netdev - Re: [net-next PATCH V6 0/2] qdisc: bulk dequeue support

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

Date:	Thu, 02 Oct 2014 10:32:47 -0700
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Florian Westphal <fw@...len.de>
Cc:	Tom Herbert <therbert@...gle.com>,
	Jesper Dangaard Brouer <brouer@...hat.com>,
	Linux Netdev List <netdev@...r.kernel.org>,
	"David S. Miller" <davem@...emloft.net>,
	Hannes Frederic Sowa <hannes@...essinduktion.org>,
	Daniel Borkmann <dborkman@...hat.com>,
	Jamal Hadi Salim <jhs@...atatu.com>,
	Alexander Duyck <alexander.duyck@...il.com>,
	John Fastabend <john.r.fastabend@...el.com>,
	Dave Taht <dave.taht@...il.com>,
	Toke Høiland-Jørgensen <toke@...e.dk>
Subject: Re: [net-next PATCH V6 0/2] qdisc: bulk dequeue support

On Thu, 2014-10-02 at 18:52 +0200, Florian Westphal wrote:
> Tom Herbert <therbert@...gle.com> wrote:
> > On Wed, Oct 1, 2014 at 1:35 PM, Jesper Dangaard Brouer
> > <brouer@...hat.com> wrote:
> > > This patchset uses DaveM's recent API changes to dev_hard_start_xmit(),
> > > from the qdisc layer, to implement dequeue bulking.
> > >
> > > Patch01: "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"
> > >  - Implement basic qdisc dequeue bulking
> > >  - This time, 100% relying on BQL limits, no magic safe-guard constants
> > >
> > > Patch02: "qdisc: dequeue bulking also pickup GSO/TSO packets"
> > >  - Extend bulking to bulk several GSO/TSO packets
> > >  - Seperate patch, as it introduce a small regression, see test section.
> > >
> > > We do have a patch03, which exports a userspace tunable as a BQL
> > > tunable, that can byte-cap or disable the bulking/bursting.  But we
> > > could not agree on it internally, thus not sending it now.  We
> > > basically strive to avoid adding any new userspace tunable.
> > >
> > Unfortunately we probably still need something. If BQL were disabled
> > (by setting BQL min_limit to infinity) then we'll always dequeue all
> > the packets in the qdisc. Disabling BQL might be legitimate in
> > deployment if say a bug is found in a device that prevents prompt
> > transmit completions for some corner case.
> 
> Hmm.  Thats confusing.
> 
> So you are saying to disable bql one should do
> 
> cat limit_max > limit_min ?
> 
> But thats not the same as having a bql-unaware driver.
> 
> Seems to get same behavior as non-bql aware driver (where
> dql_avail always returns 0 since num_queued and adj_limit remain at 0)
> is to set
> 
> echo 0 > limit_max
> 
> ... which makes dql_avail() return 0, which then also turns off bulk
> dequeue.

So Tom point is that we might have a BQL enabled driver, but for some
reason admin wants to set limit_min to 10000000.

Then the admin wants also to restrict the xmit_more batches to 13
packets.

Then a debugging facility might be nice to have.

What about adding 2 attributes :

/sys/class/net/ethX/queues/tx-Y/xmit_more_inflight   (live number of
deferred frames on this TX queue, waiting a doorbell to kick the NIC)

/sys/class/net/ethX/queues/tx-Y/xmit_more_limit      (default to 8)



--
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