Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
Hi Waiman, On Tue, Aug 07, 2018 at 07:29:49PM -0400, Waiman Long wrote: > On 07/24/2018 03:10 PM, Waiman Long wrote: > > diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c > > index 3064c50..01fcb80 100644 > > --- a/kernel/locking/rwsem-xadd.c > > +++ b/kernel/locking/rwsem-xadd.c > > @@ -233,8 +233,19 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, > > waiter.type = RWSEM_WAITING_FOR_READ; > > > > raw_spin_lock_irq(>wait_lock); > > - if (list_empty(>wait_list)) > > + if (list_empty(>wait_list)) { > > + /* > > +* In case the wait queue is empty and the lock isn't owned > > +* by a writer, this reader can exit the slowpath and return > > +* immediately as its RWSEM_ACTIVE_READ_BIAS has already > > +* been set in the count. > > +*/ > > + if (atomic_long_read(>count) >= 0) { > > + raw_spin_unlock_irq(>wait_lock); > > + return sem; > > + } > > adjustment += RWSEM_WAITING_BIAS; > > + } > > list_add_tail(, >wait_list); > > > > /* we're now waiting on the lock, but no longer actively locking */ > > Will this patch be eligible to go into 4.19 or 4.20? It's probably worth reposting with the Acks you've received, so that Ingo can easily pick it up into -tip (but it might be a bit close for 4.19 at this point). Will
Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
Hi Waiman, On Tue, Aug 07, 2018 at 07:29:49PM -0400, Waiman Long wrote: > On 07/24/2018 03:10 PM, Waiman Long wrote: > > diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c > > index 3064c50..01fcb80 100644 > > --- a/kernel/locking/rwsem-xadd.c > > +++ b/kernel/locking/rwsem-xadd.c > > @@ -233,8 +233,19 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, > > waiter.type = RWSEM_WAITING_FOR_READ; > > > > raw_spin_lock_irq(>wait_lock); > > - if (list_empty(>wait_list)) > > + if (list_empty(>wait_list)) { > > + /* > > +* In case the wait queue is empty and the lock isn't owned > > +* by a writer, this reader can exit the slowpath and return > > +* immediately as its RWSEM_ACTIVE_READ_BIAS has already > > +* been set in the count. > > +*/ > > + if (atomic_long_read(>count) >= 0) { > > + raw_spin_unlock_irq(>wait_lock); > > + return sem; > > + } > > adjustment += RWSEM_WAITING_BIAS; > > + } > > list_add_tail(, >wait_list); > > > > /* we're now waiting on the lock, but no longer actively locking */ > > Will this patch be eligible to go into 4.19 or 4.20? It's probably worth reposting with the Acks you've received, so that Ingo can easily pick it up into -tip (but it might be a bit close for 4.19 at this point). Will
Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
On 07/24/2018 03:10 PM, Waiman Long wrote: > It was discovered that a constant stream of readers with occassional > writers pounding on a rwsem may cause many of the readers to enter the > slowpath unnecessarily thus increasing latency and lowering performance. > > In the current code, a reader entering the slowpath critical section > will unconditionally set the WAITING_BIAS, if not set yet, and clear > its active count even if no one is in the wait queue and no writer > is present. This causes some incoming readers to observe the presence > of waiters in the wait queue and hence have to go into the slowpath > themselves. > > With sufficient numbers of readers and a relatively short lock hold time, > the WAITING_BIAS may be repeatedly turned on and off and a substantial > portion of the readers will go into the slowpath sustaining a rather > long queue in the wait queue spinlock and repeated WAITING_BIAS on/off > cycle until the logjam is broken opportunistically. > > To avoid this situation from happening, an additional check is added to > detect the special case that the reader in the critical section is the > only one in the wait queue and no writer is present. When that happens, > it can just exit the slowpath and return immediately as its active count > has already been set in the lock. Other incoming readers won't observe > the presence of waiters and so will not be forced into the slowpath. > > The issue was found in a customer site where they had an application > that pounded on the pread64 syscalls heavily on an XFS filesystem. The > application was run in a recent 4-socket boxes with a lot of CPUs. They > saw significant spinlock contention in the rwsem_down_read_failed() call. > With this patch applied, the system CPU usage went down from 85% to 57%, > and the spinlock contention in the pread64 syscalls was gone. > > v3: Revise the commit log and comment again. > v2: Add customer testing results and remove