From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by passt.top (Postfix) with ESMTP id 710125A0082 for ; Wed, 4 Jan 2023 01:08:58 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1672790937; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=JV9XipnkJqrpOJjDirV74v6Ri6ykUc1TbTzW9lr3qrs=; b=CAWBXPCJ806HNcocRDy6zDzF4psYWnkGbTug7xHNZIzPOOhdf1wyoJDC0stexTPlNMLySO B6Xb/O6oyteEY7A9dbNXDy4dq+Y3z8qWBcDXBaRzgiU9hvOzVwHgJFffxJ93DUH8bRpgpA TeKM9PURHAkg90i68G7ri9PsQJG9Y2A= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-472-859k1sMVMoKGst4x1pNcyQ-1; Tue, 03 Jan 2023 19:08:55 -0500 X-MC-Unique: 859k1sMVMoKGst4x1pNcyQ-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id A399E858F09; Wed, 4 Jan 2023 00:08:55 +0000 (UTC) Received: from maya.cloud.tilaa.com (ovpn-208-4.brq.redhat.com [10.40.208.4]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 39C3251E5; Wed, 4 Jan 2023 00:08:55 +0000 (UTC) Date: Wed, 4 Jan 2023 01:08:52 +0100 From: Stefano Brivio To: David Gibson Subject: Re: [PATCH 4/8] udp: Receive multiple datagrams at once on the pasta sock->tap path Message-ID: <20230104010852.02e96a70@elisabeth> In-Reply-To: References: <20221205081425.2614425-1-david@gibson.dropbear.id.au> <20221205081425.2614425-5-david@gibson.dropbear.id.au> <20221213234847.6c723ad9@elisabeth> <20221214113546.16942d3a@elisabeth> <20221220114246.737b0c3e@elisabeth> Organization: Red Hat MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Message-ID-Hash: 3H7F5AG4A4BADPI22J7JHDYJIZLFATXZ X-Message-ID-Hash: 3H7F5AG4A4BADPI22J7JHDYJIZLFATXZ X-MailFrom: sbrivio@redhat.com X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header CC: passt-dev@passt.top X-Mailman-Version: 3.3.3 Precedence: list List-Id: Development discussion and patches for passt Archived-At: Archived-At: List-Archive: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: On Wed, 21 Dec 2022 17:00:24 +1100 David Gibson wrote: > On Tue, Dec 20, 2022 at 11:42:46AM +0100, Stefano Brivio wrote: > > Sorry for the further delay, > >=20 > > On Wed, 14 Dec 2022 11:35:46 +0100 > > Stefano Brivio wrote: > > =20 > > > On Wed, 14 Dec 2022 12:42:14 +1100 > > > David Gibson wrote: > > > =20 > > > > On Tue, Dec 13, 2022 at 11:48:47PM +0100, Stefano Brivio wrote: = =20 > > > > > Sorry for the long delay here, > > > > >=20 > > > > > On Mon, 5 Dec 2022 19:14:21 +1100 > > > > > David Gibson wrote: > > > > > =20 > > > > > > Usually udp_sock_handler() will receive and forward multiple (u= p to 32) > > > > > > datagrams in udp_sock_handler(), then forward them all to the t= ap > > > > > > interface. For unclear reasons, though, when in pasta mode we = will only > > > > > > receive and forward a single datagram at a time. Change it to = receive > > > > > > multiple datagrams at once, like the other paths. =20 > > > > >=20 > > > > > This is explained in the commit message of 6c931118643c ("tcp, ud= p: > > > > > Receive batching doesn't pay off when writing single frames to ta= p"). > > > > >=20 > > > > > I think it's worth re-checking the throughput now as this path is= a bit > > > > > different, but unfortunately I didn't include this in the "perf" = tests :( > > > > > because at the time I introduced those I wasn't sure it even made= sense to > > > > > have traffic from the same host being directed to the tap device. > > > > >=20 > > > > > The iperf3 runs were I observed this are actually the ones from t= he Podman > > > > > demo. Ideally that case should be also checked in the perf/pasta_= udp tests. =20 > > > >=20 > > > > Hm, ok. > > > > =20 > > > > > How fundamental is this for the rest of the series? I couldn't fi= nd any > > > > > actual dependency on this but I might be missing something. = =20 > > > >=20 > > > > So the issue is that prior to this change in pasta we receive multi= ple > > > > frames at once on the splice path, but one frame at a time on the t= ap > > > > path. By the end of this series we can't do that any