[RFC,v4,01/15] vfs,hot_track: introduce private radix tree structures

Commit Message

Zhiyong Wu Oct. 25, 2012, 3:08 p.m. UTC

From: Zhi Yong Wu <[e-mail]>

  One root structure hot_info is defined, is hooked
up in super_block, and will be used to hold radix tree
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 <[e-mail]>
---
 fs/Makefile                  |    2 +-
 fs/dcache.c                  |    2 +
 fs/hot_tracking.c            |  107 ++++++++++++++++++++++++++++++++++++++++++
 fs/hot_tracking.h            |   23 +++++++++
 include/linux/hot_tracking.h |   73 ++++++++++++++++++++++++++++
 5 files changed, 206 insertions(+), 1 deletions(-)
 create mode 100644 fs/hot_tracking.c
 create mode 100644 fs/hot_tracking.h
 create mode 100644 include/linux/hot_tracking.h

Patch

diff --git a/fs/Makefile b/fs/Makefile
index 1d7af79..f966dea 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -11,7 +11,7 @@  obj-y :=	open.o read_write.o file_table.o super.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o drop_caches.o splice.o sync.o utimes.o \
-		stack.o fs_struct.o statfs.o
+		stack.o fs_struct.o statfs.o hot_tracking.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o
diff --git a/fs/dcache.c b/fs/dcache.c
index 3a463d0..7d5be16 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -37,6 +37,7 @@ 
 #include <linux/rculist_bl.h>
 #include <linux/prefetch.h>
 #include <linux/ratelimit.h>
+#include <linux/hot_tracking.h>
 #include "internal.h"
 #include "mount.h"
 
