From: [EMAIL PROTECTED]
Date: Thu, 10 Nov 2005 15:15:10 -0800
Simplify the TCP congestion infrastructure. Can fold the
packets acked into the cong_avoid hook.
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
This patch would break at least BIC.
Before this change, the good_ack
From: [EMAIL PROTECTED]
Date: Thu, 10 Nov 2005 15:15:11 -0800
Move all the code that does linear TCP slowstart to one
inline function to ease later patch to add ABC support.
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
Applied, but one question about this hunk.
---
From: [EMAIL PROTECTED]
Date: Thu, 10 Nov 2005 15:15:12 -0800
This is an updated version of the RFC3465 ABC patch originally
for Linux 2.6.11-rc4 by Yee-Ting Li. ABC is a way of counting
bytes ack'd rather than packets when updating congestion control.
The orignal ABC described in the RFC
From: [EMAIL PROTECTED]
Date: Thu, 10 Nov 2005 15:15:13 -0800
Specifically it addresses the problem of an interaction between rcvbuf
moderation (receiver autotuning) and rcv_ssthresh. The problem occurs when
sending small packets to a receiver with a larger MTU. (A very common case I
have
From: [EMAIL PROTECTED]
Date: Thu, 10 Nov 2005 15:15:14 -0800
Minor spelling fixes for TCP code.
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
Applied, thanks.
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More majordomo
From: [EMAIL PROTECTED]
Date: Thu, 10 Nov 2005 15:15:15 -0800
Use hits to speed up the SACK processing. Various forms
of this have been used by TCP developers (Web100, STCP, BIC)
to avoid the 2x linear search of outstanding segments.
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
From: Patrick McHardy [EMAIL PROTECTED]
Date: Fri, 11 Nov 2005 04:18:52 +0100
This is the latest set patches for netfilter IPsec support.
The use of netif_rx for the innermost SA if it used transport
mode has been replaced by explicit NF_HOOK calls in
xfrm{4,6}_input.c.
Note that I consider
From: Jeff Garzik [EMAIL PROTECTED]
Date: Fri, 11 Nov 2005 04:43:47 -0500
Recent TCP changes broke the build.
Signed-off-by: Jeff Garzik [EMAIL PROTECTED]
Thanks for catching this Jeff.
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Fri, 11 Nov 2005 10:40:42 -0800
Are you sure that removing those last two lines are correct?
Maybe this code is trying to influence the congestion window
validation engine by updating snd_cwnd_stamp like that. And
are we sure that the snd_cwnd
From: Sridhar Samudrala [EMAIL PROTECTED]
Date: Fri, 11 Nov 2005 14:00:40 -0800
Please pull the following SCTP updates from
master.kernel.org:/pub/scm/linux/kernel/git/sridhar/lksctp-2.6.git
I can't pull this cleanly into Linus's current tree, there
are some file level conflicts:
[EMAIL
From: Ingo Oeser [EMAIL PROTECTED]
Date: Fri, 11 Nov 2005 16:33:07 +0100
Are you sure, that you don't mean just rtt_sample(sk, tcp_usrtt(skb)); here?
I always believed that function pointers used like I proposed above.
Both methods of invoking a function via function pointer work
the same:
From: Sridhar Samudrala [EMAIL PROTECTED]
Date: Fri, 11 Nov 2005 15:01:42 -0800
On Fri, 2005-11-11 at 14:13 -0800, David S. Miller wrote:
[EMAIL PROTECTED]:~/src/GIT/sctp-2.6$ git pull
master.kernel.org:/pub/scm/linux/kernel/git/sridhar/lksctp-2.6.git
[EMAIL PROTECTED]'s password
From: Sridhar Samudrala [EMAIL PROTECTED]
Date: Fri, 11 Nov 2005 15:01:42 -0800
I think it is much easier for me to send the patches as attachments
rather than re-applying on a new tree. So i am attaching the 4 patches
and hope this works for you.
Actually, there are no Signed-off-by: lines
From: Sridhar Samudrala [EMAIL PROTECTED]
Date: Fri, 11 Nov 2005 15:21:03 -0800
On Fri, 2005-11-11 at 15:08 -0800, David S. Miller wrote:
From: Sridhar Samudrala [EMAIL PROTECTED]
Date: Fri, 11 Nov 2005 15:01:42 -0800
I think it is much easier for me to send the patches as attachments
From: Herbert Xu [EMAIL PROTECTED]
Date: Sat, 12 Nov 2005 15:15:49 +1100
The recent change to netlink dump done callback handling broke IPv6
which played dirty tricks with the done callback. This causes an
infinite loop during a dump.
