getrusage: fill ru_maxrss value

Make ->ru_maxrss value in struct rusage filled accordingly to rss hiwater
mark.  This struct is filled as a parameter to getrusage syscall.
->ru_maxrss value is set to KBs which is the way it is done in BSD
systems.  /usr/bin/time (gnu time) application converts ->ru_maxrss to KBs
which seems to be incorrect behavior.  Maintainer of this util was
notified by me with the patch which corrects it and cc'ed.

To make this happen we extend struct signal_struct by two fields.  The
first one is ->maxrss which we use to store rss hiwater of the task.  The
second one is ->cmaxrss which we use to store highest rss hiwater of all
task childs.  These values are used in k_getrusage() to actually fill
->ru_maxrss.  k_getrusage() uses current rss hiwater value directly if mm
struct exists.

Note:
exec() clear mm->hiwater_rss, but doesn't clear sig->maxrss.
it is intetionally behavior. *BSD getrusage have exec() inheriting.

test programs
========================================================

getrusage.c
===========
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <unistd.h>
 #include <signal.h>
 #include <sys/mman.h>

 #include "common.h"

 #define err(str) perror(str), exit(1)

int main(int argc, char** argv)
{
	int status;

	printf("allocate 100MB\n");
	consume(100);

	printf("testcase1: fork inherit? \n");
	printf("  expect: initial.self ~= child.self\n");
	show_rusage("initial");
	if (__fork()) {
		wait(&status);
	} else {
		show_rusage("fork child");
		_exit(0);
	}
	printf("\n");

	printf("testcase2: fork inherit? (cont.) \n");
	printf("  expect: initial.children ~= 100MB, but child.children = 0\n");
	show_rusage("initial");
	if (__fork()) {
		wait(&status);
	} else {
		show_rusage("child");
		_exit(0);
	}
	printf("\n");

	printf("testcase3: fork + malloc \n");
	printf("  expect: child.self ~= initial.self + 50MB\n");
	show_rusage("initial");
	if (__fork()) {
		wait(&status);
	} else {
		printf("allocate +50MB\n");
		consume(50);
		show_rusage("fork child");
		_exit(0);
	}
	printf("\n");

	printf("testcase4: grandchild maxrss\n");
	printf("  expect: post_wait.children ~= 300MB\n");
	show_rusage("initial");
	if (__fork()) {
		wait(&status);
		show_rusage("post_wait");
	} else {
		system("./child -n 0 -g 300");
		_exit(0);
	}
	printf("\n");

	printf("testcase5: zombie\n");
	printf("  expect: pre_wait ~= initial, IOW the zombie process is not accounted.\n");
	printf("          post_wait ~= 400MB, IOW wait() collect child's max_rss. \n");
	show_rusage("initial");
	if (__fork()) {
		sleep(1); /* children become zombie */
		show_rusage("pre_wait");
		wait(&status);
		show_rusage("post_wait");
	} else {
		system("./child -n 400");
		_exit(0);
	}
	printf("\n");

	printf("testcase6: SIG_IGN\n");
	printf("  expect: initial ~= after_zombie (child's 500MB alloc should be ignored).\n");
	show_rusage("initial");
	signal(SIGCHLD, SIG_IGN);
	if (__fork()) {
		sleep(1); /* children become zombie */
		show_rusage("after_zombie");
	} else {
		system("./child -n 500");
		_exit(0);
	}
	printf("\n");
	signal(SIGCHLD, SIG_DFL);

	printf("testcase7: exec (without fork) \n");
	printf("  expect: initial ~= exec \n");
	show_rusage("initial");
	execl("./child", "child", "-v", NULL);

	return 0;
}

child.c
=======
 #include <sys/types.h>
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
 #include <sys/time.h>
 #include <sys/resource.h>

 #include "common.h"

int main(int argc, char** argv)
{
	int status;
	int c;
	long consume_size = 0;
	long grandchild_consume_size = 0;
	int show = 0;

	while ((c = getopt(argc, argv, "n:g:v")) != -1) {
		switch (c) {
		case 'n':
			consume_size = atol(optarg);
			break;
		case 'v':
			show = 1;
			break;
		case 'g':

			grandchild_consume_size = atol(optarg);
			break;
		default:
			break;
		}
	}

	if (show)
		show_rusage("exec");

	if (consume_size) {
		printf("child alloc %ldMB\n", consume_size);
		consume(consume_size);
	}

	if (grandchild_consume_size) {
		if (fork()) {
			wait(&status);
		} else {
			printf("grandchild alloc %ldMB\n", grandchild_consume_size);
			consume(grandchild_consume_size);

			exit(0);
		}
	}

	return 0;
}

common.c
========
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <unistd.h>
 #include <signal.h>
 #include <sys/mman.h>

