search for: woken

This should make systems more stable where resuming the GPU fails. This can happen due to bad firmware or due to a bug within the kernel. The last thing which should happen in either case is an unusable system. Signed-off-by: Karol Herbst <kherbst at redhat.com> --- drm/nouveau/nouveau_drm.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git

On Tue, Nov 21, 2017 at 04:01:16PM +0100, Karol Herbst wrote: > This should make systems more stable where resuming the GPU fails. This > can happen due to bad firmware or due to a bug within the kernel. The > last thing which should happen in either case is an unusable system. > > v2: do the same in nouveau_pmops_resume > > Tested-by: Karl Hastings <kazen at

On Tue, Nov 21, 2017 at 08:03:20PM +0100, Karol Herbst wrote: > On Tue, Nov 21, 2017 at 6:46 PM, Thierry Reding > <thierry.reding at gmail.com> wrote: > > On Tue, Nov 21, 2017 at 04:01:16PM +0100, Karol Herbst wrote: > >> This should make systems more stable where resuming the GPU fails. This > >> can happen due to bad firmware or due to a bug within the kernel.

...crement. We'd need to restructure the code a bit, but its not fundamentally impossible. We could equally apply the head hashing to the current ticket implementation and avoid the current bitmap iteration. > Now with the old pv ticketlock code an vCPU would only go to sleep once and > be woken up when it was its turn. With this new code it is woken up twice > (and twice it goes to sleep). With an overcommit scenario this would imply > that we will have at least twice as many VMEXIT as with the previous code. An astute observation, I had not considered that. > I presume when y...

...crement. We'd need to restructure the code a bit, but its not fundamentally impossible. We could equally apply the head hashing to the current ticket implementation and avoid the current bitmap iteration. > Now with the old pv ticketlock code an vCPU would only go to sleep once and > be woken up when it was its turn. With this new code it is woken up twice > (and twice it goes to sleep). With an overcommit scenario this would imply > that we will have at least twice as many VMEXIT as with the previous code. An astute observation, I had not considered that. > I presume when y...

This should make systems more stable where resuming the GPU fails. This can happen due to bad firmware or due to a bug within the kernel. The last thing which should happen in either case is an unusable system. v2: do the same in nouveau_pmops_resume Tested-by: Karl Hastings <kazen at redhat.com> Signed-off-by: Karol Herbst <kherbst at redhat.com> --- drm/nouveau/nouveau_drm.c | 31

...t; > Currently we check if there is any tasks waiting to be run on > current cpu in rng_dev_read() by need_resched(). But need_resched() > doesn't work because rng_dev_read() is executing in user context. I don't understand this explanation? I'd expect the sysfs process to be woken by the mutex_unlock(). If we're really high priority (vs. the sysfs process) then I can see why we'd need schedule_timeout_interruptible() instead of just schedule(), and in that case, need_resched() would be false too. You could argue that's intended behaviour, but I can't see ho...

...t; > Currently we check if there is any tasks waiting to be run on > current cpu in rng_dev_read() by need_resched(). But need_resched() > doesn't work because rng_dev_read() is executing in user context. I don't understand this explanation? I'd expect the sysfs process to be woken by the mutex_unlock(). If we're really high priority (vs. the sysfs process) then I can see why we'd need schedule_timeout_interruptible() instead of just schedule(), and in that case, need_resched() would be false too. You could argue that's intended behaviour, but I can't see ho...

On Tue, Nov 21, 2017 at 6:46 PM, Thierry Reding <thierry.reding at gmail.com> wrote: > On Tue, Nov 21, 2017 at 04:01:16PM +0100, Karol Herbst wrote: >> This should make systems more stable where resuming the GPU fails. This >> can happen due to bad firmware or due to a bug within the kernel. The >> last thing which should happen in either case is an unusable system.

...aiting to be run on > > > current cpu in rng_dev_read() by need_resched(). But need_resched() > > > doesn't work because rng_dev_read() is executing in user context. > > > > I don't understand this explanation? I'd expect the sysfs process to be > > woken by the mutex_unlock(). > > But actually sysfs process's not woken always, this is they the > process gets stuck. %s/they/why/ Hi Rusty, Reference: http://www.linuxgrill.com/anonymous/fire/netfilter/kernel-hacking-HOWTO-2.html read() syscall of /dev/hwrng will enter into kernel, t...

