From: "Liu, Yong" <yong.liu@intel.com>
To: "Gavin Hu (Arm Technology China)" <Gavin.Hu@arm.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>, nd <nd@arm.com>, nd <nd@arm.com>,
"maxime.coquelin@redhat.com" <maxime.coquelin@redhat.com>,
"Bie, Tiwei" <tiwei.bie@intel.com>,
"Wang, Zhihong" <zhihong.wang@intel.com>
Subject: Re: [dpdk-dev] [PATCH v2 03/16] vhost: add burst enqueue function for packed ring
Date: Wed, 25 Sep 2019 09:36:19 +0000 [thread overview]
Message-ID: <86228AFD5BCD8E4EBFD2B90117B5E81E633B0F58@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <VI1PR08MB5376813B4A696E01AC42A54B8F870@VI1PR08MB5376.eurprd08.prod.outlook.com>
> -----Original Message-----
> From: Gavin Hu (Arm Technology China) [mailto:Gavin.Hu@arm.com]
> Sent: Wednesday, September 25, 2019 5:29 PM
> To: Liu, Yong <yong.liu@intel.com>; maxime.coquelin@redhat.com; Bie, Tiwei
> <tiwei.bie@intel.com>; Wang, Zhihong <zhihong.wang@intel.com>
> Cc: dev@dpdk.org; nd <nd@arm.com>; nd <nd@arm.com>
> Subject: RE: [dpdk-dev] [PATCH v2 03/16] vhost: add burst enqueue function
> for packed ring
>
> Hi Marvin,
>
> > -----Original Message-----
> > From: Liu, Yong <yong.liu@intel.com>
> > Sent: Tuesday, September 24, 2019 11:31 AM
> > To: Gavin Hu (Arm Technology China) <Gavin.Hu@arm.com>;
> > maxime.coquelin@redhat.com; Bie, Tiwei <tiwei.bie@intel.com>; Wang,
> > Zhihong <zhihong.wang@intel.com>
> > Cc: dev@dpdk.org; nd <nd@arm.com>
> > Subject: RE: [dpdk-dev] [PATCH v2 03/16] vhost: add burst enqueue
> function
> > for packed ring
> >
> > Thanks, Gavin. My comments are inline.
> >
> > > -----Original Message-----
> > > From: Gavin Hu (Arm Technology China) [mailto:Gavin.Hu@arm.com]
> > > Sent: Monday, September 23, 2019 7:09 PM
> > > To: Liu, Yong <yong.liu@intel.com>; maxime.coquelin@redhat.com; Bie,
> > Tiwei
> > > <tiwei.bie@intel.com>; Wang, Zhihong <zhihong.wang@intel.com>
> > > Cc: dev@dpdk.org; nd <nd@arm.com>
> > > Subject: RE: [dpdk-dev] [PATCH v2 03/16] vhost: add burst enqueue
> > function
> > > for packed ring
> > >
> > > Hi Marvin,
> > >
> > > Is it possible to vectorize the processing?
> > > Other comments inline:
> > > /Gavin
> >
> > Gavin,
> > According to our experiment, only vectorize some parts in [ed]nqueue
> > function can't benefit performance.
> > Functions like vhost_iova_to_vva and virtio_enqueue_offload can't be
> > easily vectorized as they are full of judgment conditions.
> >
> > Thanks,
> > Marvin
> >
> > > > -----Original Message-----
> > > > From: dev <dev-bounces@dpdk.org> On Behalf Of Marvin Liu
> > > > Sent: Friday, September 20, 2019 12:37 AM
> > > > To: maxime.coquelin@redhat.com; tiwei.bie@intel.com;
> > > > zhihong.wang@intel.com
> > > > Cc: dev@dpdk.org; Marvin Liu <yong.liu@intel.com>
> > > > Subject: [dpdk-dev] [PATCH v2 03/16] vhost: add burst enqueue
> function
> > > for
> > > > packed ring
> > > >
> > > > Burst enqueue function will first check whether descriptors are cache
> > > > aligned. It will also check prerequisites in the beginning. Burst
> > > > enqueue function not support chained mbufs, single packet enqueue
> > > > function will handle it.
