Re: [PATCH net-next 2/2] net/sched: fq_codel: local packets no longer count against memory limit

[Victor Nogueira <victor@mojatatu.com>]

On 14/05/2026 07:06, Paolo Abeni wrote:
> On 5/14/26 10:49 AM, Eric Dumazet wrote:
>> On Thu, May 14, 2026 at 1:24 AM Paolo Abeni <pabeni@redhat.com> wrote:
>>> On 5/12/26 11:48 AM, Eric Dumazet wrote:
>>>> Commit 95b58430abe7 ("fq_codel: add memory limitation per queue")
>>>> claimed that the 32Mb default was "reasonable even for heavy duty usages."
>>>>
>>>> In practice, this is not the case.
>>>>
>>>> Packets that are associated with local sockets sk_wmem_alloc
>>>> do not really need additional memory control.
>>>>
>>>> Signed-off-by: Eric Dumazet <edumazet@google.com>
>>>> ---
>>>>   net/sched/sch_fq_codel.c | 2 +-
>>>>   1 file changed, 1 insertion(+), 1 deletion(-)
>>>>
>>>> diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
>>>> index 1b1de693d4c64a1f5f4e9e788371829dea91740e..71107dc52be799a14f370f2ad74d2eadd93992c1 100644
>>>> --- a/net/sched/sch_fq_codel.c
>>>> +++ b/net/sched/sch_fq_codel.c
>>>> @@ -212,7 +212,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch,
>>>>                q->new_flow_count++;
>>>>                WRITE_ONCE(flow->deficit, q->quantum);
>>>>        }
>>>> -     get_codel_cb(skb)->mem_usage = skb->truesize;
>>>> +     get_codel_cb(skb)->mem_usage = is_skb_wmem(skb) ? 0 : skb->truesize;
>>>>        q->memory_usage += get_codel_cb(skb)->mem_usage;
>>>>        memory_limited = q->memory_usage > q->memory_limit;
>>>>        qdisc_qlen_inc(sch);
>>>
>>> I *think* this patch is causing TDC self-tests failures:
>>>
>>> # not ok 704 a4bb - Test FQ_CODEL with HTB parent - force packet drop with empty queue
>>> # Could not match regex pattern. Verify command output:
>>> # qdisc fq_codel 10: parent 1:10 limit 10240p flows 1 quantum 1514 target 99us interval 999us memory_limit 1b ecn drop_batch 64
>>> #  Sent 490 bytes 5 pkt (dropped 0, overlimits 0 requeues 0)
>>> #  backlog 0b 0p requeues 0
>>> #   maxpacket 98 drop_overlimit 0 new_flow_count 1 ecn_mark 0
>>> #   new_flows_len 1 old_flows_len 0
>>>
>>> whole log at:
>>>
>>> https://github.com/p4tc-dev/tc-executor/tree/storage/artifacts/645644/1-tdc-sh
>>>
>>> Looking at the test code, I think the patch broke it, but the failures
>>> started a little afterward the patch merge, so I'm possibly
>>> misunderstanding something here.
>>>
>>> Thanks,
>>>
>>> Paolo
>>>
>>
>> It seems this test uses a memory limit of 1 byte.
>>
>> $TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit
>> 1 flows 1 target 0.1ms interval 1ms
>>
>> This might be a typo, I think they expected a limit of 0 packet.
> 
> FTR, I think/agree a change to the self-tests would be preferable.

Eric, do you have a tdc fix lined up for this one?
If not, I can work something out here and send.

cheers,
Victor