aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPeter Zijlstra <[email protected]>2017-10-02 14:50:33 +0200
committerIngo Molnar <[email protected]>2017-10-10 11:45:27 +0200
commited4ad1ca08a53cf1a805478678d1e7ff0d2cf251 (patch)
treedf07167f99faa528b598d522cf023e8c7a699d8e
parent799ba82de01e7543f6b2042e1a739f3a20255f23 (diff)
sched/topology: Restore SD_PREFER_SIBLING on MC domains
The normal x86_topology on NHM+ machines degenerates because the MC and CPU domains are of the same size, therefore MC inherits SD_PREFER_SIBLING from CPU (which then gets taken out). The result is that we'll spread tasks across the first NUMA level in order to maximize cache utilization. However, for the x86_numa_in_package_topology we loose the CPU domain, and we'll not have SD_PREFER_SIBLING set anywhere, giving a distinct difference in behaviour. Commit: 8e7fbcbc22c1 ("sched: Remove stale power aware scheduling remnants and dysfunctional knobs") made a fail by not preserving the SD_PREFER_SIBLING for the !power_saving case on both CPU and MC. Then commit: 6956dc568f34 ("sched/numa: Add SD_PERFER_SIBLING to CPU domain") adds it back to the CPU but not MC. Restore that now, such that we get consistent spreading behaviour wrt L3 and NUMA. Signed-off-by: Peter Zijlstra (Intel) <[email protected]> Cc: Linus Torvalds <[email protected]> Cc: Mike Galbraith <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: [email protected] Signed-off-by: Ingo Molnar <[email protected]>
-rw-r--r--kernel/sched/topology.c1
1 files changed, 1 insertions, 0 deletions
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index f1cf4f306a82..86e81f06d36b 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1157,6 +1157,7 @@ sd_init(struct sched_domain_topology_level *tl,
sd->smt_gain = 1178; /* ~15% */
} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+ sd->flags |= SD_PREFER_SIBLING;
sd->imbalance_pct = 117;
sd->cache_nice_tries = 1;
sd->busy_idx = 2;