more, because= we > > > > don't know before the recvmmsg() which one we'll be doing. =20 > > >=20 > > > Oh, right, I see. Then let me add this path to the perf/pasta_udp tes= t > > > and check how relevant this is now, I'll get back to you in a bit. = =20 > >=20 > > I was checking the wrong path. With this: > >=20 > > diff --git a/test/perf/pasta_udp b/test/perf/pasta_udp > > index 27ea724..973c2f4 100644 > > --- a/test/perf/pasta_udp > > +++ b/test/perf/pasta_udp > > @@ -31,6 +31,14 @@ report=09pasta lo_udp 1 __FREQ__ > > =20 > > th=09MTU 1500B 4000B 16384B 65535B > > =20 > > +tr=09UDP throughput over IPv6: host to ns > > +nsout=09IFNAME ip -j link show | jq -rM '.[] | select(.link_type =3D= =3D "ether").ifname' > > +nsout=09ADDR6 ip -j -6 addr show|jq -rM '.[] | select(.ifname =3D=3D "= __IFNAME__").addr_info[] | select(.scope =3D=3D "global" and .prefixlen =3D= =3D 64).local' > > +bw=09- > > +bw=09- > > +bw=09- > > +iperf3=09BW host ns __ADDR6__ 100${i}2 __THREADS__ __TIME__ __OPTS__ -= b 15G > > +bw=09__BW__ 7.0 9.0 > > =20 > > tr=09UDP throughput over IPv6: ns to host > > ns=09ip link set dev lo mtu 1500 > > diff --git a/test/run b/test/run > > index e07513f..b53182b 100755 > > --- a/test/run > > +++ b/test/run > > @@ -67,6 +67,14 @@ run() { > > =09test build/clang_tidy > > =09teardown build > > =20 > > +=09VALGRIND=3D0 > > +=09setup passt_in_ns > > +=09test passt/ndp > > +=09test passt/dhcp > > +=09test perf/pasta_udp > > +=09test passt_in_ns/shutdown > > +=09teardown passt_in_ns > > + > > =09setup pasta > > =09test pasta/ndp > > =09test pasta/dhcp =20 >=20 > Ah, ok. Can we add that to the standard set of tests ASAP, please. >=20 > > I get 21.6 gbps after this series, and 29.7 gbps before -- it's quite > > significant. =20 >=20 > Drat. >=20 > > And there's nothing strange in perf's output, really, the distribution > > of overhead per functions is pretty much the same, but writing multiple > > messages to the tap device just takes more cycles per message compared > > to a single message. =20 >=20 > That's so weird. It should be basically an identical set of write()s, > except that they happen in a batch, rather than a bit spread out. I > guess it has to be some kind of cache locality thing. I wonder if the > difference would go away or reverse if we had a way to submit multiple > frames with a single syscall. >=20 > > I'm a bit ashamed to propose this, but do you think about something > > like: =20 >=20 > > =09if (c->mode =3D=3D MODE_PASTA) { if (recvmmsg(ref.r.s, mmh_recv, > > =09=091, 0, NULL) <=3D 0) return; =20 >=20 > > =09=09if (udp_mmh_splice_port(v6, mmh_recv)) { n =3D > > =09=09=09recvmmsg(ref.r.s, mmh_recv + 1, UDP_MAX_FRAMES > > =09=09=09- 1, 0, NULL); } =20 >=20 > > =09=09if (n > 0) n++; else n =3D 1; } else { n =3D > > =09=09=09recvmmsg(ref.r.s, mmh_recv, UDP_MAX_FRAMES, 0, > > =09=09=09NULL); if (n <=3D 0) return; } =20 >=20 > > ? Other than the inherent ugliness, it looks like a good > > approximation to me. =20 >=20 > Hmm. Well, the first question is how much impact does going 1 message > at a time have on the spliced throughput. If it's not too bad, then > we could just always go one at a time for pasta, regardless of > splicing. And we could even abstract that difference into the tap > backend with a callback like tap_batch_size(c). So, finally I had the chance to try this out. First off, baseline with the patch adding the new tests I just sent, and the series you posted: =3D=3D=3D perf/pasta_udp > pasta: throughput and latency (local traffic) Throughput in Gbps, latency in =C2=B5s, one thread at 3.6 GHz, 4 streams MTU: | 1500B | 4= 000B | 16384B | 65535B | |--------|---= -----|--------|--------| UDP throughput over IPv6: ns to host | 4.4 | = 8.5 | 19.5 | 23.0 | UDP RR latency over IPv6: ns to host | - | = - | - | 27 | |--------|---= -----|--------|--------| UDP throughput over IPv4: ns to host | 4.3 | = 8.8 | 18.5 | 24.4 | UDP RR latency over IPv4: