@@ -1003,6 +1003,13 @@ static int powerpc_smt_flags(void)
}
#endif
+/*
+ * 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);
+
/*
* P9 has a slightly odd architecture where pairs of cores share an L2 cache.
* This topology makes it *much* cheaper to migrate tasks between adjacent cores
@@ -1011,9 +1018,20 @@ 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 +1068,8 @@ 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(PKG) },
+ { cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC) },
+ { cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG) },
{ NULL, },
};
@@ -1686,6 +1704,9 @@ 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 (has_big_cores) {
pr_info("Big cores detected but using small core scheduling\n");
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. Since each thread-group is independent, running threads on both the thread-groups of a SMT8 core, should have a minimal adverse impact in non over provisioned scenarios. These changes in this patchset will not affect in the over provisioned scenario. If there are more threads than SMT domains, then asym_packing will not kick-in 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 <srikar@linux.vnet.ibm.com> --- Changelog: v4 -> v5: - commit msg update v3 -> v4: - Dont use splpar_asym_pack with SMT - Conflict resolution due to rebase (DIE changed to PKG) v2 -> v3: - Handle comments from Michael Ellerman. - Rework using existing cpu_has_features static key v1->v2: Using Jump label instead of a variable. arch/powerpc/kernel/smp.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-)