The following patch fixes it.
This bug was reported
From: Harald Welte [EMAIL PROTECTED]
Date: Sat, 12 Nov 2005 11:39:18 +0100
[NETFILTER] {ip,nf}_conntrack TCP: Accept SYN+PUSH like SYN
Some devices (e.g. Qlogic iSCSI HBA hardware like QLA4010 up to firmware
3.0.0.4) initiates TCP with SYN and PUSH flags set.
The Linux TCP/IP stack deals
From: Thomas Graf [EMAIL PROTECTED]
Date: Sat, 12 Nov 2005 12:55:13 +0100
Signed-off-by: Thomas Graf [EMAIL PROTECTED]
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
From: Harald Welte [EMAIL PROTECTED]
Date: Sun, 13 Nov 2005 22:51:59 +0100
[NETFILTER] nf_conntrack: Add missing code to TCP conntrack module
Looks like the nf_conntrack TCP code was slightly mismerged: it does
not contain an else branch present in the IPv4 version. Let's add that
code and
From: Harald Welte [EMAIL PROTECTED]
Date: Sun, 13 Nov 2005 22:51:59 +0100
[NETFILTER] nfnetlink: unconditionally require CAP_NET_ADMIN
This patch unconditionally requires CAP_NET_ADMIN for all nfnetlink
mesages. It also removes the per-message cap_required field, since all
existing
From: David S. Miller [EMAIL PROTECTED]
Date: Mon, 14 Nov 2005 21:39:22 -0800 (PST)
From: Matt Mackall [EMAIL PROTECTED]
Date: Mon, 14 Nov 2005 21:23:58 -0800
What is packet split in this context?
It's a mode of buffering used by the e1000 driver.
BTW, the issue is that in packet split
From: YOSHIFUJI Hideaki [EMAIL PROTECTED]
Date: Tue, 15 Nov 2005 10:22:37 +0900 (JST)
In article [EMAIL PROTECTED] (at Mon, 14 Nov 2005 18:42:30 +0800), Yan
Zheng [EMAIL PROTECTED] says:
The score.rule++ doesn't make any sense for me.
According to codes above, I think it should be
From: David Monro [EMAIL PROTECTED]
Date: Mon, 14 Nov 2005 13:02:42 +1030
I don't know if it just needs to be told not to calulate the checksums
for v6 packets, or what.
It generates a generic checksum calculation on all packets,
similarly to the Sun GEM chip, which ought to be totally
From: Matt Mackall [EMAIL PROTECTED]
Date: Mon, 14 Nov 2005 22:29:47 -0800
Can we make any assumptions about the size and position of fragments.
For instance, will the first N data bytes of a UDP packet all be in
the same fragment?
Nope, they can be fragmented any way possible.
For packet
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Tue, 15 Nov 2005 15:09:52 -0800
More spelling fixes. From Joe Perches
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
Applied.
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Tue, 15 Nov 2005 16:29:40 -0800
161.30.105.72.ftp-data 192.168.128.101.32792: . ack 1 win 64000
192.168.128.101.32792 161.30.105.72.ftp-data: . 1:1381(1380) ack 1 win 5840
192.168.128.101.32792 161.30.105.72.ftp-data: . 1381:2761(1380) ack 1
From: Harald Welte [EMAIL PROTECTED]
Date: Tue, 15 Nov 2005 17:16:09 +0100
[NETFILTER] Remove nf_conntrack stat proc file when cleaning up
Fix nf_conntrack statistics proc file removal. Looks like the old bug
was forward-ported from ip_conntrack. :-]
Signed-off-by: KOVACS Krisztian [EMAIL
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Thu, 17 Nov 2005 13:01:01 -0800
There is a compile error that crept in with the last patch of
TCP patches.