> > > >
> > > > Signed-off-by: Marvin Liu <yong.liu@intel.com>
> > > >
> > > > diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
> > > > index 5074226f0..67889c80a 100644
> > > > --- a/lib/librte_vhost/vhost.h
> > > > +++ b/lib/librte_vhost/vhost.h
> > > > @@ -39,6 +39,9 @@
> > > >
> > > > #define VHOST_LOG_CACHE_NR 32
> > > >
> > > > +#define PACKED_DESCS_BURST (RTE_CACHE_LINE_SIZE / \
> > > > + sizeof(struct vring_packed_desc))
> > > > +
> > > > #ifdef SUPPORT_GCC_UNROLL_PRAGMA
> > > > #define PRAGMA_PARAM "GCC unroll 4"
> > > > #endif
> > > > @@ -57,6 +60,8 @@
> > > > #define UNROLL_PRAGMA(param) do {} while(0);
> > > > #endif
> > > >
> > > > +#define PACKED_BURST_MASK (PACKED_DESCS_BURST - 1)
> > > > +
> > > > /**
> > > > * Structure contains buffer address, length and descriptor index
> > > > * from vring to do scatter RX.
> > > > diff --git a/lib/librte_vhost/virtio_net.c
> > > b/lib/librte_vhost/virtio_net.c
> > > > index 2b5c47145..c664b27c5 100644
> > > > --- a/lib/librte_vhost/virtio_net.c
> > > > +++ b/lib/librte_vhost/virtio_net.c
> > > > @@ -895,6 +895,84 @@ virtio_dev_rx_split(struct virtio_net *dev,
> > struct
> > > > vhost_virtqueue *vq,
> > > > return pkt_idx;
> > > > }
> > > >
> > > > +static __rte_unused __rte_always_inline int
> > > I remember "__rte_always_inline" should start at the first and separate
> > > line, otherwise you will get a style issue.
> > > /Gavin
> > > > +virtio_dev_rx_burst_packed(struct virtio_net *dev, struct
> > > vhost_virtqueue
> > > > *vq,
> > > > + struct rte_mbuf **pkts)
> > > > +{
> > > > + bool wrap_counter = vq->avail_wrap_counter;
> > > > + struct vring_packed_desc *descs = vq->desc_packed;
> > > > + uint16_t avail_idx = vq->last_avail_idx;
> > > > +
> > > > + uint64_t desc_addrs[PACKED_DESCS_BURST];
> > > > + struct virtio_net_hdr_mrg_rxbuf *hdrs[PACKED_DESCS_BURST];
> > > > + uint32_t buf_offset = dev->vhost_hlen;
> > > > + uint64_t lens[PACKED_DESCS_BURST];
> > > > +
> > > > + uint16_t i;
> > > > +
> > > > + if (unlikely(avail_idx & PACKED_BURST_MASK))
> > > > + return -1;
> > > > +
> > > > + UNROLL_PRAGMA(PRAGMA_PARAM)
> > > > + for (i = 0; i < PACKED_DESCS_BURST; i++) {
> > > > + if (unlikely(pkts[i]->next != NULL))
> > > > + return -1;
> > > > + if (unlikely(!desc_is_avail(&descs[avail_idx + i],
> > > > + wrap_counter)))
> > > > + return -1;
> > > > + }
> > > > +
> > > > + rte_smp_rmb();
> > > > +
> > > > + UNROLL_PRAGMA(PRAGMA_PARAM)
> > > > + for (i = 0; i < PACKED_DESCS_BURST; i++)
> > > > + lens[i] = descs[avail_idx + i].len;
> > > Looks like the code is a strong candidate for vectorization.