...aiting to be run on > > > current cpu in rng_dev_read() by need_resched(). But need_resched() > > > doesn't work because rng_dev_read() is executing in user context. > > > > I don't understand this explanation? I'd expect the sysfs process to be > > woken by the mutex_unlock(). > > But actually sysfs process's not woken always, this is they the > process gets stuck. %s/they/why/ Hi Rusty, Reference: http://www.linuxgrill.com/anonymous/fire/netfilter/kernel-hacking-HOWTO-2.html read() syscall of /dev/hwrng will enter into kernel, t...

...rmance tests against the PV ticketlock with normal and over-committed scenarios? Looking at this with a pen and paper I see that compared to PV ticketlock for the CPUs that are contending on the queue (so they go to pv_wait_head_and_link, then progress to pv_wait_head), they go sleep twice and get woken up twice. In PV ticketlock the contending CPUs would only go to sleep once and woken up once it was their turn. That of course is the worst case scenario - where the CPU that has the lock is taking forever to do its job and the host is quite overcommitted. Thanks!

...rmance tests against the PV ticketlock with normal and over-committed scenarios? Looking at this with a pen and paper I see that compared to PV ticketlock for the CPUs that are contending on the queue (so they go to pv_wait_head_and_link, then progress to pv_wait_head), they go sleep twice and get woken up twice. In PV ticketlock the contending CPUs would only go to sleep once and woken up once it was their turn. That of course is the worst case scenario - where the CPU that has the lock is taking forever to do its job and the host is quite overcommitted. Thanks!

...smaller > increments, sitting in the icecast CVS tree (this was to help with > streaming high bitrate streams). Try that out and see if it works for > you. > > I did play with select for a little bit before doing the lame sleep > tactic. I found that on linux icecast was getting woken up every few > bytes, so I thought that sleeping might actually be a bit more > CPU-friendly since it could theoretically read in larger chunks. > > Maybe we should just go to select for its simplicity and reliablity. [moved this to icecast-dev as it's now more appropriate] It al...

...om Win2k Server to Samba running on LDAP. What would be the default value that sambaPwdMustChange would be incremented? This is NT Time Right (1 unit for every 100 ms from 1600 right?) I just had to bump everybody what I'm guessing is three weeks, but I need to know soon so I don't get woken up out of bed again! -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: This is a digitally signed message part Url : http://lists.samba.org/archive/samba/attachments/20030620/7c8967bb/attachment.bi...

...k if there is any tasks waiting to be run on > > current cpu in rng_dev_read() by need_resched(). But need_resched() > > doesn't work because rng_dev_read() is executing in user context. > > I don't understand this explanation? I'd expect the sysfs process to be > woken by the mutex_unlock(). But actually sysfs process's not woken always, this is they the process gets stuck. > If we're really high priority (vs. the sysfs process) then I can see why > we'd need schedule_timeout_interruptible() instead of just schedule(), > and in that case,...

...ative case, which should greatly reduce the cost of having > CONFIG_PARAVIRT_SPINLOCKS enabled on actual hardware. Ah nice. That could be spun out as a seperate patch to optimize the existing ticket locks I presume. Now with the old pv ticketlock code an vCPU would only go to sleep once and be woken up when it was its turn. With this new code it is woken up twice (and twice it goes to sleep). With an overcommit scenario this would imply that we will have at least twice as many VMEXIT as with the previous code. I presume when you did benchmarking this did not even register? Thought I wonder i...

...re the code a bit, but > its not fundamentally impossible. > > We could equally apply the head hashing to the current ticket > implementation and avoid the current bitmap iteration. > > > Now with the old pv ticketlock code an vCPU would only go to sleep once and > > be woken up when it was its turn. With this new code it is woken up twice > > (and twice it goes to sleep). With an overcommit scenario this would imply > > that we will have at least twice as many VMEXIT as with the previous code. > > An astute observation, I had not considered that. T...

Hi Is there a way i can trigger a script within a libvirt guest immediately after resume? E.g. i don't see any log message that indicates to a guest that it had been paused and was just woken up. The problem that i am trying to solve is that when i reboot the host (pausing all guests), the guests' system clocks are a few minutes late after resume. The guests RTC (current_clocksource = kvm-clock) are correct though, so a "hwclock --hctosys" fixed the offset. I only need t...

...ative case, which should greatly reduce the cost of having > CONFIG_PARAVIRT_SPINLOCKS enabled on actual hardware. Ah nice. That could be spun out as a seperate patch to optimize the existing ticket locks I presume. Now with the old pv ticketlock code an vCPU would only go to sleep once and be woken up when it was its turn. With this new code it is woken up twice (and twice it goes to sleep). With an overcommit scenario this would imply that we will have at least twice as many VMEXIT as with the previous code. I presume when you did benchmarking this did not even register? Thought I wonder i...