Hi Ben,
From: Ben Greear gree...@candelatech.com
This saves us constantly allocating large, multi-page
skbs. It should fix the order-1 allocation errors reported,
and in a 60-vif scenario, this significantly decreases CPU
utilization, and latency, and increases bandwidth.
This patch adds error vector magnitude collection to AR9001 and
AR9002, as well as my best attempt at making sense of what the EVM
numbers actually mean. There was an obvious problem with the
AR_RxEVMn macros (parts of status4 were being used for rssi, and all
of status4 was also being used for
On Fri, 2011-01-07 at 12:12 -0800, Luis R. Rodriguez wrote:
On Thu, Jan 06, 2011 at 08:49:12PM -0800, gree...@candelatech.com wrote:
From: Ben Greear gree...@candelatech.com
The stations hold the ath_node, which holds the tid
and other xmit logic structures. In order to debug
stuck
On Fri, 2011-01-07 at 14:46 -0800, Ben Greear wrote:
On 01/07/2011 02:26 PM, Eric Dumazet wrote:
Le vendredi 07 janvier 2011 à 14:20 -0800, Ben Greear a écrit :
On 0
Using skb_copy() is wrong then, since it makes a copy (order-1
allocations)
It should use :
skb_alloc(
On Sun, Jan 9, 2011 at 2:06 AM, Ben Greear gree...@candelatech.com wrote:
On 01/08/2011 04:41 PM, Felix Fietkau wrote:
On 2011-01-08 5:36 PM, Ben Greear wrote:
On 01/08/2011 04:20 PM, Felix Fietkau wrote:
I think this should be dependent on packet size, maybe even based on the
On 2011-01-09 7:15 AM, Björn Smedman wrote:
I think we should also consider the added stability/saneness with this
patch. I for one would be willing to live with some extra cpu load if
that means the unstoppable rx dma problem can be contained (all the
time).
I don't think this patch has
On 2011-01-09 1:07 AM, Brian Prodoehl wrote:
This patch adds error vector magnitude collection to AR9001 and
AR9002, as well as my best attempt at making sense of what the EVM
numbers actually mean. There was an obvious problem with the
AR_RxEVMn macros (parts of status4 were being used for
2011/1/9 Felix Fietkau n...@openwrt.org:
On 2011-01-09 7:15 AM, Björn Smedman wrote:
I think we should also consider the added stability/saneness with this
patch. I for one would be willing to live with some extra cpu load if
that means the unstoppable rx dma problem can be contained (all the
On 01/09/2011 12:00 AM, Gabor Juhos wrote:
Hi Ben,
From: Ben Greeargree...@candelatech.com
This saves us constantly allocating large, multi-page
skbs. It should fix the order-1 allocation errors reported,
and in a 60-vif scenario, this significantly decreases CPU
utilization, and latency,
On Jan 9, 2011 10:20 AM, Felix Fietkau n...@openwrt.org wrote:
On 2011-01-09 1:07 AM, Brian Prodoehl wrote:
This patch adds error vector magnitude collection to AR9001 and
AR9002, as well as my best attempt at making sense of what the EVM
numbers actually mean. There was an obvious problem
On 2011-01-09 12:46 AM, gree...@candelatech.com wrote:
From: Ben Greeargree...@candelatech.com
The system can get into a state where the xmit queue
is stopped, but there are no packets pending, so
the queue will not be restarted.
Add logic to the xmit watchdog to attempt to restart
the
On Sat, Jan 08, 2011 at 04:36:23PM -0800, Ben Greear wrote:
On 01/08/2011 04:20 PM, Felix Fietkau wrote:
On 2011-01-08 8:33 AM, gree...@candelatech.com wrote:
From: Ben Greeargree...@candelatech.com
This saves us constantly allocating large, multi-page
skbs. It should fix the order-1
On 2011-01-09 1:14 PM, Christian Lamparter wrote:
On Sunday 09 January 2011 19:13:04 Jouni Malinen wrote:
On Sat, Jan 08, 2011 at 04:36:23PM -0800, Ben Greear wrote:
On 01/08/2011 04:20 PM, Felix Fietkau wrote:
On 2011-01-08 8:33 AM, gree...@candelatech.com wrote:
From: Ben
Since I wasn't allowed to edit the wiki page after login: Please change the
ath9k page http://wireless.kernel.org/en/users/Drivers/ath9k concerning
D-Link's DWA-645. It's not supported generally (I bought it because of the
information published there).