wording that may cause > confusion. > > Signed-off-by: Waiman Long > --- > kernel/locking/rwsem-xadd.c | 13 - > 1 file changed, 12 insertions(+), 1 deletion(-) > > diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c > index 3064c50..01fcb80 100644 > --- a/kernel/locking/rwsem-xadd.c > +++ b/kernel/locking/rwsem-xadd.c > @@ -233,8 +233,19 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, > waiter.type = RWSEM_WAITING_FOR_READ; > > raw_spin_lock_irq(>wait_lock); > - if (list_empty(>wait_list)) > + if (list_empty(>wait_list)) { > + /* > + * In case the wait queue is empty and the lock isn't owned > + * by a writer, this reader can exit the slowpath and return > + * immediately as its RWSEM_ACTIVE_READ_BIAS has already > + * been set in the count. > + */ > + if (atomic_long_read(>count) >= 0) { > + raw_spin_unlock_irq(>wait_lock); > + return sem; > + } > adjustment += RWSEM_WAITING_BIAS; > + } > list_add_tail(, >wait_list); > > /* we're now waiting on the lock, but no longer actively locking */ Will this patch be eligible to go into 4.19 or 4.20? Thanks, Longman
Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
On 07/24/2018 03:10 PM, Waiman Long wrote: > It was discovered that a constant stream of readers with occassional > writers pounding on a rwsem may cause many of the readers to enter the > slowpath unnecessarily thus increasing latency and lowering performance. > > In the current code, a reader entering the slowpath critical section > will unconditionally set the WAITING_BIAS, if not set yet, and clear > its active count even if no one is in the wait queue and no writer > is present. This causes some incoming readers to observe the presence > of waiters in the wait queue and hence have to go into the slowpath > themselves. > > With sufficient numbers of readers and a relatively short lock hold time, > the WAITING_BIAS may be repeatedly turned on and off and a substantial > portion of the readers will go into the slowpath sustaining a rather > long queue in the wait queue spinlock and repeated WAITING_BIAS on/off > cycle until the logjam is broken opportunistically. > > To avoid this situation from happening, an additional check is added to > detect the special case that the reader in the critical section is the > only one in the wait queue and no writer is present. When that happens, > it can just exit the slowpath and return immediately as its active count > has already been set in the lock. Other incoming readers won't observe > the presence of waiters and so will not be forced into the slowpath. > > The issue was found in a customer site where they had an application > that pounded on the pread64 syscalls heavily on an XFS filesystem. The > application was run in a recent 4-socket boxes with a lot of CPUs. They > saw significant spinlock contention in the rwsem_down_read_failed() call. > With this patch applied, the system CPU usage went down from 85% to 57%, > and the spinlock contention in the pread64 syscalls was gone. > > v3: Revise the commit log and comment again. > v2: Add customer testing results and remove wording that may cause > confusion. > > Signed-off-by: Waiman Long > --- > kernel/locking/rwsem-xadd.c | 13 - > 1 file changed, 12 insertions(+), 1 deletion(-) > > diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c > index 3064c50..01fcb80 100644 > --- a/kernel/locking/rwsem-xadd.c > +++ b/kernel/locking/rwsem-xadd.c > @@ -233,8 +233,19 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, > waiter.type = RWSEM_WAITING_FOR_READ; > > raw_spin_lock_irq(>wait_lock); > - if (list_empty(>wait_list)) > + if (list_empty(>wait_list)) { > + /* > + * In case the wait queue is empty and the lock isn't owned > + * by a writer, this reader can exit the slowpath and return > + * immediately as its RWSEM_ACTIVE_READ_BIAS has already > + * been set in the count. > + */ > + if (atomic_long_read(>count) >= 0) { > + raw_spin_unlock_irq(>wait_lock); > + return sem; > + } > adjustment += RWSEM_WAITING_BIAS; > + } > list_add_tail(, >wait_list); > > /* we're now waiting on the lock, but no longer actively locking */ Will this patch be eligible to go into 4.19 or 4.20? Thanks, Longman
Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
