Like we are doing in qemu driver
($COMMIT_HASH_TO_BE_FILLED_DURING_PUSHING), lets call
virNumaSetupMemoryPolicy() only if really needed. Problem is, if
we numa_set_membind() child, there's no way to change it from the
daemon afterwards. So any later attempts to change the pinning
will fail. But in very weird way - CGroups will be set, but due
to membind child will not allocate memory from any other node.
Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com>
---
src/lxc/lxc_controller.c | 31 +++++++++++++++++++++++++------
1 file changed, 25 insertions(+), 6 deletions(-)
diff --git a/src/lxc/lxc_controller.c b/src/lxc/lxc_controller.c
index 8545f29..6881a37 100644
--- a/src/lxc/lxc_controller.c
+++ b/src/lxc/lxc_controller.c
@@ -742,14 +742,33 @@ static int virLXCControllerSetupResourceLimits(virLXCControllerPtr
ctrl)
virBitmapPtr nodeset = NULL;
virDomainNumatuneMemMode mode;
- VIR_DEBUG("Setting up process resource limits");
-
- if (virLXCControllerGetNumadAdvice(ctrl, &auto_nodeset) < 0)
- goto cleanup;
-
- nodeset = virDomainNumatuneGetNodeset(ctrl->def->numa, auto_nodeset, -1);
mode = virDomainNumatuneGetMode(ctrl->def->numa, -1);
+ if (mode == VIR_DOMAIN_NUMATUNE_MEM_STRICT) {
+ virCgroupPtr cgroup;
+
+ /* Create dummy cgroup ... */
+ if (virCgroupNewSelf(&cgroup) < 0)
+ goto cleanup;
+
+ /* ... just to detect if cpuset cgroup is present */
+ if (virCgroupHasController(cgroup, VIR_CGROUP_CONTROLLER_CPUSET)) {
+ /* Because if it's not, we will pin the child onto
+ * specified nodes for good. No later cpuset.mems
+ * change will have any effect. */
+ VIR_DEBUG("Postponing setting up resource limits to CGroup set up
phase");
+ virCgroupFree(&cgroup);
+ return virLXCControllerSetupCpuAffinity(ctrl);
+ }
+ }
+
+ VIR_DEBUG("Setting up process resource limits");
+
+ if (virLXCControllerGetNumadAdvice(ctrl, &auto_nodeset) < 0)
+ goto cleanup;
+
+ nodeset = virDomainNumatuneGetNodeset(ctrl->def->numa, auto_nodeset, -1);
+
if (virNumaSetupMemoryPolicy(mode, nodeset) < 0)
goto cleanup;
--
2.0.5