From: Yoshinori Sato [EMAIL PROTECTED]
Date: Wed, 13 Jun 2007 14:59:16 +0900
At Tue, 12 Jun 2007 01:08:55 -0700 (PDT),
David Miller wrote:
2) It is much better to add the appropriate CONFIG_SYSCTL
ifdefs to the INET code than to force it on for everyone.
It examined that, but many
At Tue, 12 Jun 2007 01:08:55 -0700 (PDT),
David Miller wrote:
From: Yoshinori Sato [EMAIL PROTECTED]
Date: Tue, 12 Jun 2007 16:38:55 +0900
It cannot build with CONFIG_SYSCTL=n and CONFIG_INET=y.
In case of CONFIG_INET=y it should become CONFIG_SYSCTL=y.
Signed-off-by: Yoshinori
Hi Jeff,
The following patch adds support for the gigabit ethernet device of PS3.
It was sent out before as RFC, now I submit it for 2.6.23.
Signed-off-by: Masakazu Mokuno [EMAIL PROTECTED]
Signed-off-by: Geoff Levand [EMAIL PROTECTED]
---
drivers/net/Kconfig | 10
drivers/net/Makefile
From: MOKUNO Masakazu [EMAIL PROTECTED]
Date: Wed, 13 Jun 2007 15:58:01 +0900
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -60,6 +60,8 @@ obj-$(CONFIG_TIGON3) += tg3.o
obj-$(CONFIG_BNX2) += bnx2.o
spidernet-y += spider_net.o spider_net_ethtool.o
obj-$(CONFIG_SPIDER_NET) +=
On Wednesday 13 June 2007 10:18, Dhananjay Phadke wrote:
Mithlesh,
You don't initialize max_mc_count anywhere. The multicast address pool
can hold 16 addresses for ports {0,1} and 4 for ports {2,3}. You should
have following line in the probe routine.
adapter-max_mc_count =
From: Bill Fink [EMAIL PROTECTED]
Date: Tue, 12 Jun 2007 23:38:14 -0400
If there was a benefit, perhaps it would be useful to have a
per-route option for setting the initial_ssthresh.
We have this per-route setting already, BIC and CUBIC just override it
with their local initial_ssthresh value
On Tue, Jun 12, 2007 at 08:17:32PM +0200, Jens Axboe ([EMAIL PROTECTED]) wrote:
On Tue, Jun 12 2007, Evgeniy Polyakov wrote:
On Mon, Jun 11, 2007 at 01:59:26PM +0200, Jens Axboe ([EMAIL PROTECTED])
wrote:
Patches are against the #splice branch of the block repo, official url
of that
Hi Dave,
I am splitting this patch to two, to differentiate between readability
changes (plus a bug fix) and optimization changes.
Please review.
Thanks,
- KK
--
I am sorry to miss out during Jamal's original effort to make
- Converted to use switch/case code which looks neater.
- if (ret == NETDEV_TX_LOCKED lockless) is buggy, and the lockless
check should be removed, since driver will return NETDEV_TX_LOCKED only
if lockless is true and driver has to do the locking. In the original
code as well as the
- netif_queue_stopped need not be called inside qdisc_restart as
it has been called already in qdisc_run() before the first skb
is sent, and in __qdisc_run() after each intermediate skb is
sent (note : we are the only sender, so the queue cannot get
stopped while the tx lock was got in
Hi David,
On Wed, 13 Jun 2007 00:03:59 -0700 (PDT)
David Miller [EMAIL PROTECTED] wrote:
From: MOKUNO Masakazu [EMAIL PROTECTED]
Date: Wed, 13 Jun 2007 15:58:01 +0900
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -60,6 +60,8 @@ obj-$(CONFIG_TIGON3) += tg3.o
Am Dienstag, 12. Juni 2007 schrieb Patrick McHardy:
Oliver Neukum wrote:
with 2.6.22-rc4-git2 I am getting errors when setting IP for ethernet
interfaces:
ioctl(4, SIOCSIFADDR, 0x7fff94931600) = -1 ENOBUFS (No buffer space
available)
The error is independant of the interface.