> > > > +
> > > > + UNROLL_PRAGMA(PRAGMA_PARAM)
> > > > + for (i = 0; i < PACKED_DESCS_BURST; i++) {
> > > > + if (unlikely(pkts[i]->pkt_len > (lens[i] - buf_offset)))
> > > > + return -1;
> > > > + }
> > > > +
> > > > + UNROLL_PRAGMA(PRAGMA_PARAM)
> > > > + for (i = 0; i < PACKED_DESCS_BURST; i++)
> > > > + desc_addrs[i] = vhost_iova_to_vva(dev, vq,
> > > > + descs[avail_idx + i].addr,
> > > > + &lens[i],
> > > > + VHOST_ACCESS_RW);
> > > > + UNROLL_PRAGMA(PRAGMA_PARAM)
> > > > + for (i = 0; i < PACKED_DESCS_BURST; i++) {
> > > > + if (unlikely(lens[i] != descs[avail_idx + i].len))
> > > > + return -1;
> > > > + }
> > > > +
> > > > + UNROLL_PRAGMA(PRAGMA_PARAM)
> > > > + for (i = 0; i < PACKED_DESCS_BURST; i++) {
> > > > + rte_prefetch0((void *)(uintptr_t)desc_addrs[i]);
> > > > + hdrs[i] = (struct virtio_net_hdr_mrg_rxbuf
> *)desc_addrs[i];
> > > > + lens[i] = pkts[i]->pkt_len + dev->vhost_hlen;
> > > > + }
> > > > +
> > > > + UNROLL_PRAGMA(PRAGMA_PARAM)
> > > > + for (i = 0; i < PACKED_DESCS_BURST; i++)
> > > > + virtio_enqueue_offload(pkts[i], &hdrs[i]->hdr);
> > > > +
> > > A store barrier here is missing, last_avail_idx may be observed before
> the
> > > above enqueue completion on weak memory order architectures.
> > > For x86, a compiler barrier is also required.
> > >
> > Thanks a lot for point out. I guess your mention is that need to add
> barrier
> > between memcpy and enqueue.
> > last_avail_idx is just local variable, no barrier is need to protect it.
>
> Sorry I was wrong, yes, last_avail_idx is a local variable(or we may call
> it meta data).
> Copying the headers and payload does not need to be ordered, we just need
> to ensure all these happen before updating the idx, which is the single
> synchronization point.
> In one word, no barriers are required here.
> /Gavin
> >
NP:) Nothing changed here in V3 patch. Thanks for kindly reviewing.
> > > > + vq->last_avail_idx += PACKED_DESCS_BURST;
> > > > + if (vq->last_avail_idx >= vq->size) {
> > > > + vq->last_avail_idx -= vq->size;
> > > > + vq->avail_wrap_counter ^= 1;
> > > > + }
> > > > +
> > > > + UNROLL_PRAGMA(PRAGMA_PARAM)
> > > > + for (i = 0; i < PACKED_DESCS_BURST; i++) {
> > > > + rte_memcpy((void *)(uintptr_t)(desc_addrs[i] +
> buf_offset),
> > > > + rte_pktmbuf_mtod_offset(pkts[i], void *, 0),
> > > > + pkts[i]->pkt_len);
> > > > + }
> > > > +
> > > > + return 0;
> > > > +}
> > > > +
> > > > static __rte_unused int16_t
> > > > virtio_dev_rx_single_packed(struct virtio_net *dev, struct
> > > vhost_virtqueue
> > > > *vq,
> > > > struct rte_mbuf *pkt)
> > > > --
> > > > 2.17.1
next prev parent reply other threads:[~2019-09-25 9:36 UTC|newest]
Thread overview: 199+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-05 16:14 [dpdk-dev] [PATCH v1 00/14] vhost packed ring performance optimization Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 01/14] vhost: add single packet enqueue function Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 00/16] vhost packed ring performance optimization Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 01/16] vhost: add single packet enqueue function Marvin Liu
2019-09-23 9:09 ` Gavin Hu (Arm Technology China)
2019-09-23 9:15 ` Liu, Yong
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 00/15] vhost packed ring performance optimization Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 01/15] vhost: add single packet enqueue function Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 02/15] vhost: unify unroll pragma parameter Marvin Liu
2019-09-26 5:41 ` Tiwei Bie
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 03/15] vhost: add batch enqueue function for packed ring Marvin Liu
2019-09-25 19:31 ` Mattias Rönnblom
2019-10-09 2:45 ` Liu, Yong
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 04/15] vhost: add single packet dequeue function Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 05/15] vhost: add batch " Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 06/15] vhost: flush vhost enqueue shadow ring by batch Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 07/15] vhost: add flush function for batch enqueue Marvin Liu
2019-09-26 9:24 ` Gavin Hu (Arm Technology China)
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 08/15] vhost: buffer vhost dequeue shadow ring Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 09/15] vhost: split enqueue and dequeue flush functions Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 10/15] vhost: optimize enqueue function of packed ring Marvin Liu
2019-09-26 5:56 ` Tiwei Bie
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 11/15] vhost: add batch and single zero dequeue functions Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 12/15] vhost: optimize dequeue function of packed ring Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 13/15] vhost: cache address translation result Marvin Liu
2019-09-26 5:32 ` Tiwei Bie
2019-10-09 2:08 ` Liu, Yong
