Date: Thu, 12 Nov 2015 14:18:25 +0200 From: Konstantin Belousov <kostikbel@gmail.com> To: Michael Tuexen <tuexen@freebsd.org> Cc: freebsd-arm <freebsd-arm@freebsd.org> Subject: Re: Memory management issue on RPi? Message-ID: <20151112121825.GJ2257@kib.kiev.ua> In-Reply-To: <CB20D8FA-303C-4AA2-B2A6-1FF25DDB8A94@freebsd.org> References: <CB20D8FA-303C-4AA2-B2A6-1FF25DDB8A94@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Nov 12, 2015 at 11:28:07AM +0100, Michael Tuexen wrote:
> Dear all,
>
> I'm experiencing a behaviour I don't expect.
> When running FreeBSD head on a RPI B+ without swap space
> it shows the following behaviour on the console:
>
> [bsd10:~] tuexen% dd if=/dev/zero of=large_file bs=1m count=1024
> Nov 12 11:22:16 bsd10 kernel: pid 666 (sshd), uid 1002, was killed: out of swap space
> Nov 12 11:22:19 bsd10 kernel: pid 606 (thttpd), uid 65534, was killed: out of swap space
> Nov 12 11:22:24 bsd10 kernel: pid 316 (devd), uid 0, was killed: out of swap space
> Killed
> [bsd10:~] tuexen% Nov 12 11:22:27 bsd10 kernel: pid 676 (dd), uid 1002, was killed: out of swap space
> [bsd10:~] tuexen% uname -a
> FreeBSD bsd10.fh-muenster.de 11.0-CURRENT FreeBSD 11.0-CURRENT #10 r290676: Wed Nov 11 20:23:53 CET 2015 tuexen@bsd10.fh-muenster.de:/home/tuexen/head/sys/arm/compile/RPI-B arm
> [bsd10:~] tuexen% ls -l large_file
> -rw-r--r-- 1 tuexen tuexen 584056832 Nov 12 11:22 large_file
>
> Shouldn't I be able to use dd to generate an almost arbitrary large file (limited
> by the filesystem, not by the memory)?
This is a known problem with the swap-less OOM. The following patch
should give you an immediate relief. You might want to tweak
sysctl vm.pageout_oom_seq if default value is not right, it was selected
by 'try and see' approach on very small (32 or 64MB) i386 VM.
diff --git a/sys/vm/vm_page.h b/sys/vm/vm_page.h
index a87f682..1fa61eb 100644
--- a/sys/vm/vm_page.h
+++ b/sys/vm/vm_page.h
@@ -227,6 +227,7 @@ struct vm_domain {
long vmd_segs; /* bitmask of the segments */
boolean_t vmd_oom;
int vmd_pass; /* local pagedaemon pass */
+ int vmd_oom_seq;
int vmd_last_active_scan;
struct vm_page vmd_marker; /* marker for pagedaemon private use */
struct vm_page vmd_inacthead; /* marker for LRU-defeating insertions */
diff --git a/sys/vm/vm_pageout.c b/sys/vm/vm_pageout.c
index f564fb5..b956e25 100644
--- a/sys/vm/vm_pageout.c
+++ b/sys/vm/vm_pageout.c
@@ -122,7 +122,8 @@ static void vm_pageout_init(void);
static int vm_pageout_clean(vm_page_t m);
static int vm_pageout_cluster(vm_page_t m);
static void vm_pageout_scan(struct vm_domain *vmd, int pass);
-static void vm_pageout_mightbe_oom(struct vm_domain *vmd, int pass);
+static void vm_pageout_mightbe_oom(struct vm_domain *vmd, int page_shortage,
+ int starting_page_shortage);
SYSINIT(pagedaemon_init, SI_SUB_KTHREAD_PAGE, SI_ORDER_FIRST, vm_pageout_init,
NULL);
@@ -158,6 +159,7 @@ SYSINIT(vmdaemon, SI_SUB_KTHREAD_VM, SI_ORDER_FIRST, kproc_start, &vm_kp);
int vm_pages_needed; /* Event on which pageout daemon sleeps */
int vm_pageout_deficit; /* Estimated number of pages deficit */
int vm_pageout_wakeup_thresh;
+static int vm_pageout_oom_seq = 24;
#if !defined(NO_SWAPPING)
static int vm_pageout_req_swapout; /* XXX */
@@ -223,6 +225,10 @@ static int pageout_lock_miss;
SYSCTL_INT(_vm, OID_AUTO, pageout_lock_miss,
CTLFLAG_RD, &pageout_lock_miss, 0, "vget() lock misses during pageout");
+SYSCTL_INT(_vm, OID_AUTO, pageout_oom_seq,
+ CTLFLAG_RW, &vm_pageout_oom_seq, 0,
+ "back-to-back calls to oom detector to start OOM");
+
#define VM_PAGEOUT_PAGE_COUNT 16
int vm_pageout_page_count = VM_PAGEOUT_PAGE_COUNT;
@@ -1041,7 +1047,8 @@ vm_pageout_scan(struct vm_domain *vmd, int pass)
vm_object_t object;
long min_scan;
int act_delta, addl_page_shortage, deficit, error, maxlaunder, maxscan;
- int page_shortage, scan_tick, scanned, vnodes_skipped;
+ int page_shortage, scan_tick, scanned, starting_page_shortage;
+ int vnodes_skipped;
boolean_t pageout_ok, queues_locked;
/*
@@ -1080,6 +1087,7 @@ vm_pageout_scan(struct vm_domain *vmd, int pass)
page_shortage = vm_paging_target() + deficit;
} else
page_shortage = deficit = 0;
+ starting_page_shortage = page_shortage;
/*
* maxlaunder limits the number of dirty pages we flush per scan.