Patrick McHardy wrote:
Pavel Emelianov wrote:
Patrick McHardy wrote:
+ skb-pkt_type = PACKET_HOST;
+ skb-protocol = eth_type_trans(skb, rcv);
+ if (dev-features NETIF_F_NO_CSUM)
+ skb-ip_summed = rcv_priv-ip_summed;
+
+ dst_release(skb-dst);
+ skb-dst = NULL;
+
+
On Tue, Jun 12, 2007 at 01:02:33PM +0200, Jarek Poplawski wrote:
...
Of course such a problem should preferably be fixed by somebody who
knows the code (alas I don't know netconsole), to be sure all needed
cancels are still done after this change. I hope Jason's patch is
right but I'm a little
On 6/13/07, Shani Moideen [EMAIL PROTECTED] wrote:
Replacing alloc_pages(gfp,0) with alloc_page(gfp)
in net/core/pktgen.c
Signed-off-by: Shani Moideen [EMAIL PROTECTED]
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index b92a322..2600c7f 100644
--- a/net/core/pktgen.c
+++
On Mon, May 14, 2007 at 08:58:40AM -0700, Stephen Hemminger wrote:
Kenji Kaneshige found this race between device removal and
registration. On unregister it is possible for the old device to
exist, because sysfs file is still open. A new device with 'eth%d'
will select the same name, but
From: Keiichi KII [EMAIL PROTECTED]
The netconsole is a very useful module for collecting kernel message under
certain circumstances(e.g. disk logging fails, serial port is unavailable).
But current netconsole is not flexible. For example, if you want to change ip
address for logging agent, in
From: Keiichi KII [EMAIL PROTECTED]
This patch contains the following cleanups.
- add __init for initialization functions(option_setup() and
init_netconsole()).
Acked-by: Matt Mackall [EMAIL PROTECTED]
Signed-off-by: Keiichi KII [EMAIL PROTECTED]
Signed-off-by: Takayoshi Kochi [EMAIL
From: Keiichi KII [EMAIL PROTECTED]
This patch contains the following changes for supporting multiple logging
agents.
1. extend netconsole to multiple netpolls
To send kernel messages to multiple logging agents, extend netcosnole
to be able to use multiple netpolls. Each netpoll sends
From: Keiichi KII [EMAIL PROTECTED]
This patch contains the following changes.
create a sysfs entry for netconsole in /sys/class/misc.
This entry has elements related to netconsole as follows.
You can change configuration of netconsole(writable attributes such as IP
address, port number and so
From: Keiichi KII [EMAIL PROTECTED]
We use symbolic link for net_device.
The link in sysfs represents the corresponding network etherdevice.
-+- /sys/class/misc/
|-+- netconsole/
|-+- port1/
| |--- id [r--r--r--] id
| |--- net:net_dev [r--r--r--] net_dev: eth0,eth1,...
| ...
From: Keiichi KII [EMAIL PROTECTED]
This patch contains switch function of netpoll.
If enabled attribute of certain port is '1', this port is used
and the configurations of this port are unable to change.
If enabled attribute of certain port is '0', this port isn't used
and the configurations
From: Keiichi KII [EMAIL PROTECTED]
We add ioctls for adding/removing target.
If we use NETCONSOLE_ADD_TARGET ioctl,
we can dynamically add netconsole target.
If we use NETCONSOLE_REMOVE_TARGET ioctl,
we can dynamically remoe netconsole target.
We attach a sample program for ioctl.
