanks_netflix.com accepted this revision.Thu, Oct 2, 7:39 PM

This revision is now accepted and ready to land.Thu, Oct 2, 7:39 PM

glebius accepted this revision.Thu, Oct 2, 7:50 PM

cc accepted this revision.Thu, Oct 2, 7:52 PM

tuexen retitled this revision from tcp: bump max rcv buffer size for autoscaling to tcp: bump max snd buffer size for autoscaling.Thu, Oct 2, 7:57 PM

Is this worthy of a release note?

In D52872#1207881, @jtl wrote:

Is this worthy of a release note?

Yes, the combination of D52871, D52872, and D52873.

In D52872#1207896, @tuexen wrote:

In D52872#1207881, @jtl wrote:

Is this worthy of a release note?

Yes, the combination of D52871, D52872, and D52873.

Why not combine all three into one commit/review? IMO, the concerns are roughly the same with all three. (And, to repeat what I've said elsewhere: "My main concern about these three revisions is that they are somewhat susceptible of remote manipulation, and that could make it easier to DoS a server. However, I view that as a tradeoff that the user needs to make, and think an appropriate release note should suffice to warn about these issues."

thj accepted this revision.Fri, Oct 3, 6:39 AM

rscheff accepted this revision.Fri, Oct 3, 10:19 AM

peter.lei_ieee.org accepted this revision.Fri, Oct 3, 7:01 PM

rrs accepted this revision.Sat, Oct 4, 12:29 PM

Revision Contents
Changeset List

Path

Size

sys/

netinet/

2 lines

Diff 163382

sys/netinet/tcp_output.c

Loading...