From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 049E8A0538; Wed, 5 Feb 2020 10:10:08 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 4FCF61C12A; Wed, 5 Feb 2020 10:10:08 +0100 (CET) Received: from us-smtp-delivery-1.mimecast.com (us-smtp-1.mimecast.com [207.211.31.81]) by dpdk.org (Postfix) with ESMTP id C39241C11A for ; Wed, 5 Feb 2020 10:10:06 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1580893806; 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:autocrypt:autocrypt; bh=I4A4t9KtFSxGxzWYhz10SGw7iImwLNfmg7YfcguEReQ=; b=jSoWDQsbC3USTUkKDTUfpcPjQgjUVAI/Isv+Kx4/QOTYc2Z17RwOpnqB5mtQl3UF6x2acw mXzhdi+uAhASiyHf4OEl4AiOIR+L/w0Gz/+yTMd6GFlUuFkCyNy3PoLw+MptzpPdwrqKMP mAJVWIiDQHgCd3po2hG0/24MxNq3/5o= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-185-ShVavw3UNgiNUXM1yle6PQ-1; Wed, 05 Feb 2020 04:10:02 -0500 Received: from smtp.corp.redhat.com (int-mx01.intmail.prod.int.phx2.redhat.com [10.5.11.11]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 6356E1081FAC; Wed, 5 Feb 2020 09:10:01 +0000 (UTC) Received: from [10.36.112.40] (ovpn-112-40.ams2.redhat.com [10.36.112.40]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 06BD785750; Wed, 5 Feb 2020 09:09:56 +0000 (UTC) To: =?UTF-8?Q?Eugenio_P=c3=a9rez?= , dev@dpdk.org, yong.liu@intel.com Cc: Maxime Coquelin , Adrian Moreno Zapata , Jason Wang , "Michael S. Tsirkin" References: <20200129193310.9157-1-eperezma@redhat.com> From: Maxime Coquelin Autocrypt: addr=maxime.coquelin@redhat.com; keydata= mQINBFOEQQIBEADjNLYZZqghYuWv1nlLisptPJp+TSxE/KuP7x47e1Gr5/oMDJ1OKNG8rlNg kLgBQUki3voWhUbMb69ybqdMUHOl21DGCj0BTU3lXwapYXOAnsh8q6RRM+deUpasyT+Jvf3a gU35dgZcomRh5HPmKMU4KfeA38cVUebsFec1HuJAWzOb/UdtQkYyZR4rbzw8SbsOemtMtwOx YdXodneQD7KuRU9IhJKiEfipwqk2pufm2VSGl570l5ANyWMA/XADNhcEXhpkZ1Iwj3TWO7XR uH4xfvPl8nBsLo/EbEI7fbuUULcAnHfowQslPUm6/yaGv6cT5160SPXT1t8U9QDO6aTSo59N jH519JS8oeKZB1n1eLDslCfBpIpWkW8ZElGkOGWAN0vmpLfdyiqBNNyS3eGAfMkJ6b1A24un /TKc6j2QxM0QK4yZGfAxDxtvDv9LFXec8ENJYsbiR6WHRHq7wXl/n8guyh5AuBNQ3LIK44x0 KjGXP1FJkUhUuruGyZsMrDLBRHYi+hhDAgRjqHgoXi5XGETA1PAiNBNnQwMf5aubt+mE2Q5r qLNTgwSo2dpTU3+mJ3y3KlsIfoaxYI7XNsPRXGnZi4hbxmeb2NSXgdCXhX3nELUNYm4ArKBP LugOIT/zRwk0H0+RVwL2zHdMO1Tht1UOFGfOZpvuBF60jhMzbQARAQABtCxNYXhpbWUgQ29x dWVsaW4gPG1heGltZS5jb3F1ZWxpbkByZWRoYXQuY29tPokCOAQTAQIAIgUCV3u/5QIbAwYL CQgHAwIGFQgCCQoLBBYCAwECHgECF4AACgkQyjiNKEaHD4ma2g/+P+Hg9WkONPaY1J4AR7Uf kBneosS4NO3CRy0x4WYmUSLYMLx1I3VH6SVjqZ6uBoYy6Fs6TbF6SHNc7QbB6Qjo3neqnQR1 71Ua1MFvIob8vUEl3jAR/+oaE1UJKrxjWztpppQTukIk4oJOmXbL0nj3d8dA2QgHdTyttZ1H xzZJWWz6vqxCrUqHU7RSH9iWg9R2iuTzii4/vk1oi4Qz7y/q8ONOq6ffOy/t5xSZOMtZCspu Mll2Szzpc/trFO0pLH4LZZfz/nXh2uuUbk8qRIJBIjZH3ZQfACffgfNefLe2PxMqJZ8mFJXc RQO0ONZvwoOoHL6CcnFZp2i0P5ddduzwPdGsPq1bnIXnZqJSl3dUfh3xG5ArkliZ/++zGF1O wvpGvpIuOgLqjyCNNRoR7cP7y8F24gWE/HqJBXs1qzdj/5Hr68NVPV1Tu/l2D1KMOcL5sOrz 2jLXauqDWn1Okk9hkXAP7+0Cmi6QwAPuBT3i6t2e8UdtMtCE4sLesWS/XohnSFFscZR6Vaf3 gKdWiJ/fW64L6b9gjkWtHd4jAJBAIAx1JM6xcA1xMbAFsD8gA2oDBWogHGYcScY/4riDNKXi lw92d6IEHnSf6y7KJCKq8F+Jrj2BwRJiFKTJ6ChbOpyyR6nGTckzsLgday2KxBIyuh4w+hMq TGDSp2rmWGJjASq5Ag0EVPSbkwEQAMkaNc084Qvql+XW+wcUIY+Dn9A2D1gMr2BVwdSfVDN7 0ZYxo9PvSkzh6eQmnZNQtl8WSHl3VG3IEDQzsMQ2ftZn2sxjcCadexrQQv3Lu60Tgj7YVYRM H+fLYt9W5YuWduJ+FPLbjIKynBf6JCRMWr75QAOhhhaI0tsie3eDsKQBA0w7WCuPiZiheJaL 4MDe9hcH4rM3ybnRW7K2dLszWNhHVoYSFlZGYh+MGpuODeQKDS035+4H2rEWgg+iaOwqD7bg CQXwTZ1kSrm8NxIRVD3MBtzp9SZdUHLfmBl/tLVwDSZvHZhhvJHC6Lj6VL4jPXF5K2+Nn/Su CQmEBisOmwnXZhhu8ulAZ7S2tcl94DCo60ReheDoPBU8PR2TLg8rS5f9w6mLYarvQWL7cDtT d2eX3Z6TggfNINr/RTFrrAd7NHl5h3OnlXj7PQ1f0kfufduOeCQddJN4gsQfxo/qvWVB7PaE 1WTIggPmWS+Xxijk7xG6x9McTdmGhYaPZBpAxewK8ypl5+yubVsE9yOOhKMVo9DoVCjh5To5 aph7CQWfQsV7cd9PfSJjI2lXI0dhEXhQ7lRCFpf3V3mD6CyrhpcJpV6XVGjxJvGUale7+IOp sQIbPKUHpB2F+ZUPWds9yyVxGwDxD8WLqKKy0WLIjkkSsOb9UBNzgRyzrEC9lgQ/ABEBAAGJ Ah8EGAECAAkFAlT0m5MCGwwACgkQyjiNKEaHD4nU8hAAtt0xFJAy0sOWqSmyxTc7FUcX+pbD KVyPlpl6urKKMk1XtVMUPuae/+UwvIt0urk1mXi6DnrAN50TmQqvdjcPTQ6uoZ8zjgGeASZg jj0/bJGhgUr9U7oG7Hh2F8vzpOqZrdd65MRkxmc7bWj1k81tOU2woR/Gy8xLzi0k0KUa8ueB iYOcZcIGTcs9CssVwQjYaXRoeT65LJnTxYZif2pfNxfINFzCGw42s3EtZFteczClKcVSJ1+L +QUY/J24x0/ocQX/M1PwtZbB4c/2Pg/t5FS+s6UB1Ce08xsJDcwyOPIH6O3tccZuriHgvqKP yKz/Ble76+NFlTK1mpUlfM7PVhD5XzrDUEHWRTeTJSvJ8TIPL4uyfzhjHhlkCU0mw7Pscyxn DE8G0UYMEaNgaZap8dcGMYH/96EfE5s/nTX0M6MXV0yots7U2BDb4soLCxLOJz4tAFDtNFtA wLBhXRSvWhdBJZiig/9CG3dXmKfi2H+wdUCSvEFHRpgo7GK8/Kh3vGhgKmnnxhl8ACBaGy9n fxjSxjSO6rj4/MeenmlJw1yebzkX8ZmaSi8BHe+n6jTGEFNrbiOdWpJgc5yHIZZnwXaW54QT UhhSjDL1rV2B4F28w30jYmlRmm2RdN7iCZfbyP3dvFQTzQ4ySquuPkIGcOOHrvZzxbRjzMx1 Mwqu3GQ= Message-ID: Date: Wed, 5 Feb 2020 10:09:54 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101 Thunderbird/68.4.1 MIME-Version: 1.0 In-Reply-To: <20200129193310.9157-1-eperezma@redhat.com> Content-Language: en-US X-Scanned-By: MIMEDefang 2.79 on 10.5.11.11 X-MC-Unique: ShVavw3UNgiNUXM1yle6PQ-1 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Subject: Re: [dpdk-dev] [PATCH] vhost: flush shadow tx if there is no more packets X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On 2/4/20 3:47 PM, Eugenio