From: Keiichi KII [EMAIL PROTECTED]
update Documentation/networking/netconsole.txt
- how to use sysfs for dynamic configurability
- how to use ioctl for dynamic configurability
Signed-off-by: Keiichi KII [EMAIL PROTECTED]
---
Index: mm/Documentation/networking/netconsole.txt
Pavel Emelianov wrote:
Patrick McHardy wrote:
The question is how to proceed. I haven't read all mails yet, but it
seems there is some disagreement about whether to create all devices
in the same namespace and move them later or create them directly in
The agreement was that we can make
Oliver Neukum wrote:
Am Dienstag, 12. Juni 2007 schrieb Patrick McHardy:
Oliver Neukum wrote:
with 2.6.22-rc4-git2 I am getting errors when setting IP for ethernet
interfaces:
ioctl(4, SIOCSIFADDR, 0x7fff94931600) = -1 ENOBUFS (No buffer space
available)
The error is independant of the
Am Mittwoch, 13. Juni 2007 schrieb Patrick McHardy:
Oliver Neukum wrote:
Am Dienstag, 12. Juni 2007 schrieb Patrick McHardy:
Oliver Neukum wrote:
with 2.6.22-rc4-git2 I am getting errors when setting IP for ethernet
interfaces:
ioctl(4, SIOCSIFADDR, 0x7fff94931600) = -1 ENOBUFS (No
Zhu Yi wrote:
On Tue, 2007-06-12 at 23:17 +0200, Patrick McHardy wrote:
I've hacked up a
small multiqueue simulator device and to my big surprise my testing
showed that Jamal's suggestion of using a single queue state seems to
work better than I expected. But I've been doing mostly testing of
Am Mittwoch, 13. Juni 2007 schrieb Patrick McHardy:
Oliver Neukum wrote:
Am Mittwoch, 13. Juni 2007 schrieb Patrick McHardy:
This can happen if the initial inetdev allocation when the netdevice is
registered fails. I think it would make sense to try to allocate again
when adding addresses
Oliver Neukum wrote:
Am Mittwoch, 13. Juni 2007 schrieb Patrick McHardy:
This can happen if the initial inetdev allocation when the netdevice is
registered fails. I think it would make sense to try to allocate again
when adding addresses in that case, otherwise there is no way of
recovery other
On Wed, 2007-13-06 at 13:56 +0800, Zhu Yi wrote:
The key argument for Jamal's solution is the NIC will send out 32
packets in the full PHL in a reasonably short time (a few microsecs per
Jamal's calculation). But for wireless, the PHL hardware has low
probability to seize the wireless medium
Patrick McHardy wrote:
Marco Berizzi wrote:
Hello everybody.
I have just upgraded from 2.6.21.3 to
2.6.22-rc4 and I get a ton of
pmtu discovery on sa esp/blablab/blabla
messages (this box is running openswan).
Is this an expected behaviour?
We have some MTU opimiztations in
Marco Berizzi wrote:
Patrick McHardy wrote:
We have some MTU opimiztations in 2.6.22-rc that might be related.
Please check with tcpdump what exactly is happening and whether
the 2.6.22-rc box is sending too large packets.
I have done a tcpdump capture on the external
interface but I
On Wed, 13 Jun 2007, psr wrote:
On 6/13/07, Shani Moideen [EMAIL PROTECTED] wrote:
Replacing alloc_pages(gfp,0) with alloc_page(gfp)
in net/core/pktgen.c
Signed-off-by: Shani Moideen [EMAIL PROTECTED]
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index
jamal writes:
The key arguement i make (from day one actually) is to leave the
majority of the work to the driver.
My view of wireless WMM etc is it is a different media behavior
(compared to wired ethernet) which means a different view of strategy
for when it opens the valve to allow
Patrick McHardy wrote:
Marco Berizzi wrote:
Patrick McHardy wrote:
We have some MTU opimiztations in 2.6.22-rc that might be related.
Please check with tcpdump what exactly is happening and whether
the 2.6.22-rc box is sending too large packets.
I have done a tcpdump capture on the
Wow - Robert in the house, I cant resist i have to say something before
i run out;-
On Wed, 2007-13-06 at 15:12 +0200, Robert Olsson wrote:
Haven't got all details. IMO we need to support some bonding-like
scenario too. Where one CPU is feeding just one TX-ring. (and TX-buffers
cleared
On Tue, 2007-06-12 at 21:54 -0400, Jeff Garzik wrote:
Michael Ellerman wrote:
Linas posted the patches, I responded querying whether the bug fixes
should go into 2.6.22, and then you told him you need to order your bug
fixes first in the queue. Which seemed pretty clear to me that you'd
On 6/13/07, Robert P. J. Day [EMAIL PROTECTED] wrote:
[snip]
Does this makes any difference anyway? Both are same eventually?
What is the rational behind this? Can you please help me
understanding this?
since this is one of the TO DO items i added to the list of things at
the wiki:
On Wed, Jun 13, 2007 at 07:25:55PM +0900, Keiichi KII wrote:
From: Keiichi KII [EMAIL PROTECTED]
This patch contains the following cleanups.
- add __init for initialization functions(option_setup() and
init_netconsole()).
Acked-by: Matt Mackall [EMAIL PROTECTED]
Signed-off-by:
Hi all,
I've been doing a bit of investigation work into a problem that I've
been experiencing with the latest available r8168 driver from realtek
('r8168-8.001.00') linux kernel 2.6.21.1.
