netdev - Re: BQL + Basic Latency under load results - 100Mbit, GSO/TSO off, pfifo

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <1325478811.2526.10.camel@edumazet-laptop>
Date:	Mon, 02 Jan 2012 05:33:31 +0100
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Dave Taht <dave.taht@...il.com>
Cc:	jg@...edesktop.org, Stephen Hemminger <shemminger@...tta.com>,
	Juliusz Chroboczek <jch@....jussieu.fr>,
	Kathleen Nichols <nichols@...lere.com>,
	netdev <netdev@...r.kernel.org>
Subject: Re: BQL + Basic Latency under load results - 100Mbit, GSO/TSO off,
 pfifo_fast vs SFQ vs QFQ

Le lundi 02 janvier 2012 à 00:17 +0100, Dave Taht a écrit :
> QFQ wins even bigger vs SFQ at 50 iperfs
> 
> http://www.teklibre.com/~d/bloat/pfifo_sfq_vs_qfq_linear50.png
> 
> And I think it's going to win even bigger at 10 Mbit.
> 

Happy new year !

This makes no sense to me for such a low amount of flows, SFQ should
perform the same than QFQ :)

You dont find out why it is so.



Please try following patch :

[PATCH net-next] sch_sfq: dont put new flow at the end of flows

SFQ enqueue algo puts a new flow _behind_ all pre-existing flows in the
circular list. In fact this is probably an old SFQ implementation bug.

100 Mbits = ~8333 full frames per second, or ~8 frames per ms.

With 50 flows, it means your "new flow" will have to wait 50 packets
being sent before its own packet. Thats the ~6ms.

We certainly can change SFQ to give a priority advantage to new flows,
so that next dequeued packet is taken from a new flow, not an old one.

Reported-by: Dave Taht <dave.taht@...il.com>
Signed-off-by: Eric Dumazet <eric.dumazet@...il.com>
---
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index c23b957..f7f62a5 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -366,11 +366,11 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (slot->qlen == 1) {		/* The flow is new */
 		if (q->tail == NULL) {	/* It is the first flow */
 			slot->next = x;
+			q->tail = slot;
 		} else {
 			slot->next = q->tail->next;
 			q->tail->next = x;
 		}
-		q->tail = slot;
 		slot->allot = q->scaled_quantum;
 	}
 	if (++sch->q.qlen <= q->limit)


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html