Nice way to see what congestion control modules are loaded.
It does impose a soft limit of 32 possibilities.
Signed-off-by: Stephen Hemminger <[EMAIL PROTECTED]>
---
include/linux/sysctl.h |1 +
include/net/tcp.h |3 +++
net/ipv4/sysctl_net_ipv4.c | 25
How about another way of controlling this via sysctl.
First, add code to for read only:
/proc/sys/net/ipv4/tcp_available_congestion_control (or shorter name)
this will show all things compiled in (even if not loaded yet). Similar
to /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_f
Applied, thanks.
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
tsk, tsk:
fatal: 7 lines add trailing whitespaces.
applied to for-2.6.19 anyway, thanks.
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
On 10/28/06, David Miller <[EMAIL PROTECTED]> wrote:
Please stop all of this cross posting. I've just seen you post
this same exact email on the netfilter lists too.
Sorry
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More ma
From: Stephen Hemminger <[EMAIL PROTECTED]>
Date: Fri, 27 Oct 2006 15:21:49 -0700
> The restricted flag patch which you have ignored, would be a way to
> allow them to be configured but tag the "bad apples" for only
> root usage.
I haven't ignored it, it's in my backlog below more important
thing
On Fri, 27 Oct 2006 15:12:38 -0700 (PDT)
David Miller <[EMAIL PROTECTED]> wrote:
> From: Stephen Hemminger <[EMAIL PROTECTED]>
> Date: Fri, 27 Oct 2006 14:59:13 -0700
>
> > On Fri, 27 Oct 2006 14:37:01 -0700 (PDT)
> > David Miller <[EMAIL PROTECTED]> wrote:
> >
> > > From: Stephen Hemminger <[EM
From: Stephen Hemminger <[EMAIL PROTECTED]>
Date: Fri, 27 Oct 2006 14:59:13 -0700
> On Fri, 27 Oct 2006 14:37:01 -0700 (PDT)
> David Miller <[EMAIL PROTECTED]> wrote:
>
> > From: Stephen Hemminger <[EMAIL PROTECTED]>
> > Date: Fri, 27 Oct 2006 14:24:02 -0700
> >
> > > Only some (very few) have a
Please stop all of this cross posting. I've just seen you post
this same exact email on the netfilter lists too.
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, 27 Oct 2006 14:37:01 -0700 (PDT)
David Miller <[EMAIL PROTECTED]> wrote:
> From: Stephen Hemminger <[EMAIL PROTECTED]>
> Date: Fri, 27 Oct 2006 14:24:02 -0700
>
> > Only some (very few) have any bad consequences. So the typical
> > distribution should be able to switch with most available
Hello,
I'd like to find/gather estimates about 2.4 vs 2.6 share in [small]
linux routers in 2006. Can anyone offer estimates and/or references ?
My own estimate is that definite majority is 2.4 (I'd say >75% for 2.4),
in small linux routers in 2006. Can anyone offer support or correction ?
Whi
Hello,
I'd like to find/gather estimates about 2.4 vs 2.6 share in [small]
linux routers in 2006. Can anyone offer estimates and/or references ?
My own estimate is that definite majority is 2.4 (I'd say >75% for 2.4),
in small linux routers in 2006. Can anyone offer support or correction ?
Whi
From: Stephen Hemminger <[EMAIL PROTECTED]>
Date: Fri, 27 Oct 2006 14:24:02 -0700
> Only some (very few) have any bad consequences. So the typical
> distribution should be able to switch with most available for everyone,
> and only a few needing special privileges.
I would strongly disagree as we
On Fri, 27 Oct 2006 14:17:49 -0700 (PDT)
David Miller <[EMAIL PROTECTED]> wrote:
> From: Stephen Hemminger <[EMAIL PROTECTED]>
> Date: Fri, 27 Oct 2006 10:30:16 -0700
>
> > My proposed method restricting TCP choices to fair algorithms.
> > This a net wide, not system wide issue, it should not be
From: Stephen Hemminger <[EMAIL PROTECTED]>
Date: Fri, 27 Oct 2006 07:41:02 -0700
> Please no, it makes the socket option useless.
> If you want to tag some "bad apples" thats okay, but would need
> some more infrastructure.
The behavior of the TCP stack is a system wide decision.
If anything it
From: Stephen Hemminger <[EMAIL PROTECTED]>
Date: Fri, 27 Oct 2006 10:30:16 -0700
> My proposed method restricting TCP choices to fair algorithms.
> This a net wide, not system wide issue, it should not be done
> by kernel policy choice (capability), but by a build choice.
I think this sucks even
On Fri, Oct 27, 2006 at 07:35:18AM -0400, Ananda Raju wrote:
> Looking at all scenarios I feel the first patch is OK. Can you add the
> watchdog timer fix to first initial patch and resubmit.
Appended below.
> So -- just for grins, I thought to myself, "Maybe I can make
> s2io be the first adap
On Tue, 2006-10-17 at 03:19 +0300, Ville Nuorvala wrote:
> As the IPv6 route lookup now also returns the selected source address
> there is no need for a separate source address lookup. In fact, the
> source address selection needs to be moved to get_dst() because the
> selected IPv6 source address
If application asks for a congestion control type with setsockopt()
then it may be available as a module not included in the kernel already.
If it has permission to load modules then the tcp congestion
module should be autoloaded if needed. This is done already when
the default selection is chan
On Fri, 27 Oct 2006 10:56:45 -0700
Roland Dreier <[EMAIL PROTECTED]> wrote:
> > I don't think the userspace stuff belongs on netdev. Someone please
> > correct me if I'm wrong.
>
> Yeah, it's not a bad thing to get wider review, but your userspace
> library is pretty much your business. If you
Here is an alternative that allows runtime based restriction on some
TCP congestion control choices.
Signed-off-by: Stephen Hemminger <[EMAIL PROTECTED]>
---
include/net/tcp.h |1 +
net/ipv4/tcp_cong.c |4
2 files changed, 5 insertions(+)
--- sky2.orig/include/net/tcp.h 2006-10-
> I don't think the userspace stuff belongs on netdev. Someone please
> correct me if I'm wrong.
Yeah, it's not a bad thing to get wider review, but your userspace
library is pretty much your business. If you screw it up it doesn't
hurt anyone else, so I'm happy to let you write it however you
I think "unfair" is a difficult word. Unfair to what? It's true that
Scalable TCP is unfair to itself in that flows with unequal shares do
not converge, but it's not clear what its interactions are with other
congestion control algorithms. It's not clear to me that it's
significantly more un
On Fri, 27 Oct 2006 19:22:11 +0200
Michael Prokop <[EMAIL PROTECTED]> wrote:
> User-Agent: mutt-ng devel-r316 (Debian)
>
> Hello,
added.
--
Stephen Hemminger <[EMAIL PROTECTED]>
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
Mo
My proposed method restricting TCP choices to fair algorithms.
This a net wide, not system wide issue, it should not be done
by kernel policy choice (capability), but by a build choice.
--- sky2.orig/net/ipv4/Kconfig 2006-10-27 10:10:47.0 -0700
+++ sky2/net/ipv4/Kconfig 2006-10-27 1
The sky2 driver is no longer in experimental state.
Signed-off-by: Stephen Hemminger <[EMAIL PROTECTED]>
--- sky2.orig/drivers/net/Kconfig 2006-10-27 10:16:44.0 -0700
+++ sky2/drivers/net/Kconfig2006-10-27 10:20:20.0 -0700
@@ -2112,7 +2112,7 @@
config SKY2
tri
Hello,
another manpage, this time for rtmon. Would be great if it could be
applied to the next release too.
regards,
-mika-
--
,'"`. http://www.michael-prokop.at/
( grml.org -ยป Linux Live-CD for texttool-users and sysadmins
`._,' http://www.grml.org/
.TH RTMON 8
.SH NAME
rtmon
On Fri, Oct 27, 2006 at 08:10:01PM +0400, Evgeniy Polyakov ([EMAIL PROTECTED])
wrote:
>
> Generic event handling mechanism.
>
> Consider for inclusion.
>
> Changes from 'take20' patchset:
> * new ring buffer implementation
Test userspace application can be found in archive on project's
homepa
Socket notifications.
This patch includes socket send/recv/accept notifications.
Using trivial web server based on kevent and this features
instead of epoll it's performance increased more than noticebly.
More details about various benchmarks and server itself
(evserver_kevent.c) can be found on
Generic event handling mechanism.
Consider for inclusion.
Changes from 'take20' patchset:
* new ring buffer implementation
* removed artificial limit on possible number of kevents
With this release and fixed userspace web server it was possible to
achive 3960+ req/s with client connection rat
Timer notifications.
Timer notifications can be used for fine grained per-process time
management, since interval timers are very inconvenient to use,
and they are limited.
