[v6,2/3] vmstat: Kernel stack usage histogram

Commit Message

Pasha Tatashin July 30, 2024, 3:01 p.m. UTC

As part of the dynamic kernel stack project, we need to know the amount
of data that can be saved by reducing the default kernel stack size [1].

Provide a kernel stack usage histogram to aid in optimizing kernel stack
sizes and minimizing memory waste in large-scale environments. The
histogram divides stack usage into power-of-two buckets and reports the
results in /proc/vmstat. This information is especially valuable in
environments with millions of machines, where even small optimizations
can have a significant impact.

The histogram data is presented in /proc/vmstat with entries like
"kstack_1k", "kstack_2k", and so on, indicating the number of threads
that exited with stack usage falling within each respective bucket.

Example outputs:
Intel:
$ grep kstack /proc/vmstat
kstack_1k 3
kstack_2k 188
kstack_4k 11391
kstack_8k 243
kstack_16k 0

ARM with 64K page_size:
$ grep kstack /proc/vmstat
kstack_1k 1
kstack_2k 340
kstack_4k 25212
kstack_8k 1659
kstack_16k 0
kstack_32k 0
kstack_64k 0

Note: once the dynamic kernel stack is implemented it will depend on the
implementation the usability of this feature: On hardware that supports
faults on kernel stacks, we will have other metrics that show the total
number of pages allocated for stacks. On hardware where faults are not
supported, we will most likely have some optimization where only some
threads are extended, and for those, these metrics will still be very
useful.

[1] https://lwn.net/Articles/974367

Signed-off-by: Pasha Tatashin <[e-mail]>
Reviewed-by: Kent Overstreet <[e-mail]>
Acked-by: Shakeel Butt <[e-mail]>
---
 include/linux/vm_event_item.h | 24 ++++++++++++++++++++++
 kernel/exit.c                 | 38 +++++++++++++++++++++++++++++++++++
 mm/vmstat.c                   | 24 ++++++++++++++++++++++
 3 files changed, 86 insertions(+)

Patch

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 747943bc8cc2..37ad1c16367a 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -154,6 +154,30 @@  enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		VMA_LOCK_RETRY,
 		VMA_LOCK_MISS,
 #endif
+#ifdef CONFIG_DEBUG_STACK_USAGE
+		KSTACK_1K,
+#if THREAD_SIZE > 1024
+		KSTACK_2K,
+#endif
+#if THREAD_SIZE > 2048
+		KSTACK_4K,
+#endif
+#if THREAD_SIZE > 4096
+		KSTACK_8K,
+#endif
+#if THREAD_SIZE > 8192
+		KSTACK_16K,
+#endif
+#if THREAD_SIZE > 16384
+		KSTACK_32K,
+#endif
+#if THREAD_SIZE > 32768
+		KSTACK_64K,
+#endif
+#if THREAD_SIZE > 65536
+		KSTACK_REST,
+#endif
+#endif /* CONFIG_DEBUG_STACK_USAGE */
 		NR_VM_EVENT_ITEMS
 };
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 7430852a8571..64bfc2bae55b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -778,6 +778,43 @@  static void exit_notify(struct task_struct *tsk, int group_dead)
 }
 
 #ifdef CONFIG_DEBUG_STACK_USAGE
+/* Count the maximum pages reached in kernel stacks */
+static inline void kstack_histogram(unsigned long used_stack)
+{
+#ifdef CONFIG_VM_EVENT_COUNTERS
+	if (used_stack <= 1024)
+		count_vm_event(KSTACK_1K);
+#if THREAD_SIZE > 1024
+	else if (used_stack <= 2048)
+		count_vm_event(KSTACK_2K);
+#endif
+#if THREAD_SIZE > 2048
+	else if (used_stack <= 4096)
+		count_vm_event(KSTACK_4K);
+#endif
+#if THREAD_SIZE > 4096
+	else if (used_stack <= 8192)
+		count_vm_event(KSTACK_8K);
+#endif
+#if THREAD_SIZE > 8192
+	else if (used_stack <= 16384)
+		count_vm_event(KSTACK_16K);
+#endif
+#if THREAD_SIZE > 16384
+	else if (used_stack <= 32768)
+		count_vm_event(KSTACK_32K);
+#endif
+#if THREAD_SIZE > 32768
+	else if (used_stack <= 65536)
+		count_vm_event(KSTACK_64K);
+#endif
+#if THREAD_SIZE > 65536
+	else
+		count_vm_event(KSTACK_REST);
+#endif
+#endif /* CONFIG_VM_EVENT_COUNTERS */
+}
+
 static void check_stack_usage(void)
 {
 	static DEFINE_SPINLOCK(low_water_lock);
@@ -785,6 +822,7 @@  static void check_stack_usage(void)
 	unsigned long free;
 
 	free = stack_not_used(current);
+	kstack_histogram(THREAD_SIZE - free);
 
 	if (free >= lowest_to_date)
 		return;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 04a1cb6cc636..c7d52a9660c3 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1417,6 +1417,30 @@  const char * const vmstat_text[] = {
 	"vma_lock_retry",
 	"vma_lock_miss",
 #endif
+#ifdef CONFIG_DEBUG_STACK_USAGE
+	"kstack_1k",
+#if THREAD_SIZE > 1024
+	"kstack_2k",
+#endif
+#if THREAD_SIZE > 2048
+	"kstack_4k",
+#endif
+#if THREAD_SIZE > 4096
+	"kstack_8k",
+#endif
+#if THREAD_SIZE > 8192
+	"kstack_16k",
+#endif
+#if THREAD_SIZE > 16384
+	"kstack_32k",
+#endif
+#if THREAD_SIZE > 32768
+	"kstack_64k",
+#endif
+#if THREAD_SIZE > 65536
+	"kstack_rest",
+#endif
+#endif
 #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */
 };
 #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */