* [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt
@ 2019-12-04 13:44 Srikar Dronamraju
2019-12-04 13:44 ` [PATCH 2/2] powerpc/shared: Use static key to detect shared processor Srikar Dronamraju
` (4 more replies)
0 siblings, 5 replies; 7+ messages in thread
From: Srikar Dronamraju @ 2019-12-04 13:44 UTC (permalink / raw)
To: Michael Ellerman
Cc: Juri Lelli, Parth Shah, Srikar Dronamraju, Ihor Pasichnyk,
Waiman Long, linuxppc-dev
With commit 247f2f6f3c70 ("sched/core: Don't schedule threads on pre-empted
vCPUs"), scheduler avoids preempted vCPUs to schedule tasks on wakeup.
This leads to wrong choice of CPU, which in-turn leads to larger wakeup
latencies. Eventually, it leads to performance regression in latency
sensitive benchmarks like soltp, schbench etc.
On Powerpc, vcpu_is_preempted only looks at yield_count. If the
yield_count is odd, the vCPU is assumed to be preempted. However
yield_count is increased whenever LPAR enters CEDE state. So any CPU
that has entered CEDE state is assumed to be preempted.
Even if vCPU of dedicated LPAR is preempted/donated, it should have
right of first-use since they are suppose to own the vCPU.
On a Power9 System with 32 cores
# lscpu
Architecture: ppc64le
Byte Order: Little Endian
CPU(s): 128
On-line CPU(s) list: 0-127
Thread(s) per core: 8
Core(s) per socket: 1
Socket(s): 16
NUMA node(s): 2
Model: 2.2 (pvr 004e 0202)
Model name: POWER9 (architected), altivec supported
Hypervisor vendor: pHyp
Virtualization type: para
L1d cache: 32K
L1i cache: 32K
L2 cache: 512K
L3 cache: 10240K
NUMA node0 CPU(s): 0-63
NUMA node1 CPU(s): 64-127
# perf stat -a -r 5 ./schbench
v5.4 v5.4 + patch
Latency percentiles (usec) Latency percentiles (usec)
49.0000th: 47 50.0000th: 33
74.0000th: 64 75.0000th: 44
89.0000th: 76 90.0000th: 50
94.0000th: 83 95.0000th: 53
*98.0000th: 103 *99.0000th: 57
98.5000th: 2124 99.5000th: 59
98.9000th: 7976 99.9000th: 83
min=-1, max=10519 min=0, max=117
Latency percentiles (usec) Latency percentiles (usec)
49.0000th: 45 50.0000th: 34
74.0000th: 61 75.0000th: 45
89.0000th: 70 90.0000th: 52
94.0000th: 77 95.0000th: 56
*98.0000th: 504 *99.0000th: 62
98.5000th: 4012 99.5000th: 64
98.9000th: 8168 99.9000th: 79
min=-1, max=14500 min=0, max=123
Latency percentiles (usec) Latency percentiles (usec)
49.0000th: 48 50.0000th: 35
74.0000th: 65 75.0000th: 47
89.0000th: 76 90.0000th: 55
94.0000th: 82 95.0000th: 59
*98.0000th: 1098 *99.0000th: 67
98.5000th: 3988 99.5000th: 71
98.9000th: 9360 99.9000th: 98
min=-1, max=19283 min=0, max=137
Latency percentiles (usec) Latency percentiles (usec)
49.0000th: 46 50.0000th: 35
74.0000th: 63 75.0000th: 46
89.0000th: 73 90.0000th: 53
94.0000th: 78 95.0000th: 57
*98.0000th: 113 *99.0000th: 63
98.5000th: 2316 99.5000th: 65
98.9000th: 7704 99.9000th: 83
min=-1, max=17976 min=0, max=139
Latency percentiles (usec) Latency percentiles (usec)
49.0000th: 46 50.0000th: 34
74.0000th: 62 75.0000th: 46
89.0000th: 73 90.0000th: 53
94.0000th: 79 95.0000th: 57
*98.0000th: 97 *99.0000th: 64
98.5000th: 1398 99.5000th: 70
98.9000th: 8136 99.9000th: 100
min=-1, max=10008 min=0, max=142
Performance counter stats for 'system wide' (4 runs):
context-switches 42,604 ( +- 0.87% ) 45,397 ( +- 0.25% )
cpu-migrations 0,195 ( +- 2.70% ) 230 ( +- 7.23% )
page-faults 16,783 ( +- 14.87% ) 16,781 ( +- 9.77% )
Waiman Long suggested using static_keys.