ns to host | - | = - | - | 26 | |--------|---= -----|--------|--------| UDP throughput over IPv6: host to ns | - | = - | - | 22.5 | UDP RR latency over IPv6: host to ns | - | = - | - | 30 | |--------|---= -----|--------|--------| UDP throughput over IPv4: host to ns | - | = - | - | 24.5 | UDP RR latency over IPv4: host to ns | - | = - | - | 25 | '--------'---= -----'--------'--------' ...passed. > pasta: throughput and latency (traffic via tap) Throughput in Gbps, latency in =C2=B5s, one thread at 3.6 GHz, 4 streams MTU: | 1500B | 4= 000B | 16384B | 65520B | |--------|---= -----|--------|--------| UDP throughput over IPv6: ns to host | 4.4 | = 10.4 | 16.0 | 23.4 | UDP RR latency over IPv6: ns to host | - | = - | - | 27 | |--------|---= -----|--------|--------| UDP throughput over IPv4: ns to host | 5.2 | = 10.8 | 16.0 | 24.0 | UDP RR latency over IPv4: ns to host | - | = - | - | 28 | |--------|---= -----|--------|--------| UDP throughput over IPv6: host to ns | - | = - | - | 21.5 | UDP RR latency over IPv6: host to ns | - | = - | - | 29 | |--------|---= -----|--------|--------| UDP throughput over IPv4: host to ns | - | = - | - | 26.3 | UDP RR latency over IPv4: host to ns | - | = - | - | 26 | '--------'---= -----'--------'--------' which seems to indicate the whole "splicing" thing is pretty much useless, for UDP (except for that 16 KiB MTU case, but I wonder how relevant that is). If I set UDP_MAX_FRAMES to 1, with a quick workaround for the resulting warning in udp_tap_send() (single frame to send, hence single message), it gets somewhat weird: =3D=3D=3D perf/pasta_udp > pasta: throughput and latency (local traffic) Throughput in Gbps, latency in =C2=B5s, one thread at 3.6 GHz, 4 streams MTU: | 1500B | 4= 000B | 16384B | 65535B | |--------|---= -----|--------|--------| UDP throughput over IPv6: ns to host | 3.4 | = 7.0 | 21.6 | 31.6 | UDP RR latency over IPv6: ns to host | - | = - | - | 30 | |--------|---= -----|--------|--------| UDP throughput over IPv4: ns to host | 3.8 | = 7.0 | 22.0 | 32.4 | UDP RR latency over IPv4: ns to host | - | = - | - | 26 | |--------|---= -----|--------|--------| UDP throughput over IPv6: host to ns | - | = - | - | 29.3 | UDP RR latency over IPv6: host to ns | - | = - | - | 31 | |--------|---= -----|--------|--------| UDP throughput over IPv4: host to ns | - | = - | - | 33.8 | UDP RR latency over IPv4: host to ns | - | = - | - | 25 | '--------'---= -----'--------'--------' ...passed. > pasta: throughput and latency (traffic via tap) Throughput in Gbps, latency in =C2=B5s, one thread at 3.6 GHz, 4 streams MTU: | 1500B | 4= 000B | 16384B | 65520B | |--------|---= -----|--------|--------| UDP throughput over IPv6: ns to host | 4.7 | = 10.3 | 16.0 | 24.0 | UDP RR latency over IPv6: ns to host | - | = - | - | 27 | |--------|---= -----|--------|--------| UDP throughput over IPv4: ns to host | 5.6 | = 11.4 | 16.0 | 24.0 | UDP RR latency over IPv4: ns to host | - | = - | - | 26 | |--------|---= -----|--------|--------| UDP throughput over IPv6: host to ns | - | = - | - | 21.5 | UDP RR latency over IPv6: host to ns | - | = - | - | 29 | |--------|---= -----|--------|--------| UDP throughput over IPv4: host to ns | - | = - | - | 28.7 | UDP RR latency over IPv4: host to ns | - | = - | - | 29 | '--------'---= -----'--------'--------' ...except for the cases with low MTUs, throughput is significantly higher if we read and send one message at a time on the "spliced" path. Next, I would like to: - bisect between 32 and 1 for UDP_MAX_FRAMES: maybe 32 affects data locality too much, but some lower value would still be beneficial by lowering syscall overhead - try with sendmsg() instead of sendmmsg(), at this point. Looking at the kernel, that doesn't seem to make a real difference. About this series: should we just go ahead and apply it with UDP_MAX_FRAMES set to 1 for the moment being? It's anyway better than the existing situation. --=20 Stefano