spec: add scheduler entity

extend the process struct to represent scheduling attributes for a
process based on the sched_setattr(2) syscall.

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>

config.md

@@ -291,6 +291,33 @@ For Linux-based systems, the `process` object supports the following process-spe
 
     This is a per-process setting, where as [`disableOOMKiller`](config-linux.md#memory) is scoped for a memory cgroup.
     For more information on how these two settings work together, see [the memory cgroup documentation section 10. OOM Contol][cgroup-v1-memory_2].
+* **`scheduler`** (object, OPTIONAL) is an object describing the scheduler properties for the process.  The `scheduler` contains the following properties:
+
+    * **`policy`** (string, REQUIRED) represents the scheduling policy.  A valid list of values is:
+
+        * `SCHED_OTHER`
+        * `SCHED_FIFO`
+        * `SCHED_RR`
+        * `SCHED_BATCH`
+        * `SCHED_ISO`
+        * `SCHED_IDLE`
+        * `SCHED_DEADLINE`
+
+    * **`nice`** (int32, OPTIONAL) is the nice value for the process, affecting its priority. A lower nice value corresponds to a higher priority. If not set, the runtime must use the value 0.
+    * **`priority`** (int32, OPTIONAL) represents the static priority of the process, used by real-time policies like SCHED_FIFO and SCHED_RR. If not set, the runtime must use the value 0.
+    * **`flags`** (array of strings, OPTIONAL) is an array of strings representing scheduling flags.  A valid list of values is:
+
+        * `SCHED_FLAG_RESET_ON_FORK`
+        * `SCHED_FLAG_RECLAIM`
+        * `SCHED_FLAG_DL_OVERRUN`
+        * `SCHED_FLAG_KEEP_POLICY`
+        * `SCHED_FLAG_KEEP_PARAMS`
+        * `SCHED_FLAG_UTIL_CLAMP_MIN`
+        * `SCHED_FLAG_UTIL_CLAMP_MAX`
+
+    * **`runtime`** (uint64, OPTIONAL) represents the amount of time in nanoseconds during which the process is allowed to run in a given period, used by the deadline scheduler. If not set, the runtime must use the value 0.
+    * **`deadline`** (uint64, OPTIONAL) represents the absolute deadline for the process to complete its execution, used by the deadline scheduler. If not set, the runtime must use the value 0.
+    * **`period`** (uint64, OPTIONAL) represents the length of the period in nanoseconds used for determining the process runtime, used by the deadline scheduler. If not set, the runtime must use the value 0.
 * **`selinuxLabel`** (string, OPTIONAL) specifies the SELinux label for the process.
     For more information about SELinux, see  [SELinux documentation][selinux].
 

schema/config-schema.json

@@ -147,6 +147,32 @@
                 "noNewPrivileges": {
                     "type": "boolean"
                 },
+                "scheduler": {
+                    "type": "object",
+                    "properties": {
+                        "policy": {
+                            "type": "string"
+                        },
+                        "nice": {
+                            "$ref": "defs.json#/definitions/int32"
+                        },
+                        "priority": {
+                            "$ref": "defs.json#/definitions/int32"
+                        },
+                        "flags": {
+                            "$ref": "defs.json#/definitions/ArrayOfStrings"
+                        },
+                        "runtime": {
+                            "$ref": "defs.json#/definitions/uint64"
+                        },
+                        "deadline": {
+                            "$ref": "defs.json#/definitions/uint64"
+                        },
+                        "period": {
+                            "$ref": "defs.json#/definitions/uint64"
+                        }
+                    }
+                },
                 "rlimits": {
                     "type": "array",
                     "items": {

specs-go/config.go

@@ -33,6 +33,34 @@ type Spec struct {
 	ZOS *ZOS `json:"zos,omitempty" platform:"zos"`
 }
 