Reported-by: Parth Shah <parth@linux.ibm.com>
Reported-by: Ihor Pasichnyk <Ihor.Pasichnyk@ibm.com>
Cc: Parth Shah <parth@linux.ibm.com>
Cc: Ihor Pasichnyk <Ihor.Pasichnyk@ibm.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/spinlock.h | 5 +++--
arch/powerpc/mm/numa.c | 4 ++++
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index e9a960e28f3c..866f6ca0427a 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -35,11 +35,12 @@
#define LOCK_TOKEN 1
#endif
-#ifdef CONFIG_PPC_PSERIES
+#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_PPC_SPLPAR)
+DECLARE_STATIC_KEY_FALSE(shared_processor);
#define vcpu_is_preempted vcpu_is_preempted
static inline bool vcpu_is_preempted(int cpu)
{
- if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+ if (!static_branch_unlikely(&shared_processor))
return false;
return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
}
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 50d68d21ddcc..ffb971f3a63c 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1568,9 +1568,13 @@ int prrn_is_enabled(void)
return prrn_enabled;
}
+DEFINE_STATIC_KEY_FALSE(shared_processor);
+EXPORT_SYMBOL_GPL(shared_processor);
+
void __init shared_proc_topology_init(void)
{
if (lppaca_shared_proc(get_lppaca())) {
+ static_branch_enable(&shared_processor);
bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
nr_cpumask_bits);
numa_update_cpu_topology(false);
--
2.18.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH 2/2] powerpc/shared: Use static key to detect shared processor
2019-12-04 13:44 [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt Srikar Dronamraju
@ 2019-12-04 13:44 ` Srikar Dronamraju
2019-12-04 16:18 ` [PATCH v2 " Srikar Dronamraju
2019-12-04 15:05 ` [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt Srikar Dronamraju
` (3 subsequent siblings)
4 siblings, 1 reply; 7+ messages in thread
From: Srikar Dronamraju @ 2019-12-04 13:44 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev, Srikar Dronamraju
With the static key shared processor available, is_shared_processor()
can return without having to query the lppaca structure.
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/spinlock.h | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 866f6ca0427a..699eb306a835 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -115,9 +115,8 @@ static inline bool is_shared_processor(void)
* LPPACA is only available on Pseries so guard anything LPPACA related to
* allow other platforms (which include this common header) to compile.
*/
-#ifdef CONFIG_PPC_PSERIES
- return (IS_ENABLED(CONFIG_PPC_SPLPAR) &&
- lppaca_shared_proc(local_paca->lppaca_ptr));
+#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_PPC_SPLPAR)
+ return static_branch_unlikely(&shared_processor);
#else
return false;
#endif
--
2.18.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt
2019-12-04 13:44 [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt Srikar Dronamraju
2019-12-04 13:44 ` [PATCH 2/2] powerpc/shared: Use static key to detect shared processor Srikar Dronamraju
@ 2019-12-04 15:05 ` Srikar Dronamraju
2019-12-04 16:58 ` Waiman Long
` (2 subsequent siblings)
4 siblings, 0 replies; 7+ messages in thread
From: Srikar Dronamraju @ 2019-12-04 15:05 UTC (permalink / raw)
To: Michael Ellerman
Cc: Juri Lelli, Parth Shah, linuxppc-dev, Waiman Long, Ihor Pasichnyk
* Srikar Dronamraju <srikar@linux.vnet.ibm.com> [2019-12-04 19:14:58]:
>
>
> # perf stat -a -r 5 ./schbench
> v5.4 v5.4 + patch
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 47 50.0000th: 33
> 74.0000th: 64 75.0000th: 44
> 89.0000th: 76 90.0000th: 50
> 94.0000th: 83 95.0000th: 53
> *98.0000th: 103 *99.0000th: 57
> 98.5000th: 2124 99.5000th: 59
> 98.9000th: 7976 99.9000th: 83
> min=-1, max=10519 min=0, max=117
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 45 50.0000th: 34
> 74.0000th: 61 75.0000th: 45
> 89.0000th: 70 90.0000th: 52
> 94.0000th: 77 95.0000th: 56
> *98.0000th: 504 *99.0000th: 62
> 98.5000th: 4012 99.5000th: 64
> 98.9000th: 8168 99.9000th: 79
> min=-1, max=14500 min=0, max=123
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 48 50.0000th: 35
> 74.0000th: 65 75.0000th: 47
> 89.0000th: 76 90.0000th: 55
> 94.0000th: 82 95.0000th: 59
> *98.0000th: 1098 *99.0000th: 67
> 98.5000th: 3988 99.5000th: 71
> 98.9000th: 9360 99.9000th: 98
> min=-1, max=19283 min=0, max=137
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 46 50.0000th: 35
> 74.0000th: 63 75.0000th: 46
> 89.0000th: 73 90.0000th: 53
> 94.0000th: 78 95.0000th: 57
> *98.0000th: 113 *99.0000th: 63
> 98.5000th: 2316 99.5000th: 65
> 98.9000th: 7704 99.9000th: 83
> min=-1, max=17976 min=0, max=139
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 46 50.0000th: 34
> 74.0000th: 62 75.0000th: 46
> 89.0000th: 73 90.0000th: 53
> 94.0000th: 79 95.0000th: 57
> *98.0000th: 97 *99.0000th: 64
> 98.5000th: 1398 99.5000th: 70
> 98.9000th: 8136 99.9000th: 100
> min=-1, max=10008 min=0, max=142
>
Just to be clear, since these are latency values, lesser number is better.
--
Thanks and Regards
Srikar Dronamraju
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH v2 2/2] powerpc/shared: Use static key to detect shared processor
2019-12-04 13:44 ` [PATCH 2/2] powerpc/shared: Use static key to detect shared processor Srikar Dronamraju
@ 2019-12-04 16:18 ` Srikar Dronamraju
0 siblings, 0 replies; 7+ messages in thread
From: Srikar Dronamraju @ 2019-12-04 16:18 UTC (permalink / raw)
To: Michael Ellerman
Cc: Juri Lelli, Parth Shah, Phil Auld, Ihor Pasichnyk, Waiman Long,
linuxppc-dev
With the static key shared processor available, is_shared_processor()
can return without having to query the lppaca structure.
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v1->v2:
Now that we no more refer to lppaca, remove the comment.
arch/powerpc/include/asm/spinlock.h | 9 ++-------
1 file changed, 2 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 866f6ca0427a..251fe6e47471 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -111,13 +111,8 @@ static inline void splpar_rw_yield(arch_rwlock_t *lock) {};
static inline bool is_shared_processor(void)
{
-/*
- * LPPACA is only available on Pseries so guard anything LPPACA related to
- * allow other platforms (which include this common header) to compile.
- */
-#ifdef CONFIG_PPC_PSERIES
- return (IS_ENABLED(CONFIG_PPC_SPLPAR) &&
- lppaca_shared_proc(local_paca->lppaca_ptr));
+#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_PPC_SPLPAR)
+ return static_branch_unlikely(&shared_processor);
#else
return false;
#endif
--
2.18.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt
2019-12-04 13:44 [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt Srikar Dronamraju
2019-12-04 13:44 ` [PATCH 2/2] powerpc/shared: Use static key to detect shared processor Srikar Dronamraju
2019-12-04 15:05 ` [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt Srikar Dronamraju
@ 2019-12-04 16:58 ` Waiman Long
2019-12-05 5:07 ` Gautham R Shenoy
2019-12-05 7:08 ` Juri Lelli
4 siblings, 0 replies; 7+ messages in thread
From: Waiman Long @ 2019-12-04 16:58 UTC (permalink / raw)
To: Srikar Dronamraju, Michael Ellerman
Cc: Juri Lelli, Parth Shah, linuxppc-dev, Ihor Pasichnyk
On 12/4/19 8:44 AM, Srikar Dronamraju wrote:
> With commit 247f2f6f3c70 ("sched/core: Don't schedule threads on pre-empted
> vCPUs"), scheduler avoids preempted vCPUs to schedule tasks on wakeup.
> This leads to wrong choice of CPU, which in-turn leads to larger wakeup
> latencies. Eventually, it leads to performance regression in latency
> sensitive benchmarks like soltp, schbench etc.
>
> On Powerpc, vcpu_is_preempted only looks at yield_count. If the
> yield_count is odd, the vCPU is assumed to be preempted. However
> yield_count is increased whenever LPAR enters CEDE state. So any CPU
> that has entered CEDE state is assumed to be preempted.
>
> Even if vCPU of dedicated LPAR is preempted/donated, it should have
> right of first-use since they are suppose to own the vCPU.
>
> On a Power9 System with 32 cores
> # lscpu
> Architecture: ppc64le
> Byte Order: Little Endian
> CPU(s): 128
> On-line CPU(s) list: 0-127
> Thread(s) per core: 8
> Core(s) per socket: 1
> Socket(s): 16
> NUMA node(s): 2
> Model: 2.2 (pvr 004e 0202)
> Model name: POWER9 (architected), altivec supported
> Hypervisor vendor: pHyp
> Virtualization type: para
> L1d cache: 32K
> L1i cache: 32K
> L2 cache: 512K
> L3 cache: 10240K
> NUMA node0 CPU(s): 0-63
> NUMA node1 CPU(s): 64-127
>
>
> # perf stat -a -r 5 ./schbench
> v5.4 v5.4 + patch
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 47 50.0000th: 33
> 74.0000th: 64 75.0000th: 44
> 89.0000th: 76 90.0000th: 50
> 94.0000th: 83 95.0000th: 53
> *98.0000th: 103 *99.0000th: 57
> 98.5000th: 2124 99.5000th: 59
> 98.9000th: 7976 99.9000th: 83
> min=-1, max=10519 min=0, max=117
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 45 50.0000th: 34
> 74.0000th: 61 75.0000th: 45
> 89.0000th: 70 90.0000th: 52
> 94.0000th: 77 95.0000th: 56
> *98.0000th: 504 *99.0000th: 62
> 98.5000th: 4012 99.5000th: 64
> 98.9000th: 8168 99.9000th: 79
> min=-1, max=14500 min=0, max=123
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 48 50.0000th: 35
> 74.0000th: 65 75.0000th: 47
> 89.0000th: 76 90.0000th: 55
> 94.0000th: 82 95.0000th: 59
> *98.0000th: 1098 *99.0000th: 67
> 98.5000th: 3988 99.5000th: 71
> 98.9000th: 9360 99.9000th: 98
> min=-1, max=19283 min=0, max=137
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 46 50.0000th: 35
> 74.0000th: 63 75.0000th: 46
> 89.0000th: 73 90.0000th: 53
> 94.0000th: 78 95.0000th: 57
> *98.0000th: 113 *99.0000th: 63
> 98.5000th: 2316 99.5000th: 65
> 98.9000th: 7704 99.9000th: 83
> min=-1, max=17976 min=0, max=139
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 46 50.0000th: 34
> 74.0000th: 62 75.0000th: 46
> 89.0000th: 73 90.0000th: 53
> 94.0000th: 79 95.0000th: 57
> *98.0000th: 97 *99.0000th: 64
> 98.5000th: 1398 99.5000th: 70
> 98.9000th: 8136 99.9000th: 100
> min=-1, max=10008 min=0, max=142
>
> Performance counter stats for 'system wide' (4 runs):
>
> context-switches 42,604 ( +- 0.87% ) 45,397 ( +- 0.25% )
> cpu-migrations 0,195 ( +- 2.70% ) 230 ( +- 7.23% )
> page-faults 16,783 ( +- 14.87% ) 16,781 ( +- 9.77% )
>
> Waiman Long suggested using static_keys.
