On Mon, Sep 03, 2007 at 12:31:49PM -0700, Christoph Lameter wrote:
> So you'd be fine with replacing the allocs with
>
> get_free_pages(GFP_xxx, get_order(size)) ?
Yes. And rip out all that code related to setting up the slabs. I plan
to add WARN_ONs to bio_add_page and friends to detect
On Mon, 3 Sep 2007, Christoph Hellwig wrote:
> > How about getting rid of the slabs there and use kmalloc? Kmalloc in mm
> > (and therfore hopefully 2.6.24) will convert kmallocs > PAGE_SIZE to page
> > allocator calls. Not sure what to do about the 1k and 2k requests though.
>
> The problem
On Mon, Sep 03, 2007 at 12:55:04AM -0700, Christoph Lameter wrote:
> On Sun, 2 Sep 2007, Christoph Hellwig wrote:
>
> > > We are doing what you describe right now. So the current code is broken?
> > Yes.
>
> How about getting rid of the slabs there and use kmalloc? Kmalloc in mm
> (and therfore
On Sun, 2 Sep 2007, Christoph Hellwig wrote:
> > We are doing what you describe right now. So the current code is broken?
> Yes.
How about getting rid of the slabs there and use kmalloc? Kmalloc in mm
(and therfore hopefully 2.6.24) will convert kmallocs > PAGE_SIZE to page
allocator calls.
On Sun, 2 Sep 2007, Christoph Hellwig wrote:
We are doing what you describe right now. So the current code is broken?
Yes.
How about getting rid of the slabs there and use kmalloc? Kmalloc in mm
(and therfore hopefully 2.6.24) will convert kmallocs PAGE_SIZE to page
allocator calls. Not
On Mon, 3 Sep 2007, Christoph Hellwig wrote:
How about getting rid of the slabs there and use kmalloc? Kmalloc in mm
(and therfore hopefully 2.6.24) will convert kmallocs PAGE_SIZE to page
allocator calls. Not sure what to do about the 1k and 2k requests though.
The problem is that we
On Mon, Sep 03, 2007 at 12:31:49PM -0700, Christoph Lameter wrote:
So you'd be fine with replacing the allocs with
get_free_pages(GFP_xxx, get_order(size)) ?
Yes. And rip out all that code related to setting up the slabs. I plan
to add WARN_ONs to bio_add_page and friends to detect further
On Sun, Sep 02, 2007 at 04:40:21AM -0700, Christoph Lameter wrote:
> On Sat, 1 Sep 2007, Christoph Hellwig wrote:
>
> > On Fri, Aug 31, 2007 at 05:12:18PM -0700, Mingming Cao wrote:
> > > >From clameter:
> > > Teach jbd/jbd2 slab management to support >8k block size. Without this,
> > > it
On Sat, 1 Sep 2007, Christoph Hellwig wrote:
> On Fri, Aug 31, 2007 at 05:12:18PM -0700, Mingming Cao wrote:
> > >From clameter:
> > Teach jbd/jbd2 slab management to support >8k block size. Without this, it
> > refused to mount on >8k ext3.
>
>
> But the real fix is to kill this code. We
On Sat, 1 Sep 2007, Christoph Hellwig wrote:
On Fri, Aug 31, 2007 at 05:12:18PM -0700, Mingming Cao wrote:
From clameter:
Teach jbd/jbd2 slab management to support 8k block size. Without this, it
refused to mount on 8k ext3.
But the real fix is to kill this code. We can't send down
On Sun, Sep 02, 2007 at 04:40:21AM -0700, Christoph Lameter wrote:
On Sat, 1 Sep 2007, Christoph Hellwig wrote:
On Fri, Aug 31, 2007 at 05:12:18PM -0700, Mingming Cao wrote:
From clameter:
Teach jbd/jbd2 slab management to support 8k block size. Without this,
it refused to mount on
On Fri, Aug 31, 2007 at 05:12:18PM -0700, Mingming Cao wrote:
> >From clameter:
> Teach jbd/jbd2 slab management to support >8k block size. Without this, it
> refused to mount on >8k ext3.
But the real fix is to kill this code. We can't send down slab pages
down the block layer without
On Fri, Aug 31, 2007 at 05:12:18PM -0700, Mingming Cao wrote:
From clameter:
Teach jbd/jbd2 slab management to support 8k block size. Without this, it
refused to mount on 8k ext3.
But the real fix is to kill this code. We can't send down slab pages
down the block layer without breaking
>From clameter:
Teach jbd/jbd2 slab management to support >8k block size. Without this, it
refused to mount on >8k ext3.
Signed-off-by: Mingming Cao <[EMAIL PROTECTED]>
Index: my2.6/fs/jbd/journal.c
===
---
From clameter:
Teach jbd/jbd2 slab management to support 8k block size. Without this, it
refused to mount on 8k ext3.
Signed-off-by: Mingming Cao [EMAIL PROTECTED]
Index: my2.6/fs/jbd/journal.c
===
--- my2.6.orig/fs/jbd/journal.c
15 matches
Mail list logo