On Wed, Jun 13, 2007 at 03:51:14PM +1000, Rusty Russell wrote:
> > > static unsigned long
> > > ondemand_readahead(struct address_space *mapping,
> > > struct file_ra_state *ra, struct file *filp,
> > > -struct page *page, pgoff_t offset,
> > > +bool
On Wed, Jun 13, 2007 at 03:51:14PM +1000, Rusty Russell wrote:
static unsigned long
ondemand_readahead(struct address_space *mapping,
struct file_ra_state *ra, struct file *filp,
-struct page *page, pgoff_t offset,
+bool hit_lookahead_marker,
On Wed, 2007-06-13 at 12:00 +0800, Fengguang Wu wrote:
> On Wed, Jun 13, 2007 at 11:40:33AM +1000, Rusty Russell wrote:
> > +/* If page has PG_readahead flag set, call async readahead logic. */
> > +static inline void
> > +page_cache_check_readahead_page(struct address_space *mapping,
> > +
On Wed, Jun 13, 2007 at 11:40:33AM +1000, Rusty Russell wrote:
> On Tue, 2007-06-12 at 18:35 +0800, Fengguang Wu wrote:
> > > This seems a little like two functions crammed into one. Do you think
> > > page_cache_readahead_ondemand() should be split into
> > > "page_cache_readahead()" which
On Tue, 2007-06-12 at 18:35 +0800, Fengguang Wu wrote:
> > This seems a little like two functions crammed into one. Do you think
> > page_cache_readahead_ondemand() should be split into
> > "page_cache_readahead()" which doesn't take a page*, and
> > "page_cache_check_readahead_page()" which is
Hi Rusty,
On Tue, Jun 12, 2007 at 02:36:26PM +1000, Rusty Russell wrote:
> On Thu, 2007-05-17 at 06:47 +0800, Fengguang Wu wrote:
> > +static unsigned long
> > +ondemand_readahead(struct address_space *mapping,
> > + struct file_ra_state *ra, struct file *filp,
> > +
Hi Rusty,
On Tue, Jun 12, 2007 at 02:36:26PM +1000, Rusty Russell wrote:
On Thu, 2007-05-17 at 06:47 +0800, Fengguang Wu wrote:
+static unsigned long
+ondemand_readahead(struct address_space *mapping,
+ struct file_ra_state *ra, struct file *filp,
+ struct page
On Tue, 2007-06-12 at 18:35 +0800, Fengguang Wu wrote:
This seems a little like two functions crammed into one. Do you think
page_cache_readahead_ondemand() should be split into
page_cache_readahead() which doesn't take a page*, and
page_cache_check_readahead_page() which is an inline
On Wed, Jun 13, 2007 at 11:40:33AM +1000, Rusty Russell wrote:
On Tue, 2007-06-12 at 18:35 +0800, Fengguang Wu wrote:
This seems a little like two functions crammed into one. Do you think
page_cache_readahead_ondemand() should be split into
page_cache_readahead() which doesn't take a
On Wed, 2007-06-13 at 12:00 +0800, Fengguang Wu wrote:
On Wed, Jun 13, 2007 at 11:40:33AM +1000, Rusty Russell wrote:
+/* If page has PG_readahead flag set, call async readahead logic. */
+static inline void
+page_cache_check_readahead_page(struct address_space *mapping,
+
On Thu, 2007-05-17 at 06:47 +0800, Fengguang Wu wrote:
> +static unsigned long
> +ondemand_readahead(struct address_space *mapping,
> +struct file_ra_state *ra, struct file *filp,
> +struct page *page, pgoff_t offset,
> +unsigned long req_size)
> +{
On Thu, 2007-05-17 at 06:47 +0800, Fengguang Wu wrote:
+static unsigned long
+ondemand_readahead(struct address_space *mapping,
+struct file_ra_state *ra, struct file *filp,
+struct page *page, pgoff_t offset,
+unsigned long req_size)
+{
+
On Fri, May 18, 2007 at 11:23:35PM -0700, Andrew Morton wrote:
>
> That would have to be the best changelog I've ever seen ;) Thanks for
> persisting with this.
Thank you :)
> > sysbench oltp (trans/sec): up to 8% gain
>
> Have you given any thought to identifying workloads which may be
On Thu, 17 May 2007 06:47:57 +0800 Fengguang Wu <[EMAIL PROTECTED]> wrote:
> This is a minimal readahead algorithm that aims to replace the current one.
> It is more flexible and reliable, while maintaining almost the same behavior
> and performance. Also it is full integrated with adaptive
On Thu, 17 May 2007 06:47:57 +0800 Fengguang Wu [EMAIL PROTECTED] wrote:
This is a minimal readahead algorithm that aims to replace the current one.
It is more flexible and reliable, while maintaining almost the same behavior
and performance. Also it is full integrated with adaptive readahead.
On Fri, May 18, 2007 at 11:23:35PM -0700, Andrew Morton wrote:
That would have to be the best changelog I've ever seen ;) Thanks for
persisting with this.
Thank you :)
sysbench oltp (trans/sec): up to 8% gain
Have you given any thought to identifying workloads which may be worsened
by
This is a minimal readahead algorithm that aims to replace the current one.
It is more flexible and reliable, while maintaining almost the same behavior
and performance. Also it is full integrated with adaptive readahead.
It is designed to be called on demand:
- on a missing page, to do
This is a minimal readahead algorithm that aims to replace the current one.
It is more flexible and reliable, while maintaining almost the same behavior
and performance. Also it is full integrated with adaptive readahead.
It is designed to be called on demand:
- on a missing page, to do
18 matches
Mail list logo
