On Tuesday 17 July 2007 20:56, Ingo Molnar wrote:
> i logged these not via netconsole but via logging on over the console
> and using dmesg, so it should include everything. in the 100hz case the
> following seems to show the anomaly:
>
> NETDEV WATCHDOG: eth0: transmit timed out
So, it seems as if for some reason, dev->poll isn't called frequently
enough.
Here's a debugging patch that tries to locate the problem - can you give it
a try, please?
Olaf
--
Olaf Kirch | --- o --- Nous sommes du soleil we love when we play
[EMAIL PROTECTED] | / | \ sol.dhoop.naytheet.ah kin.ir.samse.qurax
--------
patching file drivers/net/e1000/e1000_main.c
---
include/linux/netdevice.h | 1 +
net/core/dev.c | 7 +++++++
net/core/netpoll.c | 2 ++
3 files changed, 10 insertions(+)
Index: build-2.6/include/linux/netdevice.h
===================================================================
--- build-2.6.orig/include/linux/netdevice.h
+++ build-2.6/include/linux/netdevice.h
@@ -692,6 +692,7 @@ struct softnet_data
#ifdef CONFIG_NET_DMA
struct dma_chan *net_dma;
#endif
+ unsigned long scheduled;
};
DECLARE_PER_CPU(struct softnet_data,softnet_data);
Index: build-2.6/net/core/dev.c
===================================================================
--- build-2.6.orig/net/core/dev.c
+++ build-2.6/net/core/dev.c
@@ -1199,6 +1199,7 @@ void __netif_rx_schedule(struct net_devi
dev->quota += dev->weight;
else
dev->quota = dev->weight;
+ __get_cpu_var(softnet_data).scheduled = jiffies;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
local_irq_restore(flags);
}
@@ -2028,6 +2029,9 @@ static void net_rx_action(struct softirq
local_irq_disable();
+ /* Complain if we're scheduled way too late. */
+ WARN_ON(time_after(jiffies, __get_cpu_var(softnet_data).scheduled +
HZ));
+
while (!list_empty(&queue->poll_list)) {
struct net_device *dev;
@@ -2038,8 +2042,10 @@ static void net_rx_action(struct softirq
dev = list_entry(queue->poll_list.next,
struct net_device, poll_list);
+
have = netpoll_poll_lock(dev);
+ BUG_ON(test_bit(__LINK_STATE_POLL_LIST_FROZEN, &dev->state));
if (dev->quota <= 0 || dev->poll(dev, &budget)) {
netpoll_poll_unlock(have);
local_irq_disable();
@@ -2074,6 +2080,7 @@ out:
softnet_break:
__get_cpu_var(netdev_rx_stat).time_squeeze++;
+ __get_cpu_var(softnet_data).scheduled = jiffies;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
goto out;
}
Index: build-2.6/net/core/netpoll.c
===================================================================
--- build-2.6.orig/net/core/netpoll.c
+++ build-2.6/net/core/netpoll.c
@@ -130,6 +130,7 @@ static void poll_napi(struct netpoll *np
* Setting POLL_LIST_FROZEN tells netif_rx_complete
* to leave the NAPI state alone.
*/
+ local_bh_disable();
set_bit(__LINK_STATE_POLL_LIST_FROZEN, &np->dev->state);
npinfo->rx_flags |= NETPOLL_RX_DROP;
atomic_inc(&trapped);
@@ -140,6 +141,7 @@ static void poll_napi(struct netpoll *np
npinfo->rx_flags &= ~NETPOLL_RX_DROP;
clear_bit(__LINK_STATE_POLL_LIST_FROZEN, &np->dev->state);
spin_unlock(&npinfo->poll_lock);
+ local_bh_enable();
}
}
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