@@ -3172,4 +3173,5 @@  void __init vfs_caches_init(unsigned long mempages)
 	mnt_init();
 	bdev_cache_init();
 	chrdev_init();
+	hot_cache_init();
 }
diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c
new file mode 100644
index 0000000..6a0f2a3
--- /dev/null
+++ b/fs/hot_tracking.c
@@ -0,0 +1,107 @@ 
+/*
+ * fs/hot_tracking.c
+ *
+ * Copyright (C) 2012 IBM Corp. All rights reserved.
+ * Written by Zhi Yong Wu <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ */
+
+#include <linux/list.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+#include <linux/types.h>
+#include <linux/limits.h>
+#include "hot_tracking.h"
+
+/* kmem_cache pointers for slab caches */
+static struct kmem_cache *hot_inode_item_cachep __read_mostly;
+static struct kmem_cache *hot_range_item_cachep __read_mostly;
+
+/*
+ * Initialize the inode tree. Should be called for each new inode
+ * access or other user of the hot_inode interface.
+ */
+static void hot_inode_tree_init(struct hot_info *root)
+{
+	INIT_RADIX_TREE(&root->hot_inode_tree, GFP_ATOMIC);
+	spin_lock_init(&root->lock);
+}
+
+/*
+ * Initialize the hot range tree. Should be called for each new inode
+ * access or other user of the hot_range interface.
+ */
+void hot_range_tree_init(struct hot_inode_item *he)
+{
+	INIT_RADIX_TREE(&he->hot_range_tree, GFP_ATOMIC);
+	spin_lock_init(&he->lock);
+}
+
+/*
+ * Initialize a new hot_range_item structure. The new structure is
+ * returned with a reference count of one and needs to be
+ * freed using free_range_item()
+ */
+static void hot_range_item_init(struct hot_range_item *hr, u32 start,
+				struct hot_inode_item *he)
+{
+	hr->start = start;
+	hr->len = RANGE_SIZE;
+	hr->hot_inode = he;
+	kref_init(&hr->hot_range.refs);
+	spin_lock_init(&hr->hot_range.lock);
+	hr->hot_range.hot_freq_data.avg_delta_reads = (u64) -1;
+	hr->hot_range.hot_freq_data.avg_delta_writes = (u64) -1;
+	hr->hot_range.hot_freq_data.flags = FREQ_DATA_TYPE_RANGE;
+}
+
+/*
+ * Initialize a new hot_inode_item structure. The new structure is
+ * returned with a reference count of one and needs to be
+ * freed using hot_free_inode_item()
+ */
+static void hot_inode_item_init(struct hot_inode_item *he, u64 ino,
+				struct radix_tree_root *hot_inode_tree)
+{
+	he->i_ino = ino;
+	he->hot_inode_tree = hot_inode_tree;
+	kref_init(&he->hot_inode.refs);
+	spin_lock_init(&he->hot_inode.lock);
+	he->hot_inode.hot_freq_data.avg_delta_reads = (u64) -1;
+	he->hot_inode.hot_freq_data.avg_delta_writes = (u64) -1;
+	he->hot_inode.hot_freq_data.flags = FREQ_DATA_TYPE_INODE;
+	hot_range_tree_init(he);
+}
+
+/*
+ * Initialize kmem cache for hot_inode_item and hot_range_item.
+ */
+void __init hot_cache_init(void)
+{
+	hot_inode_item_cachep = kmem_cache_create("hot_inode_item",
+			sizeof(struct hot_inode_item), 0,
+			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+			NULL);
+	if (!hot_inode_item_cachep)
+		return;
+
+	hot_range_item_cachep = kmem_cache_create("hot_range_item",
+			sizeof(struct hot_range_item), 0,
+			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+			NULL);
+	if (!hot_range_item_cachep)
+		goto err;
+
+	return;
+
+err:
+	kmem_cache_destroy(hot_inode_item_cachep);
+}
diff --git a/fs/hot_tracking.h b/fs/hot_tracking.h
new file mode 100644
index 0000000..febf699
--- /dev/null
+++ b/fs/hot_tracking.h
@@ -0,0 +1,23 @@ 
+/*
+ * fs/hot_tracking.h
+ *
+ * Copyright (C) 2012 IBM Corp. All rights reserved.
+ * Written by Zhi Yong Wu <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ */
+
+#ifndef __HOT_TRACKING__
+#define __HOT_TRACKING__
+
+#include <linux/radix-tree.h>
+#include <linux/workqueue.h>
+#include <linux/hot_tracking.h>
+
+/* values for hot_freq_data flags */
+#define FREQ_DATA_TYPE_INODE (1 << 0)
+#define FREQ_DATA_TYPE_RANGE (1 << 1)
+
+#endif /* __HOT_TRACKING__ */
diff --git a/include/linux/hot_tracking.h b/include/linux/hot_tracking.h
new file mode 100644
index 0000000..fcd4ad1
--- /dev/null
+++ b/include/linux/hot_tracking.h
@@ -0,0 +1,73 @@ 
+/*
+ *  include/linux/hot_tracking.h
+ *
+ * This file has definitions for VFS hot data tracking
+ * structures etc.
+ *
+ * Copyright (C) 2012 IBM Corp. All rights reserved.
+ * Written by Zhi Yong Wu <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ */
+
+#ifndef _LINUX_HOTTRACK_H
+#define _LINUX_HOTTRACK_H
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/kref.h>
+#include <linux/fs.h>
+
+/*
+ * 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
+ */
+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;
+	u32 flags;
+	u32 last_temp;
+};
+
+/* The common info for both following structures */
+struct hot_comm_item {
+	struct hot_freq_data hot_freq_data;  /* frequency data */
+	spinlock_t lock; /* protects object data */
+	struct kref refs;  /* prevents kfree */
+};
+
+/* An item representing an inode and its access frequency */
+struct hot_inode_item {
+	struct hot_comm_item hot_inode; /* node in hot_inode_tree */
+	struct radix_tree_root hot_range_tree; /* tree of ranges */
+	spinlock_t lock; /* protect range tree */
+	struct radix_tree_root *hot_inode_tree;
+	u64 i_ino; /* inode number from inode */
+};
+
+/*
+ * An item representing a range inside of
+ * an inode whose frequency is being tracked
+ */
+struct hot_range_item {
+	struct hot_comm_item hot_range;
+	struct hot_inode_item *hot_inode; /* associated hot_inode_item */
+	u32 start; /* item index in hot_range_tree */
+	u32 len; /* length in bytes */
+};
+
+struct hot_info {
+	struct radix_tree_root hot_inode_tree;
+	spinlock_t lock; /*protect inode tree */
+};
+
+void __init hot_cache_init(void);
+
+#endif  /* _LINUX_HOTTRACK_H */