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
There is no use of pkts_acked nor data_acked in that
hstcp_cong_avoid() function, so
From: Harald Welte [EMAIL PROTECTED]
Date: Tue, 15 Nov 2005 11:03:51 +0100
[NETFILTER] ip_conntrack: fix ftp/irc/tftp helpers on ports = 32768
Since we've converted the ftp/irc/tftp helpers to use the new
module_parm_array() some time ago, we ware accidentially using signed data
types -
From: Olaf Rempel [EMAIL PROTECTED]
Date: Tue, 15 Nov 2005 23:15:31 +0100
On Tue, 15 Nov 2005 22:53:19 +0100
Olaf Rempel [EMAIL PROTECTED] wrote:
gnaa, typo.
should be br not br0
Your patch won't apply anyways because your email client
changes tab characters into spaces. Please fix up the
: large integer implicitly truncated to
unsigned type
Thanks for the report, I've fixed it like so:
diff-tree 381998241fd1fc635596f4e8ae835f0d64ca1ba2 (from
2fce76afdb067fa3e7f8ee33c9fe366bd65887ea)
Author: David S. Miller [EMAIL PROTECTED]
Date: Thu Nov 17 15:17:42 2005 -0800
[LLC]: Fix
From: Andrea Bittau [EMAIL PROTECTED]
Date: Fri, 18 Nov 2005 21:48:47 +
From: Andrea Bittau [EMAIL PROTECTED]
If two packets were queued to be sent at the same time in the future, their
order would be reversed. This would occur because the queue is traversed back
to front, and a
From: Eric Dumazet [EMAIL PROTECTED]
Date: Thu, 17 Nov 2005 16:21:45 +0100
It should probably use vfree() like :
+ for_each_cpu(cpu) {
+ if (info-size = PAGE_SIZE)
+ kfree(info-entries[cpu]);
+ else
+ vfree(info-entries[cpu]);
From: Ingo Oeser [EMAIL PROTECTED]
Date: Tue, 18 Apr 2006 18:29:59 +0200
But shouldn't we put this kind of hairy manipulation into some nice
functions? Driver writers were already confused by all that size,
len and truesize stuff, as this bug showed.
It's 2 lines and frankly it's a bit
From: Herbert Xu [EMAIL PROTECTED]
Date: Tue, 18 Apr 2006 22:32:04 +1000
You're absolutely right about there being a problem with the TSO packet
trimming code. The cause of this lies in the tcp_fragment() function.
When we allocate a fragment for a completely non-linear packet the
truesize
From: Herbert Xu [EMAIL PROTECTED]
Date: Tue, 18 Apr 2006 16:54:48 +1000
Looking at this again, the root of this problem is the IGMPv3
patch which started using the skb-nh.iph-protocol as a key.
So what we really should do is make the protocol an explicit parameter
to the ip_route_input
From: Alexey Kuznetsov [EMAIL PROTECTED]
Date: Wed, 19 Apr 2006 03:52:22 +0400
Actually, this weird case in inet_get_route() is the only place, where
a dummy skb is used and it is needed mostly to resolve multicast routes.
In this case this fake skb really passes through all the engine, even
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Wed, 19 Apr 2006 09:53:48 -0700
Please put this in the next -stable load...
I already sent it to -stable.
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
From: Christian Borntraeger [EMAIL PROTECTED]
Date: Wed, 19 Apr 2006 12:45:48 +0200
As spinlock debugging still does not work with the qeth driver I
want to pick up the discussion.
Does something like the patch below work?
But this all begs the question, what happens if you want to
dig into
From: Hua Zhong [EMAIL PROTECTED]
Date: Wed, 19 Apr 2006 12:01:06 -0700
There is a missing initialization of err in sockfd_lookup_light() that could
return random error for an invalid file handle.
Signed-off-by: Hua Zhong [EMAIL PROTECTED]
Applied, thanks a lot for this bug fix.
-
To
this:
diff-tree 5185db09f46ed64d520d09db6e93852e44106628 (from
3672558c6180ca28a7aa46765702467a37e58fc5)
Author: David S. Miller [EMAIL PROTECTED]
Date: Wed Apr 19 15:37:13 2006 -0700
[LLC]: Use pskb_trim_rcsum() in llc_fixup_skb().
