Provide /proc/sys/vm/stat_refresh to force an immediate update of per-cpu into global vmstats: useful to avoid a sleep(2) or whatever before checking counts when testing. Originally added to work around a bug which left counts stranded indefinitely on a cpu going idle (an inaccuracy magnified when small below-batch numbers represent "huge" amounts of memory), but I believe that bug is now fixed: nonetheless, this is still a useful knob. Its schedule_on_each_cpu() is probably too expensive just to fold into reading /proc/meminfo itself: give this mode 0600 to prevent abuse. Allow a write or a read to do the same: nothing to read, but "grep -h Shmem /proc/sys/vm/stat_refresh /proc/meminfo" is convenient. Oh, and since global_page_state() itself is careful to disguise any underflow as 0, hack in an "Invalid argument" and pr_warn() if a counter is negative after the refresh - this helped to fix a misaccounting of NR_ISOLATED_FILE in my migration code. But on recent kernels, I find that NR_ALLOC_BATCH and NR_PAGES_SCANNED often go negative some of the time. I have not yet worked out why, but have no evidence that it's actually harmful. Punt for the moment by just ignoring the anomaly on those.
Unified · Split
| @@ -57,6 +57,7 @@ Currently, these files are in /proc/sys/vm: · 56 unmodified lines | |||
| 57 | - panic_on_oom | 57 | - panic_on_oom |
| 58 | - percpu_pagelist_fraction | 58 | - percpu_pagelist_fraction |
| 59 | - stat_interval | 59 | - stat_interval |
| 60 | - stat_refresh | ||
| 60 | - swappiness | 61 | - swappiness |
| 61 | - user_reserve_kbytes | 62 | - user_reserve_kbytes |
| 62 | - vfs_cache_pressure | 63 | - vfs_cache_pressure |
| @@ -755,6 +756,19 @@ is 1 second. · 692 unmodified lines | |||
| 755 | 756 | ||
| 756 | ============================================================== | 757 | ============================================================== |
| 757 | 758 | ||
| 759 | stat_refresh | ||
| 760 | |||
| 761 | Any read or write (by root only) flushes all the per-cpu vm statistics | ||
| 762 | into their global totals, for more accurate reports when testing | ||
| 763 | e.g. cat /proc/sys/vm/stat_refresh /proc/meminfo | ||
| 764 | |||
| 765 | As a side-effect, it also checks for negative totals (elsewhere reported | ||
| 766 | as 0) and "fails" with EINVAL if any are found, with a warning in dmesg. | ||
| 767 | (At time of writing, a few stats are known sometimes to be found negative, | ||
| 768 | with no ill effects: errors and warnings on these stats are suppressed.) | ||
| 769 | |||
| 770 | ============================================================== | ||
| 771 | |||
| 758 | swappiness | 772 | swappiness |
| 759 | 773 | ||
| 760 | This control is used to define how aggressive the kernel will swap | 774 | This control is used to define how aggressive the kernel will swap |
| @@ -193,6 +193,10 @@ void quiet_vmstat(void); · 192 unmodified lines | |||
| 193 | void cpu_vm_stats_fold(int cpu); | 193 | void cpu_vm_stats_fold(int cpu); |
| 194 | void refresh_zone_stat_thresholds(void); | 194 | void refresh_zone_stat_thresholds(void); |
| 195 | 195 | ||
| 196 | struct ctl_table; | ||
| 197 | int vmstat_refresh(struct ctl_table *, int write, | ||
| 198 | void __user *buffer, size_t *lenp, loff_t *ppos); | ||
| 199 | |||
| 196 | void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); | 200 | void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); |
| 197 | 201 | ||
| 198 | int calculate_pressure_threshold(struct zone *zone); | 202 | int calculate_pressure_threshold(struct zone *zone); |