I have been experiencing wierd problems with slow outbound traffic that
seem to go away if there's
-Original Message-
From: J Hadi Salim [mailto:[EMAIL PROTECTED] On Behalf Of jamal
For the Leonid-NIC (for lack of better name) it may be harder to do
parallelization on rcv if you use what i said above. But you could
use a different model on receive - such as create a single
Hi Keiichi,
On 6/13/07, Keiichi KII [EMAIL PROTECTED] wrote:
+struct netconsole_target {
+ struct list_head list;
+ int id;
+ struct netpoll np;
+};
+
+static LIST_HEAD(target_list);
+static DEFINE_SPINLOCK(target_list_lock);
Some description of the struct netconsole_target
Patrick McHardy wrote:
Pavel Emelianov wrote:
Patrick McHardy wrote:
The question is how to proceed. I haven't read all mails yet, but it
seems there is some disagreement about whether to create all devices
in the same namespace and move them later or create them directly in
The agreement
Pavel Emelianov wrote:
Patrick McHardy wrote:
I'm going to push my latest patches to Dave today, the easiest way is
probably is you just add whatever you need to the API afterwards.
OK. Dave didn't object against the driver. Hope he will accept it as well.
I have also found a BUG in
Hi,
On 6/13/07, Keiichi KII [EMAIL PROTECTED] wrote:
From: Keiichi KII [EMAIL PROTECTED]
This patch contains the following changes.
create a sysfs entry for netconsole in /sys/class/misc.
This entry has elements related to netconsole as follows.
You can change configuration of
On Tue, Jun 12, 2007 at 08:04:18PM -0400, Jeff Garzik wrote:
Should I just drop all spidernet patches and start over?
No. Apply the series I just sent you, dropping the one called
patch 6/15, the one from Florin Malita, as it appears you'd
previously picked this up. The rest of the
On Sat, 2007-06-09 at 20:21 +0400, Vitaly Bordug wrote:
device_bind_driver() error code returning has been fixed.
release() function has been written, so that to free resources
in correct way; the release path is now clean.
Before the rework, it used to cause
Device '[EMAIL PROTECTED]:1'
jamal writes:
I think the one described by Leonid has not just 8 tx/rx rings but also
a separate register set, MSI binding etc iirc. The only shared resources
as far as i understood Leonid are the bus and the ethernet wire.
AFAIK most new NIC will look like this...
I still lack a
On Wed, 13 Jun 2007 12:45:21 +0300
Dan Aloni [EMAIL PROTECTED] wrote:
On Mon, May 14, 2007 at 08:58:40AM -0700, Stephen Hemminger wrote:
Kenji Kaneshige found this race between device removal and
registration. On unregister it is possible for the old device to
exist, because sysfs file is
I'm starting to wonder how a multi-queue NIC differs from a bunch of
bonded single-queue NICs, and if there is leverage opportunity there.
rick jones
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
Hi,
On 6/13/07, Keiichi KII [EMAIL PROTECTED] wrote:
[...]
+static DECLARE_MUTEX(netdev_change_sem);
The preferred style these days is to use a DEFINE_MUTEX
(and the struct mutex primitives) for such locks that are used
as binary semaphores.
BTW, a comment here to note what this lock
Hi Dave,
these are the updated rtnl_link API patches and dummy, ifb and VLAN
conversions. The documentation is not quite done yet, I'll finish
it when I find some spare time.
Changes since the last post:
- fix attribute parsing after module load
- fix module aliases
- refuse all unsupported
[RTNETLINK]: Split up rtnl_setlink
Split up rtnl_setlink into a function performing validation and a function
performing the actual changes. This allows to share the modifcation logic
with rtnl_newlink, which is introduced by the next patch.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
[DUMMY]: Use dev-stats
Use dev-stats instead of netdev_priv().
