On some large machines with a high number of CPUs running a 64K kernel,
we found that the 'RES' field is always 0 displayed by the top command
for some processes, which will cause a lot of confusion for users.
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
875525 root 20 0 12480 0 0 R 0.3 0.0 0:00.08 top
1 root 20 0 172800 0 0 S 0.0 0.0 0:04.52 systemd
The main reason is that the batch size of the percpu counter is quite large
on these machines, caching a significant percpu value, since converting mm's
rss stats into percpu_counter by commit f1a7941243c1 ("mm: convert mm's rss
stats into percpu_counter"). Intuitively, the batch number should be optimized,
but on some paths, performance may take precedence over statistical accuracy.
Therefore, introducing a new interface to add the percpu statistical count
and display it to users, which can remove the confusion. In addition, this
change is not expected to be on a performance-critical path, so the modification
should be acceptable.
Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
---
fs/proc/task_mmu.c | 14 +++++++-------
include/linux/mm.h | 5 +++++
2 files changed, 12 insertions(+), 7 deletions(-)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index b9e4fbbdf6e6..f629e6526935 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -36,9 +36,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
unsigned long text, lib, swap, anon, file, shmem;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
- anon = get_mm_counter(mm, MM_ANONPAGES);
- file = get_mm_counter(mm, MM_FILEPAGES);
- shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+ anon = get_mm_counter_sum(mm, MM_ANONPAGES);
+ file = get_mm_counter_sum(mm, MM_FILEPAGES);
+ shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES);
/*
* Note: to minimize their overhead, mm maintains hiwater_vm and
@@ -59,7 +59,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
text = min(text, mm->exec_vm << PAGE_SHIFT);
lib = (mm->exec_vm << PAGE_SHIFT) - text;
- swap = get_mm_counter(mm, MM_SWAPENTS);
+ swap = get_mm_counter_sum(mm, MM_SWAPENTS);
SEQ_PUT_DEC("VmPeak:\t", hiwater_vm);
SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm);
SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm);
@@ -92,12 +92,12 @@ unsigned long task_statm(struct mm_struct *mm,
unsigned long *shared, unsigned long *text,
unsigned long *data, unsigned long *resident)
{
- *shared = get_mm_counter(mm, MM_FILEPAGES) +
- get_mm_counter(mm, MM_SHMEMPAGES);
+ *shared = get_mm_counter_sum(mm, MM_FILEPAGES) +
+ get_mm_counter_sum(mm, MM_SHMEMPAGES);
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
*data = mm->data_vm + mm->stack_vm;
- *resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
+ *resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES);
return mm->total_vm;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 185424858f23..15ec5cfe9515 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2568,6 +2568,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
return percpu_counter_read_positive(&mm->rss_stat[member]);
}
+static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member)
+{
+ return percpu_counter_sum_positive(&mm->rss_stat[member]);
+}
+
void mm_trace_rss_stat(struct mm_struct *mm, int member);
static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
--
2.43.5
