search for: vhost_can_busy_pol

...anged, 22 insertions(+), 13 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 3939c50..811c0e5 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -396,13 +396,10 @@ static inline unsigned long busy_clock(void) return local_clock() >> 10; } -static bool vhost_can_busy_poll(struct vhost_dev *dev, - unsigned long endtime) +static bool vhost_can_busy_poll(unsigned long endtime) { - return likely(!need_resched()) && - likely(!time_after(busy_clock(), endtime)) && - likely(!signal_pending(current)) && - !vhost_has_work(dev...

...insertions(+), 30 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index eeaf6739215f..0e85f628b965 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -391,13 +391,14 @@ static inline unsigned long busy_clock(void) return local_clock() >> 10; } -static bool vhost_can_busy_poll(struct vhost_dev *dev, - unsigned long endtime) +static bool vhost_can_busy_poll(unsigned long endtime) { - return likely(!need_resched()) && - likely(!time_after(busy_clock(), endtime)) && - likely(!signal_pending(current)) && - !vhost_has_work(dev...

...insertions(+), 30 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index eeaf6739215f..0e85f628b965 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -391,13 +391,14 @@ static inline unsigned long busy_clock(void) return local_clock() >> 10; } -static bool vhost_can_busy_poll(struct vhost_dev *dev, - unsigned long endtime) +static bool vhost_can_busy_poll(unsigned long endtime) { - return likely(!need_resched()) && - likely(!time_after(busy_clock(), endtime)) && - likely(!signal_pending(current)) && - !vhost_has_work(dev...

Under heavy load vhost tx busypoll tend not to suppress vq kicks, which causes poor guest tx performance. The detailed scenario is described in commitlog of patch 2. Rx seems not to have that serious problem, but for consistency I made a similar change on rx to avoid rx wakeups (patch 3). Additionary patch 4 is to avoid rx kicks under heavy load during busypoll. Tx performance is greatly improved

...+ b/drivers/vhost/net.c > @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + likely(!time_after(busy_clock(), endtime)) && > + likely(!signal_pending(current)) && > + !vhost_has_work(dev) && > +...

...+ b/drivers/vhost/net.c > @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + likely(!time_after(busy_clock(), endtime)) && > + likely(!signal_pending(current)) && > + !vhost_has_work(dev) && > +...

...b/drivers/vhost/net.c > @@ -287,6 +287,41 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + likely(!time_after(busy_clock(), endtime)) && > + likely(!signal_pending(current)) && > + !vhost_has_work(dev) && > +...

...b/drivers/vhost/net.c > @@ -287,6 +287,41 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + likely(!time_after(busy_clock(), endtime)) && > + likely(!signal_pending(current)) && > + !vhost_has_work(dev) && > +...

...py_callback(struct ubuf_info *ubuf, bool success) > >> rcu_read_unlock_bh(); > >> } > >> > >>+static inline unsigned long busy_clock(void) > >>+{ > >>+ return local_clock() >> 10; > >>+} > >>+ > >>+static bool vhost_can_busy_poll(struct vhost_dev *dev, > >>+ unsigned long endtime) > >>+{ > >>+ return likely(!need_resched()) && > >>+ likely(!time_after(busy_clock(), endtime)) && > >>+ likely(!signal_pending(current)) && > >>+...

...py_callback(struct ubuf_info *ubuf, bool success) > >> rcu_read_unlock_bh(); > >> } > >> > >>+static inline unsigned long busy_clock(void) > >>+{ > >>+ return local_clock() >> 10; > >>+} > >>+ > >>+static bool vhost_can_busy_poll(struct vhost_dev *dev, > >>+ unsigned long endtime) > >>+{ > >>+ return likely(!need_resched()) && > >>+ likely(!time_after(busy_clock(), endtime)) && > >>+ likely(!signal_pending(current)) && > >>+...

...it a/drivers/vhost/net.c b/drivers/vhost/net.c > index eeaf6739215f..0e85f628b965 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -391,13 +391,14 @@ static inline unsigned long busy_clock(void) > return local_clock() >> 10; > } > > -static bool vhost_can_busy_poll(struct vhost_dev *dev, > - unsigned long endtime) > +static bool vhost_can_busy_poll(unsigned long endtime) > { > - return likely(!need_resched()) && > - likely(!time_after(busy_clock(), endtime)) && > - likely(!signal_pending(current)) &&amp...

