diff --git a/head/sys/netinet/tcp_output.c b/head/sys/netinet/tcp_output.c
--- a/head/sys/netinet/tcp_output.c
+++ b/head/sys/netinet/tcp_output.c
@@ -130,6 +130,16 @@
&VNET_NAME(tcp_autosndbuf_max), 0,
"Max size of automatic send buffer");
+/*
+ * Make sure that either retransmit or persist
___
freebsd-net@freebsd.org mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "freebsd-net-unsubscr...@freebsd.org"
sepherosa_gmail.com added a comment.
Any comment? I'd like to get this in before 11 code freeze.
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreferences/
To: sepherosa_gmail.com, #network, glebius, adrian, delphij,
sepherosa_gmail.com added a comment.
In https://reviews.freebsd.org/D5872#130813, @lstewart wrote:
> In https://reviews.freebsd.org/D5872#130806, @sepherosa_gmail.com wrote:
>
> > In https://reviews.freebsd.org/D5872#130805, @lstewart wrote:
> >
> > > In https://reviews.freebsd.org
sepherosa_gmail.com updated this revision to Diff 16171.
sepherosa_gmail.com added a comment.
Change if(..) {panic} into assertion and wrap the assertion using macro.
CHANGES SINCE LAST UPDATE
https://reviews.freebsd.org/D5872?vs=15642&id=16171
REVISION DETAIL
https://reviews.freebsd.org/
sepherosa_gmail.com added a comment.
In https://reviews.freebsd.org/D5872#130813, @lstewart wrote:
> In https://reviews.freebsd.org/D5872#130806, @sepherosa_gmail.com wrote:
>
> > In https://reviews.freebsd.org/D5872#130805, @lstewart wrote:
> >
> > > In https://reviews.freebsd.org
lstewart added a comment.
In https://reviews.freebsd.org/D5872#130806, @sepherosa_gmail.com wrote:
> In https://reviews.freebsd.org/D5872#130805, @lstewart wrote:
>
> > In https://reviews.freebsd.org/D5872#130179, @sepherosa_gmail.com wrote:
> >
> > > We probably can leave the cwnd
sepherosa_gmail.com added a comment.
In https://reviews.freebsd.org/D5872#130805, @lstewart wrote:
> In https://reviews.freebsd.org/D5872#130179, @sepherosa_gmail.com wrote:
>
> > We probably can leave the cwnd resetting to later rexmt timeout or
possible later fast retransmit (I thin
lstewart added a comment.
In https://reviews.freebsd.org/D5872#130179, @sepherosa_gmail.com wrote:
> We probably can leave the cwnd resetting to later rexmt timeout or possible
later fast retransmit (I think fast retransmit could kick in under some cases,
if ENOBUFS happened); instead of
sepherosa_gmail.com added inline comments.
INLINE COMMENTS
sys/netinet/tcp_output.c:1551 It's what I am testing w/, since I need
non-INVARIANT kernel to generate enough traffic to make ENOBUFS happen.
We can change it into KASSERT, however, I am wondering should we just use "if
(__predict
jtl added inline comments.
INLINE COMMENTS
sys/netinet/tcp_output.c:1551 In my opinion, this does //not// need to be a
panic. A KASSERT() should be sufficient.
Also, this is not the re-usable macro which Lawrence suggested.
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFER
sepherosa_gmail.com added a comment.
In https://reviews.freebsd.org/D5872#130173, @mike-karels.net wrote:
> I disagree; congestion is congestion, not "congestion for everyone but me".
I'd prefer to leave the cwnd change until it is replaced by something more
modern.
We probably
mike-karels.net added a comment.
I disagree; congestion is congestion, not "congestion for everyone but me".
I'd prefer to leave the cwnd change until it is replaced by something more
modern.
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.freebsd.or
sepherosa_gmail.com added a comment.