Kernel Bugzilla #6409
If we use plain skb_trim
Morton [EMAIL PROTECTED]
Signed-off-by: David S. Miller [EMAIL PROTECTED]
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 66bd932..84b9af7 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -824,9 +824,9 @@ static int
From: James Morris [EMAIL PROTECTED]
Date: Sun, 16 Apr 2006 01:10:50 -0400 (EDT)
So, I propose to introduce a secmark field (per the patch below), which is
only present when enabled as a sub-feature of LSM. That is, it does not
have any effect at all for the default kernel. As an integer
From: Andrew Morton [EMAIL PROTECTED]
Date: Wed, 19 Apr 2006 15:59:25 -0700
David S. Miller [EMAIL PROTECTED] wrote:
An earlier variant of your patch was applied already, included below.
You'll need to submit the newer parts relative to the current tree.
This is a similar-but-different
From: Herbert Xu [EMAIL PROTECTED]
Date: Thu, 20 Apr 2006 13:26:02 +1000
On Thu, Apr 20, 2006 at 11:01:11AM +1000, herbert wrote:
Hi Dave:
Since sk_stream_alloc_pskb takes an extra argument that accounts for
paged data all we need to do to account sk_buff overhead correctly
is to use
Herbert what do you think of this?
I know it might be better to check this right where we
make the manipulations, but this catch-all trap at the
end points seems to make sense and will catch other kinds
of errors.
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index
From: jamal [EMAIL PROTECTED]
Date: Thu, 20 Apr 2006 06:58:45 -0400
On Fri, 2006-14-04 at 15:05 -0700, David S. Miller wrote:
From: jamal [EMAIL PROTECTED]
Date: Thu, 13 Apr 2006 09:00:08 -0400
There is dependency on the previous patch i sent since the issue that
patch fixes
[ Maybe ask questions like this on netdev where the networking
developers hang out? Added to CC: ]
Van fell off the face of the planet after giving his presentation and
never published his code, only his slides.
I've started to make a slow attempt at implementing his ideas, nothing
but pure
From: Mike Christie [EMAIL PROTECTED]
Date: Thu, 20 Apr 2006 14:29:06 -0500
I was wondering if it is ok to pass sendpage high mem pages. If a piece
of code does this:
struct socket *sock;
sock-ops-sendpage(pg...)
and pg is a highmem page will the network layer do the right thing or
From: Andrew Grover [EMAIL PROTECTED]
Date: Thu, 20 Apr 2006 15:14:15 -0700
First obviously it's a technology for RX CPU improvement so there's no
benefit on TX workloads. Second it depends on there being buffers to
copy the data into *before* the data arrives. This happens to be the
case for
From: Olof Johansson [EMAIL PROTECTED]
Date: Thu, 20 Apr 2006 18:33:43 -0500
On Thu, Apr 20, 2006 at 03:14:15PM -0700, Andrew Grover wrote:
In
addition, there may be workloads (file serving? backup?) where we
could do a skb-page-in-page-cache copy and avoid cache pollution?
Yes, NFS is
From: Rick Jones [EMAIL PROTECTED]
Date: Thu, 20 Apr 2006 18:00:37 -0700
Actually, that brings-up a question - presently, and for reasons that
are lost to me in the mists of time - netperf will access the buffer
before it calls recv(). I'm wondering if that should be changed to an
access
From: Olof Johansson [EMAIL PROTECTED]
Date: Thu, 20 Apr 2006 22:04:26 -0500
On Thu, Apr 20, 2006 at 05:27:42PM -0700, David S. Miller wrote:
Besides the control overhead of the DMA engines, the biggest thing
lost in my opinion is the perfect cache warming that a cpu based copy
does from
From: Ingo Oeser [EMAIL PROTECTED]
Date: Sun, 23 Apr 2006 02:05:32 +0200
On Saturday, 22. April 2006 15:49, Jörn Engel wrote:
That was another main point, yes. And the endpoints should be as
little burden on the bottlenecks as possible. One bottleneck is the
receive interrupt, which
From: Jörn Engel [EMAIL PROTECTED]
Date: Sat, 22 Apr 2006 13:48:46 +0200
Unless I completely misunderstand something, one of the main points of
the netchannels if to have *zero* fields written to by both producer
and consumer. Receiving and sending a lot can be expected to be the
common
From: bert hubert [EMAIL PROTECTED]
Date: Sat, 22 Apr 2006 21:30:24 +0200
On Thu, Apr 20, 2006 at 12:09:55PM -0700, David S. Miller wrote:
Going all the way to the socket is a large endeavor and will require a
lot of restructuring to do it right, so expect this to take on the
order
From: Ingo Oeser [EMAIL PROTECTED]
Date: Sat, 22 Apr 2006 15:29:58 +0200
On Saturday, 22. April 2006 13:48, Jörn Engel wrote:
Unless I completely misunderstand something, one of the main points of
the netchannels if to have *zero* fields written to by both producer
and consumer.
