Re: [PATCH v2] mm: vmalloc: Replace purge_lock spinlock with atomic refcount
Hi Nick, On Sun, Oct 16, 2016 at 9:00 PM, Nicholas Pigginwrote: > On Sat, 15 Oct 2016 03:42:42 -0700 > Joel Fernandes wrote: > >> The purge_lock spinlock causes high latencies with non RT kernel. This has >> been >> reported multiple times on lkml [1] [2] and affects applications like audio. >> >> In this patch, I replace the spinlock with an atomic refcount so that >> preemption is kept turned on during purge. This Ok to do since [3] builds the >> lazy free list in advance and atomically retrieves the list so any instance >> of >> purge will have its own list it is purging. Since the individual vmap area >> frees are themselves protected by a lock, this is Ok. > > This is a good idea, and good results, but that's not what the spinlock was > for -- it was for enforcing the sync semantics. > > Going this route, you'll have to audit callers to expect changed behavior > and change documentation of sync parameter. > > I suspect a better approach would be to instead use a mutex for this, and > require that all sync=1 callers be able to sleep. I would say that most > probably already can. Thanks, I agree mutex is the right way to fix this. Regards, Joel
Re: [PATCH v2] mm: vmalloc: Replace purge_lock spinlock with atomic refcount
Hi Nick, On Sun, Oct 16, 2016 at 9:00 PM, Nicholas Piggin wrote: > On Sat, 15 Oct 2016 03:42:42 -0700 > Joel Fernandes wrote: > >> The purge_lock spinlock causes high latencies with non RT kernel. This has >> been >> reported multiple times on lkml [1] [2] and affects applications like audio. >> >> In this patch, I replace the spinlock with an atomic refcount so that >> preemption is kept turned on during purge. This Ok to do since [3] builds the >> lazy free list in advance and atomically retrieves the list so any instance >> of >> purge will have its own list it is purging. Since the individual vmap area >> frees are themselves protected by a lock, this is Ok. > > This is a good idea, and good results, but that's not what the spinlock was > for -- it was for enforcing the sync semantics. > > Going this route, you'll have to audit callers to expect changed behavior > and change documentation of sync parameter. > > I suspect a better approach would be to instead use a mutex for this, and > require that all sync=1 callers be able to sleep. I would say that most > probably already can. Thanks, I agree mutex is the right way to fix this. Regards, Joel
Re: [PATCH v2] mm: vmalloc: Replace purge_lock spinlock with atomic refcount
On Sat, 15 Oct 2016 03:42:42 -0700 Joel Fernandeswrote: > The purge_lock spinlock causes high latencies with non RT kernel. This has > been > reported multiple times on lkml [1] [2] and affects applications like audio. > > In this patch, I replace the spinlock with an atomic refcount so that > preemption is kept turned on during purge. This Ok to do since [3] builds the > lazy free list in advance and atomically retrieves the list so any instance of > purge will have its own list it is purging. Since the individual vmap area > frees are themselves protected by a lock, this is Ok. This is a good idea, and good results, but that's not what the spinlock was for -- it was for enforcing the sync semantics. Going this route, you'll have to audit callers to expect changed behavior and change documentation of sync parameter. I suspect a better approach would be to instead use a mutex for this, and require that all sync=1 callers be able to sleep. I would say that most probably already can. Thanks, Nick
Re: [PATCH v2] mm: vmalloc: Replace purge_lock spinlock with atomic refcount
On Sat, 15 Oct 2016 03:42:42 -0700 Joel Fernandes wrote: > The purge_lock spinlock causes high latencies with non RT kernel. This has > been > reported multiple times on lkml [1] [2] and affects applications like audio. > > In this patch, I replace the spinlock with an atomic refcount so that > preemption is kept turned on during purge. This Ok to do since [3] builds the > lazy free list in advance and atomically retrieves the list so any instance of > purge will have its own list it is purging. Since the individual vmap area > frees are themselves protected by a lock, this is Ok. This is a good idea, and good results, but that's not what the spinlock was for -- it was for enforcing the sync semantics. Going this route, you'll have to audit callers to expect changed behavior and change documentation of sync parameter. I suspect a better approach would be to instead use a mutex for this, and require that all sync=1 callers be able to sleep. I would say that most probably already can. Thanks, Nick