* [PATCH 1/2] rcu: Remove unnecessary condition in rcu_implicit_dynticks_qs @ 2016-11-09 6:32 Byungchul Park 2016-11-09 6:32 ` [PATCH 2/2] rcu: Force resched_cpu when jiffies >= rcu_state.jiffies_resched Byungchul Park 0 siblings, 1 reply; 7+ messages in thread From: Byungchul Park @ 2016-11-09 6:32 UTC (permalink / raw) To: paulmck, josh, rostedt, mathieu.desnoyers, jiangshanlai; +Cc: linux-kernel Given two conditions like, COND 1. jiffies >= rdp->rsp->gp_start + 2 * jiffies_till_sched_qs COND 2. jiffies >= rdp->rsp->gp_start + jiffies_till_sched_qs A set of jiffies satisfying COND 2 includes another set satisfying COND 1. Thus COND 1 can be removed from a condition, (COND 1 || COND 2). Signed-off-by: Byungchul Park <byungchul.park@lge.com> --- kernel/rcu/tree.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 5d80925..d8e8859 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1220,9 +1220,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, } /* And if it has been a really long time, kick the CPU as well. */ - if (ULONG_CMP_GE(jiffies, - rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) || - ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) + if (ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ return 0; -- 1.9.1 ^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH 2/2] rcu: Force resched_cpu when jiffies >= rcu_state.jiffies_resched 2016-11-09 6:32 [PATCH 1/2] rcu: Remove unnecessary condition in rcu_implicit_dynticks_qs Byungchul Park @ 2016-11-09 6:32 ` Byungchul Park 2016-11-22 8:12 ` Byungchul Park 0 siblings, 1 reply; 7+ messages in thread From: Byungchul Park @ 2016-11-09 6:32 UTC (permalink / raw) To: paulmck, josh, rostedt, mathieu.desnoyers, jiangshanlai; +Cc: linux-kernel Currently rcu code forces CPU into scheduler when jiffies >= rcu_state.gp_start + jiffies_till_sched_qs, via resched_cpu(). It would be better to force CPU into scheduler when jiffies >= rcu_state.jiffies_resched, too. Signed-off-by: Byungchul Park <byungchul.park@lge.com> --- kernel/rcu/tree.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index d8e8859..287f468 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1217,11 +1217,10 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask); } rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ - } - /* And if it has been a really long time, kick the CPU as well. */ - if (ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) + /* And if it has been a really long time, kick the CPU as well. */ resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ + } return 0; } -- 1.9.1 ^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH 2/2] rcu: Force resched_cpu when jiffies >= rcu_state.jiffies_resched 2016-11-09 6:32 ` [PATCH 2/2] rcu: Force resched_cpu when jiffies >= rcu_state.jiffies_resched Byungchul Park @ 2016-11-22 8:12 ` Byungchul Park 2016-11-25 8:34 ` Paul E. McKenney 0 siblings, 1 reply; 7+ messages in thread From: Byungchul Park @ 2016-11-22 8:12 UTC (permalink / raw) To: paulmck, josh, rostedt, mathieu.desnoyers, jiangshanlai; +Cc: linux-kernel On Wed, Nov 09, 2016 at 03:32:15PM +0900, Byungchul Park wrote: > Currently rcu code forces CPU into scheduler when jiffies >= > rcu_state.gp_start + jiffies_till_sched_qs, via resched_cpu(). > > It would be better to force CPU into scheduler when jiffies >= > rcu_state.jiffies_resched, too. Hello, I think these two patches are necessary to call resched_cpu() even in case of jiffies >= rcu_state.jiffies_resched, too. Am I wrong? It would be appriciated if you let me know if I was wrong. Thank you, Byungchul > > Signed-off-by: Byungchul Park <byungchul.park@lge.com> > --- > kernel/rcu/tree.c | 5 ++--- > 1 file changed, 2 insertions(+), 3 deletions(-) > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c > index d8e8859..287f468 100644 > --- a/kernel/rcu/tree.c > +++ b/kernel/rcu/tree.c > @@ -1217,11 +1217,10 