Hmm,
From: Herbert Xu [EMAIL PROTECTED]
Date: Sat, 22 Apr 2006 15:22:54 +1000
Jeff Garzik [EMAIL PROTECTED] wrote:
05/10: [PATCH] Update truesize with the length of the packet for
packet split
These 10 patches look OK, but since the current kernel version is
From: Ingo Oeser [EMAIL PROTECTED]
Date: Fri, 21 Apr 2006 18:52:47 +0200
nice to see you getting started with it.
Thanks for reviewing.
I'm not sure about the queue logic there.
1867 /* Caller must have exclusive producer access to the netchannel. */
1868 int netchannel_enqueue(struct
From: Andi Kleen [EMAIL PROTECTED]
Date: Tue, 25 Apr 2006 09:43:49 +0200
On Tuesday 25 April 2006 09:31, John Que wrote:
Hello,
What is the right way to determine on which interface card
(eth0 or eth1) will a packet be sent (according to the dest IP)?
You can send a rtnetlink
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Tue, 25 Apr 2006 10:01:49 -0700
# Hit# miss Function:[EMAIL PROTECTED]
! 0 50505 tcp_transmit_skb():net/ipv4/[EMAIL PROTECTED]
...
How about just taking off the likely/unlikely in this case.
Why remove it when we'll now
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Tue, 25 Apr 2006 15:16:35 -0700
On Tue, 25 Apr 2006 14:46:49 -0700 (PDT)
David S. Miller [EMAIL PROTECTED] wrote:
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Tue, 25 Apr 2006 10:01:49 -0700
# Hit# miss Function:[EMAIL
From: Kok, Auke [EMAIL PROTECTED]
Date: Tue, 25 Apr 2006 23:12:30 -0700
This patch was already merged in Jeff Garzik's netdev upstream branch but
needs to go into 12.6.16.y and 2.6.17rc* as it fixes a critical buffersize
skb bug that is exposed by an earlier patch by Dave Miller and Herbert
From: Kelly Daly [EMAIL PROTECTED]
Date: Wed, 26 Apr 2006 11:47:34 +
Noting Dave's recent release of his implementation, we thought we'd
better get this out there so we can do some early
comparison/combining and come up with the best possible
implementation.
Thanks for publishing your
Ok I have comments already just glancing at the initial patch.
With the 32-bit descriptors in the channel, you indeed end up
with a fixed sized pool with a lot of hard-to-finesse sizing
and lookup problems to solve.
So what I wanted to do was finesse the entire issue by simply
side-stepping it
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Tue, 25 Apr 2006 11:08:12 -0700
Need to allow for VLAN header when bridging.
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
Applied, thanks Stephen.
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message
From: Hua Zhong [EMAIL PROTECTED]
Date: Mon, 24 Apr 2006 16:25:39 -0700
Hi,
I am developing a profiling tool to check if likely/unlikely usages are wise.
I find that the following one is always a miss:
# Hit# miss Function:[EMAIL PROTECTED]
! 0 50505
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Mon, 24 Apr 2006 15:23:41 -0700
This follows after the earlier two patches.
Change the initialization of the class device portion of the net device
to be done earlier, so that any races before registration completes are
harmless. Add a mutex
From: Caitlin Bestler [EMAIL PROTECTED]
Date: Wed, 26 Apr 2006 09:57:22 -0700
The major element I liked about Kelly's approach is that the ring
is clearly designed to allow a NIC to place packets directly into
a ring that is directly accessible by the user. Evolutionary steps
are good, but
From: John Heffner [EMAIL PROTECTED]
Date: Tue, 25 Apr 2006 10:27:37 -0400
Yours is the first complaint of this kind I recall seeing, but I've
expected for a while someone would have this type of problem. RFC2861
seems conceptually nice at first, but there are a few things about it
that
From: Rick Jones [EMAIL PROTECTED]
Date: Wed, 26 Apr 2006 15:16:18 -0700
BTW, is the RFC 2681? I looked that one up on ietf.org and the RFC by
that number was a different beast entirely - at least at a very quick
glance.
