On Sun, Sep 23, 2012 at 08:56:26PM +0800, zwu.kernel@gmail.com wrote:

From: Zhi Yong Wu <redacted>

  One root structure hot_info is defined, is hooked
up in super_block, and will be used to hold rb trees
root, hash list root and some other information, etc.
  Adds hot_inode_tree struct to keep track of
frequently accessed files, and be keyed by {inode, offset}.
Trees contain hot_inode_items representing those files
and ranges.
  Having these trees means that vfs can quickly determine the
temperature of some data by doing some calculations on the
hot_freq_data struct that hangs off of the tree item.
  Define two items hot_inode_item and hot_range_item,
one of them represents one tracked file
to keep track of its access frequency and the tree of
ranges in this file, while the latter represents
a file range of one inode.
  Each of the two structures contains a hot_freq_data
struct with its frequency of access metrics (number of
{reads, writes}, last {read,write} time, frequency of
{reads,writes}).
  Also, each hot_inode_item contains one hot_range_tree
struct which is keyed by {inode, offset, length}
and used to keep track of all the ranges in this file.

Signed-off-by: Zhi Yong Wu <redacted>

Just a coupl eof minor formatting things first up - I'll have more
comments as I get deeper into the series.

....

+/*
+ * Initialize the inode tree. Should be called for each new inode
+ * access or other user of the hot_inode interface.
+ */
+static void hot_rb_inode_tree_init(struct hot_inode_tree *tree)

The names of these are a bit clunky. You probably don't need the
"_rb_" in the function name. i.e. hot_inode_tree_init() is
sufficient, and if we every want to change in the tree type we don't
have to rename every single function...

.....

+/*
+ * Initialize a new hot_inode_item structure. The new structure is
+ * returned with a reference count of one and needs to be
+ * freed using free_inode_item()
+ */
+void hot_rb_inode_item_init(void *_item)
+{

The usual naming convention for slab initialiser functions is to use
a suffix of "_once" to indicate it is only ever called once per
slab object instantiation, not every time the object is allocated
fom the slab. See, for example, inode_init_once() and
inode_init_always().

so, that would make this function hot_inode_item_init_once().

....

+/* init hot_inode_item and hot_range_item kmem cache */
+static int __init hot_rb_item_cache_init(void)
+{
+	hot_inode_item_cache = kmem_cache_create("hot_inode_item",
+			sizeof(struct hot_inode_item), 0,
+			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+			hot_rb_inode_item_init);
+	if (!hot_inode_item_cache)
+		goto inode_err;
+
+	hot_range_item_cache = kmem_cache_create("hot_range_item",
+					sizeof(struct hot_range_item), 0,
+					SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+					hot_rb_range_item_init);
+	if (!hot_range_item_cache)
+		goto range_err;
+
+	return 0;
+
+range_err:
+	kmem_cache_destroy(hot_inode_item_cache);
+inode_err:
+	return -ENOMEM;
+}
+
+/*
+ * Initialize kmem cache for hot_inode_item
+ * and hot_range_item
+ */
+void __init hot_track_cache_init(void)
+{
+	if (hot_rb_item_cache_init())
+		return;

No real need to have a hot_rb_item_cache_init() function here - just
open code it all in the hot_track_cache_init() function.

The comments are redundant - the name of the object documents it's
use sufficiently.  ie.

/* values for hot_freq_data flags */
#define FREQ_DATA_TYPE_INODE (1 << 0)
#define FREQ_DATA_TYPE_RANGE (1 << 1)

is just fine by itself.

....

+/* A frequency data struct holds values that are used to
+ * determine temperature of files and file ranges. These structs
+ * are members of hot_inode_item and hot_range_item
+ */

/*
 * This is a
 * multiline comment. ;)
 */

+struct hot_freq_data {
+	struct timespec last_read_time;
+	struct timespec last_write_time;
+	u32 nr_reads;
+	u32 nr_writes;
+	u64 avg_delta_reads;
+	u64 avg_delta_writes;
+	u8 flags;
+	u32 last_temperature;

may as well make the flags a u32 - the compiler will ues that much
space anyway as it aligned the u32 last_temperature variable after
it.

+};
+
+/* An item representing an inode and its access frequency */
+struct hot_inode_item {
+	/* node for hot_inode_tree rb_tree */
+	struct rb_node rb_node;
+	/* tree of ranges in this inode */
+	struct hot_range_tree hot_range_tree;
+	/* frequency data for this inode */
+	struct hot_freq_data hot_freq_data;
+	/* inode number, copied from inode */
+	unsigned long i_ino;
+	/* used to check for errors in ref counting */
+	u8 in_tree;
+	/* protects hot_freq_data, i_no, in_tree */
+	spinlock_t lock;
+	/* prevents kfree */
+	struct kref refs;

It's hard to see the code in the commentsi, and some of comments are
redundant.. It's easier to read if you do this:

struct hot_inode_item {
	struct rb_node node;			/* hot_inode_tree index */
	struct hot_range_tree hot_range_tree;	/* tree of ranges */
	struct hot_freq_data hot_freq_data;	/* frequency data */
	unsigned long i_ino;			/* inode number from inode */
	u8 in_tree;				/* ref counting check */
	spinlock_t lock;			/* protects object data */
	struct kref refs;			/* prevents kfree */
}

Also: 
	- i_ino really needs to be a 64 bit quantity as some
	  filesystems can use 64 bit inode numbers even on 32
	  bit systems (e.g. XFS).
	- in_tree can be u32 or a flags field if it is boolean. if
	  it is just debug, then maybe it can be removed whenteh
	  code is ready for commit.

+};
+
+/*
+ * An item representing a range inside of an inode whose frequency
+ * is being tracked
+ */
+struct hot_range_item {
+	/* node for hot_range_tree rb_tree */
+	struct rb_node rb_node;
+	/* frequency data for this range */
+	struct hot_freq_data hot_freq_data;
+	/* the hot_inode_item associated with this hot_range_item */
+	struct hot_inode_item *hot_inode;
+	/* starting offset of this range */
+	u64 start;
+	/* length of this range */
+	u64 len;

What units?
	u64 start;	/* start offset in bytes */
	u64 len		/* length in bytes */

+	/* used to check for errors in ref counting */
+	u8 in_tree;
+	/* protects hot_freq_data, start, len, and in_tree */
+	spinlock_t lock;
+	/* prevents kfree */
+	struct kref refs;
+};
+
+struct hot_info {
+	/* red-black tree that keeps track of fs-wide hot data */
+	struct hot_inode_tree hot_inode_tree;
+};

The comment is redundant...

Cheers,

Dave.

-- 
Dave Chinner
david@fromorbit.com