public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: John Fastabend <john.fastabend@gmail•com>
To: Eric Dumazet <eric.dumazet@gmail•com>
Cc: xiyou.wangcong@gmail•com, jhs@mojatatu•com,
	alexei.starovoitov@gmail•com, brouer@redhat•com,
	john.r.fastabend@intel•com, netdev@vger•kernel.org,
	davem@davemloft•net
Subject: Re: [RFC PATCH 01/13] net: sched: allow qdiscs to handle locking
Date: Wed, 17 Aug 2016 15:48:50 -0700	[thread overview]
Message-ID: <57B4E9D2.1090302@gmail.com> (raw)
In-Reply-To: <1471473242.29842.45.camel@edumazet-glaptop3.roam.corp.google.com>

On 16-08-17 03:34 PM, Eric Dumazet wrote:
> On Wed, 2016-08-17 at 12:33 -0700, John Fastabend wrote:
> 
> 
>> diff --git a/net/core/dev.c b/net/core/dev.c
>> index 4ce07dc..5db395d 100644
>> --- a/net/core/dev.c
>> +++ b/net/core/dev.c
>> @@ -3076,6 +3076,26 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
>>  	int rc;
>>  
>>  	qdisc_calculate_pkt_len(skb, q);
>> +
>> +	if (q->flags & TCQ_F_NOLOCK) {
>> +		if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
>> +			__qdisc_drop(skb, &to_free);
>> +			rc = NET_XMIT_DROP;
>> +		} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q)) {
> 
> For a lockless qdisc, do you believe TCQ_F_CAN_BYPASS is still a gain ?
> 

For the benchmarks from pktgen it appears to be a win or mute to just
drop the TCQ_F_CAN_BYPASS (just taking a look at one sample below)

    nolock & nobypass   locked (current master)
----------------------------------------------
1:  1435796 		1471479
2:  1880642		1746231
4:  1922935		1119626
8:  1585055		1001471
12: 1479273		989269

The only thing would be to test a bunch of netperf RR sessions to be
sure.

> Also !qdisc_qlen(q) looks racy anyway ?

Yep its racy unless you make it an atomic but this hurts performance
metrics. There is a patch further in the stack here that adds the
atomic variants but I tend to think we can just drop the bypass logic
in the lockless case assuming the netperf tests look good.

> 
>> +			qdisc_bstats_cpu_update(q, skb);
>> +			if (sch_direct_xmit(skb, q, dev, txq, root_lock, true))
>> +				__qdisc_run(q);
>> +			rc = NET_XMIT_SUCCESS;
>> +		} else {
>> +			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
>> +			__qdisc_run(q);
>> +		}
>> +
>> +		if (unlikely(to_free))
>> +			kfree_skb_list(to_free);
>> +		return rc;
>> +	}
>> +
> 
> 

  reply	other threads:[~2016-08-17 22:49 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-08-17 19:33 [RFC PATCH 00/13] Series short description John Fastabend
2016-08-17 19:33 ` [RFC PATCH 01/13] net: sched: allow qdiscs to handle locking John Fastabend
2016-08-17 22:33   ` Eric Dumazet
2016-08-17 22:49     ` John Fastabend
2016-08-17 22:34   ` Eric Dumazet
2016-08-17 22:48     ` John Fastabend [this message]
2016-08-17 19:34 ` [RFC PATCH 02/13] net: sched: qdisc_qlen for per cpu logic John Fastabend
2016-08-17 19:34 ` [RFC PATCH 03/13] net: sched: provide per cpu qstat helpers John Fastabend
2016-08-17 19:35 ` [RFC PATCH 04/13] net: sched: provide atomic qlen helpers for bypass case John Fastabend
2016-08-17 19:35 ` [RFC PATCH 05/13] net: sched: a dflt qdisc may be used with per cpu stats John Fastabend
2016-08-17 19:35 ` [RFC PATCH 06/13] net: sched: per cpu gso handlers John Fastabend
2016-08-17 19:36 ` [RFC PATCH 07/13] net: sched: support qdisc_reset on NOLOCK qdisc John Fastabend
2016-08-17 22:53   ` Eric Dumazet
2016-08-17 22:59     ` John Fastabend
2016-08-17 19:36 ` [RFC PATCH 08/13] net: sched: support skb_bad_tx with lockless qdisc John Fastabend
2016-08-17 22:58   ` Eric Dumazet
2016-08-17 23:00     ` John Fastabend
2016-08-23 20:11       ` John Fastabend
2016-08-17 19:37 ` [RFC PATCH 09/13] net: sched: helper to sum qlen John Fastabend
2016-08-17 19:37 ` [RFC PATCH 10/13] net: sched: lockless support for netif_schedule John Fastabend
2016-08-17 19:46   ` John Fastabend
2016-08-17 23:01   ` Eric Dumazet
2016-08-17 23:17     ` John Fastabend
2016-08-17 23:33       ` Eric Dumazet
2016-08-17 19:38 ` [RFC PATCH 11/13] net: sched: pfifo_fast use alf_queue John Fastabend
2016-08-19 10:13   ` Jesper Dangaard Brouer
2016-08-19 15:44     ` John Fastabend
2016-08-17 19:38 ` [RFC PATCH 12/13] net: sched: add support for TCQ_F_NOLOCK subqueues to sch_mq John Fastabend
2016-08-17 19:49   ` John Fastabend
2016-08-17 23:04   ` Eric Dumazet
2016-08-17 23:18     ` John Fastabend
2016-08-17 19:39 ` [RFC PATCH 13/13] net: sched: add support for TCQ_F_NOLOCK subqueues to sch_mqprio John Fastabend

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=57B4E9D2.1090302@gmail.com \
    --to=john.fastabend@gmail$(echo .)com \
    --cc=alexei.starovoitov@gmail$(echo .)com \
    --cc=brouer@redhat$(echo .)com \
    --cc=davem@davemloft$(echo .)net \
    --cc=eric.dumazet@gmail$(echo .)com \
    --cc=jhs@mojatatu$(echo .)com \
    --cc=john.r.fastabend@intel$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    --cc=xiyou.wangcong@gmail$(echo .)com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox