If there are shared processor LPARs, underlying Hypervisor can have more
virtual cores to handle than actual physical cores.
Starting with Power 9, a big core (aka SMT8 core) has 2 nearly
independent thread groups. On a shared processors LPARs, it helps to
pack threads to lesser number of cores so that the overall system
performance and utilization improves. PowerVM schedules at a big core
level. Hence packing to fewer cores helps.
For example: Lets says there are two 8-core Shared LPARs that are
actually sharing a 8 Core shared physical pool, each running 8 threads
each. Then Consolidating 8 threads to 4 cores on each LPAR would help
them to perform better. This is because each of the LPAR will get
100% time to run applications and there will no switching required by
the Hypervisor.
To achieve this, enable SD_ASYM_PACKING flag at CACHE, MC and DIE level
when the system is running in shared processor mode and has big cores.
Signed-off-by: Srikar Dronamraju <sri...@linux.vnet.ibm.com>
---
Changelog:
v1->v2: Using Jump label instead of a variable.
v2 -> v3:
- Handle comments on commit message (Michael Ellerman)
- Rework using existing cpu_has_features static key (Michael Ellerman)
- Added a comment on why we do asym_packing at core (Peter Zijlstra)
arch/powerpc/kernel/smp.c | 32 ++++++++++++++++++++++++--------
1 file changed, 24 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 5826f5108a12..dbf0a584804b 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -988,18 +988,22 @@ static int __init init_thread_group_cache_map(int cpu,
int cache_property)
}
static bool shared_caches;
+/*
+ * On shared processor LPARs scheduled on a big core (which has two or more
+ * independent thread groups per core), prefer lower numbered CPUs, so
+ * that workload consolidates to lesser number of cores.
+ */
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack);
#ifdef CONFIG_SCHED_SMT
/* cpumask of CPUs with asymmetric SMT dependency */
static int powerpc_smt_flags(void)
{
- int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+ if (cpu_has_feature(CPU_FTR_ASYM_SMT) ||
+ static_branch_unlikely(&splpar_asym_pack))
+ return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES |
SD_ASYM_PACKING;
- if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
- printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
- flags |= SD_ASYM_PACKING;
- }
- return flags;
+ return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
}
#endif
@@ -1011,9 +1015,20 @@ static int powerpc_smt_flags(void)
*/
static int powerpc_shared_cache_flags(void)
{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING;
+
return SD_SHARE_PKG_RESOURCES;
}
+static int powerpc_shared_proc_flags(void)
+{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return SD_ASYM_PACKING;
+
+ return 0;
+}
+
/*
* We can't just pass cpu_l2_cache_mask() directly because
* returns a non-const pointer and the compiler barfs on that.
@@ -1050,8 +1065,8 @@ static struct sched_domain_topology_level
powerpc_topology[] = {
{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
#endif
{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
- { cpu_mc_mask, SD_INIT_NAME(MC) },
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC) },
+ { cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(DIE) },
{ NULL, },
};
@@ -1686,7 +1701,13 @@ static void __init fixup_topology(void)
{
int i;
+ if (is_shared_processor() && has_big_cores)
+ static_branch_enable(&splpar_asym_pack);
+
#ifdef CONFIG_SCHED_SMT
+ if (cpu_has_feature(CPU_FTR_ASYM_SMT))
+ pr_info_once("Enabling Asymmetric SMT scheduling\n");
+
if (has_big_cores) {
pr_info("Big cores detected but using small core scheduling\n");
powerpc_topology[smt_idx].mask = smallcore_smt_mask;
--
2.31.1
