feat(sched): 实现初步的cpu多核心上的负载均衡

[sparkzky]

初步的cpu多核心上的负载均衡

目前DragonOS启动时会有两个CPU核心，但是之前进程只会调度到第一个核心上运行，第二个核心空转，现在在调度进程之前加入核心选择，进程将调度到当前负载较低的核心上执行

核心选择策略:

优先级从高到低：
1. 负载均衡未启用 → 返回当前CPU
2. 单核系统 → 返回当前CPU
3. IDLE策略任务 → 找最空闲CPU
4. 当前CPU负载 < 原CPU负载 → 当前CPU（缓存热度）
5. 原CPU负载 ≤ 2 → 原CPU（缓存亲和性）
6. 当前CPU负载 ≤ 1 → 当前CPU
7. 默认 → 找负载最低的CPU

[Copilot]

Pull request overview

This PR implements initial multi-core CPU load balancing for the DragonOS scheduler. The feature enables tasks to be distributed across multiple CPU cores based on load conditions, with a priority-based selection strategy that balances performance (cache locality) against load distribution.

Key changes include:

• Added a new load balancer module with CPU selection logic for task wakeup
• Integrated load balancing into the scheduler tick and process wakeup paths
• Added test programs to verify load distribution across CPUs

Reviewed changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated 7 comments.

Show a summary per file

File	Description
kernel/src/sched/load_balance.rs	New module implementing CPU selection strategy and load balancing logic
kernel/src/sched/mod.rs	Integrated load balancer into scheduler tick, added nr_running_lockless() method and migration flag handling
kernel/src/process/mod.rs	Updated process wakeup to use load balancer for CPU selection with migration support
kernel/src/smp/mod.rs	Enabled load balancing after SMP initialization
kernel/src/smp/core.rs	Updated documentation comment style from @brief to ##
user/apps/c_unitest/test_smp_balance.c	Simple test program to verify multi-core load balancing
user/apps/c_unitest/test_load_balance.c	Comprehensive test suite for load balancing functionality

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Array size mismatch: cpu_usage is declared with size 2 but later code accesses indices up to 16 (lines 160-162, 166-169). This will cause buffer overflow if final_cpu >= 2. The array size should be at least 16 to match the loop bounds.

Suggested change

	int cpu_usage[2] = {0}; /* 假设最多2个CPU */
	int cpu_usage[16] = {0}; /* 支持最多16个CPU */

[Copilot]

[nitpick] Corrected spelling of '测例' (test case) to '测试用例' for consistency with standard terminology.

Suggested change

	// 这个测例会报错，先注释掉
	// 这个测试用例会报错，先注释掉

[Copilot]

[nitpick] The comment says 'execute one load balance check' but doesn't clarify what happens after the interval. Consider rephrasing to '每隔100个jiffies执行一次负载均衡检查' (execute load balance check every 100 jiffies) for clarity.

Suggested change

	/// ## 负载均衡间隔（单位：jiffies），执行一次负载均衡检查
	/// ## 负载均衡间隔（单位：jiffies），每隔100个jiffies执行一次负载均衡检查

[Copilot]

The TODO comment contains important implementation status (that migrate_tasks is empty), but uses lowercase 'todo' instead of the standard 'TODO:' format. For consistency with other TODOs in the codebase, use 'TODO:' prefix.

Suggested change

	//todo 检查并执行负载均衡（只检测不均衡，migrate_tasks 内部是空的）
	// TODO: 检查并执行负载均衡（只检测不均衡，migrate_tasks 内部是空的）

[Copilot]

[nitpick] Magic number 2 used for load threshold without explanation. Consider defining a named constant like CACHE_HOT_LOAD_THRESHOLD to make the cache affinity strategy more explicit.

[Copilot]

[nitpick] Magic number 1 used for load threshold without explanation. Consider defining a named constant like IDLE_LOAD_THRESHOLD to clarify when a CPU is considered idle enough for immediate use.

[Copilot]

[nitpick] Magic number 2 appears again for load threshold. This should use the same named constant as suggested for line 103 to maintain consistency in the load balancing strategy.