mm: balance_dirty_pages() vs throttle_vm_writeout() deadlock

However unstable pages don't go away automagickally, they need a push. While balance_dirty_pages() does this push, throttle_vm_writeout() doesn't. So we can sit here ad infintum.

Hence I propose to remove the NR_UNSTABLE_NFS count from throttle_vm_writeout().

If we have a lot of dirty memory and hit the throttle in balance_dirty_pages() we (potentially) generate a lot of writeback and unstable pages, if however during this writeback we need to reclaim a bit, we might hit throttle_vm_writeout(), which might delay us until the combined total of NR_UNSTABLE_NFS + NR_WRITEBACK falls below the dirty limit.

However unstable pages don't go away automagickally, they need a push. While balance_dirty_pages() does this push, throttle_vm_writeout() doesn't. So we can sit here ad infintum.

Hence I propose to remove the NR_UNSTABLE_NFS count from throttle_vm_writeout().

Signed-off-by Peter Zijlstra <[email protected]>

---
 mm/page-writeback.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

Index: linux-2.6-git/mm/page-writeback.c
===================================================================

Quoted 26 lines · On Tue, 20 Feb 2007 16:49:24 +0100 Peter Zijlstra <[email protected]>…

If we have a lot of dirty memory and hit the throttle in balance_dirty_pages() we (potentially) generate a lot of writeback and unstable pages, if however during this writeback we need to reclaim a bit, we might hit throttle_vm_writeout(), which might delay us until the combined total of NR_UNSTABLE_NFS + NR_WRITEBACK falls below the dirty limit.

However unstable pages don't go away automagickally, they need a push. While balance_dirty_pages() does this push, throttle_vm_writeout() doesn't. So we can sit here ad infintum.

Hence I propose to remove the NR_UNSTABLE_NFS count from throttle_vm_writeout().

Signed-off-by Peter Zijlstra <[email protected]>

---
 mm/page-writeback.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

Index: linux-2.6-git/mm/page-writeback.c
===================================================================

mm/page-writeback.c +0 -0

@@ -310,8 +310,7 @@ void throttle_vm_writeout(void)
                  */
                 dirty_thresh += dirty_thresh / 10;      /* wheeee... */
 

mm/page-writeback.c void throttle_vm_writeout(void) · line 316

Quoted 6 lines

mm/page-writeback.c +1 -2

-                if (global_page_state(NR_UNSTABLE_NFS) +
-			global_page_state(NR_WRITEBACK) <= dirty_thresh)
+                if (global_page_state(NR_WRITEBACK) <= dirty_thresh)
                         	break;
                 congestion_wait(WRITE, HZ/10);
         }

I think we need the below. It is to address a deadlock which usb-storage triggered doing a GFP_NOIO allocation, but I suspect it'll fix NFS too?

From: Andrew Morton <[email protected]>

throttle_vm_writeout() is designed to wait for the dirty levels to subside. But if the caller holds IO or FS locks, we might be holding up that writeout.

So change it to take a single nap to give other devices a chance to clean some memory, then return.

Cc Nick Piggin <[email protected]>

Cc OGAWA Hirofumi <[email protected]>

Cc Kumar Gala <[email protected]>

Cc Pete Zaitcev <[email protected]>

Signed-off-by Andrew Morton <[email protected]>

---

 include/linux/writeback.h |    2 +-
 mm/page-writeback.c       |   13 +++++++++++--
 mm/vmscan.c               |    2 +-
 3 files changed, 13 insertions(+), 4 deletions(-)

diff -puN mm/vmscan.c~throttle_vm_writeout-dont-loop-on-gfp_nofs-and-gfp_noio-allocations mm/vmscan.c

mm/vmscan.c renamed from mm/vmscan.c~throttle_vm_writeout-dont-loop-on-gfp_nofs-and-gfp_noio-allocations +1 -1

@@ -952,7 +952,7 @@ static unsigned long shrink_zone(int pri
 		}
 	}
 
-	throttle_vm_writeout();
+	throttle_vm_writeout(sc->gfp_mask);
 
 	atomic_dec(&zone->reclaim_in_progress);
 	return nr_reclaimed;

diff -puN mm/page-writeback.c~throttle_vm_writeout-dont-loop-on-gfp_nofs-and-gfp_noio-allocations mm/page-writeback.c

mm/page-writeback.c renamed from mm/page-writeback.c~throttle_vm_writeout-dont-loop-on-gfp_nofs-and-gfp_noio-allocations +11 -2

@@ -296,11 +296,21 @@ void balance_dirty_pages_ratelimited_nr(
 }
 EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
 
-void throttle_vm_writeout(void)
+void throttle_vm_writeout(gfp_t gfp_mask)
 {
 	long background_thresh;
 	long dirty_thresh;
 
+	if ((gfp_mask & (__GFP_FS|__GFP_IO)) != ) {
+		/*
+		 * The caller might hold locks which can prevent IO completion
+		 * or progress in the filesystem.  So we cannot just sit here
+		 * waiting for IO to complete.
+		 */
+		congestion_wait(WRITE, HZ/10);
+		return;
+	}
+
         for ( ; ; ) {
 		get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
 

@@ -317,7 +327,6 @@ void throttle_vm_writeout(void)
         }
 }
 
-
 /*
  * writeback at least _min_pages, and keep writing until the amount of dirty
  * memory is less than the background threshold, or until we're all clean.

diff -puN include/linux/writeback.h~throttle_vm_writeout-dont-loop-on-gfp_nofs-and-gfp_noio-allocations include/linux/writeback.h

include/linux/writeback.h renamed from include/linux/writeback.h~throttle_vm_writeout-dont-loop-on-gfp_nofs-and-gfp_noio-allocations +1 -1

@@ -84,7 +84,7 @@ static inline void wait_on_inode(struct 
 int wakeup_pdflush(long nr_pages);
 void laptop_io_completion(void);
 void laptop_sync_completion(void);
-void throttle_vm_writeout(void);
+void throttle_vm_writeout(gfp_t gfp_mask);
 
 /* These are exported to sysctl. */
 extern int dirty_background_ratio;

_

It might, but I'm afraid that the NFS writeout path includes a GFP_ATOMIC allocation, in which case this would not suffice.