Congestion window validation is the correct RFC.
-
To unsubscribe
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Wed, 26 Apr 2006 10:45:21 -0700
+struct brifinfo {
+ __u8state;
+ __u32 cost;
+};
+
Maybe put the __u32 first and explicitly pad out the 3
bytes after the __u8? Just to be safe.
I know you use an assignment initializer, so your
From: Caitlin Bestler [EMAIL PROTECTED]
Date: Wed, 26 Apr 2006 15:53:44 -0700
The netchannel qualifiers should only deal with TCP packets
for established connections. Listens would continue to be
dealt with by the existing stack logic, vj_channelizing
only occurring when the the connection
From: James Morris [EMAIL PROTECTED]
Date: Thu, 27 Apr 2006 00:58:41 -0400 (EDT)
On Thu, 27 Apr 2006, Rusty Russell wrote:
netfilter (similarly raw sockets, bonding, divert). Or, we could delay
LOCAL_IN hook processing until we get to socket receive.
This an idea proposed for skfilter
From: Evgeniy Polyakov [EMAIL PROTECTED]
Date: Thu, 27 Apr 2006 15:51:26 +0400
There are some caveats here found while developing zero-copy sniffer
[1]. Project's goal was to remap skbs into userspace in real-time.
While absolute numbers (posted to netdev@) were really high, it is only
From: John Heffner [EMAIL PROTECTED]
Date: Thu, 27 Apr 2006 13:47:33 -0400
(Most OS's don't do 2861, and it is not a standard.)
Are you so sure? Doing cwnd timeout largely predates the congestion
window validation work, in fact by several years.
In RFC 2581, it mentions Van Jacobson's
From: Auke Kok [EMAIL PROTECTED]
Date: Thu, 27 Apr 2006 18:54:28 -0700
Dave Jones wrote:
With 2.6.17-rc3, my E1000 won't get a dhcp lease.
Looking at tcpdump and ifconfig output, it's easy to see why.
It's recieving packets, but the packets transmitted field
of ifconfig never increases.
From: Evgeniy Polyakov [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 10:10:54 +0400
On Thu, Apr 27, 2006 at 02:12:09PM -0700, Caitlin Bestler ([EMAIL PROTECTED])
wrote:
So the real issue is when there is an intelligent device that
uses hardware packet classification to place the packet in
the
From: Evgeniy Polyakov [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 11:32:16 +0400
Definitely, userspace application must be very smart to deal with
ip/tcp/option headers...
That is why we will put an offset+len in the ring so they need not
parse the packet headers.
-
To unsubscribe from this
From: Shaun Pereira [EMAIL PROTECTED]
Date: Thu, 20 Apr 2006 15:03:23 +1000
From: [EMAIL PROTECTED]
When the sk_timer function x25_heartbeat_expiry() is called by the kernel
in a running/terminating process, spinlock-recursion and spinlock-lockup
locks up the kernel.
This has happened
From: Evgeniy Polyakov [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 20:12:21 +0400
If there is dataflow, not flow of packets or flow of data with holes,
it could be possible to modify recv() to just return the right pointer,
so in theory userspace modifications would be minimal.
With copy in
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 10:18:33 -0700
Please just use existing AIO interface.
I totally disagree, the existing AIO interface is garbage.
We need new APIs to do this right, to get the ring buffer
and the zero-copy'ness correct.
-
To unsubscribe from
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 10:22:40 -0700
The following one line fix is needed to make loss function of
netem work right when doing loss on the local host.
Otherwise, higher layers just recover.
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
From: Evgeniy Polyakov [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 21:25:36 +0400
The more complex userspace interface we create the less users it will
have. It is completely unconvenient to read 100 bytes and receive only
80, since 20 were eaten by header.
These bytes are charged to socket
From: Evgeniy Polyakov [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 21:55:39 +0400
On Fri, Apr 28, 2006 at 10:41:18AM -0700, Stephen Hemminger ([EMAIL
PROTECTED]) wrote:
Second, introducing
kevents, seems unnecessary and hasn't been accepted in the mainline.
kevent was never sent to lkml@
From: Rusty Russell [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 18:24:08 +1000
Note that the problem space AFAICT includes strange advanced routing
setups, ingress qos and possibly others, not just netfilter. But
perhaps the same solutions apply, so I'll concentrate on nf.