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 14/15] vhost: check whether disable software pre-fetch Marvin Liu
2019-09-25 17:13 ` [dpdk-dev] [PATCH v3 15/15] vhost: optimize packed ring dequeue when in-order Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 00/14] vhost packed ring performance optimization Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 01/14] vhost: add single packet enqueue function Marvin Liu
2019-10-11 12:34 ` Maxime Coquelin
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 02/14] vhost: unify unroll pragma parameter Marvin Liu
2019-10-11 12:48 ` Maxime Coquelin
2019-10-14 6:57 ` Liu, Yong
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 03/14] vhost: add batch enqueue function for packed ring Marvin Liu
2019-10-11 12:49 ` Maxime Coquelin
2019-10-11 14:22 ` Maxime Coquelin
2019-10-15 6:15 ` Liu, Yong
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 04/14] vhost: add single packet dequeue function Marvin Liu
2019-10-11 13:04 ` Maxime Coquelin
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 05/14] vhost: add batch " Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 06/14] vhost: flush vhost enqueue shadow ring by batch Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 07/14] vhost: add flush function for batch enqueue Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 08/14] vhost: buffer vhost dequeue shadow ring Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 09/14] vhost: split enqueue and dequeue flush functions Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 10/14] vhost: optimize enqueue function of packed ring Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 11/14] vhost: add batch and single zero dequeue functions Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 12/14] vhost: optimize dequeue function of packed ring Marvin Liu
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 13/14] vhost: check whether disable software pre-fetch Marvin Liu
2019-10-11 14:12 ` Maxime Coquelin
2019-10-14 3:08 ` Liu, Yong
2019-10-09 13:38 ` [dpdk-dev] [PATCH v4 14/14] vhost: optimize packed ring dequeue when in-order Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 00/13] vhost packed ring performance optimization Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 01/13] vhost: add packed ring indexes increasing function Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 02/13] vhost: add packed ring single enqueue Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 03/13] vhost: try to unroll for each loop Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 04/13] vhost: add packed ring batch enqueue Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 05/13] vhost: add packed ring single dequeue Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 06/13] vhost: add packed ring batch dequeue Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 07/13] vhost: flush enqueue updates by batch Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 08/13] vhost: flush batched enqueue descs flags directly Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 09/13] vhost: buffer packed ring dequeue updates Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 10/13] vhost: optimize packed ring enqueue Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 11/13] vhost: add packed ring zcopy batch and single dequeue Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 12/13] vhost: optimize packed ring dequeue Marvin Liu
2019-10-15 14:30 ` [dpdk-dev] [PATCH v5 13/13] vhost: optimize packed ring dequeue when in-order Marvin Liu
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 00/13] vhost packed ring performance optimization Marvin Liu
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 01/13] vhost: add packed ring indexes increasing function Marvin Liu
2019-10-16 10:28 ` Maxime Coquelin
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 02/13] vhost: add packed ring single enqueue Marvin Liu
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 03/13] vhost: try to unroll for each loop Marvin Liu
2019-10-16 10:30 ` Maxime Coquelin
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 04/13] vhost: add packed ring batch enqueue Marvin Liu
2019-10-15 11:35 ` Gavin Hu (Arm Technology China)
2019-10-15 12:45 ` Liu, Yong
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 05/13] vhost: add packed ring single dequeue Marvin Liu
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 06/13] vhost: add packed ring batch dequeue Marvin Liu
2019-10-16 10:36 ` Maxime Coquelin
2019-10-17 1:30 ` Liu, Yong
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 07/13] vhost: flush enqueue updates by batch Marvin Liu
2019-10-16 11:05 ` Maxime Coquelin
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 08/13] vhost: flush batched enqueue descs directly Marvin Liu
2019-10-16 11:06 ` Maxime Coquelin
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 09/13] vhost: buffer packed ring dequeue updates Marvin Liu
