LinuxLists.cc - [PATCH percpu/for-3.11] percpu-refcount: use RCU-sched insted of normal RCU

2013-06-16 21:55:54

Subject: [PATCH percpu/for-3.11] percpu-refcount: use RCU-sched insted of normal RCU

percpu-refcount was incorrectly using preempt_disable/enable() for RCU
critical sections against call_rcu(). 6a24474da8 ("percpu-refcount:
consistently use plain (non-sched) RCU") fixed it by converting the
preepmtion operations with rcu_read_[un]lock() citing that there isn't
any advantage in using sched-RCU over using the usual one; however,
rcu_read_[un]lock() for the preemptible RCU implementation -
CONFIG_TREE_PREEMPT_RCU, chosen when CONFIG_PREEMPT - are slightly
more expensive than preempt_disable/enable().

In a contrived microbench which repeats the followings,

- percpu_ref_get()
- copy 32 bytes of data into percpu buffer
- percpu_put_get()
- copy 32 bytes of data into percpu buffer

rcu_read_[un]lock() used in percpu_ref_get/put() makes it go slower by
about 15% when compared to using sched-RCU.

As the RCU critical sections are extremely short, using sched-RCU
shouldn't have any latency implications. Convert to RCU-sched.

Signed-off-by: Tejun Heo <[email protected]>
Cc: Kent Overstreet <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: "Paul E. McKenney" <[email protected]>
Cc: Rusty Russell <[email protected]>
---
include/linux/percpu-refcount.h | 12 ++++++------
lib/percpu-refcount.c | 2 +-
2 files changed, 7 insertions(+), 7 deletions(-)

--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -105,7 +105,7 @@ static inline void percpu_ref_get(struct
{
unsigned __percpu *pcpu_count;

- rcu_read_lock();
+ rcu_read_lock_sched();

pcpu_count = ACCESS_ONCE(ref->pcpu_count);

@@ -114,7 +114,7 @@ static inline void percpu_ref_get(struct
else
atomic_inc(&ref->count);

- rcu_read_unlock();
+ rcu_read_unlock_sched();
}

/**
@@ -134,7 +134,7 @@ static inline bool percpu_ref_tryget(str
unsigned __percpu *pcpu_count;
int ret = false;

- rcu_read_lock();
+ rcu_read_lock_sched();

pcpu_count = ACCESS_ONCE(ref->pcpu_count);

@@ -143,7 +143,7 @@ static inline bool percpu_ref_tryget(str
ret = true;
}

- rcu_read_unlock();
+ rcu_read_unlock_sched();

return ret;
}
@@ -159,7 +159,7 @@ static inline void percpu_ref_put(struct
{
unsigned __percpu *pcpu_count;

- rcu_read_lock();
+ rcu_read_lock_sched();

pcpu_count = ACCESS_ONCE(ref->pcpu_count);

@@ -168,7 +168,7 @@ static inline void percpu_ref_put(struct
else if (unlikely(atomic_dec_and_test(&ref->count)))
ref->release(ref);

- rcu_read_unlock();
+ rcu_read_unlock_sched();
}

#endif
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -154,5 +154,5 @@ void percpu_ref_kill_and_confirm(struct
(((unsigned long) ref->pcpu_count)|PCPU_REF_DEAD);
ref->confirm_kill = confirm_kill;

- call_rcu(&ref->rcu, percpu_ref_kill_rcu);
+ call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
}

2013-06-16 23:04:15

by Paul E. McKenney

[permalink] [raw]

Subject: Re: [PATCH percpu/for-3.11] percpu-refcount: use RCU-sched insted of normal RCU

On Sun, Jun 16, 2013 at 02:55:46PM -0700, Tejun Heo wrote:
> percpu-refcount was incorrectly using preempt_disable/enable() for RCU
> critical sections against call_rcu(). 6a24474da8 ("percpu-refcount:
> consistently use plain (non-sched) RCU") fixed it by converting the
> preepmtion operations with rcu_read_[un]lock() citing that there isn't
> any advantage in using sched-RCU over using the usual one; however,
> rcu_read_[un]lock() for the preemptible RCU implementation -
> CONFIG_TREE_PREEMPT_RCU, chosen when CONFIG_PREEMPT - are slightly
> more expensive than preempt_disable/enable().
>
> In a contrived microbench which repeats the followings,
>
> - percpu_ref_get()
> - copy 32 bytes of data into percpu buffer
> - percpu_put_get()
> - copy 32 bytes of data into percpu buffer
>
> rcu_read_[un]lock() used in percpu_ref_get/put() makes it go slower by
> about 15% when compared to using sched-RCU.
>
> As the RCU critical sections are extremely short, using sched-RCU
> shouldn't have any latency implications. Convert to RCU-sched.
>
> Signed-off-by: Tejun Heo <[email protected]>
> Cc: Kent Overstreet <[email protected]>
> Cc: Michal Hocko <[email protected]>
> Cc: "Paul E. McKenney" <[email protected]>

Acked-by: Paul E. McKenney <[email protected]>

> Cc: Rusty Russell <[email protected]>
> ---
> include/linux/percpu-refcount.h | 12 ++++++------
> lib/percpu-refcount.c | 2 +-
> 2 files changed, 7 insertions(+), 7 deletions(-)
>
> --- a/include/linux/percpu-refcount.h
> +++ b/include/linux/percpu-refcount.h
> @@ -105,7 +105,7 @@ static inline void percpu_ref_get(struct
> {
> unsigned __percpu *pcpu_count;
>
> - rcu_read_lock();
> + rcu_read_lock_sched();
>
> pcpu_count = ACCESS_ONCE(ref->pcpu_count);
>
> @@ -114,7 +114,7 @@ static inline void percpu_ref_get(struct
> else
> atomic_inc(&ref->count);
>
> - rcu_read_unlock();
> + rcu_read_unlock_sched();
> }
>
> /**
> @@ -134,7 +134,7 @@ static inline bool percpu_ref_tryget(str
> unsigned __percpu *pcpu_count;
> int ret = false;
>
> - rcu_read_lock();
> + rcu_read_lock_sched();
>
> pcpu_count = ACCESS_ONCE(ref->pcpu_count);
>
> @@ -143,7 +143,7 @@ static inline bool percpu_ref_tryget(str
> ret = true;
> }
>
> - rcu_read_unlock();
> + rcu_read_unlock_sched();
>
> return ret;
> }
> @@ -159,7 +159,7 @@ static inline void percpu_ref_put(struct
> {
> unsigned __percpu *pcpu_count;
>
> - rcu_read_lock();
> + rcu_read_lock_sched();
>
> pcpu_count = ACCESS_ONCE(ref->pcpu_count);
>
> @@ -168,7 +168,7 @@ static inline void percpu_ref_put(struct
> else if (unlikely(atomic_dec_and_test(&ref->count)))
> ref->release(ref);
>
> - rcu_read_unlock();
> + rcu_read_unlock_sched();
> }
>
> #endif
> --- a/lib/percpu-refcount.c
> +++ b/lib/percpu-refcount.c
> @@ -154,5 +154,5 @@ void percpu_ref_kill_and_confirm(struct
> (((unsigned long) ref->pcpu_count)|PCPU_REF_DEAD);
> ref->confirm_kill = confirm_kill;
>
> - call_rcu(&ref->rcu, percpu_ref_kill_rcu);
> + call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
> }
>

2013-06-16 23:10:22

by Kent Overstreet

[permalink] [raw]

Subject: Re: [PATCH percpu/for-3.11] percpu-refcount: use RCU-sched insted of normal RCU

2013-06-16 23:13:10

by Tejun Heo

[permalink] [raw]