--
E-Mails an die Absender-Adresse werden
On 01/09/2011 10:13 AM, Jouni Malinen wrote:
On Sat, Jan 08, 2011 at 04:36:23PM -0800, Ben Greear wrote:
On 01/08/2011 04:20 PM, Felix Fietkau wrote:
On 2011-01-08 8:33 AM, gree...@candelatech.com wrote:
From: Ben Greeargree...@candelatech.com
This saves us constantly allocating large,
On 01/09/2011 10:19 AM, Felix Fietkau wrote:
On 2011-01-09 12:46 AM, gree...@candelatech.com wrote:
From: Ben Greeargree...@candelatech.com
The system can get into a state where the xmit queue
is stopped, but there are no packets pending, so
the queue will not be restarted.
Add logic to
On 2011-01-09 9:39 PM, Ben Greear wrote:
On 01/09/2011 10:19 AM, Felix Fietkau wrote:
On 2011-01-09 12:46 AM, gree...@candelatech.com wrote:
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c
b/drivers/net/wireless/ath/ath9k/xmit.c
index d9a4144..1b3a62c 100644
---
On 01/09/2011 09:38 PM, Vasanthakumar Thiagarajan wrote:
On Fri, Jan 07, 2011 at 11:30:59PM +0530, gree...@candelatech.com wrote:
From: Ben Greeargree...@candelatech.com
It is not guaranteed that the ath_tx_complete_poll_work runs
after some fixed duration because the channel-reset logic
From: Ben Greear gree...@candelatech.com
The system can get into a state where the xmit queue
is stopped, but there are no packets pending, so
the queue will not be restarted.
Add logic to the xmit watchdog to attempt to restart
the xmit logic if this situation is detected.
Example 'dmesg'
Here is my current ath9k patch queue. These have all been
posted before, but this should make it easier to apply them.
The final 'copy-break' patch still needs some work to
function properly on non PCI busses it seems, and maybe
disable copybreak on larger packets.
From: Ben Greear gree...@candelatech.com
I thought this might help track down stuck queues, etc.
Signed-off-by: Ben Greear gree...@candelatech.com
---
:100644 100644 3586c43... 5075faa... M drivers/net/wireless/ath/ath9k/debug.c
drivers/net/wireless/ath/ath9k/debug.c | 16
1
From: Ben Greear gree...@candelatech.com
Previous code left it NULL.
Signed-off-by: Ben Greear gree...@candelatech.com
---
:100644 100644 767d8b8... 23b2998... M drivers/net/wireless/ath/ath9k/init.c
drivers/net/wireless/ath/ath9k/init.c |1 +
1 files changed, 1 insertions(+), 0
From: Ben Greear gree...@candelatech.com
If the txq-axq_q is empty, the code was breaking out
of the tx_processq logic without checking to see if it should
transmit other queued AMPDU frames (txq-axq_acq).
This patches ensures ath_txq_schedule is called.
This needs review.
Signed-off-by: Ben
From: Ben Greear gree...@candelatech.com
The system can get into a state where the xmit queue
is stopped, but there are no packets pending, so
the queue will not be restarted.
Add logic to the xmit watchdog to attempt to restart
the xmit logic if this situation is detected.
Example 'dmesg'
From: Ben Greear gree...@candelatech.com
Should help debug strange tx lockup type issues.
Signed-off-by: Ben Greear gree...@candelatech.com
---
:100644 100644 5075faa... 577bc5a... M drivers/net/wireless/ath/ath9k/debug.c
:100644 100644 1e5078b... cd2db3f... M
From: Ben Greear gree...@candelatech.com
This saves us constantly allocating large, multi-page
skbs. It should fix the order-1 allocation errors reported,
and in a 60-vif scenario, this significantly decreases CPU
utilization, and latency, and increases bandwidth.
Signed-off-by: Ben Greear
From: Ben Greear gree...@candelatech.com
There can be multiple struct ath_atx_ac entries for each
txq, so if the first one doesn't have any packets to send
now, try the rest of them. This should help keep xmit
going when using multiple stations, especially with AMPDU
enabled.
Signed-off-by: Ben
From: Ben Greear gree...@candelatech.com
To try to figure out why xmit logic hangs.
Signed-off-by: Ben Greear gree...@candelatech.com
---
:100644 100644 650f00f... 9e009cc... M drivers/net/wireless/ath/ath9k/debug.c
drivers/net/wireless/ath/ath9k/debug.c | 26 ++
1
2011.01.09. 18:49 keltezéssel, Ben Greear írta:
On 01/09/2011 12:00 AM, Gabor Juhos wrote:
Hi Ben,
From: Ben Greeargree...@candelatech.com
This saves us constantly allocating large, multi-page
skbs. It should fix the order-1 allocation errors reported,
and in a 60-vif scenario, this
29 matches
Mail list logo