2019-10-16 12:38 ` Maxime Coquelin
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 10/13] vhost: optimize packed ring enqueue Marvin Liu
2019-10-16 12:41 ` Maxime Coquelin
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 11/13] vhost: add packed ring zcopy batch and single dequeue Marvin Liu
2019-10-17 7:25 ` Maxime Coquelin
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 12/13] vhost: optimize packed ring dequeue Marvin Liu
2019-10-17 7:28 ` Maxime Coquelin
2019-10-15 16:07 ` [dpdk-dev] [PATCH v6 13/13] vhost: optimize packed ring dequeue when in-order Marvin Liu
2019-10-17 7:29 ` Maxime Coquelin
2019-10-17 7:31 ` [dpdk-dev] [PATCH v6 00/13] vhost packed ring performance optimization Maxime Coquelin
2019-10-17 7:32 ` Liu, Yong
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 " Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 01/13] vhost: add packed ring indexes increasing function Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 02/13] vhost: add packed ring single enqueue Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 03/13] vhost: try to unroll for each loop Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 04/13] vhost: add packed ring batch enqueue Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 05/13] vhost: add packed ring single dequeue Marvin Liu
2019-10-21 9:45 ` Maxime Coquelin
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 06/13] vhost: add packed ring batch dequeue Marvin Liu
2019-10-21 9:47 ` Maxime Coquelin
2019-10-21 14:29 ` Liu, Yong
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 07/13] vhost: flush enqueue updates by cacheline Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 08/13] vhost: flush batched enqueue descs directly Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 09/13] vhost: buffer packed ring dequeue updates Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 10/13] vhost: optimize packed ring enqueue Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 11/13] vhost: add packed ring zcopy batch and single dequeue Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 12/13] vhost: optimize packed ring dequeue Marvin Liu
2019-10-21 15:40 ` [dpdk-dev] [PATCH v7 13/13] vhost: optimize packed ring dequeue when in-order Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 00/13] vhost packed ring performance optimization Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 01/13] vhost: add packed ring indexes increasing function Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 02/13] vhost: add packed ring single enqueue Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 03/13] vhost: try to unroll for each loop Marvin Liu
2019-10-24 6:16 ` Maxime Coquelin
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 04/13] vhost: add packed ring batch enqueue Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 05/13] vhost: add packed ring single dequeue Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 06/13] vhost: add packed ring batch dequeue Marvin Liu
2019-10-24 6:27 ` Maxime Coquelin
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 07/13] vhost: flush enqueue updates by cacheline Marvin Liu
2019-10-24 6:29 ` Maxime Coquelin
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 08/13] vhost: flush batched enqueue descs directly Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 09/13] vhost: buffer packed ring dequeue updates Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 10/13] vhost: optimize packed ring enqueue Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 11/13] vhost: add packed ring zcopy batch and single dequeue Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 12/13] vhost: optimize packed ring dequeue Marvin Liu
2019-10-21 22:08 ` [dpdk-dev] [PATCH v8 13/13] vhost: optimize packed ring dequeue when in-order Marvin Liu
2019-10-24 6:49 ` [dpdk-dev] [PATCH v8 00/13] vhost packed ring performance optimization Maxime Coquelin
2019-10-24 7:18 ` Liu, Yong
2019-10-24 8:24 ` Maxime Coquelin
2019-10-24 8:29 ` Liu, Yong
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 " Marvin Liu
2019-10-24 10:18 ` Maxime Coquelin
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 01/13] vhost: add packed ring indexes increasing function Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 02/13] vhost: add packed ring single enqueue Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 03/13] vhost: try to unroll for each loop Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 04/13] vhost: add packed ring batch enqueue Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 05/13] vhost: add packed ring single dequeue Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 06/13] vhost: add packed ring batch dequeue Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 07/13] vhost: flush enqueue updates by cacheline Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 08/13] vhost: flush batched enqueue descs directly Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 09/13] vhost: buffer packed ring dequeue updates Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 10/13] vhost: optimize packed ring enqueue Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 11/13] vhost: add packed ring zcopy batch and single dequeue Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 12/13] vhost: optimize packed ring dequeue Marvin Liu