@@ -1343,6 +1351,12 @@ relock_queues:
(void)speedup_syncer();
/*
+ * If the inactive queue scan fails repeatedly to meet its
+ * target, kill the largest process.
+ */
+ vm_pageout_mightbe_oom(vmd, page_shortage, starting_page_shortage);
+
+ /*
* Compute the number of pages we want to try to move from the
* active queue to the inactive queue.
*/
@@ -1453,15 +1467,6 @@ relock_queues:
}
}
#endif
-
- /*
- * If we are critically low on one of RAM or swap and low on
- * the other, kill the largest process. However, we avoid
- * doing this on the first pass in order to give ourselves a
- * chance to flush out dirty vnode-backed pages and to allow
- * active pages to be moved to the inactive queue and reclaimed.
- */
- vm_pageout_mightbe_oom(vmd, pass);
}
static int vm_pageout_oom_vote;
@@ -1472,12 +1477,17 @@ static int vm_pageout_oom_vote;
* failed to reach free target is premature.
*/
static void
-vm_pageout_mightbe_oom(struct vm_domain *vmd, int pass)
+vm_pageout_mightbe_oom(struct vm_domain *vmd, int page_shortage,
+ int starting_page_shortage)
{
int old_vote;
- if (pass <= 1 || !((swap_pager_avail < 64 && vm_page_count_min()) ||
- (swap_pager_full && vm_paging_target() > 0))) {
+ if (starting_page_shortage <= 0 || starting_page_shortage !=
+ page_shortage)
+ vmd->vmd_oom_seq = 0;
+ else
+ vmd->vmd_oom_seq++;
+ if (vmd->vmd_oom_seq < vm_pageout_oom_seq) {
if (vmd->vmd_oom) {
vmd->vmd_oom = FALSE;
atomic_subtract_int(&vm_pageout_oom_vote, 1);
@@ -1485,6 +1495,12 @@ vm_pageout_mightbe_oom(struct vm_domain *vmd, int pass)
return;
}
+ /*
+ * Do not follow the call sequence until OOM condition is
+ * cleared.
+ */
+ vmd->vmd_oom_seq = 0;
+
if (vmd->vmd_oom)
return;
@@ -1510,6 +1526,37 @@ vm_pageout_mightbe_oom(struct vm_domain *vmd, int pass)
atomic_subtract_int(&vm_pageout_oom_vote, 1);
}
+static long
+vm_pageout_resident_count(struct vmspace *vmspace)
+{
+ vm_map_t map;
+ vm_map_entry_t entry;
+ vm_object_t obj;
+ long res;
+
+ map = &vmspace->vm_map;
+ KASSERT(!map->system_map, ("system map"));
+ sx_assert(&map->lock, SA_LOCKED);
+ res = 0;
+ for (entry = map->header.next; entry != &map->header;
+ entry = entry->next) {
+ if ((entry->eflags & MAP_ENTRY_IS_SUB_MAP) != 0)
+ continue;
+ obj = entry->object.vm_object;
+ if (obj == NULL)
+ continue;
+ switch (obj->type) {
+ case OBJT_DEFAULT:
+ case OBJT_SWAP:
+ case OBJT_VNODE:
+ case OBJT_PHYS:
+ res += obj->resident_page_count;
+ break;
+ }
+ }
+ return (res);
+}
+
void
vm_pageout_oom(int shortage)
{
@@ -1554,7 +1601,8 @@ vm_pageout_oom(int shortage)
if (!TD_ON_RUNQ(td) &&
!TD_IS_RUNNING(td) &&
!TD_IS_SLEEPING(td) &&
- !TD_IS_SUSPENDED(td)) {
+ !TD_IS_SUSPENDED(td) &&
+ !TD_IS_SWAPPED(td)) {
thread_unlock(td);
breakout = 1;
break;
@@ -1582,12 +1630,13 @@ vm_pageout_oom(int shortage)
}
PROC_UNLOCK(p);
size = vmspace_swap_count(vm);
- vm_map_unlock_read(&vm->vm_map);
if (shortage == VM_OOM_MEM)
- size += vmspace_resident_count(vm);
+ size += vm_pageout_resident_count(vm);
+ vm_map_unlock_read(&vm->vm_map);
vmspace_free(vm);
+
/*
- * if the this process is bigger than the biggest one
+ * If this process is bigger than the biggest one,
* remember it.
*/
if (size > bigsize) {
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20151112121825.GJ2257>