Re: [PATCH] sendfile removal

[Fengguang Wu <fengguang.wu@gmail.com>]

On Sun, Jun 03, 2007 at 09:05:08PM +0800, Fengguang Wu wrote:
> In non-block splicing, return EAGAIN once for all possible I/O waits.
> 
> It works by checking (ra.prev_index != index) in
> __generic_file_splice_read().  Another reader on the same fd will at
> worst cause a few more splice syscalls.
> 
> If keep calling generic_file_splice_read() in non-block mode, it will
> return partial data before the first hole; then return EAGAIN at
> second call; at last it will block on the I/O page.

Here is a better one, comments are welcome.
---

In non-block splicing read, return EAGAIN once for all possible I/O waits.

It avoids busy waiting by checking (ra.prev_index != index) in
__generic_file_splice_read().  Possible other readers on the same fd
may temporarily cheat the logic, but will at worst cause a few more
splice syscalls.

If keep calling generic_file_splice_read() in non-blocking mode, it
will return partial data before the first wait point; then return
EAGAIN at second call; at last it will block on the I/O page. This
behavior should be compatible with old apps that are unaware of
EAGAIN.

Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---
 fs/splice.c               |   33 ++++++++++++++++++---------------
 include/linux/pipe_fs_i.h |    2 ++
 2 files changed, 20 insertions(+), 15 deletions(-)

--- linux-2.6.22-rc3-mm1.orig/fs/splice.c
+++ linux-2.6.22-rc3-mm1/fs/splice.c
@@ -264,7 +264,7 @@ static ssize_t splice_to_pipe(struct pip
 static int
 __generic_file_splice_read(struct file *in, loff_t *ppos,
 			   struct pipe_inode_info *pipe, size_t len,
-			   unsigned int flags)
+			   unsigned int *flags)
 {
 	struct address_space *mapping = in->f_mapping;
 	unsigned int loff, nr_pages;
@@ -278,7 +278,7 @@ __generic_file_splice_read(struct file *
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
-		.flags = flags,
+		.flags = *flags,
 		.ops = &page_cache_pipe_buf_ops,
 	};
 
@@ -299,12 +299,16 @@ __generic_file_splice_read(struct file *
 	 * Lookup the (hopefully) full range of pages we need.
 	 */
 	spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages);
+	index += spd.nr_pages;
 
 	/*
 	 * If find_get_pages_contig() returned fewer pages than we needed,
-	 * allocate the rest.
+	 * readahead/allocate the rest.
 	 */
-	index += spd.nr_pages;
+	if (spd.nr_pages < nr_pages)
+		page_cache_readahead_ondemand(mapping, &in->f_ra, in,
+				NULL, index, nr_pages - spd.nr_pages);
+
 	while (spd.nr_pages < nr_pages) {
 		/*
 		 * Page could be there, find_get_pages_contig() breaks on
@@ -312,9 +316,6 @@ __generic_file_splice_read(struct file *
 		 */
 		page = find_get_page(mapping, index);
 		if (!page) {
-			page_cache_readahead_ondemand(mapping, &in->f_ra, in,
-					NULL, index, nr_pages - spd.nr_pages);
-
 			/*
 			 * page didn't exist, allocate one.
 			 */
@@ -326,8 +327,6 @@ __generic_file_splice_read(struct file *
 					      GFP_KERNEL);
 			if (unlikely(error)) {
 				page_cache_release(page);
-				if (error == -EEXIST)
-					continue;
 				break;
 			}
 			/*
@@ -369,12 +368,13 @@ __generic_file_splice_read(struct file *
 		 */
 		if (!PageUptodate(page)) {
 			/*
-			 * If in nonblock mode then dont block on waiting
-			 * for an in-flight io page
+			 * In non-block mode, only block at the second try.
 			 */
-			if (flags & SPLICE_F_NONBLOCK) {
-				if (TestSetPageLocked(page))
-					break;
+			if ((*flags & SPLICE_F_NONBLOCK) &&
+				TestSetPageLocked(page) &&
+				in->f_ra.prev_index != index) {
+				*flags |= SPLICE_INTERNAL_WILLBLOCK;
+				break;
 			} else
 				lock_page(page);
 
@@ -480,7 +480,7 @@ ssize_t generic_file_splice_read(struct 
 	spliced = 0;
 
 	while (len) {
-		ret = __generic_file_splice_read(in, ppos, pipe, len, flags);
+		ret = __generic_file_splice_read(in, ppos, pipe, len, &flags);
 
 		if (ret < 0)
 			break;
@@ -496,6 +496,9 @@ ssize_t generic_file_splice_read(struct 
 		*ppos += ret;
 		len -= ret;
 		spliced += ret;
+
+		if (flags & SPLICE_INTERNAL_WILLBLOCK)
+			break;
 	}
 
 	if (spliced)
--- linux-2.6.22-rc3-mm1.orig/include/linux/pipe_fs_i.h
+++ linux-2.6.22-rc3-mm1/include/linux/pipe_fs_i.h
@@ -82,6 +82,8 @@ int generic_pipe_buf_steal(struct pipe_i
 #define SPLICE_F_MORE	(0x04)	/* expect more data */
 #define SPLICE_F_GIFT	(0x08)	/* pages passed in are a gift */
 
+#define SPLICE_INTERNAL_WILLBLOCK  (0x100) /* read on next page will block */
+
 /*
  * Passed to the actors
  */

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/