>
> Reported-by: Parth Shah <parth@linux.ibm.com>
> Reported-by: Ihor Pasichnyk <Ihor.Pasichnyk@ibm.com>
> Cc: Parth Shah <parth@linux.ibm.com>
> Cc: Ihor Pasichnyk <Ihor.Pasichnyk@ibm.com>
> Cc: Juri Lelli <juri.lelli@redhat.com>
> Cc: Waiman Long <longman@redhat.com>
> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
> ---
> arch/powerpc/include/asm/spinlock.h | 5 +++--
> arch/powerpc/mm/numa.c | 4 ++++
> 2 files changed, 7 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
> index e9a960e28f3c..866f6ca0427a 100644
> --- a/arch/powerpc/include/asm/spinlock.h
> +++ b/arch/powerpc/include/asm/spinlock.h
> @@ -35,11 +35,12 @@
> #define LOCK_TOKEN 1
> #endif
>
> -#ifdef CONFIG_PPC_PSERIES
> +#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_PPC_SPLPAR)
> +DECLARE_STATIC_KEY_FALSE(shared_processor);
> #define vcpu_is_preempted vcpu_is_preempted
> static inline bool vcpu_is_preempted(int cpu)
> {
> - if (!firmware_has_feature(FW_FEATURE_SPLPAR))
> + if (!static_branch_unlikely(&shared_processor))
> return false;
> return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
> }
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index 50d68d21ddcc..ffb971f3a63c 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -1568,9 +1568,13 @@ int prrn_is_enabled(void)
> return prrn_enabled;
> }
>
> +DEFINE_STATIC_KEY_FALSE(shared_processor);
> +EXPORT_SYMBOL_GPL(shared_processor);
> +
> void __init shared_proc_topology_init(void)
> {
> if (lppaca_shared_proc(get_lppaca())) {
> + static_branch_enable(&shared_processor);
> bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
> nr_cpumask_bits);
> numa_update_cpu_topology(false);
The patch looks good to me.
Just a minor nit. According to the Kconfig file, PPC_SPLPAR depends on
PPC_PSERIES. IOW, when PPC_SPLPAR is defined, PPC_PSERIES must have been
defined. So you can probably drop CONFIG_PPC_PSERIES. The same is true
for patch 2.
Acked-by: Waiman Long <longman@redhat.com>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt
2019-12-04 13:44 [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt Srikar Dronamraju
` (2 preceding siblings ...)
2019-12-04 16:58 ` Waiman Long
@ 2019-12-05 5:07 ` Gautham R Shenoy
2019-12-05 7:08 ` Juri Lelli
4 siblings, 0 replies; 7+ messages in thread
From: Gautham R Shenoy @ 2019-12-05 5:07 UTC (permalink / raw)
To: Srikar Dronamraju
Cc: Juri Lelli, Parth Shah, Ihor Pasichnyk, Waiman Long, linuxppc-dev
Hi Srikar,
On Wed, Dec 04, 2019 at 07:14:58PM +0530, Srikar Dronamraju wrote:
> With commit 247f2f6f3c70 ("sched/core: Don't schedule threads on pre-empted
> vCPUs"), scheduler avoids preempted vCPUs to schedule tasks on wakeup.