On Tue, Jul 24, 2018 at 03:10:25PM -0400, Waiman Long wrote: > It was discovered that a constant stream of readers with occassional > writers pounding on a rwsem may cause many of the readers to enter the > slowpath unnecessarily thus increasing latency and lowering performance. > > In the current code, a reader entering the slowpath critical section > will unconditionally set the WAITING_BIAS, if not set yet, and clear > its active count even if no one is in the wait queue and no writer > is present. This causes some incoming readers to observe the presence > of waiters in the wait queue and hence have to go into the slowpath > themselves. > > With sufficient numbers of readers and a relatively short lock hold time, > the WAITING_BIAS may be repeatedly turned on and off and a substantial > portion of the readers will go into the slowpath sustaining a rather > long queue in the wait queue spinlock and repeated WAITING_BIAS on/off > cycle until the logjam is broken opportunistically. > > To avoid this situation from happening, an additional check is added to > detect the special case that the reader in the critical section is the > only one in the wait queue and no writer is present. When that happens, > it can just exit the slowpath and return immediately as its active count > has already been set in the lock. Other incoming readers won't observe > the presence of waiters and so will not be forced into the slowpath. > > The issue was found in a customer site where they had an application > that pounded on the pread64 syscalls heavily on an XFS filesystem. The > application was run in a recent 4-socket boxes with a lot of CPUs. They > saw significant spinlock contention in the rwsem_down_read_failed() call. > With this patch applied, the system CPU usage went down from 85% to 57%, > and the spinlock contention in the pread64 syscalls was gone. > > v3: Revise the commit log and comment again. > v2: Add customer testing results and remove wording that may cause > confusion. > > Signed-off-by: Waiman Long > --- > kernel/locking/rwsem-xadd.c | 13 - > 1 file changed, 12 insertions(+), 1 deletion(-) My nits with the commit message have been addressed, so: Acked-by: Will Deacon Thanks! Will
Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
On Tue, Jul 24, 2018 at 03:10:25PM -0400, Waiman Long wrote: > It was discovered that a constant stream of readers with occassional > writers pounding on a rwsem may cause many of the readers to enter the > slowpath unnecessarily thus increasing latency and lowering performance. > > In the current code, a reader entering the slowpath critical section > will unconditionally set the WAITING_BIAS, if not set yet, and clear > its active count even if no one is in the wait queue and no writer > is present. This causes some incoming readers to observe the presence > of waiters in the wait queue and hence have to go into the slowpath > themselves. > > With sufficient numbers of readers and a relatively short lock hold time, > the WAITING_BIAS may be repeatedly turned on and off and a substantial > portion of the readers will go into the slowpath sustaining a rather > long queue in the wait queue spinlock and repeated WAITING_BIAS on/off > cycle until the logjam is broken opportunistically. > > To avoid this situation from happening, an additional check is added to > detect the special case that the reader in the critical section is the > only one in the wait queue and no writer is present. When that happens, > it can just exit the slowpath and return immediately as its active count > has already been set in the lock. Other incoming readers won't observe > the presence of waiters and so will not be forced into the slowpath. > > The issue was found in a customer site where they had an application > that pounded on the pread64 syscalls heavily on an XFS filesystem. The > application was run in a recent 4-socket boxes with a lot of CPUs. They > saw significant spinlock contention in the rwsem_down_read_failed() call. > With this patch applied, the system CPU usage went down from 85% to 57%, > and the spinlock contention in the pread64 syscalls was gone. > > v3: Revise the commit log and comment again. > v2: Add customer testing results and remove wording that may cause > confusion. > > Signed-off-by: Waiman Long > --- > kernel/locking/rwsem-xadd.c | 13 - > 1 file changed, 12 insertions(+), 1 deletion(-) My nits with the commit message have been addressed, so: Acked-by: Will Deacon Thanks! Will
Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