P=C3=A9rez wrote: > The current implementation of vhost_net in packed vring tries to fill > the shadow vector before send any actual changes to the guest. While > this can be beneficial for the throughput, it conflicts with some > bufferfloats methods like the linux kernel napi, that stops > transmitting packets if there are too much bytes/buffers in the > driver. >=20 > To solve it, we flush the shadow packets at the end of > virtio_dev_tx_packed if we have starved the vring, i.e., the next > buffer is not available for the device. >=20 > Since this last check can be expensive because of the atomic, we only > check it if we have not obtained the expected (count) packets. If it > happens to obtain "count" packets and there is no more available > packets the caller needs to keep call virtio_dev_tx_packed again. >=20 > Signed-off-by: Eugenio P=C3=A9rez > --- > lib/librte_vhost/virtio_net.c | 27 ++++++++++++++++++++++++++- > 1 file changed, 26 insertions(+), 1 deletion(-) >=20 > diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.= c > index 21c311732..ac2842b2d 100644 > --- a/lib/librte_vhost/virtio_net.c > +++ b/lib/librte_vhost/virtio_net.c > @@ -2133,6 +2133,20 @@ virtio_dev_tx_packed_zmbuf(struct virtio_net *dev, > =09return pkt_idx; > } > =20 > +static __rte_always_inline bool > +next_desc_is_avail(const struct vhost_virtqueue *vq) > +{ > +=09bool wrap_counter =3D vq->avail_wrap_counter; > +=09uint16_t next_used_idx =3D vq->last_used_idx + 1; > + > +=09if (next_used_idx >=3D vq->size) { > +=09=09next_used_idx -=3D vq->size; > +=09=09wrap_counter ^=3D 1; > +=09} > + > +=09return desc_is_avail(&vq->desc_packed[next_used_idx], wrap_counter); > +} > + > static __rte_noinline uint16_t > virtio_dev_tx_packed(struct virtio_net *dev, > =09=09 struct vhost_virtqueue *vq, > @@ -2165,9 +2179,20 @@ virtio_dev_tx_packed(struct virtio_net *dev, > =20 > =09} while (remained); > =20 > -=09if (vq->shadow_used_idx) > +=09if (vq->shadow_used_idx) { > =09=09do_data_copy_dequeue(vq); > =20 > +=09=09if (remained && !next_desc_is_avail(vq)) { > +=09=09=09/* > +=09=09=09 * The guest may be waiting to TX some buffers to > +=09=09=09 * enqueue more to avoid bufferfloat, so we try to > +=09=09=09 * reduce latency here. > +=09=09=09 */ > +=09=09=09vhost_flush_dequeue_shadow_packed(dev, vq); > +=09=09=09vhost_vring_call_packed(dev, vq); > +=09=09} > +=09} > + > =09return pkt_idx; > } > =20 >=20 Reviewed-by: Maxime Coquelin I'll fix the commit message while applying. Thanks, Maxime