search for: single_task_running

...(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) && > + single_task_running(); So I find it quite unfortunate that this still uses single_task_running. This means that for example a SCHED_IDLE task will prevent polling from becoming active, and that seems like a bug, or at least an undocumented feature :). Unfortunately this logic affects the behaviour as observed by use...

...(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) && > + single_task_running(); So I find it quite unfortunate that this still uses single_task_running. This means that for example a SCHED_IDLE task will prevent polling from becoming active, and that seems like a bug, or at least an undocumented feature :). Unfortunately this logic affects the behaviour as observed by use...

...e) >> > +{ >> > + return likely(!need_resched()) && >> > + likely(!time_after(busy_clock(), endtime)) && >> > + likely(!signal_pending(current)) && >> > + !vhost_has_work(dev) && >> > + single_task_running(); > So I find it quite unfortunate that this still uses single_task_running. > This means that for example a SCHED_IDLE task will prevent polling from > becoming active, and that seems like a bug, or at least > an undocumented feature :). Yes, it may need more thoughts. > > Unf...

...(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) && > + single_task_running(); > +} > + > +static int vhost_net_tx_get_vq_desc(struct vhost_net *net, > + struct vhost_virtqueue *vq, > + struct iovec iov[], unsigned int iov_size, > + unsigned int *out_num, unsigned int *in_num) > +{ > + unsigned long uninitialized_var(endtime); &...

...(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) && > + single_task_running(); > +} > + > +static int vhost_net_tx_get_vq_desc(struct vhost_net *net, > + struct vhost_virtqueue *vq, > + struct iovec iov[], unsigned int iov_size, > + unsigned int *out_num, unsigned int *in_num) > +{ > + unsigned long uninitialized_var(endtime); &...

...o vhost-net ([1], [2]). Some of them seem relevant for these > > patches as well: > > > > - What happens in overcommit scenarios? > > We have an optimization here: busy polling will end if more than one > processes is runnable on local cpu. This was done by checking > single_task_running() in each iteration. So at the worst case, busy > polling should be as fast as or only a minor regression compared to > normal case. You can see this from the last test result. > > > - Have you checked the effect of polling on some macro benchmarks? > > I'm not sure I get...

...o vhost-net ([1], [2]). Some of them seem relevant for these > > patches as well: > > > > - What happens in overcommit scenarios? > > We have an optimization here: busy polling will end if more than one > processes is runnable on local cpu. This was done by checking > single_task_running() in each iteration. So at the worst case, busy > polling should be as fast as or only a minor regression compared to > normal case. You can see this from the last test result. > > > - Have you checked the effect of polling on some macro benchmarks? > > I'm not sure I get...

...ix would be to record the CPU id and break out of loop if that changes. Also - defer this until we actually know we need it? > + > + return busyloop_timeout && !need_resched() && > + !time_after(now, endtime) && !vhost_has_work(dev) && > + single_task_running(); signal pending as well? > +} > + > /* Expects to be always run from workqueue - which acts as > * read-size critical section for our kind of RCU. */ > static void handle_tx(struct vhost_net *net) > { > struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_...

...ix would be to record the CPU id and break out of loop if that changes. Also - defer this until we actually know we need it? > + > + return busyloop_timeout && !need_resched() && > + !time_after(now, endtime) && !vhost_has_work(dev) && > + single_task_running(); signal pending as well? > +} > + > /* Expects to be always run from workqueue - which acts as > * read-size critical section for our kind of RCU. */ > static void handle_tx(struct vhost_net *net) > { > struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_...

...(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) && > + single_task_running(); > +} > + > +static int vhost_net_tx_get_vq_desc(struct vhost_net *net, > + struct vhost_virtqueue *vq, > + struct iovec iov[], unsigned int iov_size, > + unsigned int *out_num, unsigned int *in_num) > +{ > + unsigned long uninitialized_var(endtime); &...