> This leads to wrong choice of CPU, which in-turn leads to larger wakeup
> latencies. Eventually, it leads to performance regression in latency
> sensitive benchmarks like soltp, schbench etc.
The regression in the latency sensitive benchmarks is due to
preferring potentially busy vCPUs over vCPUs in the CEDE state.
>
> On Powerpc, vcpu_is_preempted only looks at yield_count. If the
> yield_count is odd, the vCPU is assumed to be preempted. However
> yield_count is increased whenever LPAR enters CEDE state. So any CPU
> that has entered CEDE state is assumed to be preempted.
>
> Even if vCPU of dedicated LPAR is preempted/donated, it should have
> right of first-use since they are suppose to own the vCPU.
>
> On a Power9 System with 32 cores
> # lscpu
> Architecture: ppc64le
> Byte Order: Little Endian
> CPU(s): 128
> On-line CPU(s) list: 0-127
> Thread(s) per core: 8
> Core(s) per socket: 1
> Socket(s): 16
> NUMA node(s): 2
> Model: 2.2 (pvr 004e 0202)
> Model name: POWER9 (architected), altivec supported
> Hypervisor vendor: pHyp
> Virtualization type: para
> L1d cache: 32K
> L1i cache: 32K
> L2 cache: 512K
> L3 cache: 10240K
> NUMA node0 CPU(s): 0-63
> NUMA node1 CPU(s): 64-127
>
>
> # perf stat -a -r 5 ./schbench
> v5.4 v5.4 + patch
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 47 50.0000th: 33
> 74.0000th: 64 75.0000th: 44
> 89.0000th: 76 90.0000th: 50
> 94.0000th: 83 95.0000th: 53
> *98.0000th: 103 *99.0000th: 57
> 98.5000th: 2124 99.5000th: 59
> 98.9000th: 7976 99.9000th: 83
> min=-1, max=10519 min=0, max=117
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 45 50.0000th: 34
> 74.0000th: 61 75.0000th: 45
> 89.0000th: 70 90.0000th: 52
> 94.0000th: 77 95.0000th: 56
> *98.0000th: 504 *99.0000th: 62
> 98.5000th: 4012 99.5000th: 64
> 98.9000th: 8168 99.9000th: 79
> min=-1, max=14500 min=0, max=123
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 48 50.0000th: 35
> 74.0000th: 65 75.0000th: 47
> 89.0000th: 76 90.0000th: 55
> 94.0000th: 82 95.0000th: 59
> *98.0000th: 1098 *99.0000th: 67
> 98.5000th: 3988 99.5000th: 71
> 98.9000th: 9360 99.9000th: 98
> min=-1, max=19283 min=0, max=137
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 46 50.0000th: 35
> 74.0000th: 63 75.0000th: 46
> 89.0000th: 73 90.0000th: 53
> 94.0000th: 78 95.0000th: 57
> *98.0000th: 113 *99.0000th: 63
> 98.5000th: 2316 99.5000th: 65
> 98.9000th: 7704 99.9000th: 83
> min=-1, max=17976 min=0, max=139
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 46 50.0000th: 34
> 74.0000th: 62 75.0000th: 46
> 89.0000th: 73 90.0000th: 53
> 94.0000th: 79 95.0000th: 57
> *98.0000th: 97 *99.0000th: 64
> 98.5000th: 1398 99.5000th: 70
> 98.9000th: 8136 99.9000th: 100
> min=-1, max=10008 min=0, max=142
>
> Performance counter stats for 'system wide' (4 runs):
>
> context-switches 42,604 ( +- 0.87% ) 45,397 ( +- 0.25% )
> cpu-migrations 0,195 ( +- 2.70% ) 230 ( +- 7.23% )
> page-faults 16,783 ( +- 14.87% ) 16,781 ( +- 9.77% )
>
> Waiman Long suggested using static_keys.
