On Thu, 2007-11-01 at 20:19 +0100, Miklos Szeredi wrote:
> > >
> > > See the file "Locking" for more details.
> > >
> > >
> > > The "should set PG_Writeback" bit threw me off I guess.
> >
> > Hmm, set_page_writeback() is also the one clearing the radix tree dirty
> > tag. So if that is n
> >
> > See the file "Locking" for more details.
> >
> >
> > The "should set PG_Writeback" bit threw me off I guess.
>
> Hmm, set_page_writeback() is also the one clearing the radix tree dirty
> tag. So if that is not called, we get in a bit of a mess, no?
>
> Which makes me think hostfs
On Thu, 2007-11-01 at 18:16 +0100, Peter Zijlstra wrote:
> On Thu, 2007-11-01 at 18:09 +0100, Peter Zijlstra wrote:
> > On Thu, 2007-11-01 at 18:00 +0100, Miklos Szeredi wrote:
> > > > > Hi,
> > > > >
> > > > > It looks like bdi_thresh will always be zero if filesystem does
> > > > > synchronous w
On Thu, 2007-11-01 at 18:28 +0100, Miklos Szeredi wrote:
> > The page not having PG_writeback set on return is a hint, but not fool
> > proof, it could be the device is just blazing fast.
>
> Hmm, does it actually has to be foolproof though? What will happen if
> bdi_writeout_inc() is called twic
> The page not having PG_writeback set on return is a hint, but not fool
> proof, it could be the device is just blazing fast.
Hmm, does it actually has to be foolproof though? What will happen if
bdi_writeout_inc() is called twice for the page? The device will get
twice the number of pages it d
On Thu, 2007-11-01 at 18:09 +0100, Peter Zijlstra wrote:
> On Thu, 2007-11-01 at 18:00 +0100, Miklos Szeredi wrote:
> > > > Hi,
> > > >
> > > > It looks like bdi_thresh will always be zero if filesystem does
> > > > synchronous writepage, resulting in very poor write performance.
> > > >
> > > >
On Thu, 2007-11-01 at 18:00 +0100, Miklos Szeredi wrote:
> > > Hi,
> > >
> > > It looks like bdi_thresh will always be zero if filesystem does
> > > synchronous writepage, resulting in very poor write performance.
> > >
> > > Hostfs (UML) is one such example, but there might be others.
> > >
> >
> > Hi,
> >
> > It looks like bdi_thresh will always be zero if filesystem does
> > synchronous writepage, resulting in very poor write performance.
> >
> > Hostfs (UML) is one such example, but there might be others.
> >
> > The only solution I can think of is to add a set_page_writeback();
> >
On Thu, 2007-11-01 at 17:49 +0100, Miklos Szeredi wrote:
> Hi,
>
> It looks like bdi_thresh will always be zero if filesystem does
> synchronous writepage, resulting in very poor write performance.
>
> Hostfs (UML) is one such example, but there might be others.
>
> The only solution I can think
Hi,
It looks like bdi_thresh will always be zero if filesystem does
synchronous writepage, resulting in very poor write performance.
Hostfs (UML) is one such example, but there might be others.
The only solution I can think of is to add a set_page_writeback();
end_page_writeback() pair (or some
10 matches
Mail list logo