2019-10-24 16:08 ` [dpdk-dev] [PATCH v9 13/13] vhost: optimize packed ring dequeue when in-order Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 02/16] vhost: unify unroll pragma parameter Marvin Liu
2019-09-23 5:21 ` Tiwei Bie
2019-09-23 10:08 ` Gavin Hu (Arm Technology China)
2019-09-24 3:12 ` Liu, Yong
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 03/16] vhost: add burst enqueue function for packed ring Marvin Liu
2019-09-23 5:46 ` Tiwei Bie
2019-09-23 11:08 ` Gavin Hu (Arm Technology China)
2019-09-24 3:30 ` Liu, Yong
2019-09-25 9:29 ` Gavin Hu (Arm Technology China)
2019-09-25 9:36 ` Liu, Yong [this message]
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 04/16] vhost: add single packet dequeue function Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 05/16] vhost: add burst " Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 06/16] vhost: rename flush shadow used ring functions Marvin Liu
2019-09-23 6:05 ` Tiwei Bie
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 07/16] vhost: flush vhost enqueue shadow ring by burst Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 08/16] vhost: add flush function for burst enqueue Marvin Liu
2019-09-25 3:37 ` Gavin Hu (Arm Technology China)
2019-09-25 5:37 ` Liu, Yong
2019-09-25 6:51 ` Liu, Yong
2019-09-25 7:15 ` Gavin Hu (Arm Technology China)
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 09/16] vhost: buffer vhost dequeue shadow ring Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 10/16] vhost: split enqueue and dequeue flush functions Marvin Liu
2019-09-25 4:11 ` Gavin Hu (Arm Technology China)
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 11/16] vhost: optimize enqueue function of packed ring Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 12/16] vhost: add burst and single zero dequeue functions Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 13/16] vhost: optimize dequeue function of packed ring Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 14/16] vhost: cache address translation result Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 15/16] vhost: check whether disable software pre-fetch Marvin Liu
2019-09-19 16:36 ` [dpdk-dev] [PATCH v2 16/16] vhost: optimize packed ring dequeue when in-order Marvin Liu
2019-09-23 9:05 ` [dpdk-dev] [PATCH v2 00/16] vhost packed ring performance optimization Gavin Hu (Arm Technology China)
2019-09-23 9:29 ` Liu, Yong
2019-09-23 16:06 ` [dpdk-dev] [PATCH v1 01/14] vhost: add single packet enqueue function Stephen Hemminger
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 02/14] vhost: add burst enqueue function for packed ring Marvin Liu
[not found] ` <CGME20190905103107eucas1p2296feb0cc7be0538332dc698a72585bb@eucas1p2.samsung.com>
2019-09-05 10:31 ` Ilya Maximets
2019-09-06 1:42 ` Liu, Yong
2019-09-06 9:00 ` Liu, Yong
2019-09-06 9:11 ` Bruce Richardson
2019-09-06 9:23 ` Liu, Yong
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 03/14] vhost: add single packet dequeue function Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 04/14] vhost: add burst " Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 05/14] vhost: rename flush shadow used ring functions Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 06/14] vhost: flush vhost enqueue shadow ring by burst Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 07/14] vhost: add flush function for burst enqueue Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 08/14] vhost: buffer vhost dequeue shadow ring Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 09/14] vhost: split enqueue and dequeue flush functions Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 10/14] vhost: optimize Rx function of packed ring Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 11/14] vhost: add burst and single zero dequeue functions Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 12/14] vhost: optimize Tx function of packed ring Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 13/14] vhost: cache address translation result Marvin Liu
2019-09-05 16:14 ` [dpdk-dev] [PATCH v1 14/14] vhost: check whether disable software pre-fetch Marvin Liu
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=86228AFD5BCD8E4EBFD2B90117B5E81E633B0F58@SHSMSX103.ccr.corp.intel.com \
--to=yong.liu@intel.com \
--cc=Gavin.Hu@arm.com \
--cc=dev@dpdk.org \
--cc=maxime.coquelin@redhat.com \
--cc=nd@arm.com \
--cc=tiwei.bie@intel.com \
--cc=zhihong.wang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
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;
as well as URLs for NNTP newsgroup(s).