I think I'm seeing the same VM behavior with NFS/ext3 that was described
with fuse.
I have a shared storage unit with 2 servers. The local filesystem is
ext3 and I'm failing
the ext3 mounting and NFS serving from one node to another. I'm running
I/O on the NFS
mount point to the active serve
On Mon, Mar 26, 2007 at 03:30:27PM +0200, Peter Zijlstra wrote:
> On Mon, 2007-03-26 at 02:08 -0800, Andrew Morton wrote:
> > On Mon, 26 Mar 2007 11:32:47 +0200 Miklos Szeredi <[EMAIL PROTECTED]> wrote:
> >
> > > Stopping writers which have idle queues is completely unproductive,
> > > and that is
On Mon, Mar 26, 2007 at 01:01:24AM -0800, Andrew Morton wrote:
> On Mon, 26 Mar 2007 10:26:18 +0200 Miklos Szeredi <[EMAIL PROTECTED]> wrote:
> > Ditto for the case, when there are no more dirty pages destined for
> > this queue.
> >
> > I understand, that this can fill up the memory with under wr
On Mon, 2007-03-26 at 02:08 -0800, Andrew Morton wrote:
> On Mon, 26 Mar 2007 11:32:47 +0200 Miklos Szeredi <[EMAIL PROTECTED]> wrote:
>
> > Stopping writers which have idle queues is completely unproductive,
> > and that is basically what the current algorithm does.
>
> This is because the kerne
On Mon, 26 Mar 2007 11:32:47 +0200 Miklos Szeredi <[EMAIL PROTECTED]> wrote:
> Stopping writers which have idle queues is completely unproductive,
> and that is basically what the current algorithm does.
This is because the kernel permits all of its allotment of dirty+writeback
pages to be dirty+
> > Well, not a picture, but a sort of indented call trace:
> >
> > [some process, which has a fuse file writably mmaped]
> > write fault on upper filesystem
> > balance_dirty_pages
> > loop...
> > submit write requests
>
> This, I assume, is the upper fs
>
> > --
> > > > This is a slightly different take on the fix for the deadlock in fuse
> > > > with dirty balancing. David Chinner convinced me, that per-bdi
> > > > counters are too expensive, and that it's not worth trying to account
> > > > the number of pages under writeback, as they will be limited by
On Mon, 26 Mar 2007 11:20:11 +0200 Miklos Szeredi <[EMAIL PROTECTED]> wrote:
> > > > > It also makes a deadlock possible when one filesystem is writing data
> > > > > through another, and the balance_dirty_pages() for the lower
> > > > > filesystem is stalling the writeback for the upper filesyste
> > > > It also makes a deadlock possible when one filesystem is writing data
> > > > through another, and the balance_dirty_pages() for the lower
> > > > filesystem is stalling the writeback for the upper filesystem's
> > > > data (*).
> > >
> > > I still don't understand this one. I got lost wh
On Mon, 26 Mar 2007 10:26:18 +0200 Miklos Szeredi <[EMAIL PROTECTED]> wrote:
> > > This is a slightly different take on the fix for the deadlock in fuse
> > > with dirty balancing. David Chinner convinced me, that per-bdi
> > > counters are too expensive, and that it's not worth trying to account
> > This is a slightly different take on the fix for the deadlock in fuse
> > with dirty balancing. David Chinner convinced me, that per-bdi
> > counters are too expensive, and that it's not worth trying to account
> > the number of pages under writeback, as they will be limited by the
> > queue a
On Sat, 24 Mar 2007 22:55:29 +0100 Miklos Szeredi <[EMAIL PROTECTED]> wrote:
> This is a slightly different take on the fix for the deadlock in fuse
> with dirty balancing. David Chinner convinced me, that per-bdi
> counters are too expensive, and that it's not worth trying to account
> the numbe
> for (;;) {
> struct writeback_control wbc = {
> .bdi= bdi,
> .sync_mode = WB_SYNC_NONE,
> .older_than_this = NULL,
> .nr_to_write= write_chunk,
>
On Sun, 2007-03-25 at 13:34 +0200, Miklos Szeredi wrote:
> > >
> > > Please have a look at this:
> > > http://lkml.org/lkml/2007/3/19/220
> >
> >
> >
> > > + if (bdi_nr_reclaimable + bdi_stat(bdi, BDI_WRITEBACK) <=
> > > + bdi_thresh)
> > > +
> >
> > Please have a look at this:
> > http://lkml.org/lkml/2007/3/19/220
>
>
>
> > + if (bdi_nr_reclaimable + bdi_stat(bdi, BDI_WRITEBACK) <=
> > + bdi_thresh)
> > + break;
> >
>
> Yes, this will resolve the deadlock as
> On Sat, 2007-03-24 at 22:55 +0100, Miklos Szeredi wrote:
> > This is a slightly different take on the fix for the deadlock in fuse
> > with dirty balancing. David Chinner convinced me, that per-bdi
> > counters are too expensive, and that it's not worth trying to account
> > the number of pages
On Sat, 2007-03-24 at 22:55 +0100, Miklos Szeredi wrote:
> This is a slightly different take on the fix for the deadlock in fuse
> with dirty balancing. David Chinner convinced me, that per-bdi
> counters are too expensive, and that it's not worth trying to account
> the number of pages under writ
This is a slightly different take on the fix for the deadlock in fuse
with dirty balancing. David Chinner convinced me, that per-bdi
counters are too expensive, and that it's not worth trying to account
the number of pages under writeback, as they will be limited by the
queue anyway.
From: M
18 matches
Mail list logo