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, > READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask); > } > rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ > - } > > - /* And if it has been a really long time, kick the CPU as well. */ > - if (ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) > + /* And if it has been a really long time, kick the CPU as well. */ > resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ > + } > > return 0; > } > -- > 1.9.1 ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH 2/2] rcu: Force resched_cpu when jiffies >= rcu_state.jiffies_resched 2016-11-22 8:12 ` Byungchul Park @ 2016-11-25 8:34 ` Paul E. McKenney 2016-11-26 12:00 ` Paul E. McKenney 0 siblings, 1 reply; 7+ messages in thread From: Paul E. McKenney @ 2016-11-25 8:34 UTC (permalink / raw) To: Byungchul Park Cc: josh, rostedt, mathieu.desnoyers, jiangshanlai, linux-kernel On Tue, Nov 22, 2016 at 05:12:20PM +0900, Byungchul Park wrote: > On Wed, Nov 09, 2016 at 03:32:15PM +0900, Byungchul Park wrote: > > Currently rcu code forces CPU into scheduler when jiffies >= > > rcu_state.gp_start + jiffies_till_sched_qs, via resched_cpu(). > > > > It would be better to force CPU into scheduler when jiffies >= > > rcu_state.jiffies_resched, too. > > Hello, > > I think these two patches are necessary to call resched_cpu() even in > case of jiffies >= rcu_state.jiffies_resched, too. Am I wrong? > > It would be appriciated if you let me know if I was wrong. My current thought is that both the "if" statement and the call to resched_cpu() should be removed, but I am still testing and working through the timing. Either way, I do very much appreciate your having called my attention to this code! Thanx, Paul > Thank you, > Byungchul > > > > > Signed-off-by: Byungchul Park <byungchul.park@lge.com> > > --- > > kernel/rcu/tree.c | 5 ++--- > > 1 file changed, 2 insertions(+), 3 deletions(-) > > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c > > index d8e8859..287f468 100644 > > --- a/kernel/rcu/tree.c > > +++ b/kernel/rcu/tree.c > > @@ -1217,11 +1217,10 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, > > READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask); > > } > > rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ > > - } > > > > - /* And if it has been a really long time, kick the CPU as well. */ > > - if (ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) > > + /* And if it has been a really long time, kick the CPU as well. */ > > resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ > > + } > > > > return 0; > > } > > -- > > 1.9.1 > ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH 2/2] rcu: Force resched_cpu when jiffies >= rcu_state.jiffies_resched 2016-11-25 8:34 ` Paul E. McKenney @ 2016-11-26 12:00 ` Paul E. McKenney 2016-11-28 6:46 ` Byungchul Park 0 siblings, 1 reply; 7+ messages in thread From: Paul E. McKenney @ 2016-11-26 12:00 UTC (permalink / raw) To: Byungchul Park Cc: josh, rostedt, mathieu.desnoyers, jiangshanlai, linux-kernel On Fri, Nov 25, 2016 at 12:34:26AM -0800, Paul E. McKenney wrote: > On Tue, Nov 22, 2016 at 05:12:20PM +0900, Byungchul Park wrote: > > On Wed, Nov 09, 2016 at 03:32:15PM +0900, Byungchul Park wrote: > > > Currently rcu code forces CPU into scheduler when jiffies >= > > > rcu_state.gp_start + jiffies_till_sched_qs, via resched_cpu(). > > > > > > It would be better to force CPU into scheduler when jiffies >= > > > rcu_state.jiffies_resched, too. > > > > Hello, > > > > I think these two patches are necessary to call resched_cpu() even in > > case of jiffies >= rcu_state.jiffies_resched, too. Am I wrong? > > > > It would be appriciated if you let me know if I was wrong. > > My current thought is that both the "if" statement and the call to > resched_cpu() should be removed, but I am still testing and working > through the timing. > > Either way, I do very much appreciate your having called my attention > to this code! And the patch shown below seems to do the trick. Thoughts? Thanx, Paul ------------------------------------------------------------------------ commit d2db185bfee894c573faebed93461e9938bdbb61 Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Date: Fri Nov 25 00:07:23 2016 -0800 rcu: Remove short-term CPU kicking Commit 4914950aaa12d ("rcu: Stop treating in-kernel CPU-bound workloads as errors") added a (relatively) short-timeout call to resched_cpu(). This was inspired by as issue that was fixed by b7e7ade34e61 ("sched/core: Fix remote wakeups"). But given that this issue was fixed, it is time for the current commit to remove this call to resched_cpu(). Reported-by: Byungchul Park <byungchul.park@lge.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 5f4f80d07852..91a68e4e6671 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1345,12 +1345,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ } - /* And if it has been a really long time, kick the CPU as well. */ - if (ULONG_CMP_GE(jiffies, - rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) || - ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) - resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ - return 0; } ^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH 2/2] rcu: Force resched_cpu when jiffies >= rcu_state.jiffies_resched 2016-11-26 12:00 ` Paul E. McKenney @ 2016-11-28 6:46 ` Byungchul Park 2016-11-28 10:58 ` Paul E. McKenney 0 siblings, 1 reply; 7+ messages in thread From: Byungchul Park @ 2016-11-28 6:46 UTC (permalink / raw) To: Paul E. McKenney Cc: josh, rostedt, mathieu.desnoyers, jiangshanlai, linux-kernel On Sat, Nov 26, 2016 at 04:00:46AM -0800, Paul E. McKenney wrote: > On Fri, Nov 25, 2016 at 12:34:26AM -0800, Paul E. McKenney wrote: > > On Tue, Nov 22, 2016 at 05:12:20PM +0900, Byungchul Park wrote: > > > On Wed, Nov 09, 2016 at 03:32:15PM +0900, Byungchul Park wrote: > > > > Currently rcu code forces CPU into scheduler when jiffies >= > > > > rcu_state.gp_start + jiffies_till_sched_qs, via resched_cpu(). > > > > > > > > It would be better to force CPU into scheduler when jiffies >= > > > > rcu_state.jiffies_resched, too. > > > > > > Hello, > > > > > > I think these two patches are necessary to call resched_cpu() even in > > > case of jiffies >= rcu_state.jiffies_resched, too. Am I wrong? > > > > > > It would be appriciated if you let me know if I was wrong. > > > > My current thought is that both the "if" statement and the call to > > resched_cpu() should be removed, but I am still testing and working > > through the timing. > > > > Either way, I do very much appreciate your having called my attention > > to this code! > > And the patch shown below seems to do the trick. Thoughts? Hello, I see.. I didn't check the log 'rcu: Stop treating in-kernel CPU-bound workloads as errors'. If you are convinced to remove them, no objection. Thank you, Byungchul > > Thanx, Paul > > ------------------------------------------------------------------------ > > commit d2db185bfee894c573faebed93461e9938bdbb61 > Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > Date: Fri Nov 25 00:07:23 2016 -0800 > > rcu: Remove short-term CPU kicking > > Commit 4914950aaa12d ("rcu: Stop treating in-kernel CPU-bound workloads > as errors") added a (relatively) short-timeout call to resched_cpu(). > This was inspired by as issue that was fixed by b7e7ade34e61 ("sched/core: > Fix remote wakeups"). But given that this issue was fixed, it is time > for the current commit to remove this call to resched_cpu(). > > Reported-by: Byungchul Park <byungchul.park@lge.com> > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c > index 5f4f80d07852..91a68e4e6671 100644 > --- a/kernel/rcu/tree.c > +++ b/kernel/rcu/tree.c > @@ -1345,12 +1345,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, > rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ > } > > - /* And if it has been a really long time, kick the CPU as well. */ > - if (ULONG_CMP_GE(jiffies, > - rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) || > - ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) > - resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ > - > return 0; > } > ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH 2/2] rcu: Force resched_cpu when jiffies >= rcu_state.jiffies_resched 2016-11-28 6:46 ` Byungchul Park @ 2016-11-28 10:58 ` Paul E. McKenney 0 siblings, 0 replies; 7+ messages in thread From: Paul E. McKenney @ 2016-11-28 10:58 UTC (permalink / raw) To: Byungchul Park Cc: josh, rostedt, mathieu.desnoyers, jiangshanlai, linux-kernel On Mon, Nov 28, 2016 at 03:46:39PM +0900, Byungchul Park wrote: > On Sat, Nov 26, 2016 at 04:00:46AM -0800, Paul E. McKenney wrote: > > On Fri, Nov 25, 2016 at 12:34:26AM -0800, Paul E. McKenney wrote: > > > On Tue, Nov 22, 2016 at 05:12:20PM +0900, Byungchul Park wrote: > > > > On Wed, Nov 09, 2016 at 03:32:15PM +0900, Byungchul Park wrote: > > > > > Currently rcu code forces CPU into scheduler when jiffies >= > > > > > rcu_state.gp_start + jiffies_till_sched_qs, via resched_cpu(). > > > > > > > > > > It would be better to force CPU into scheduler when jiffies >= > > > > > rcu_state.jiffies_resched, too. > > > > > > > > Hello, > > > > > > > > I think these two patches are necessary to call resched_cpu() even in > > > > case of jiffies >= rcu_state.jiffies_resched, too. Am I wrong? > > > > > > > > It would be appriciated if you let me know if I was wrong. > > > > > > My current thought is that both the "if" statement and the call to > > > resched_cpu() should be removed, but I am still testing and working > > > through the timing. > > > > > > Either way, I do very much appreciate your having called my attention > > > to this code! > > > > And the patch shown below seems to do the trick. Thoughts? > > Hello, > > I see.. I didn't check the log 'rcu: Stop treating in-kernel CPU-bound > workloads as errors'. > > If you are convinced to remove them, no objection. It is quite possible that additional time-related adjustments are needed, but this change is a step in the right direction. Thanx, Paul > Thank you, > Byungchul > > > > > Thanx, Paul > > > > ------------------------------------------------------------------------ > > > > commit d2db185bfee894c573faebed93461e9938bdbb61 > > Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > Date: Fri Nov 25 00:07:23 2016 -0800 > > > > rcu: Remove short-term CPU kicking > > > > Commit 4914950aaa12d ("rcu: Stop treating in-kernel CPU-bound workloads > > as errors") added a (relatively) short-timeout call to resched_cpu(). > > This was inspired by as issue that was fixed by b7e7ade34e61 ("sched/core: > > Fix remote wakeups"). But given that this issue was fixed, it is time > > for the current commit to remove this call to resched_cpu(). > > > > Reported-by: Byungchul Park <byungchul.park@lge.com> > > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c > > index 5f4f80d07852..91a68e4e6671 100644 > > --- a/kernel/rcu/tree.c > > +++ b/kernel/rcu/tree.c > > @@ -1345,12 +1345,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, > > rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ > > } > > > > - /* And if it has been a really long time, kick the CPU as well. */ > > - if (ULONG_CMP_GE(jiffies, > > - rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) || > > - ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) > > - resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ > > - > > return 0; > > } > > > ^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2016-11-28 10:58 UTC | newest] Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2016-11-09 6:32 [PATCH 1/2] rcu: Remove unnecessary condition in rcu_implicit_dynticks_qs Byungchul Park 2016-11-09 6:32 ` [PATCH 2/2] rcu: Force resched_cpu when jiffies >= rcu_state.jiffies_resched Byungchul Park 2016-11-22 8:12 ` Byungchul Park 2016-11-25 8:34 ` Paul E. McKenney 2016-11-26 12:00 ` Paul E. McKenney 2016-11-28 6:46 ` Byungchul Park 2016-11-28 10:58 ` Paul E. McKenney
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).