| @@ -1521,6 +1521,13 @@ static struct ctl_table vm_table[] = { · 1520 unmodified lines | |||
| 1521 | .mode = 0644, | 1521 | .mode = 0644, |
| 1522 | .proc_handler = proc_dointvec_jiffies, | 1522 | .proc_handler = proc_dointvec_jiffies, |
| 1523 | }, | 1523 | }, |
| 1524 | { | ||
| 1525 | .procname = "stat_refresh", | ||
| 1526 | .data = NULL, | ||
| 1527 | .maxlen = 0, | ||
| 1528 | .mode = 0600, | ||
| 1529 | .proc_handler = vmstat_refresh, | ||
| 1530 | }, | ||
| 1524 | #endif | 1531 | #endif |
| 1525 | #ifdef CONFIG_MMU | 1532 | #ifdef CONFIG_MMU |
| 1526 | { | 1533 | { |
| @@ -1379,6 +1379,66 @@ static DEFINE_PER_CPU(struct delayed_work, vmstat_work); · 1378 unmodified lines | |||
| 1379 | int sysctl_stat_interval __read_mostly = HZ; | 1379 | int sysctl_stat_interval __read_mostly = HZ; |
| 1380 | static cpumask_var_t cpu_stat_off; | 1380 | static cpumask_var_t cpu_stat_off; |
| 1381 | 1381 | ||
| 1382 | #ifdef CONFIG_PROC_FS | ||
| 1383 | static void refresh_vm_stats(struct work_struct *work) | ||
| 1384 | { | ||
| 1385 | refresh_cpu_vm_stats(true); | ||
| 1386 | } | ||
| 1387 | |||
| 1388 | int vmstat_refresh(struct ctl_table *table, int write, | ||
| 1389 | void __user *buffer, size_t *lenp, loff_t *ppos) | ||
| 1390 | { | ||
| 1391 | long val; | ||
| 1392 | int err; | ||
| 1393 | int i; | ||
| 1394 | |||
| 1395 | /* | ||
| 1396 | * The regular update, every sysctl_stat_interval, may come later | ||
| 1397 | * than expected: leaving a significant amount in per_cpu buckets. | ||
| 1398 | * This is particularly misleading when checking a quantity of HUGE | ||
| 1399 | * pages, immediately after running a test. /proc/sys/vm/stat_refresh, | ||
| 1400 | * which can equally be echo'ed to or cat'ted from (by root), | ||
| 1401 | * can be used to update the stats just before reading them. | ||
| 1402 | * | ||
| 1403 | * Oh, and since global_page_state() etc. are so careful to hide | ||
| 1404 | * transiently negative values, report an error here if any of | ||
| 1405 | * the stats is negative, so we know to go looking for imbalance. | ||
| 1406 | */ | ||
| 1407 | err = schedule_on_each_cpu(refresh_vm_stats); | ||
| 1408 | if (err) | ||
| 1409 | return err; | ||
| 1410 | for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { | ||
| 1411 | val = atomic_long_read(&vm_stat[i]); | ||
| 1412 | if (val < 0) { | ||
| 1413 | switch (i) { | ||
| 1414 | case NR_ALLOC_BATCH: | ||
| 1415 | case NR_PAGES_SCANNED: | ||
| 1416 | /* | ||
| 1417 | * These are often seen to go negative in | ||
| 1418 | * recent kernels, but not to go permanently | ||
| 1419 | * negative. Whilst it would be nicer not to | ||
| 1420 | * have exceptions, rooting them out would be | ||
| 1421 | * another task, of rather low priority. | ||
| 1422 | */ | ||
| 1423 | break; | ||
| 1424 | default: | ||
| 1425 | pr_warn("%s: %s %ld\n", | ||
| 1426 | __func__, vmstat_text[i], val); | ||
| 1427 | err = -EINVAL; | ||
| 1428 | break; | ||
| 1429 | } | ||
| 1430 | } | ||
| 1431 | } | ||
| 1432 | if (err) | ||
| 1433 | return err; | ||
| 1434 | if (write) | ||
| 1435 | *ppos += *lenp; | ||
| 1436 | else | ||
| 1437 | *lenp = 0; | ||
| 1438 | return 0; | ||
| 1439 | } | ||
| 1440 | #endif /* CONFIG_PROC_FS */ | ||
| 1441 | |||
| 1382 | static void vmstat_update(struct work_struct *w) | 1442 | static void vmstat_update(struct work_struct *w) |
| 1383 | { | 1443 | { |
| 1384 | if (refresh_cpu_vm_stats(true)) { | 1444 | if (refresh_cpu_vm_stats(true)) { |