 #include "common.h"
 #define err(str) perror(str), exit(1)

void show_rusage(char *prefix)
{
    	int err, err2;
    	struct rusage rusage_self;
    	struct rusage rusage_children;

    	printf("%s: ", prefix);
    	err = getrusage(RUSAGE_SELF, &rusage_self);
    	if (!err)
    		printf("self %ld ", rusage_self.ru_maxrss);
    	err2 = getrusage(RUSAGE_CHILDREN, &rusage_children);
    	if (!err2)
    		printf("children %ld ", rusage_children.ru_maxrss);

    	printf("\n");
}

/* Some buggy OS need this worthless CPU waste. */
void make_pagefault(void)
{
	void *addr;
	int size = getpagesize();
	int i;

	for (i=0; i<1000; i++) {
		addr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
		if (addr == MAP_FAILED)
			err("make_pagefault");
		memset(addr, 0, size);
		munmap(addr, size);
	}
}

void consume(int mega)
{
    	size_t sz = mega * 1024 * 1024;
    	void *ptr;

    	ptr = malloc(sz);
    	memset(ptr, 0, sz);
	make_pagefault();
}

pid_t __fork(void)
{
	pid_t pid;

	pid = fork();
	make_pagefault();

	return pid;
}

common.h
========
void show_rusage(char *prefix);
void make_pagefault(void);
void consume(int mega);
pid_t __fork(void);

FreeBSD result (expected result)
========================================================
allocate 100MB
testcase1: fork inherit?
  expect: initial.self ~= child.self
initial: self 103492 children 0
fork child: self 103540 children 0

testcase2: fork inherit? (cont.)
  expect: initial.children ~= 100MB, but child.children = 0
initial: self 103540 children 103540
child: self 103564 children 0

testcase3: fork + malloc
  expect: child.self ~= initial.self + 50MB
initial: self 103564 children 103564
allocate +50MB
fork child: self 154860 children 0

testcase4: grandchild maxrss
  expect: post_wait.children ~= 300MB
initial: self 103564 children 154860
grandchild alloc 300MB
post_wait: self 103564 children 308720

testcase5: zombie
  expect: pre_wait ~= initial, IOW the zombie process is not accounted.
          post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 103564 children 308720
child alloc 400MB
pre_wait: self 103564 children 308720
post_wait: self 103564 children 411312

testcase6: SIG_IGN
  expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 103564 children 411312
child alloc 500MB
after_zombie: self 103624 children 411312

testcase7: exec (without fork)
  expect: initial ~= exec
initial: self 103624 children 411312
exec: self 103624 children 411312

Linux result (actual test result)
========================================================
allocate 100MB
testcase1: fork inherit?
  expect: initial.self ~= child.self
initial: self 102848 children 0
fork child: self 102572 children 0

testcase2: fork inherit? (cont.)
  expect: initial.children ~= 100MB, but child.children = 0
initial: self 102876 children 102644
child: self 102572 children 0

testcase3: fork + malloc
  expect: child.self ~= initial.self + 50MB
initial: self 102876 children 102644
allocate +50MB
fork child: self 153804 children 0

testcase4: grandchild maxrss
  expect: post_wait.children ~= 300MB
initial: self 102876 children 153864
grandchild alloc 300MB
post_wait: self 102876 children 307536

testcase5: zombie
  expect: pre_wait ~= initial, IOW the zombie process is not accounted.
          post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 102876 children 307536
child alloc 400MB
pre_wait: self 102876 children 307536
post_wait: self 102876 children 410076

testcase6: SIG_IGN
  expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 102876 children 410076
child alloc 500MB
after_zombie: self 102880 children 410076

testcase7: exec (without fork)
  expect: initial ~= exec
initial: self 102880 children 410076
exec: self 102880 children 410076

Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 6 insertions, 0 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 61bb1761c7b8..60d6fdcc9265 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -947,6 +947,8 @@ NORET_TYPE void do_exit(long code)
 	if (group_dead) {
 		hrtimer_cancel(&tsk->signal->real_timer);
 		exit_itimers(tsk->signal);
+		if (tsk->mm)
+			setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
 	}
 	acct_collect(code, group_dead);
 	if (group_dead)
@@ -1210,6 +1212,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	if (likely(!traced) && likely(!task_detached(p))) {
 		struct signal_struct *psig;
 		struct signal_struct *sig;
+		unsigned long maxrss;
 
 		/*
 		 * The resource counters for the group leader are in its
@@ -1258,6 +1261,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		psig->coublock +=
 			task_io_get_oublock(p) +
 			sig->oublock + sig->coublock;
+		maxrss = max(sig->maxrss, sig->cmaxrss);
+		if (psig->cmaxrss < maxrss)
+			psig->cmaxrss = maxrss;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
 		spin_unlock_irq(&p->real_parent->sighand->siglock);