On Wed, Nov 23, 2016 at 12:03:28PM -0800, Eric Dumazet wrote:
On Wed, Nov 23, 2016 at 10:21 AM, Brian Starkey <brian.star...@arm.com> wrote:
This patch didn't help.
I did get some new traces though - I've attached the diff for the
trace_printks I added.
It looks like the difference is that after 4cd13c21b207 the RX softirq
isn't running, and RX interrupts don't call softirq_raise anymore -
presumably because there's one pending, but I didn't have time to
track that down to a code-path.
Looks like netif_rx() drops the incoming packets then ?
Maybe netif_running() is not happy :(
Could you trace netif_rx() return value (NET_RX_SUCCESS or NET_RX_DROP)
Some packets are dropped, but not very many:
$ grep NET_RX_SUCCESS trace_netif_rx.txt | wc -l
$ grep NET_RX_DROP trace_netif_rx.txt | wc -l
Without the ksoftirqd change there were zero NET_RX_DROPs.