...a/drivers/vhost/net.c b/drivers/vhost/net.c > index eeaf6739215f..0e85f628b965 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -391,13 +391,14 @@ static inline unsigned long busy_clock(void) > return local_clock() >> 10; > } > > -static bool vhost_can_busy_poll(struct vhost_dev *dev, > - unsigned long endtime) > +static bool vhost_can_busy_poll(unsigned long endtime) > { > - return likely(!need_resched()) && > - likely(!time_after(busy_clock(), endtime)) && > - likely(!signal_pending(current)) &&am...

...gt; @@ -437,10 +438,21 @@ static int vhost_net_tx_get_vq_desc(struct >> vhost_net *net, >> ? ????? if (r == vq->num && vq->busyloop_timeout) { >> ????????? preempt_disable(); >> -??????? endtime = busy_clock() + vq->busyloop_timeout; >> -??????? while (vhost_can_busy_poll(vq->dev, endtime) && >> -?????????????? vhost_vq_avail_empty(vq->dev, vq)) >> +??????? if (vq->busyloop_endtime) { >> +??????????? endtime = vq->busyloop_endtime; >> +??????????? vq->busyloop_endtime = 0; > > Looks like endtime may be before cu...

...gt; @@ -437,10 +438,21 @@ static int vhost_net_tx_get_vq_desc(struct >> vhost_net *net, >> ? ????? if (r == vq->num && vq->busyloop_timeout) { >> ????????? preempt_disable(); >> -??????? endtime = busy_clock() + vq->busyloop_timeout; >> -??????? while (vhost_can_busy_poll(vq->dev, endtime) && >> -?????????????? vhost_vq_avail_empty(vq->dev, vq)) >> +??????? if (vq->busyloop_endtime) { >> +??????????? endtime = vq->busyloop_endtime; >> +??????????? vq->busyloop_endtime = 0; > > Looks like endtime may be before cu...

...VQ_TX: VHOST_NET_VQ_RX); > + > + vhost_disable_notify(&net->dev, vq); > + sock = rvq->private_data; > + busyloop_timeout = rx ? rvq->busyloop_timeout : tvq->busyloop_timeout; > + > + preempt_disable(); > + endtime = busy_clock() + busyloop_timeout; > + while (vhost_can_busy_poll(tvq->dev, endtime) && > + !(sock && sk_has_rx_data(sock->sk)) && > + vhost_vq_avail_empty(tvq->dev, tvq)) > + cpu_relax(); > + preempt_enable(); > + > + if ((rx && !vhost_vq_avail_empty(&net->dev, vq)) || > + (...

...VQ_TX: VHOST_NET_VQ_RX); > + > + vhost_disable_notify(&net->dev, vq); > + sock = rvq->private_data; > + busyloop_timeout = rx ? rvq->busyloop_timeout : tvq->busyloop_timeout; > + > + preempt_disable(); > + endtime = busy_clock() + busyloop_timeout; > + while (vhost_can_busy_poll(tvq->dev, endtime) && > + !(sock && sk_has_rx_data(sock->sk)) && > + vhost_vq_avail_empty(tvq->dev, tvq)) > + cpu_relax(); > + preempt_enable(); > + > + if ((rx && !vhost_vq_avail_empty(&net->dev, vq)) || > + (...

...b/drivers/vhost/net.c > @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + likely(!time_after(busy_clock(), endtime)) && > + likely(!signal_pending(current)) && > + !vhost_has_work(dev) && > +...

...b/drivers/vhost/net.c > @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + likely(!time_after(busy_clock(), endtime)) && > + likely(!signal_pending(current)) && > + !vhost_has_work(dev) && > +...

This series tries to add basic busy polling for vhost net. The idea is simple: at the end of tx/rx processing, busy polling for new tx added descriptor and rx receive socket for a while. The maximum number of time (in us) could be spent on busy polling was specified ioctl. Test A were done through: - 50 us as busy loop timeout - Netperf 2.6 - Two machines with back to back connected mlx4 - Guest

This series tries to add basic busy polling for vhost net. The idea is simple: at the end of tx/rx processing, busy polling for new tx added descriptor and rx receive socket for a while. The maximum number of time (in us) could be spent on busy polling was specified ioctl. Test A were done through: - 50 us as busy loop timeout - Netperf 2.6 - Two machines with back to back connected mlx4 - Guest