readahead: add look-ahead support to __do_page_cache_readahead()

Add look-ahead support to __do_page_cache_readahead().

It works by
	- mark the Nth backwards page with PG_readahead,
	(which instructs the page's first reader to invoke readahead)
	- and only do the marking for newly allocated pages.
	(to prevent blindly doing readahead on already cached pages)

Look-ahead is a technique to achieve I/O pipelining:

While the application is working through a chunk of cached pages, the kernel
reads-ahead the next chunk of pages _before_ time of need.  It effectively
hides low level I/O latencies to high level applications.

Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Cc: Steven Pratt <slpratt@austin.ibm.com>
Cc: Ram Pai <linuxram@us.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/readahead.c b/mm/readahead.c
index 9861e883fe57e069d43492ebdbd7d7671464f371..88ea0f29aac898fa4ce49f07cf1e56584f74e3b4 100644 (file)
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -265,7 +265,8 @@ out:
  */
 static int
 __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
-                       pgoff_t offset, unsigned long nr_to_read)
+                       pgoff_t offset, unsigned long nr_to_read,
+                       unsigned long lookahead_size)
 {
        struct inode *inode = mapping->host;
        struct page *page;
@@ -278,7 +279,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
        if (isize == 0)
                goto out;
 
-       end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
+       end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
 
        /*
         * Preallocate as many pages as we will need.
@@ -301,6 +302,8 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
                        break;
                page->index = page_offset;
                list_add(&page->lru, &page_pool);
+               if (page_idx == nr_to_read - lookahead_size)
+                       SetPageReadahead(page);
                ret++;
        }
        read_unlock_irq(&mapping->tree_lock);
@@ -337,7 +340,7 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
                if (this_chunk > nr_to_read)
                        this_chunk = nr_to_read;
                err = __do_page_cache_readahead(mapping, filp,
-                                               offset, this_chunk);
+                                               offset, this_chunk, 0);
                if (err < 0) {
                        ret = err;
                        break;
@@ -384,7 +387,7 @@ int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
        if (bdi_read_congested(mapping->backing_dev_info))
                return -1;
 
-       return __do_page_cache_readahead(mapping, filp, offset, nr_to_read);
+       return __do_page_cache_readahead(mapping, filp, offset, nr_to_read, 0);
 }
 
 /*
@@ -404,7 +407,7 @@ blockable_page_cache_readahead(struct address_space *mapping, struct file *filp,
        if (!block && bdi_read_congested(mapping->backing_dev_info))
                return 0;
 
-       actual = __do_page_cache_readahead(mapping, filp, offset, nr_to_read);
+       actual = __do_page_cache_readahead(mapping, filp, offset, nr_to_read, 0);
 
        return check_ra_success(ra, nr_to_read, actual);
 }
@@ -449,7 +452,7 @@ static int make_ahead_window(struct address_space *mapping, struct file *filp,
  * @req_size: hint: total size of the read which the caller is performing in
  *            PAGE_CACHE_SIZE units
  *
- * page_cache_readahead() is the main function.  If performs the adaptive
+ * page_cache_readahead() is the main function.  It performs the adaptive
  * readahead window size management and submits the readahead I/O.
  *
  * Note that @filp is purely used for passing on to the ->readpage[s]()