Merge pull request #1282 from askervin/5aD-oci-mempolicy

Add support for Linux memory policy

Author: AkihiroSuda

config-linux.md

@@ -812,6 +812,45 @@ Tasks inside the container:
 }
 ```
 
+## <a name="configLinuxMemoryPolicy" />Memory policy
+
+**`memoryPolicy`** (object, OPTIONAL) sets the NUMA memory policy for the container.
+For more information see the [set_mempolicy(2)][set_mempolicy.2] man page.
+
+* **`mode`** *(string, REQUIRED)* -
+
+    A valid list of constants is shown below.
+
+    * `MPOL_DEFAULT`
+    * `MPOL_BIND`
+    * `MPOL_INTERLEAVE`
+    * `MPOL_WEIGHTED_INTERLEAVE`
+    * `MPOL_PREFERRED`
+    * `MPOL_PREFERRED_MANY`
+    * `MPOL_LOCAL`
+
+* **`nodes`** *(string, REQUIRED)* - list of memory nodes from which nodemask is constructed to set_mempolicy(2). This is a comma-separated list, with dashes to represent ranges. For example, `0-3,7` represents memory nodes 0,1,2,3, and 7.
+
+* **`flags`** *(array of strings, OPTIONAL)* - list of flags to use with set_mempolicy(2).
+
+    A valid list of constants is shown below.
+
+    * `MPOL_F_NUMA_BALANCING`
+    * `MPOL_F_RELATIVE_NODES`
+    * `MPOL_F_STATIC_NODES`
+
+### Example
+
+```json
+"linux": {
+    "memoryPolicy": {
+        "mode": "MPOL_INTERLEAVE",
+        "nodes": "2-3"
+        "flags": ["MPOL_F_STATIC_NODES"],
+    }
+}
+```
+
 ## <a name="configLinuxSysctl" />Sysctl
 
 **`sysctl`** (object, OPTIONAL) allows kernel parameters to be modified at runtime for the container.
@@ -1094,6 +1133,7 @@ subset of the available options.
 [tmpfs]: https://www.kernel.org/doc/Documentation/filesystems/tmpfs.txt
 
 [full.4]: https://man7.org/linux/man-pages/man4/full.4.html
+[set_mempolicy.2]: https://man7.org/linux/man-pages/man2/set_mempolicy.2.html
 [mknod.1]: https://man7.org/linux/man-pages/man1/mknod.1.html
 [mknod.2]: https://man7.org/linux/man-pages/man2/mknod.2.html
 [namespaces.7_2]: https://man7.org/linux/man-pages/man7/namespaces.7.html

features-linux.md

@@ -195,6 +195,37 @@ Irrelevant to the availability of SELinux on the host operating system.
 }
 ```
 
+## <a name="linuxFeaturesMemoryPolicy" />MemoryPolicy
+
+**`memoryPolicy`** (object, OPTIONAL) represents the runtime's implementation status of memoryPolicy.
+
+* **`modes`** (array of strings, OPTIONAL). Recognized memory policies. Includes policies that may not be supported by the host operating system.
+  The runtime MUST recognize the elements in this array as the [`mode` of `linux.memoryPolicy` objects in `config.json`](config-linux.md#memory-policy).
+
+* **`flags`** (array of strings, OPTIONAL). Recognized flags for memory policies. Includes flags that may not be supported by the host operating system.
+  The runtime MUST recognize the elements in this in the [`flags` property of the `linux.memoryPolicy` object in `config.json`](config-linux.md#memory-policy)
+
+### Example
+
+```json
+"memoryPolicy": {
+  "modes": [
+    "MPOL_DEFAULT",
+    "MPOL_BIND",
+    "MPOL_INTERLEAVE",
+    "MPOL_WEIGHTED_INTERLEAVE",
+    "MPOL_PREFERRED",
+    "MPOL_PREFERRED_MANY",
+    "MPOL_LOCAL"
+  ],
+  "flags": [
+    "MPOL_F_NUMA_BALANCING",
+    "MPOL_F_RELATIVE_NODES",
+    "MPOL_F_STATIC_NODES"
+  ]
+}
+```
+
 ## <a name="linuxFeaturesIntelRdt" />Intel RDT
 
 **`intelRdt`** (object, OPTIONAL) represents the runtime's implementation status of Intel RDT.

features.md

@@ -354,6 +354,22 @@ Here is a full example for reference.
     "selinux": {
       "enabled": true
     },
+    "memoryPolicy": {
+      "modes": [
+        "MPOL_DEFAULT",
+        "MPOL_BIND",
+        "MPOL_INTERLEAVE",
+        "MPOL_WEIGHTED_INTERLEAVE",
+        "MPOL_PREFERRED",
+        "MPOL_PREFERRED_MANY",
+        "MPOL_LOCAL"
+      ],
+      "flags": [
+        "MPOL_F_NUMA_BALANCING",
+        "MPOL_F_RELATIVE_NODES",
+        "MPOL_F_STATIC_NODES"
+      ]
+    },
     "intelRdt": {
       "enabled": true,
       "schemata": true

schema/config-linux.json

@@ -283,6 +283,23 @@
                     }
                 }
             },
+            "memoryPolicy": {
+                "type": "object",
+                "properties": {
+                    "mode": {
+                        "$ref": "defs-linux.json#/definitions/MemoryPolicyMode"
+                    },
+                    "nodes": {
+                        "type": "string"
+                    },
+                    "flags": {
+                        "type": "array",
+                        "items": {
+                            "$ref": "defs-linux.json#/definitions/MemoryPolicyFlag"
+                        }
+                    }
+                }
+            },
             "personality": {
                 "type": "object",
                 "$ref": "defs-linux.json#/definitions/Personality"

