On Wed, 21 Feb 2007 16:22:17 -0500 (EST)
Alan Stern <[EMAIL PROTECTED]> wrote:
> On Wed, 21 Feb 2007, Andrew Morton wrote:
>
> > > > It seems like usb-storage and aio are completely off in the weeds.
> > > > Ideas?
> > >
> > > It seems usb-storage should remove some kmalloc and use mempool() for
> > > urb... Is someone working on this? And idea?
> >
> > I think Pete said that we're supposed to be using GFP_NOIO in there.
>
> We _are_ using it.
How admirably prompt.
> > Not that it'll help much: the VM calls throttle_vm_writeout() for GFP_NOIO
> > and GFP_NOFS allocations, which is a bug. Because if the caller holds
> > locks which prevent filesystem or IO progress, we deadlock.
> >
> > I'll fix the VM if someone else fixes USB ;)
>
> What else needs to be fixed?
Would be nice if someone can confirm that this fixes it:
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
---
a/mm/vmscan.c~throttle_vm_writeout-dont-loop-on-gfp_nofs-and-gfp_noio-allocations
+++ a/mm/vmscan.c
@@ -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
---
a/mm/page-writeback.c~throttle_vm_writeout-dont-loop-on-gfp_nofs-and-gfp_noio-allocations
+++ a/mm/page-writeback.c
@@ -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)) != (__GFP_FS|__GFP_IO)) {
+ /*
+ * The caller might hold locks which can prevert 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
---
a/include/linux/writeback.h~throttle_vm_writeout-dont-loop-on-gfp_nofs-and-gfp_noio-allocations
+++ a/include/linux/writeback.h
@@ -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;
_
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