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit af03e9fd45eb64f27bcc2ac79d0d615e563100a9
tree 9a1aa56016d17805dd2b41e955fbb41d46d9c3f5
parent 8a4171f86c516a43a7ed07f198c6cad2273ce2a7
author Patrick McHardy [EMAIL
[RTNETLINK]: Link creation API
Add rtnetlink API for creating, changing and deleting software devices.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit 8a4171f86c516a43a7ed07f198c6cad2273ce2a7
tree 6bab9e96dd04c4ea13654fcda6a402a20a4f43c1
parent
[DUMMY]: Keep dummy devices on list
Use a list instead of an array to allow creating new devices.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit 18094391f33349687e35eaf0e768b18a71523100
tree 8697434fd6ce5c2d16b4e823482ba9cf7ee8cea2
parent af03e9fd45eb64f27bcc2ac79d0d615e563100a9
[DUMMY]: Use rtnl_link API
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit 379884fb0587cd4832ecf8785467209885204124
tree 8bce1ffae7d2b2afabba9bc5ab2c7b06402c51c1
parent 18094391f33349687e35eaf0e768b18a71523100
author Patrick McHardy [EMAIL PROTECTED] Wed, 06 Jun 2007 14:46:12 +0200
[IFB]: Use rtnl_link API
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit 7cd41b2caa4f124f84d6f458fe913de8e3b492a3
tree c62fa740c7e41ab388da72b67a4e4538ad97eda7
parent cfbc876235237d990af80b7fc396f4458b5a1657
author Patrick McHardy [EMAIL PROTECTED] Wed, 06 Jun 2007 14:46:22 +0200
[IFB]: Keep ifb devices on list
Use a list instead of an array to allow creating new devices.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit cfbc876235237d990af80b7fc396f4458b5a1657
tree 1ebce533598ae9220b8e3edef269bd4f054961e7
parent 379884fb0587cd4832ecf8785467209885204124
author
[VLAN]: Convert name-based configuration functions to struct netdevice *
Move the device lookup and checks to the ioctl handler under the RTNL and
change all name-based interfaces to take a struct net_device * instead.
This allows to use them from a netlink interface, which identifies devices
[VLAN]: Move device registation to seperate function
Move device registration and configuration of the underlying device to a
seperate function.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit 0bd5a42a938a42aa15a4e9ac01777d74653e7c8d
tree e7ddfd00b19f52f1e04ad955fa3e4037485e0cdc
[VLAN]: Split up device checks
Move the checks of the underlying device to a seperate function.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit 8defb0af6d2f31cfa6180b0b4c83124f5d90cb32
tree a460163ea31c953a60b894a24051deee5f401006
parent db130c75de212df303702758f553a7f4349ae56a
[VLAN]: Move vlan_group allocation to seperate function
Move group allocation to a seperate function to clean up the code a bit
and allocate groups before registering the device. Device registration
is globally visible and causes netlink events, so we shouldn't fail
afterwards.
Signed-off-by:
[VLAN]: Move some device intialization code to dev-init callback
Move some device initialization code to new dev-init callback to make
it shareable with netlink. Additionally this fixes a minor bug, dev-iflink
is set after registration, which causes an incorrect value in the initial
netlink
[VLAN]: Return proper error codes in register_vlan_device
The returned device is unused, return proper error codes instead and avoid
having the ioctl handler guess the error.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit 5924a55528b3a6897ea49f4af9fa7dcefc50fd57
tree
[VLAN]: Use 32 bit value for skb-priority mapping
skb-priority has only 32 bits and even VLAN uses 32 bit values in its API.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit a285e1ab7cfb856fc9e503eefd507eb7958b7524
tree 0f95eb6c73eedc66a305bb0ca5cd1ee1391b47d3
parent
[VLAN]: Keep track of number of QoS mappings
Keep track of the number of configured ingress/egress QoS mappings to
avoid iteration while calculating the netlink attribute size.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit fc3fa5f1275ec357ae719066eef18c51c186c2b9
tree
[VLAN]: Introduce symbolic constants for flag values
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit 84bb1e021b6c3567bebccfc5e3dd4ab7d8f5bfae
tree 74f71648d2821cc86765694a7d41d94b39bffce4
parent fc3fa5f1275ec357ae719066eef18c51c186c2b9
author Patrick McHardy [EMAIL PROTECTED] Wed, 13
[VLAN]: Use rtnl_link API
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit b4bb367897c114980367013f1a636bb6a9630a11
tree 8f1904816e27d07df5a7a910dc1e81a08215b490
parent 84bb1e021b6c3567bebccfc5e3dd4ab7d8f5bfae
author Patrick McHardy [EMAIL PROTECTED] Wed, 06 Jun 2007 14:47:07 +0200
Hi,
I was testing 2.6.22-rc4 from yesterday,
but communication speed of 8139 side is very slower
than 2.6.21.* (less than 10kbytes/sec at
100MBPS,FULL-DUPLEX).