This needs to be Cc'ed to the stable kernel 4.18+
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
>
> Reported-by: Parth Shah <parth@linux.ibm.com>
> Reported-by: Ihor Pasichnyk <Ihor.Pasichnyk@ibm.com>
> Cc: Parth Shah <parth@linux.ibm.com>
> Cc: Ihor Pasichnyk <Ihor.Pasichnyk@ibm.com>
> Cc: Juri Lelli <juri.lelli@redhat.com>
> Cc: Waiman Long <longman@redhat.com>
> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
> ---
> arch/powerpc/include/asm/spinlock.h | 5 +++--
> arch/powerpc/mm/numa.c | 4 ++++
> 2 files changed, 7 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
> index e9a960e28f3c..866f6ca0427a 100644
> --- a/arch/powerpc/include/asm/spinlock.h
> +++ b/arch/powerpc/include/asm/spinlock.h
> @@ -35,11 +35,12 @@
> #define LOCK_TOKEN 1
> #endif
>
> -#ifdef CONFIG_PPC_PSERIES
> +#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_PPC_SPLPAR)
> +DECLARE_STATIC_KEY_FALSE(shared_processor);
> #define vcpu_is_preempted vcpu_is_preempted
> static inline bool vcpu_is_preempted(int cpu)
> {
> - if (!firmware_has_feature(FW_FEATURE_SPLPAR))
> + if (!static_branch_unlikely(&shared_processor))
> return false;
> return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
> }
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index 50d68d21ddcc..ffb971f3a63c 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -1568,9 +1568,13 @@ int prrn_is_enabled(void)
> return prrn_enabled;
> }
>
> +DEFINE_STATIC_KEY_FALSE(shared_processor);
> +EXPORT_SYMBOL_GPL(shared_processor);
> +
> void __init shared_proc_topology_init(void)
> {
> if (lppaca_shared_proc(get_lppaca())) {
> + static_branch_enable(&shared_processor);
> bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
> nr_cpumask_bits);
> numa_update_cpu_topology(false);
> --
> 2.18.1
>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt
2019-12-04 13:44 [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt Srikar Dronamraju
` (3 preceding siblings ...)
2019-12-05 5:07 ` Gautham R Shenoy
@ 2019-12-05 7:08 ` Juri Lelli
4 siblings, 0 replies; 7+ messages in thread
From: Juri Lelli @ 2019-12-05 7:08 UTC (permalink / raw)
To: Srikar Dronamraju; +Cc: Ihor Pasichnyk, linuxppc-dev, Waiman Long, Parth Shah
Hi,
On 04/12/19 19:14, Srikar Dronamraju wrote:
> With commit 247f2f6f3c70 ("sched/core: Don't schedule threads on pre-empted
> vCPUs"), scheduler avoids preempted vCPUs to schedule tasks on wakeup.
> This leads to wrong choice of CPU, which in-turn leads to larger wakeup
> latencies. Eventually, it leads to performance regression in latency
> sensitive benchmarks like soltp, schbench etc.
>
> On Powerpc, vcpu_is_preempted only looks at yield_count. If the
> yield_count is odd, the vCPU is assumed to be preempted. However
> yield_count is increased whenever LPAR enters CEDE state. So any CPU
> that has entered CEDE state is assumed to be preempted.
>
> Even if vCPU of dedicated LPAR is preempted/donated, it should have
> right of first-use since they are suppose to own the vCPU.
