Thanks for the reviews,
I¹m about to send a v2
On 9/19/14, 3:49 PM, "Pravin Shelar" wrote:
>On Fri, Sep 19, 2014 at 1:28 PM, Daniele Di Proietto
> wrote:
>> If a packet didn't match a rule in the fast path classifier its memory
>>was
>> never freed. The issue was particularly clear with DPDK de
On Fri, Sep 19, 2014 at 1:28 PM, Daniele Di Proietto
wrote:
> If a packet didn't match a rule in the fast path classifier its memory was
> never freed. The issue was particularly clear with DPDK devices because it was
> not possible to process more than ~25 DPDK mbufs in the slow path.
>
> Thi
Acked-by: Alex Wang
Hey Pravin, could you also have a look~
On Fri, Sep 19, 2014 at 1:28 PM, Daniele Di Proietto wrote:
> If a packet didn't match a rule in the fast path classifier its memory was
> never freed. The issue was particularly clear with DPDK devices because it
> was
> not possible
If a packet didn't match a rule in the fast path classifier its memory was
never freed. The issue was particularly clear with DPDK devices because it was
not possible to process more than ~25 DPDK mbufs in the slow path.
This commit fixes the problem by:
* calling dpif_packet_delete() if the u