In https://reviews.freebsd.org/D5872#128542, @mike-karels.net wrote:
> btw, I think the line to set the snd_cwnd should remain for now, until
something replaces it. ENOBUFS signals local congestion.
Well, resetting the cwnd can be unfair for
sepherosa_gmail.com updated the summary for this revision.
sepherosa_gmail.com updated this revision to Diff 15642.
CHANGES SINCE LAST UPDATE
https://reviews.freebsd.org/D5872?vs=14968&id=15642
REVISION DETAIL
https://reviews.freebsd.org/D5872
AFFECTED FILES
sys/netinet/tcp_output.c
CHANG
lstewart added a comment.
In https://reviews.freebsd.org/D5872#128556, @hiren wrote:
> In https://reviews.freebsd.org/D5872#128555, @lstewart wrote:
>
> > I thought that had been fixed ages ago... oops.
>
>
> Fixed? i.e. doing something other than setting cwnd to 1 seg?
Y
sepherosa_gmail.com added a comment.
In https://reviews.freebsd.org/D5872#128556, @hiren wrote:
> In https://reviews.freebsd.org/D5872#128555, @lstewart wrote:
>
> > I thought that had been fixed ages ago... oops.
>
>
> Fixed? i.e. doing something other than setting cwnd to 1 seg
hiren added a comment.
In https://reviews.freebsd.org/D5872#128555, @lstewart wrote:
> I thought that had been fixed ages ago... oops.
Fixed? i.e. doing something other than setting cwnd to 1 seg?
> It should be calling cc_cong_signal() with a new congestion type.
Hum...
lstewart added a comment.
I thought that had been fixed ages ago... oops. It should be calling
cc_cong_signal() with a new congestion type. Just leave that line as is for the
moment though as Mike says.
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.
sepherosa_gmail.com added a comment.
In https://reviews.freebsd.org/D5872#128542, @mike-karels.net wrote:
> btw, I think the line to set the snd_cwnd should remain for now, until
something replaces it. ENOBUFS signals local congestion.
ok.
REVISION DETAIL
https://reviews.fre
mike-karels.net added a comment.
btw, I think the line to set the snd_cwnd should remain for now, until
something replaces it. ENOBUFS signals local congestion.
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreference
hiren added a comment.
In https://reviews.freebsd.org/D5872#128539, @lstewart wrote:
> ... but replace with a macro to check that the rexmit/persist timer is
armed if appropriate!
Yes, that would be useful!
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
lstewart added a comment.
... but replace with a macro to check that the rexmit/persist timer is armed
if appropriate!
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreferences/
To: sepherosa_gmail.com, network, glebi
hiren added a comment.
Ack for removing ENOBUFs case.
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreferences/
To: sepherosa_gmail.com, network, glebius, adrian, delphij,
decui_microsoft.com, honzhan_microsoft.com,
jtl added a comment.
FWIW, I agree with deleting the ENOBUFs special-case. If we haven't already
set the right timers by here, we have another bug which needs to be fixed.
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/email
sepherosa_gmail.com added a comment.
In https://reviews.freebsd.org/D5872#128535, @gnn wrote:
> Not my comment "once everyone agrees" :-)
heh, just read the first part of the comment :P
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.freebs
gnn added a comment.
Not my comment "once everyone agrees" :-)
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreferences/
To: sepherosa_gmail.com, network, glebius, adrian, delphij,
decui_microsoft.com, honzhan_micros
sepherosa_gmail.com added a comment.
In https://reviews.freebsd.org/D5872#128530, @gnn wrote:
> Let's keep this moving along. Mike isn't (yet) a committer but if someone
can commit this once everyone agrees that would be great.
OK, I will do it.
REVISION DETAIL
https://reviews
gnn added a comment.
Let's keep this moving along. Mike isn't (yet) a committer but if someone
can commit this once everyone agrees that would be great.
REVISION DETAIL
https://reviews.freebsd.org/D5872
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreferences/
To:
29 matches
Mail list logo