On Tue, 24 Jul 2018, Waiman Long wrote: It was discovered that a constant stream of readers with occassional writers pounding on a rwsem may cause many of the readers to enter the slowpath unnecessarily thus increasing latency and lowering performance. In the current code, a reader entering the slowpath critical section will unconditionally set the WAITING_BIAS, if not set yet, and clear its active count even if no one is in the wait queue and no writer is present. This causes some incoming readers to observe the presence of waiters in the wait queue and hence have to go into the slowpath themselves. With sufficient numbers of readers and a relatively short lock hold time, the WAITING_BIAS may be repeatedly turned on and off and a substantial portion of the readers will go into the slowpath sustaining a rather long queue in the wait queue spinlock and repeated WAITING_BIAS on/off cycle until the logjam is broken opportunistically. To avoid this situation from happening, an additional check is added to detect the special case that the reader in the critical section is the only one in the wait queue and no writer is present. When that happens, it can just exit the slowpath and return immediately as its active count has already been set in the lock. Other incoming readers won't observe the presence of waiters and so will not be forced into the slowpath. The issue was found in a customer site where they had an application that pounded on the pread64 syscalls heavily on an XFS filesystem. The application was run in a recent 4-socket boxes with a lot of CPUs. They saw significant spinlock contention in the rwsem_down_read_failed() call. With this patch applied, the system CPU usage went down from 85% to 57%, and the spinlock contention in the pread64 syscalls was gone. v3: Revise the commit log and comment again. v2: Add customer testing results and remove wording that may cause confusion. Signed-off-by: Waiman Long Reviewed-by: Davidlohr Bueso
Re: [PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
On Tue, 24 Jul 2018, Waiman Long wrote: It was discovered that a constant stream of readers with occassional writers pounding on a rwsem may cause many of the readers to enter the slowpath unnecessarily thus increasing latency and lowering performance. In the current code, a reader entering the slowpath critical section will unconditionally set the WAITING_BIAS, if not set yet, and clear its active count even if no one is in the wait queue and no writer is present. This causes some incoming readers to observe the presence of waiters in the wait queue and hence have to go into the slowpath themselves. With sufficient numbers of readers and a relatively short lock hold time, the WAITING_BIAS may be repeatedly turned on and off and a substantial portion of the readers will go into the slowpath sustaining a rather long queue in the wait queue spinlock and repeated WAITING_BIAS on/off cycle until the logjam is broken opportunistically. To avoid this situation from happening, an additional check is added to detect the special case that the reader in the critical section is the only one in the wait queue and no writer is present. When that happens, it can just exit the slowpath and return immediately as its active count has already been set in the lock. Other incoming readers won't observe the presence of waiters and so will not be forced into the slowpath. The issue was found in a customer site where they had an application that pounded on the pread64 syscalls heavily on an XFS filesystem. The application was run in a recent 4-socket boxes with a lot of CPUs. They saw significant spinlock contention in the rwsem_down_read_failed() call. With this patch applied, the system CPU usage went down from 85% to 57%, and the spinlock contention in the pread64 syscalls was gone. v3: Revise the commit log and comment again. v2: Add customer testing results and remove wording that may cause confusion. Signed-off-by: Waiman Long Reviewed-by: Davidlohr Bueso
[PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
It was discovered that a constant stream of readers with occassional writers pounding on a rwsem may cause many of the readers to enter the slowpath unnecessarily thus increasing latency and lowering performance. In the current code, a reader entering the slowpath critical section will unconditionally set the WAITING_BIAS, if not set yet, and clear its active count even if no one is in the wait queue and no writer is present. This causes some incoming readers to observe the presence of waiters in the wait queue and hence have to go into the slowpath themselves. With sufficient numbers of readers and a relatively short lock hold time, the WAITING_BIAS may be repeatedly turned on and off and a substantial portion of the readers will go into the slowpath sustaining a rather long queue in the wait queue spinlock and repeated WAITING_BIAS on/off cycle until the logjam is broken opportunistically. To avoid this situation