I was not test from 2.6.22-rc ,yesterday I started to test 2.6.22-rc.
So, I *must* set HALF-DUPLEX to 8139 side below:
ethtool -s
Hi Stephen,
these patches add support for the rtnl_link stuff and VLAN configuration
to iproute. Since the old link configuration was entirely ioctl based and
mixing the two would be really ugly, this patch keeps the old ioctl stuff
guarded by an ifdef (defaults to enabled) and probes for support
[IPROUTE]: iplink: use netlink for link configuration
Add support for using netlink for link configuration. Kernel-support is
probed, when not available it falls back to using ioctls.
Signed-off-by: Patrick McHardy [EMAIL PROTECTED]
---
commit 4feb48d12295eb41850c39996f3a8c1dd7909ed5
tree
[IPROUTE]: VLAN support
---
commit 90727b2bf5b4a7ef9d0638ca80206083b965a0b5
tree 173722acd855b7fe1eb1a5f22cf7706814f72c8f
parent 4feb48d12295eb41850c39996f3a8c1dd7909ed5
author Patrick McHardy [EMAIL PROTECTED] Wed, 13 Jun 2007 18:46:21 +0200
committer Patrick McHardy [EMAIL PROTECTED] Wed, 13
Hi Keiichi,
On 6/13/07, Keiichi KII [EMAIL PROTECTED] wrote:
From: Keiichi KII [EMAIL PROTECTED]
This patch contains switch function of netpoll.
If enabled attribute of certain port is '1', this port is used
and the configurations of this port are unable to change.
If enabled attribute of
Kyuma Ohta wrote:
Hi,
I was testing 2.6.22-rc4 from yesterday,
but communication speed of 8139 side is very slower
than 2.6.21.* (less than 10kbytes/sec at
100MBPS,FULL-DUPLEX).
I was not test from 2.6.22-rc ,yesterday I started to test 2.6.22-rc.
So, I *must* set HALF-DUPLEX to 8139 side
Hi,
On 6/13/07, Keiichi KII [EMAIL PROTECTED] wrote:
From: Keiichi KII [EMAIL PROTECTED]
update Documentation/networking/netconsole.txt
- how to use sysfs for dynamic configurability
- how to use ioctl for dynamic configurability
Signed-off-by: Keiichi KII [EMAIL PROTECTED]
Ah, so here
Remove the initial slow start override from TCP cubic.
The old code caused Cubic to start out in slow start mode, which
is less agressive but caused slow performance.
The administrator can override initial slow start threshold on any
TCP congestion control method via the TCP route metrics.
On Wed, 13 Jun 2007 19:02:32 +0200 (MEST)
Patrick McHardy [EMAIL PROTECTED] wrote:
Hi Stephen,
these patches add support for the rtnl_link stuff and VLAN configuration
to iproute. Since the old link configuration was entirely ioctl based and
mixing the two would be really ugly, this patch
- netif_queue_stopped need not be called inside qdisc_restart as
it has been called already in qdisc_run() before the first skb
is sent, and in __qdisc_run() after each intermediate skb is
sent (note : we are the only sender, so the queue cannot get
stopped while the tx lock was got
Stephen Hemminger wrote:
On Wed, 13 Jun 2007 19:02:32 +0200 (MEST)
Patrick McHardy [EMAIL PROTECTED] wrote:
Please apply, thanks.
I'm putting out a new iproute2 next week. IF this is in mainline, it will
go in then. If not, then there will be a development branch
Thanks. The first
From: jamal [EMAIL PROTECTED]
Date: Wed, 13 Jun 2007 09:33:22 -0400
So in such a case (assuming 8 rings), One model is creating 4 netdev
devices each based on single tx/rx ring and register set and then
having a mother netdev (what you call the bond) that feeds these
children netdev based on
From: jamal [EMAIL PROTECTED]
Date: Wed, 13 Jun 2007 09:33:22 -0400
So in such a case (assuming 8 rings), One model is creating
4 netdev
devices each based on single tx/rx ring and register set and then
having a mother netdev (what you call the bond) that feeds these
children
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Wed, 13 Jun 2007 10:27:18 -0700
Please make patches against my net-2.6 tree, I already
made changes in this area.
Remove the initial slow start override from TCP cubic.
The old code caused Cubic to start out in slow start mode, which
is less
Use the 'sundance' driver that's been in the kernel for quite a while.