...(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) && > + single_task_running(); > +} > + > +static int vhost_net_tx_get_vq_desc(struct vhost_net *net, > + struct vhost_virtqueue *vq, > + struct iovec iov[], unsigned int iov_size, > + unsigned int *out_num, unsigned int *in_num) > +{ > + unsigned long uninitialized_var(endtime); &...

...endtime) > >>+{ > >>+ return likely(!need_resched()) && > >>+ likely(!time_after(busy_clock(), endtime)) && > >>+ likely(!signal_pending(current)) && > >>+ !vhost_has_work(dev) && > >>+ single_task_running(); > >>+} > >>+ > >>+static int vhost_net_tx_get_vq_desc(struct vhost_net *net, > >>+ struct vhost_virtqueue *vq, > >>+ struct iovec iov[], unsigned int iov_size, > >>+ unsigned int *out_num, unsigned int *in_num) > >&...

...endtime) > >>+{ > >>+ return likely(!need_resched()) && > >>+ likely(!time_after(busy_clock(), endtime)) && > >>+ likely(!signal_pending(current)) && > >>+ !vhost_has_work(dev) && > >>+ single_task_running(); > >>+} > >>+ > >>+static int vhost_net_tx_get_vq_desc(struct vhost_net *net, > >>+ struct vhost_virtqueue *vq, > >>+ struct iovec iov[], unsigned int iov_size, > >>+ unsigned int *out_num, unsigned int *in_num) > >&...

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

This path introduces a helper which can give a hint for whether or not there's a work queued in the work list. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vhost.c | 6 ++++++ drivers/vhost/vhost.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index eec2f11..d42d11e 100644 --- a/drivers/vhost/vhost.c +++

This path introduces a helper which can give a hint for whether or not there's a work queued in the work list. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vhost.c | 6 ++++++ drivers/vhost/vhost.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index eec2f11..d42d11e 100644 --- a/drivers/vhost/vhost.c +++

...h(); } +static bool tx_can_busy_poll(struct vhost_dev *dev, + unsigned long endtime) +{ + unsigned long now = local_clock() >> 10; + + return busyloop_timeout && !need_resched() && + !time_after(now, endtime) && !vhost_has_work(dev) && + single_task_running(); +} + /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_tx(struct vhost_net *net) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; + unsign...

...-3%/ -11%/ +23%/ +7%/ +42% 16384/ 4/ -3%/ -3%/ -4%/ +5%/ +115% 16384/ 8/ -1%/ 0%/ -1%/ -3%/ +32% 65535/ 1/ +1%/ 0%/ +2%/ 0%/ +66% 65535/ 4/ -1%/ -1%/ 0%/ +4%/ +492% 65535/ 8/ 0%/ -1%/ -1%/ +4%/ +38% Changes from V3: - drop single_task_running() - use cpu_relax_lowlatency() instead of cpu_relax() Changes from V2: - rename vhost_vq_more_avail() to vhost_vq_avail_empty(). And return false we __get_user() fails. - do not bother premmptions/timers for good path. - use vhost_vring_state as ioctl parameter instead of reinveting a new one. - a...

...-3%/ -11%/ +23%/ +7%/ +42% 16384/ 4/ -3%/ -3%/ -4%/ +5%/ +115% 16384/ 8/ -1%/ 0%/ -1%/ -3%/ +32% 65535/ 1/ +1%/ 0%/ +2%/ 0%/ +66% 65535/ 4/ -1%/ -1%/ 0%/ +4%/ +492% 65535/ 8/ 0%/ -1%/ -1%/ +4%/ +38% Changes from V3: - drop single_task_running() - use cpu_relax_lowlatency() instead of cpu_relax() Changes from V2: - rename vhost_vq_more_avail() to vhost_vq_avail_empty(). And return false we __get_user() fails. - do not bother premmptions/timers for good path. - use vhost_vring_state as ioctl parameter instead of reinveting a new one. - a...