From 46fdb0937f26124700fc9fc80da4776330cc00d3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 26 Oct 2010 02:11:40 -0700 Subject: rcu: Make synchronize_srcu_expedited() fast if running readers The synchronize_srcu_expedited() function is currently quick if there are no active readers, but will delay a full jiffy if there are any. If these readers leave their SRCU read-side critical sections quickly, this is way too long to wait. So this commit first waits ten microseconds, and only then falls back to jiffy-at-a-time waiting. Reported-by: Avi Kivity Reported-by: Marcelo Tosatti Tested-by: Takuya Yoshikawa Signed-off-by: Paul E. McKenney --- kernel/srcu.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/srcu.c') diff --git a/kernel/srcu.c b/kernel/srcu.c index c71e07500536..98d8c1e80edb 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -31,6 +31,7 @@ #include #include #include +#include #include static int init_srcu_struct_fields(struct srcu_struct *sp) @@ -203,9 +204,14 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void)) * all srcu_read_lock() calls using the old counters have completed. * Their corresponding critical sections might well be still * executing, but the srcu_read_lock() primitives themselves - * will have finished executing. + * will have finished executing. We initially give readers + * an arbitrarily chosen 10 microseconds to get out of their + * SRCU read-side critical sections, then loop waiting 1/HZ + * seconds per iteration. */ + if (srcu_readers_active_idx(sp, idx)) + udelay(CONFIG_SRCU_SYNCHRONIZE_DELAY); while (srcu_readers_active_idx(sp, idx)) schedule_timeout_interruptible(1); -- cgit v1.2.2 From c072a388d59a1d48e36864d0e66f42d71745be1c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 7 Jan 2011 02:33:47 -0800 Subject: rcu: demote SRCU_SYNCHRONIZE_DELAY from kernel-parameter status Because the adaptive synchronize_srcu_expedited() approach has worked very well in testing, remove the kernel parameter and replace it by a C-preprocessor macro. If someone finds problems with this approach, a more complex and aggressively adaptive approach might be required. Longer term, SRCU will be merged with the other RCU implementations, at which point synchronize_srcu_expedited() will be event driven, just as synchronize_sched_expedited() currently is. At that point, there will be no need for this adaptive approach. Reported-by: Linus Torvalds Signed-off-by: Paul E. McKenney --- kernel/srcu.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'kernel/srcu.c') diff --git a/kernel/srcu.c b/kernel/srcu.c index 98d8c1e80edb..73ce23feaea9 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -155,6 +155,16 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx) } EXPORT_SYMBOL_GPL(__srcu_read_unlock); +/* + * We use an adaptive strategy for synchronize_srcu() and especially for + * synchronize_srcu_expedited(). We spin for a fixed time period + * (defined below) to allow SRCU readers to exit their read-side critical + * sections. If there are still some readers after 10 microseconds, + * we repeatedly block for 1-millisecond time periods. This approach + * has done well in testing, so there is no need for a config parameter. + */ +#define SYNCHRONIZE_SRCU_READER_DELAY 10 + /* * Helper function for synchronize_srcu() and synchronize_srcu_expedited(). */ @@ -207,11 +217,12 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void)) * will have finished executing. We initially give readers * an arbitrarily chosen 10 microseconds to get out of their * SRCU read-side critical sections, then loop waiting 1/HZ - * seconds per iteration. + * seconds per iteration. The 10-microsecond value has done + * very well in testing. */ if (srcu_readers_active_idx(sp, idx)) - udelay(CONFIG_SRCU_SYNCHRONIZE_DELAY); + udelay(SYNCHRONIZE_SRCU_READER_DELAY); while (srcu_readers_active_idx(sp, idx)) schedule_timeout_interruptible(1); -- cgit v1.2.2