This subsystem uses high-resolution timers.
id.raw[0] is used as number of seconds
id.raw[1] is used as number of nanosec
Core files.
This patch includes core kevent files:
* userspace controlling
* kernelspace interfaces
* initialization
* notification state machines
Some bits of documentation can be found on project's homepage (and links from
there):
http://tservice.net.ru/~s0mbre/old/?section=projects&item=
poll/select() notifications.
This patch includes generic poll/select notifications.
kevent_poll works simialr to epoll and has the same issues (callback
is invoked not from internal state machine of the caller, but through
process awake, a lot of allocations and so on).
Signed-off-by: Evgeniy Po
Hagen Paul Pfeifer wrote:
* Stephen Hemminger | 2006-10-27 07:41:02 [-0700]:
Please no, it makes the socket option useless.
Technical no, in the sense of usability for everybody yes. You are right
Stephen, as a programmer I understand you complete!
But on the other side: We know for
* Stephen Hemminger | 2006-10-27 07:41:02 [-0700]:
>Please no, it makes the socket option useless.
Technical no, in the sense of usability for everybody yes. You are right
Stephen, as a programmer I understand you complete!
But on the other side: We know for sure that this IS a problem if we all
[...snip...]
> +extern void set_interface(
> +UINT32ip_addr,
These should probably be the standard linux types u32, or uint32
> +UINT32mask,
> +UINT32bcastaddr,
> +
Matthew Wilcox wrote:
On Thu, Oct 26, 2006 at 01:04:32PM -0700, Auke Kok wrote:
no objections, so I'll ACK it with the notion that I'm going to let our
labs do some more testing on it with all the latest changes to it.
Thanks, Auke. Here's the equivalent patch for e1000. I don't have a
conve
On Thu, 26 Oct 2006, Glenn Grundstrom wrote:
> diff -ruNp old/drivers/infiniband/hw/nes/Makefile
> new/drivers/infiniband/hw/nes/Makefile
> --- old/drivers/infiniband/hw/nes/Makefile1969-12-31
> 18:00:00.0 -0600
> +++ new/drivers/infiniband/hw/nes/Makefile2006-10-25
> 11:10:26.00
On Fri, 27 Oct 2006 12:43:11 +0200
Hagen Paul Pfeifer <[EMAIL PROTECTED]> wrote:
> * David Miller | 2006-10-26 17:02:21 [-0700]:
>
> >Your email client turned the tabs into spaces in the patch making it
> >useless.
>
> Sorry my mistake! I am en route and I paste the patch into my editor, who eat
Looking at all scenarios I feel the first patch is OK. Can you add the
watchdog timer fix to first initial patch and resubmit.
-Original Message-
From: Linas Vepstas [mailto:[EMAIL PROTECTED]
Sent: Thursday, October 26, 2006 3:52 PM
To: Ananda Raju
Cc: Wen Xiong; linux-kernel@vger.kernel
Andrew Morton <[EMAIL PROTECTED]> wrote on 27.10.2006 05:13:13:
> On Wed, 25 Oct 2006 13:11:42 +0200
> Jan-Bernd Themann <[EMAIL PROTECTED]> wrote:
>
> > This patch fixes kzalloc parameters (GFP_ATOMIC instead of GFP_KERNEL)
>
> why?
these few kcallocs run in atomic context in some situations.
* David Miller | 2006-10-26 17:02:21 [-0700]:
>Your email client turned the tabs into spaces in the patch making it
>useless.
Sorry my mistake! I am en route and I paste the patch into my editor, who eat
all tabs. One more time: sorry!
Check if user has CAP_NET_ADMIN capability to change
conges
[ ... ]
Dmitry Mishin wrote:
Stephen,
Virtualized container can be secure, if it is complete system virtualization,
not just an application container. OpenVZ implements such and it is used hard
over the world. And of course, we care a lot to keep hostile root from
killing whole system.
Op
On Thursday 26 October 2006 19:56, Stephen Hemminger wrote:
> On Thu, 26 Oct 2006 11:44:55 +0200
>
> Daniel Lezcano <[EMAIL PROTECTED]> wrote:
> > Stephen Hemminger wrote:
> > > On Wed, 25 Oct 2006 17:51:28 +0200
> > >
> > > Daniel Lezcano <[EMAIL PROTECTED]> wrote:
> > >>Hi Stephen,
> > >>
> > >>c
44 matches
Mail list logo
