similar to: [PATCH] vhost: try avoiding avail index access when getting descriptor

On 2020/6/3 ??5:48, Michael S. Tsirkin wrote: > On Wed, Jun 03, 2020 at 03:13:56PM +0800, Jason Wang wrote: >> On 2020/6/2 ??9:05, Michael S. Tsirkin wrote: [...] >>> + >>> +static int fetch_indirect_descs(struct vhost_virtqueue *vq, >>> + struct vhost_desc *indirect, >>> + u16 head) >>> +{ >>> + struct vring_desc desc;

When event index was enabled, we need to fetch used event from userspace memory each time. This userspace fetch (with memory barrier) could be saved sometime when 1) caching used event and 2) if used event is ahead of new and old to new updating does not cross it, we're sure there's no need to notify guest. This will be useful for heavy tx load e.g guest pktgen test with Linux driver

When event index was enabled, we need to fetch used event from userspace memory each time. This userspace fetch (with memory barrier) could be saved sometime when 1) caching used event and 2) if used event is ahead of new and old to new updating does not cross it, we're sure there's no need to notify guest. This will be useful for heavy tx load e.g guest pktgen test with Linux driver

The idea is to support multiple ring formats by converting to a format-independent array of descriptors. This costs extra cycles, but we gain in ability to fetch a batch of descriptors in one go, which is good for code cache locality. When used, this causes a minor performance degradation, it's been kept as simple as possible for ease of review. A follow-up patch gets us back the performance

The idea is to support multiple ring formats by converting to a format-independent array of descriptors. This costs extra cycles, but we gain in ability to fetch a batch of descriptors in one go, which is good for code cache locality. When used, this causes a minor performance degradation, it's been kept as simple as possible for ease of review. A follow-up patch gets us back the performance

The idea is to support multiple ring formats by converting to a format-independent array of descriptors. This costs extra cycles, but we gain in ability to fetch a batch of descriptors in one go, which is good for code cache locality. When used, this causes a minor performance degradation, it's been kept as simple as possible for ease of review. A follow-up patch gets us back the performance

On Wed, Jun 03, 2020 at 03:13:56PM +0800, Jason Wang wrote: > > On 2020/6/2 ??9:05, Michael S. Tsirkin wrote: > > The idea is to support multiple ring formats by converting > > to a format-independent array of descriptors. > > > > This costs extra cycles, but we gain in ability > > to fetch a batch of descriptors in one go, which > > is good for code

The idea is to support multiple ring formats by converting to a format-independent array of descriptors. This costs extra cycles, but we gain in ability to fetch a batch of descriptors in one go, which is good for code cache locality. To simplify benchmarking, I kept the old code around so one can switch back and forth by writing into a module parameter. This will go away in the final

This is used to hide the metadata address from virtqueue helpers. This will allow to implement a vmap based fast accessing to metadata. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vhost.c | 94 +++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 77 insertions(+), 17 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index

On 2019/3/6 ??6:45, Christophe de Dinechin wrote: > >> On 6 Mar 2019, at 08:18, Jason Wang <jasowang at redhat.com> wrote: >> >> This is used to hide the metadata address from virtqueue helpers. This >> will allow to implement a vmap based fast accessing to metadata. >> >> Signed-off-by: Jason Wang <jasowang at redhat.com> >> --- >>

Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/net.c | 3 +- drivers/vhost/vhost.c | 539 ++++++++++++++++++++++++++++++++++++++++++++++---- drivers/vhost/vhost.h | 8 +- 3 files changed, 513 insertions(+), 37 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 30273ad..f55c82f8 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@

> On 6 Mar 2019, at 08:18, Jason Wang <jasowang at redhat.com> wrote: > > This is used to hide the metadata address from virtqueue helpers. This > will allow to implement a vmap based fast accessing to metadata. > > Signed-off-by: Jason Wang <jasowang at redhat.com> > --- > drivers/vhost/vhost.c | 94 +++++++++++++++++++++++++++++++++++++++++---------- > 1

> On 6 Mar 2019, at 08:18, Jason Wang <jasowang at redhat.com> wrote: > > This is used to hide the metadata address from virtqueue helpers. This > will allow to implement a vmap based fast accessing to metadata. > > Signed-off-by: Jason Wang <jasowang at redhat.com> > --- > drivers/vhost/vhost.c | 94 +++++++++++++++++++++++++++++++++++++++++---------- > 1

This patch introduces vhost_prefetch_desc_indices() which could batch descriptor indices fetching and used ring updating. This intends to reduce the cache misses of indices fetching and updating and reduce cache line bounce when virtqueue is almost full. copy_to_user() was used in order to benefit from modern cpus that support fast string copy. Batched virtqueue processing will be the first user.

This patch introduces basic support for packed ring. The idea behinds packed ring is to use a single descriptor ring instead of three different rings (avail, used and descriptor). This could help to reduce the cache contention and PCI transactions. So it was designed to help for the performance for both software implementation and hardware implementation. The implementation was straightforward,

On 2020/6/2 ??9:05, Michael S. Tsirkin wrote: > The idea is to support multiple ring formats by converting > to a format-independent array of descriptors. > > This costs extra cycles, but we gain in ability > to fetch a batch of descriptors in one go, which > is good for code cache locality. > > When used, this causes a minor performance degradation, > it's been kept

On 2020/6/2 ??9:05, Michael S. Tsirkin wrote: > The idea is to support multiple ring formats by converting > to a format-independent array of descriptors. > > This costs extra cycles, but we gain in ability > to fetch a batch of descriptors in one go, which > is good for code cache locality. > > When used, this causes a minor performance degradation, > it's been kept

As testing shows no performance change, switch to that now. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> Signed-off-by: Eugenio P?rez <eperezma at redhat.com> Link: https://lore.kernel.org/r/20200401183118.8334-3-eperezma at redhat.com Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- drivers/vhost/vhost.c | 251 +-----------------------------------------

As testing shows no performance change, switch to that now. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> Signed-off-by: Eugenio P?rez <eperezma at redhat.com> Link: https://lore.kernel.org/r/20200401183118.8334-3-eperezma at redhat.com Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- drivers/vhost/vhost.c | 251 +-----------------------------------------

As testing shows no performance change, switch to that now. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> Signed-off-by: Eugenio P?rez <eperezma at redhat.com> Link: https://lore.kernel.org/r/20200401183118.8334-3-eperezma at redhat.com Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- drivers/vhost/vhost.c | 251 +-----------------------------------------