+// Scheduler represents the scheduling attributes for a process. It is based on
+// the Linux sched_setattr(2) syscall.
+type Scheduler struct {
+	// Policy represents the scheduling policy (e.g., SCHED_FIFO, SCHED_RR, SCHED_OTHER).
+	Policy LinuxSchedulerPolicy `json:"policy"`
+
+	// Nice is the nice value for the process, which affects its priority.
+	Nice int32 `json:"nice"`
+
+	// Priority represents the static priority of the process.
+	Priority int32 `json:"priority"`
+
+	// Flags is an array of scheduling flags.
+	Flags []LinuxSchedulerFlag `json:"flags"`
+
+	// The following ones are used by the DEADLINE scheduler.
+
+	// Runtime is the amount of time in nanoseconds during which the process
+	// is allowed to run in a given period.
+	Runtime uint64 `json:"runtime"`
+
+	// Deadline is the absolute deadline for the process to complete its execution.
+	Deadline uint64 `json:"deadline"`
+
+	// Period is the length of the period in nanoseconds used for determining the process runtime.
+	Period uint64 `json:"period"`
+}
+
 // Process contains information to start a specific application inside the container.
 type Process struct {
 	// Terminal creates an interactive terminal for the container.
@@ -60,6 +88,8 @@ type Process struct {
 	ApparmorProfile string `json:"apparmorProfile,omitempty" platform:"linux"`
 	// Specify an oom_score_adj for the container.
 	OOMScoreAdj *int `json:"oomScoreAdj,omitempty" platform:"linux"`
+	// Scheduler specifies the scheduling attributes for a process
+	Scheduler *Scheduler `json:"scheduler,omitempty" platform:"linux"`
 	// SelinuxLabel specifies the selinux context that the container process is run as.
 	SelinuxLabel string `json:"selinuxLabel,omitempty" platform:"linux"`
 }
@@ -788,3 +818,43 @@ type ZOSDevice struct {
 	// Gid of the device.
 	GID *uint32 `json:"gid,omitempty"`
 }
+
+// LinuxSchedulerPolicy represents different scheduling policies used with the Linux Scheduler
+type LinuxSchedulerPolicy string
+
+const (
+	// SCHED_OTHER is the default scheduling policy
+	SCHED_OTHER LinuxSchedulerPolicy = "SCHED_OTHER"
+	// SCHED_FIFO is the First-In-First-Out scheduling policy
+	SCHED_FIFO LinuxSchedulerPolicy = "SCHED_FIFO"
+	// SCHED_RR is the Round-Robin scheduling policy
+	SCHED_RR LinuxSchedulerPolicy = "SCHED_RR"
+	// SCHED_BATCH is the Batch scheduling policy
+	SCHED_BATCH LinuxSchedulerPolicy = "SCHED_BATCH"
+	// SCHED_ISO is the Isolation scheduling policy
+	SCHED_ISO LinuxSchedulerPolicy = "SCHED_ISO"
+	// SCHED_IDLE is the Idle scheduling policy
+	SCHED_IDLE LinuxSchedulerPolicy = "SCHED_IDLE"
+	// SCHED_DEADLINE is the Deadline scheduling policy
+	SCHED_DEADLINE LinuxSchedulerPolicy = "SCHED_DEADLINE"
+)
+
+// LinuxSchedulerFlag represents the flags used by the Linux Scheduler.
+type LinuxSchedulerFlag string
+
+const (
+	// SCHED_FLAG_RESET_ON_FORK represents the reset on fork scheduling flag
+	SCHED_FLAG_RESET_ON_FORK LinuxSchedulerFlag = "SCHED_FLAG_RESET_ON_FORK"
+	// SCHED_FLAG_RECLAIM represents the reclaim scheduling flag
+	SCHED_FLAG_RECLAIM LinuxSchedulerFlag = "SCHED_FLAG_RECLAIM"
+	// SCHED_FLAG_DL_OVERRUN represents the deadline overrun scheduling flag
+	SCHED_FLAG_DL_OVERRUN LinuxSchedulerFlag = "SCHED_FLAG_DL_OVERRUN"
+	// SCHED_FLAG_KEEP_POLICY represents the keep policy scheduling flag
+	SCHED_FLAG_KEEP_POLICY LinuxSchedulerFlag = "SCHED_FLAG_KEEP_POLICY"
+	// SCHED_FLAG_KEEP_PARAMS represents the keep parameters scheduling flag
+	SCHED_FLAG_KEEP_PARAMS LinuxSchedulerFlag = "SCHED_FLAG_KEEP_PARAMS"
+	// SCHED_FLAG_UTIL_CLAMP_MIN represents the utilization clamp minimum scheduling flag
+	SCHED_FLAG_UTIL_CLAMP_MIN LinuxSchedulerFlag = "SCHED_FLAG_UTIL_CLAMP_MIN"
+	// SCHED_FLAG_UTIL_CLAMP_MAX represents the utilization clamp maximum scheduling flag
+	SCHED_FLAG_UTIL_CLAMP_MAX LinuxSchedulerFlag = "SCHED_FLAG_UTIL_CLAMP_MAX"
+)