2010-06-08 19:10:27 |
Tim Gardner |
bug |
|
|
added bug |
2010-06-08 19:10:53 |
Tim Gardner |
nominated for series |
|
Ubuntu Maverick |
|
2010-06-08 19:10:53 |
Tim Gardner |
bug task added |
|
linux (Ubuntu Maverick) |
|
2010-06-08 19:11:57 |
Tim Gardner |
linux (Ubuntu Maverick): importance |
Undecided |
High |
|
2010-06-08 19:11:57 |
Tim Gardner |
linux (Ubuntu Maverick): status |
New |
In Progress |
|
2010-06-08 19:11:57 |
Tim Gardner |
linux (Ubuntu Maverick): milestone |
|
maverick-alpha-2 |
|
2010-06-08 19:11:57 |
Tim Gardner |
linux (Ubuntu Maverick): assignee |
|
Tim Gardner (timg-tpi) |
|
2010-06-08 23:20:12 |
Tim Gardner |
summary |
igb: Do not overflow num_rx_queues with skb_record_rx_queue() |
Maverick: 2.6.35-rc2 CONFIG_RPS=y fills log with noise |
|
2010-06-09 13:06:05 |
Tim Gardner |
description |
The igb driver records a receive queue number in the received SKB that is larger then has been allocated by the net core. |
Most users of skb_record_rx_queue() do not use alloc_netdev_mq() for network device initialization, so don't print a warning about num_rx_queues overflow in get_rps_cpu() unless they have actually been allocated.
|
|
2010-06-09 15:55:25 |
Tim Gardner |
description |
Most users of skb_record_rx_queue() do not use alloc_netdev_mq() for network device initialization, so don't print a warning about num_rx_queues overflow in get_rps_cpu() unless they have actually been allocated.
|
There are a number of network drivers (bridge, bonding, etc) that are not yet receive multi-queue enabled and use alloc_netdev(), so don't print a num_rx_queues imbalance warning in that case.
Also, only print the warning once for those drivers that _are_ multi-queue enabled. |
|
2010-06-10 03:20:10 |
Launchpad Janitor |
linux (Ubuntu Maverick): status |
In Progress |
Fix Released |
|