Re: [RFC][PATCH] block: Isolate the buffer cache in it's own mappings.

2007-10-21 Thread David Chinner
On Sun, Oct 21, 2007 at 02:24:46PM +1000, Nick Piggin wrote: > On Saturday 20 October 2007 07:27, Eric W. Biederman wrote: > > Currently only > > metadata is more or less in sync with the contents of /dev/hda1. > > It either is or it isn't, right? And it is, isn't it? (at least > for the common f

Re: [RFC][PATCH] block: Isolate the buffer cache in it's own mappings.

2007-10-21 Thread Eric W. Biederman
Nick Piggin <[EMAIL PROTECTED]> writes: > On Sunday 21 October 2007 14:53, Eric W. Biederman wrote: >> Nick Piggin <[EMAIL PROTECTED]> writes: >> > On Saturday 20 October 2007 07:27, Eric W. Biederman wrote: >> >> Andrew Morton <[EMAIL PROTECTED]> writes: >> >> > I don't think we little angels wan

Re: [RFC][PATCH] block: Isolate the buffer cache in it's own mappings.

2007-10-20 Thread Nick Piggin
On Sunday 21 October 2007 14:53, Eric W. Biederman wrote: > Nick Piggin <[EMAIL PROTECTED]> writes: > > On Saturday 20 October 2007 07:27, Eric W. Biederman wrote: > >> Andrew Morton <[EMAIL PROTECTED]> writes: > >> > I don't think we little angels want to tread here. There are so many > >> > weir

Re: [RFC][PATCH] block: Isolate the buffer cache in it's own mappings.

2007-10-20 Thread Eric W. Biederman
Nick Piggin <[EMAIL PROTECTED]> writes: > On Saturday 20 October 2007 07:27, Eric W. Biederman wrote: >> Andrew Morton <[EMAIL PROTECTED]> writes: >> > I don't think we little angels want to tread here. There are so many >> > weirdo things out there which will break if we bust the coherence betwe

Re: [RFC][PATCH] block: Isolate the buffer cache in it's own mappings.

2007-10-20 Thread Nick Piggin
On Saturday 20 October 2007 07:27, Eric W. Biederman wrote: > Andrew Morton <[EMAIL PROTECTED]> writes: > > I don't think we little angels want to tread here. There are so many > > weirdo things out there which will break if we bust the coherence between > > the fs and /dev/hda1. > > We broke cohe

Re: [RFC][PATCH] block: Isolate the buffer cache in it's own mappings.

2007-10-19 Thread Eric W. Biederman
Nick Piggin <[EMAIL PROTECTED]> writes: > > [*] The ramdisk code is simply buggy, right? (and not the buffer > cache) >From the perspective of the ramdisk it expects the buffer cache to simply be a user of the page cache, and thus the buffer cache is horribly buggy. >From the perspective of

Re: [RFC][PATCH] block: Isolate the buffer cache in it's own mappings.

2007-10-19 Thread Eric W. Biederman
Andrew Morton <[EMAIL PROTECTED]> writes: > > I don't think we little angels want to tread here. There are so many > weirdo things out there which will break if we bust the coherence between > the fs and /dev/hda1. We broke coherence between the fs and /dev/hda1 when we introduced the page cache

Re: [RFC][PATCH] block: Isolate the buffer cache in it's own mappings.

2007-10-17 Thread Nick Piggin
On Thursday 18 October 2007 13:59, Eric W. Biederman wrote: > If filesystems care at all they want absolute control over the buffer > cache. Controlling which buffers are dirty and when. Because we > keep the buffer cache in the page cache for the block device we have > not quite been giving file

Re: [RFC][PATCH] block: Isolate the buffer cache in it's own mappings.

2007-10-17 Thread Andrew Morton
On Wed, 17 Oct 2007 21:59:02 -0600 [EMAIL PROTECTED] (Eric W. Biederman) wrote: > If filesystems care at all they want absolute control over the buffer > cache. Controlling which buffers are dirty and when. Because we > keep the buffer cache in the page cache for the block device we have > not q