Re: [PATCH] Allow increasing the buffer-head per-CPU LRU size

[Andrew Morton <akpm@linux-foundation.org>]

On Mon, 7 Jul 2014 18:30:03 +0200 Andi Kleen <andi@firstfloor.org> wrote:

> > diff --git a/fs/Kconfig b/fs/Kconfig
> > index c229f82..c08844c 100644
> > --- a/fs/Kconfig
> > +++ b/fs/Kconfig
> > @@ -268,4 +268,13 @@ endif # NETWORK_FILESYSTEMS
> >  source "fs/nls/Kconfig"
> >  source "fs/dlm/Kconfig"
> > 
> > +config BH_LRU_SIZE
> > +      int
> > +      range 8 64
> > +      default "16"
> 
> So who sets it then? 
> 
> You need it for ext4 and quota right? So this combination
> should set it at least. Something like (unested)
> 
> It would be also good to audit or test other file systems if they need the
> same if that's possible.
> 
> config BH_LARGE_LRU
> 	bool
> 	depends on (EXT4_FS && QUOTA)
> 
> config BH_LRU_SIZE
> ....
> 	default "16" if BH_LARGE_LRU
> 	default "8" if !BH_LARGE_LRU

Can anyone demonstrate why we shouldn't just do

--- a/fs/buffer.c~a
+++ a/fs/buffer.c
@@ -1258,7 +1258,7 @@ static struct buffer_head *__bread_slow(
  * a local interrupt disable for that.
  */
 
-#define BH_LRU_SIZE	8
+#define BH_LRU_SIZE	16
 
 struct bh_lru {
 	struct buffer_head *bhs[BH_LRU_SIZE];
_