orangefs: remember count when reading.

Orangefs wins when it can do IO on large (up to four meg) blocks at a time,
and looses when it has to do tiny "small io" reads and writes. Accessing
Orangefs through the pagecache with the kernel module helps with small io,
both reading and writing, a great deal. Readpage generally tries to fetch a
page (four k) at a time. We'll let users use "count" (as in read(2) or
pread(2) for example) as a knob to control how much data they get from
Orangefs at a time and we'll try to use the data to fill extra
pagecache pages when we get to ->readpage, hopefully resulting in
fewer calls to readpage and Orangefs userspace.

We need a way to remember how they set count so that we can still have
it available when we get to ->readpage.

 - We'll use file->private_data to keep track of "count".
   We'll wrap generic_file_open with orangefs_file_open and
   initialize private_data to NULL there.

 - In ->read_iter we have access to both "count" and file, so
   we'll kmalloc some space onto file->private_data and store
   "count" there.

 - We'll kfree file->private_data each time we visit ->flush and
   reinitialize it to NULL.

Signed-off-by: Mike Marshall <hubcap@omnibond.com>
Signed-off-by: Martin Brandenburg <martin@omnibond.com>

2 files changed, 29 insertions, 1 deletions

diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index faa5b61cdfd6..74292d31d113 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -286,8 +286,23 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb,
     struct iov_iter *iter)
 {
 	int ret;
+	struct orangefs_read_options *ro;
+
 	orangefs_stats.reads++;
 
+	/*
+	 * Remember how they set "count" in read(2) or pread(2) or whatever -
+	 * users can use count as a knob to control orangefs io size and later
+	 * we can try to help them fill as many pages as possible in readpage.
+	 */
+	if (!iocb->ki_filp->private_data) {
+		iocb->ki_filp->private_data = kmalloc(sizeof *ro, GFP_KERNEL);
+		if (!iocb->ki_filp->private_data)
+			return(ENOMEM);
+		ro = iocb->ki_filp->private_data;
+		ro->blksiz = iter->count;
+	}
+
 	down_read(&file_inode(iocb->ki_filp)->i_rwsem);
 	ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp));
 	if (ret)
@@ -556,6 +571,12 @@ static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl)
 	return rc;
 }
 
+static int orangefs_file_open(struct inode * inode, struct file *file)
+{
+	file->private_data = NULL;
+	return generic_file_open(inode, file);
+}
+
 static int orangefs_flush(struct file *file, fl_owner_t id)
 {
 	/*
@@ -569,6 +590,9 @@ static int orangefs_flush(struct file *file, fl_owner_t id)
 	struct inode *inode = file->f_mapping->host;
 	int r;
 
+	kfree(file->private_data);
+	file->private_data = NULL;
+
 	if (inode->i_state & I_DIRTY_TIME) {
 		spin_lock(&inode->i_lock);
 		inode->i_state &= ~I_DIRTY_TIME;
@@ -591,7 +615,7 @@ const struct file_operations orangefs_file_operations = {
 	.lock		= orangefs_lock,
 	.unlocked_ioctl	= orangefs_ioctl,
 	.mmap		= orangefs_file_mmap,
-	.open		= generic_file_open,
+	.open		= orangefs_file_open,
 	.flush		= orangefs_flush,
 	.release	= orangefs_file_release,
 	.fsync		= orangefs_fsync,
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 87beab10326a..3ae2f129b9c7 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -239,6 +239,10 @@ struct orangefs_write_range {
 	kgid_t gid;
 };
 
+struct orangefs_read_options {
+	ssize_t blksiz;
+};
+
 extern struct orangefs_stats orangefs_stats;
 
 /*