from happening, an additional check is added to detect the special case that the reader in the critical section is the only one in the wait queue and no writer is present. When that happens, it can just exit the slowpath and return immediately as its active count has already been set in the lock. Other incoming readers won't observe the presence of waiters and so will not be forced into the slowpath. The issue was found in a customer site where they had an application that pounded on the pread64 syscalls heavily on an XFS filesystem. The application was run in a recent 4-socket boxes with a lot of CPUs. They saw significant spinlock contention in the rwsem_down_read_failed() call. With this patch applied, the system CPU usage went down from 85% to 57%, and the spinlock contention in the pread64 syscalls was gone. v3: Revise the commit log and comment again. v2: Add customer testing results and remove wording that may cause confusion. Signed-off-by: Waiman Long --- kernel/locking/rwsem-xadd.c | 13 - 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 3064c50..01fcb80 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -233,8 +233,19 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, waiter.type = RWSEM_WAITING_FOR_READ; raw_spin_lock_irq(>wait_lock); - if (list_empty(>wait_list)) + if (list_empty(>wait_list)) { + /* +* In case the wait queue is empty and the lock isn't owned +* by a writer, this reader can exit the slowpath and return +* immediately as its RWSEM_ACTIVE_READ_BIAS has already +* been set in the count. +*/ + if (atomic_long_read(>count) >= 0) { + raw_spin_unlock_irq(>wait_lock); + return sem; + } adjustment += RWSEM_WAITING_BIAS; + } list_add_tail(, >wait_list); /* we're now waiting on the lock, but no longer actively locking */ -- 1.8.3.1
[PATCH v3] locking/rwsem: Exit read lock slowpath if queue empty & no writer
It was discovered that a constant stream of readers with occassional writers pounding on a rwsem may cause many of the readers to enter the slowpath unnecessarily thus increasing latency and lowering performance. In the current code, a reader entering the slowpath critical section will unconditionally set the WAITING_BIAS, if not set yet, and clear its active count even if no one is in the wait queue and no writer is present. This causes some incoming readers to observe the presence of waiters in the wait queue and hence have to go into the slowpath themselves. With sufficient numbers of readers and a relatively short lock hold time, the WAITING_BIAS may be repeatedly turned on and off and a substantial portion of the readers will go into the slowpath sustaining a rather long queue in the wait queue spinlock and repeated WAITING_BIAS on/off cycle until the logjam is broken opportunistically. To avoid this situation from happening, an additional check is added to detect the special case that the reader in the critical section is the only one in the wait queue and no writer is present. When that happens, it can just exit the slowpath and return immediately as its active count has already been set in the lock. Other incoming readers won't observe the presence of waiters and so will not be forced into the slowpath. The issue was found in a customer site where they had an application that pounded on the pread64 syscalls heavily on an XFS filesystem. The application was run in a recent 4-socket boxes with a lot of CPUs. They saw significant spinlock contention in the rwsem_down_read_failed() call. With this patch applied, the system CPU usage went down from 85% to 57%, and the spinlock contention in the pread64 syscalls was gone. v3: Revise the commit log and comment again. v2: Add customer testing results and remove wording that may cause confusion. Signed-off-by: Waiman Long --- kernel/locking/rwsem-xadd.c | 13 - 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 3064c50..01fcb80 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -233,8 +233,19 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, waiter.type = RWSEM_WAITING_FOR_READ; raw_spin_lock_irq(>wait_lock); - if (list_empty(>wait_list)) + if (list_empty(>wait_list)) { + /* +* In case the wait queue is empty and the lock isn't owned +* by a writer, this reader can exit the slowpath and return +* immediately as its RWSEM_ACTIVE_READ_BIAS has already +* been set in the count. +*/ + if (atomic_long_read(>count) >= 0) { + raw_spin_unlock_irq(>wait_lock); + return sem; + } adjustment += RWSEM_WAITING_BIAS; + } list_add_tail(, >wait_list); /* we're now waiting on the lock, but no longer actively locking */ -- 1.8.3.1