schema/defs-linux.json

@@ -272,6 +272,26 @@
                 "allow"
             ]
         },
+        "MemoryPolicyMode": {
+            "type": "string",
+            "enum": [
+                "MPOL_DEFAULT",
+                "MPOL_BIND",
+                "MPOL_INTERLEAVE",
+                "MPOL_WEIGHTED_INTERLEAVE",
+                "MPOL_PREFERRED",
+                "MPOL_PREFERRED_MANY",
+                "MPOL_LOCAL"
+            ]
+        },
+        "MemoryPolicyFlag": {
+            "type": "string",
+            "enum": [
+                "MPOL_F_NUMA_BALANCING",
+                "MPOL_F_RELATIVE_NODES",
+                "MPOL_F_STATIC_NODES"
+            ]
+        },
         "NetworkInterfacePriority": {
             "type": "object",
             "properties": {

specs-go/config.go

@@ -251,6 +251,8 @@ type Linux struct {
 	// IntelRdt contains Intel Resource Director Technology (RDT) information for
 	// handling resource constraints and monitoring metrics (e.g., L3 cache, memory bandwidth) for the container
 	IntelRdt *LinuxIntelRdt `json:"intelRdt,omitempty"`
+	// MemoryPolicy contains NUMA memory policy for the container.
+	MemoryPolicy *LinuxMemoryPolicy `json:"memoryPolicy,omitempty"`
 	// Personality contains configuration for the Linux personality syscall
 	Personality *LinuxPersonality `json:"personality,omitempty"`
 	// TimeOffsets specifies the offset for supporting time namespaces.
@@ -860,6 +862,19 @@ type LinuxIntelRdt struct {
 	EnableMonitoring bool `json:"enableMonitoring,omitempty"`
 }
 
+// LinuxMemoryPolicy represents input for the set_mempolicy syscall.
+type LinuxMemoryPolicy struct {
+	// Mode for the set_mempolicy syscall.
+	Mode MemoryPolicyModeType `json:"mode"`
+
+	// Nodes representing the nodemask for the set_mempolicy syscall in comma separated ranges format.
+	// Format: "<node0>-<node1>,<node2>,<node3>-<node4>,..."
+	Nodes string `json:"nodes"`
+
+	// Flags for the set_mempolicy syscall.
+	Flags []MemoryPolicyFlagType `json:"flags,omitempty"`
+}
+
 // ZOS contains platform-specific configuration for z/OS based containers.
 type ZOS struct {
 	// Namespaces contains the namespaces that are created and/or joined by the container
@@ -889,6 +904,26 @@ const (
 	ZOSUTSNamespace ZOSNamespaceType = "uts"
 )
 
+type MemoryPolicyModeType string
+
+const (
+	MpolDefault            MemoryPolicyModeType = "MPOL_DEFAULT"
+	MpolBind               MemoryPolicyModeType = "MPOL_BIND"
+	MpolInterleave         MemoryPolicyModeType = "MPOL_INTERLEAVE"
+	MpolWeightedInterleave MemoryPolicyModeType = "MPOL_WEIGHTED_INTERLEAVE"
+	MpolPreferred          MemoryPolicyModeType = "MPOL_PREFERRED"
+	MpolPreferredMany      MemoryPolicyModeType = "MPOL_PREFERRED_MANY"
+	MpolLocal              MemoryPolicyModeType = "MPOL_LOCAL"
+)
+
+type MemoryPolicyFlagType string
+
+const (
+	MpolFNumaBalancing MemoryPolicyFlagType = "MPOL_F_NUMA_BALANCING"
+	MpolFRelativeNodes MemoryPolicyFlagType = "MPOL_F_RELATIVE_NODES"
+	MpolFStaticNodes   MemoryPolicyFlagType = "MPOL_F_STATIC_NODES"
+)
+
 // LinuxSchedulerPolicy represents different scheduling policies used with the Linux Scheduler
 type LinuxSchedulerPolicy string
 

specs-go/features/features.go

@@ -47,6 +47,7 @@ type Linux struct {
 	Apparmor        *Apparmor        `json:"apparmor,omitempty"`
 	Selinux         *Selinux         `json:"selinux,omitempty"`
 	IntelRdt        *IntelRdt        `json:"intelRdt,omitempty"`
+	MemoryPolicy    *MemoryPolicy    `json:"memoryPolicy,omitempty"`
 	MountExtensions *MountExtensions `json:"mountExtensions,omitempty"`
 	NetDevices      *NetDevices      `json:"netDevices,omitempty"`
 }
@@ -132,6 +133,14 @@ type IntelRdt struct {
 	Enabled *bool `json:"enabled,omitempty"`
 }
 
+// MemoryPolicy represents the "memoryPolicy" field.
+type MemoryPolicy struct {
+	// modes is the list of known memory policy modes, e.g., "MPOL_INTERLEAVE".
+	Modes []string `json:"modes,omitempty"`
+	// flags is the list of known memory policy mode flags, e.g., "MPOL_F_STATIC_NODES".
+	Flags []string `json:"flags,omitempty"`
+}
+
 // MountExtensions represents the "mountExtensions" field.
 type MountExtensions struct {
 	// IDMap represents the status of idmap mounts support.