Er... that driver specifically does not list the IP1000's PCI device ID
(13f0:1023), nor does it support anything over 100 Mbit/s.
Are you *quite* sure that adding 13f0:1023 to the sundance_pci_tbl is
all that's required?
-
On Wed, 13 Jun 2007 11:26:52 -0700 (PDT)
David Miller [EMAIL PROTECTED] wrote:
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Wed, 13 Jun 2007 10:27:18 -0700
Please make patches against my net-2.6 tree, I already
made changes in this area.
Remove the initial slow start override from
PJ Waskiewicz wrote:
diff --git a/net/sched/sch_generic.c
b/net/sched/sch_generic.c index
f28bb2d..b9dc2a6 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -123,7 +123,8 @@ static inline int qdisc_restart(struct
net_device *dev)
/* And
On 12 Jun 2007 21:56:38 -0400
[EMAIL PROTECTED] wrote:
It kind of surprised me that sending 254 arp packets by using the arp-scan
tool (http://www.nta-monitor.com/tools/arp-scan/) on a /24 consistently
triggers a burst of eth0: excessive work at interrupt.
This is a 600 MHz PIII,
Michael Ellerman wrote:
I was just
keen to see the major bugfixes get into 22, rather than waiting
another few months for 23.
Agreed.
Jeff
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Wed, 13 Jun 2007 11:31:49 -0700
Maybe it is time to remove BIC?
I don't see any compelling reason, the same could be said
of the other experimental protocols we include in the tree.
-
To unsubscribe from this list: send the line unsubscribe netdev
Linas Vepstas wrote:
git branch shows that I'm on upstream. So I performed a git pull
(without any additional arguments) assuming that it would sync to your
upstream branch. And so my email was based on this.
Some googling seems to show that git pull has a bug/feature of
ignoring the branch
As of this moment there are -no- spidernet patches in netdev. I just
rebased 'upstream', and dropped the existing spidernet patches.
Jeff
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
I wish there was a git option to just make my shit look like the
remote, dammit! The above is the easiest way I know how to do that.
git-fetch -f remote:local ?
Segher
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More
Segher Boessenkool wrote:
I wish there was a git option to just make my shit look like the
remote, dammit! The above is the easiest way I know how to do that.
git-fetch -f remote:local ?
If that works... great :) Much better than what I described.
Jeff
-
To unsubscribe from
Hi again,
Ok, so sysfs_create_link() would be illegal from inside spin_lock_irqsave(),
and this is why we have to use the dual-list mechanism to react to the net
device rename. This isn't so obvious, a comment at the point where you
declare modify_target_list would be nice? (BTW temporary_list
Bryan Wu wrote:
From: Wu, Bryan [EMAIL PROTECTED]
This patch implements the driver necessary use the Analog Devices
Blackfin processor's on-chip ethernet MAC controller.
Signed-off-by: Bryan Wu [EMAIL PROTECTED]
Cc: Jeff Garzik [EMAIL PROTECTED]
Signed-off-by: Andrew Morton [EMAIL PROTECTED]
Stephen Hemminger wrote:
The code for checksum is more complex than needed when dealing with VLAN's;
the higher layers already pass down the location of the IP header.
Compile tested only, no hardware available.
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
Ron, do you ACK patch #2 and
Bill Nottingham wrote:
Recent gcc versions emit warnings when unsigned variables are compared 0 or
= 0.
Signed-off-by: Bill Nottingham [EMAIL PROTECTED]
---
mlx4/qp.c |3 +--
netxen/netxen_nic_niu.c |6 +++---
tulip/de2104x.c |1 -
3 files changed, 4
Divy Le Ray wrote:
From: Divy Le Ray [EMAIL PROTECTED]
Streamline sge page management.
Fix dma mappings when buffers are recycled.
Signed-off-by: Divy Le Ray [EMAIL PROTECTED]
---
drivers/net/cxgb3/adapter.h | 38 ++--
drivers/net/cxgb3/sge.c | 423
Thomas Klein wrote:
This patch fixes several whitespace issues.
Signed-off-by: Thomas Klein [EMAIL PROTECTED]
Patch is obviously OK, but needs rediffing since I had to apply fixes
before cleanups (standard patch ordering)
-
To unsubscribe from this list: send the line unsubscribe netdev
1 - 100 of 147 matches
Mail list logo