>
> On a Power9 System with 32 cores
> # lscpu
> Architecture: ppc64le
> Byte Order: Little Endian
> CPU(s): 128
> On-line CPU(s) list: 0-127
> Thread(s) per core: 8
> Core(s) per socket: 1
> Socket(s): 16
> NUMA node(s): 2
> Model: 2.2 (pvr 004e 0202)
> Model name: POWER9 (architected), altivec supported
> Hypervisor vendor: pHyp
> Virtualization type: para
> L1d cache: 32K
> L1i cache: 32K
> L2 cache: 512K
> L3 cache: 10240K
> NUMA node0 CPU(s): 0-63
> NUMA node1 CPU(s): 64-127
>
>
> # perf stat -a -r 5 ./schbench
> v5.4 v5.4 + patch
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 47 50.0000th: 33
> 74.0000th: 64 75.0000th: 44
> 89.0000th: 76 90.0000th: 50
> 94.0000th: 83 95.0000th: 53
> *98.0000th: 103 *99.0000th: 57
> 98.5000th: 2124 99.5000th: 59
> 98.9000th: 7976 99.9000th: 83
> min=-1, max=10519 min=0, max=117
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 45 50.0000th: 34
> 74.0000th: 61 75.0000th: 45
> 89.0000th: 70 90.0000th: 52
> 94.0000th: 77 95.0000th: 56
> *98.0000th: 504 *99.0000th: 62
> 98.5000th: 4012 99.5000th: 64
> 98.9000th: 8168 99.9000th: 79
> min=-1, max=14500 min=0, max=123
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 48 50.0000th: 35
> 74.0000th: 65 75.0000th: 47
> 89.0000th: 76 90.0000th: 55
> 94.0000th: 82 95.0000th: 59
> *98.0000th: 1098 *99.0000th: 67
> 98.5000th: 3988 99.5000th: 71
> 98.9000th: 9360 99.9000th: 98
> min=-1, max=19283 min=0, max=137
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 46 50.0000th: 35
> 74.0000th: 63 75.0000th: 46
> 89.0000th: 73 90.0000th: 53
> 94.0000th: 78 95.0000th: 57
> *98.0000th: 113 *99.0000th: 63
> 98.5000th: 2316 99.5000th: 65
> 98.9000th: 7704 99.9000th: 83
> min=-1, max=17976 min=0, max=139
> Latency percentiles (usec) Latency percentiles (usec)
> 49.0000th: 46 50.0000th: 34
> 74.0000th: 62 75.0000th: 46
> 89.0000th: 73 90.0000th: 53
> 94.0000th: 79 95.0000th: 57
> *98.0000th: 97 *99.0000th: 64
> 98.5000th: 1398 99.5000th: 70
> 98.9000th: 8136 99.9000th: 100
> min=-1, max=10008 min=0, max=142
>
> Performance counter stats for 'system wide' (4 runs):
>
> context-switches 42,604 ( +- 0.87% ) 45,397 ( +- 0.25% )
> cpu-migrations 0,195 ( +- 2.70% ) 230 ( +- 7.23% )
> page-faults 16,783 ( +- 14.87% ) 16,781 ( +- 9.77% )
>
> Waiman Long suggested using static_keys.
>
> Reported-by: Parth Shah <parth@linux.ibm.com>
> Reported-by: Ihor Pasichnyk <Ihor.Pasichnyk@ibm.com>
> Cc: Parth Shah <parth@linux.ibm.com>
> Cc: Ihor Pasichnyk <Ihor.Pasichnyk@ibm.com>
> Cc: Juri Lelli <juri.lelli@redhat.com>
> Cc: Waiman Long <longman@redhat.com>
> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
> ---
I could reproduce the performace regression and can confirm that this
patch fixes it.
Tested-by: Juri Lelli <juri.lelli@redhat.com>
Thanks,
Juri
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2019-12-05 12:37 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-12-04 13:44 [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt Srikar Dronamraju
2019-12-04 13:44 ` [PATCH 2/2] powerpc/shared: Use static key to detect shared processor Srikar Dronamraju
2019-12-04 16:18 ` [PATCH v2 " Srikar Dronamraju
2019-12-04 15:05 ` [PATCH 1/2] powerpc/vcpu: Assume dedicated processors as non-preempt Srikar Dronamraju
2019-12-04 16:58 ` Waiman Long
2019-12-05 5:07 ` Gautham R Shenoy
2019-12-05 7:08 ` Juri Lelli
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).