Re: [Patch net-next v2] net_sched: introduce tracepoint trace_qdisc_enqueue()

On Sun, Jul 11, 2021 at 8:49 PM Tonghao Zhang [off-list ref] wrote:

On Mon, Jul 12, 2021 at 11:39 AM Cong Wang [off-list ref] wrote:

quoted

On Sun, Jul 11, 2021 at 8:36 PM Tonghao Zhang [off-list ref] wrote:

quoted

On Mon, Jul 12, 2021 at 11:23 AM Cong Wang [off-list ref] wrote:

quoted

Sure, in that case a different packet is dropped, once again you
can trace it with kfree_skb() if you want. What's the problem?

It's ok, but we can make it better. Yunsheng Lin may have explained why?

Why it is better to trace dropped packets both in enqueue and in kfree_skb()?

I mean we can use one tracepoint to know what happened in the queue,
not necessary to trace enqueue and  kfree_skb()

This is wrong, packets can be dropped for other reasons too, tracing
enqueue is clearly not sufficient even if you trace it unconditionally.
For a quick example, codel drops packets at dequeue rather than
enqueue. ;)

If so, we must match when the packet is dropped and what packets. if
we use the return value in trace_qdisc_requeue. It
is easy to know what happened(when, where, what packets were dropped ).

I am afraid you have to watch the dropped packets.

Thanks.