Yes, this hasn't been
From: Evgeniy Polyakov [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 23:59:30 +0400
kevent can be used as poll without any changes to the socket code.
There are two types of network related kevents - socket events
(recv/send/accept) and network aio, which can be turned completely off
in config.
From: Herbert Xu [EMAIL PROTECTED]
Date: Thu, 27 Apr 2006 21:56:45 +1000
I was looking through the xfrm input/output code in order to abstract
out the address family specific encapsulation/decapsulation code. During
that process I found this bug in the IP ID selection code in xfrm4_output.c.
From: Hua Zhong [EMAIL PROTECTED]
Date: Wed, 26 Apr 2006 09:50:28 -0700 (PDT)
[I hope this time it's OK - I'm sending from pine/Linux]
It adds an extra space in the diff lines which corrupts
the patch.
I've applied this by hand, but please try to get something
which works before providing new
From: Rusty Russell [EMAIL PROTECTED]
Date: Sat, 29 Apr 2006 08:04:04 +1000
You're still thinking you can bypass classifiers for established
sockets, but I really don't think you can. I think the simplest
solution is to effectively remove from (or flag) the established
listening hashes
From: Rusty Russell [EMAIL PROTECTED]
Date: Sat, 29 Apr 2006 08:17:01 +1000
On Fri, 2006-04-28 at 10:55 -0700, Caitlin Bestler wrote:
vj_netchannels represent a strategy of minimizing
registration/pinning costs even if it means paying for an extra copy.
Because the extra copy is closely
From: YOSHIFUJI Hideaki [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 02:04:56 +0900 (JST)
We eliminated rt6_dflt_lock (to protect default router pointer)
at 2.6.17-rc1, and introduced rt6_select() for general router selection.
The function is called in the context of rt6_lock read-lock held,
but
From: Michael Chan [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 16:35:35 -0700
Do the full chip reset when changing MAC address if ASF is enabled.
ASF sometimes uses a different MAC address than the driver. Without
the reset, the ASF MAC address may be overwritten when the driver's
MAC address
From: Michael Chan [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 16:36:08 -0700
Add a reset_phy parameter to tg3_reset_hw() and tg3_init_hw(). With
the full chip reset during MAC address change, the automatic PHY reset
during chip reset will cause a link down and bonding will not work
properly as
From: Michael Chan [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 16:36:21 -0700
Fix bug in nvram write function. If the starting nvram address offset
happens to be the last dword of the page, the NVRAM_CMD_LAST bit will
not get set in the existing code. This patch fixes the bug by changing
the
From: Michael Chan [EMAIL PROTECTED]
Date: Fri, 28 Apr 2006 16:36:30 -0700
Update version to 3.57.
Signed-off-by: Michael Chan [EMAIL PROTECTED]
Applied.
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
At least for the TG3PCI_MEM_WIN_DATA register, I don't know how safe
it is to use tw32_f() there. Reads from a location can have side
effects, so doing a forced readback after a write could be dangerous.
And it isn't needed, as the tw32_f() done as we set the
TG3PCI_MEM_WIN_BASE_ADDR back to
From: Bernard Pidoux [EMAIL PROTECTED]
Date: Sun, 30 Apr 2006 21:34:32 +0200
Ralf Baechle wrote :
Convert all NET/ROM sysctl time values from jiffies to ms as units.
Signed-off-by: Ralf Baechle [EMAIL PROTECTED]
With such extensive patches for netrom and rose modules that will go
Ralf, I have all of your patches queued up, I'll review them
and merge them in soon.
Thanks a lot.
-
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
From: Andi Kleen [EMAIL PROTECTED]
Date: Tue, 2 May 2006 18:02:43 +0200
On Tuesday 02 May 2006 18:19, Just Marc wrote:
I thought that maybe it's time to either set TCP_DEBUG to 0 or
alternatively allow an admin to toggle the printing of this message
off/on? On a few busy web servers
I don't think we should be defining driver APIs when we haven't even
figured out how the core of it would even work yet.
A key part of this is the netfilter bits, that will require
non-trivial flow identification, a hash will simply not be enough, and
it will not be allowed to not support the
301 - 400 of 1167 matches
Mail list logo