From: Zhi Yong Wu <wu...@linux.vnet.ibm.com>
Add a /sys/kernel/debug/hot_track/<device_name>/ directory for each
volume that contains two files. The first, `inode_data', contains the
heat information for inodes that have been brought into the hot data map
structures. The second, `range_data', contains similar information for
subfile ranges.
Signed-off-by: Zhi Yong Wu <wu...@linux.vnet.ibm.com>
---
fs/Makefile | 2 +-
fs/hot_debugfs.c | 488 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/hot_debugfs.h | 60 +++++++
fs/hot_track.c | 1 +
fs/hot_track.h | 3 +-
fs/namespace.c | 6 +
6 files changed, 557 insertions(+), 3 deletions(-)
create mode 100644 fs/hot_debugfs.c
create mode 100644 fs/hot_debugfs.h
diff --git a/fs/Makefile b/fs/Makefile
index f925a66..a70f288 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -12,7 +12,7 @@ obj-y := open.o read_write.o file_table.o super.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 \
- hot_rb.o hot_track.o hot_hash.o
+ hot_rb.o hot_track.o hot_hash.o hot_debugfs.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/hot_debugfs.c b/fs/hot_debugfs.c
new file mode 100644
index 0000000..362f093
--- /dev/null
+++ b/fs/hot_debugfs.c
@@ -0,0 +1,488 @@
+/*
+ * fs/hot_debugfs.c
+ *
+ * This file contains the code to interface with the debugfs.
+ * The debugfs outputs range- and file-level access frequency
+ * statistics for each mounted volume.
+ *
+ * Copyright (C) 2012 IBM Corp. All rights reserved.
+ * Written by Zhi Yong Wu <wu...@linux.vnet.ibm.com>
+ * Ben Chociej <bchoc...@gmail.com>
+ *
+ * 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/debugfs.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+#include <linux/limits.h>
+#include <linux/slab.h>
+#include "hot_debugfs.h"
+
+/* list to keep track of each mounted volumes debugfs_vol_data */
+static struct list_head hot_debugfs_vol_data_list;
+
+/* lock for debugfs_vol_data_list */
+static spinlock_t hot_debugfs_data_list_lock;
+
+/* pointer to top level debugfs dentry */
+static struct dentry *hot_debugfs_root_dentry;
+
+static int hot_debugfs_copy(struct debugfs_vol_data *data, char *msg, int len)
+{
+ struct lstring *debugfs_log = data->debugfs_log;
+ uint new_log_alloc_size;
+ char *new_log;
+ static char err_msg[] = "No more memory!\n";
+
+ if (len >= data->log_alloc_size - debugfs_log->len) {
+ /* Not enough room in the log buffer for the new message. */
+ /* Allocate a bigger buffer. */
+ new_log_alloc_size = data->log_alloc_size + LOG_PAGE_SIZE;
+ new_log = vmalloc(new_log_alloc_size);
+
+ if (new_log) {
+ memcpy(new_log, debugfs_log->str, debugfs_log->len);
+ memset(new_log + debugfs_log->len, 0,
+ new_log_alloc_size - debugfs_log->len);
+ vfree(debugfs_log->str);
+ debugfs_log->str = new_log;
+ data->log_alloc_size = new_log_alloc_size;
+ } else {
+ WARN_ON(1);
+ if (data->log_alloc_size - debugfs_log->len) {
+ strlcpy(debugfs_log->str +
+ debugfs_log->len,
+ err_msg,
+ data->log_alloc_size - debugfs_log->len);
+ debugfs_log->len +=
+ min((typeof(debugfs_log->len))
+ sizeof(err_msg),
+ ((typeof(debugfs_log->len))
+ data->log_alloc_size - debugfs_log->len));
+ }
+ return 0;
+ }
+ }
+
+ memcpy(debugfs_log->str + debugfs_log->len, data->log_work_buff, len);
+ debugfs_log->len += (unsigned long) len;
+
+ return len;
+}
+
+/* Returns the number of bytes written to the log. */
+static int hot_debugfs_log(struct debugfs_vol_data *data, const char *fmt, ...)
+{
+ struct lstring *debugfs_log = data->debugfs_log;
+ va_list args;
+ int len;
+ static char trunc_msg[] =
+ "The next message has been truncated.\n";
+
+ if (debugfs_log->str == NULL)
+ return -1;
+
+ spin_lock(&data->log_lock);
+
+ va_start(args, fmt);
+ len = vsnprintf(data->log_work_buff,
+ sizeof(data->log_work_buff), fmt, args);
+ va_end(args);
+
+ if (len >= sizeof(data->log_work_buff)) {
+ hot_debugfs_copy(data, trunc_msg, sizeof(trunc_msg));
+ }
+
+ len = hot_debugfs_copy(data, data->log_work_buff, len);
+ spin_unlock(&data->log_lock);
+
+ return len;
+}
+
+/* initialize a log corresponding to a fs volume */
+static int hot_debugfs_log_init(struct debugfs_vol_data *data)
+{
+ int err = 0;
+ struct lstring *debugfs_log = data->debugfs_log;
+
+ spin_lock(&data->log_lock);
+ debugfs_log->str = vmalloc(INIT_LOG_ALLOC_SIZE);
+ if (debugfs_log->str) {
+ memset(debugfs_log->str, 0, INIT_LOG_ALLOC_SIZE);
+ data->log_alloc_size = INIT_LOG_ALLOC_SIZE;
+ } else {
+ err = -ENOMEM;
+ }
+ spin_unlock(&data->log_lock);
+
+ return err;
+}
+
+/* free a log corresponding to a fs volume */
+static void hot_debugfs_log_exit(struct debugfs_vol_data *data)
+{
+ struct lstring *debugfs_log = data->debugfs_log;
+
+ spin_lock(&data->log_lock);
+ vfree(debugfs_log->str);
+ debugfs_log->str = NULL;
+ debugfs_log->len = 0;
+ spin_unlock(&data->log_lock);
+}
+
+/* debugfs open file override from fops table */
+static int __hot_debugfs_open(struct inode *inode, struct file *file)
+{
+ if (inode->i_private)
+ file->private_data = inode->i_private;
+
+ return 0;
+}
+
+static void __hot_debugfs_print_range_freq_data(
+ struct hot_inode_item *hot_inode,
+ struct hot_range_item *hot_range,
+ struct debugfs_vol_data *data,
+ struct hot_info *root)
+{
+ struct hot_freq_data *freq_data;
+ u64 start;
+ u64 len;
+
+ freq_data = &hot_range->hot_freq_data;
+
+ spin_lock(&hot_range->lock);
+ start = hot_range->start;
+ len = hot_range->len;
+ spin_unlock(&hot_range->lock);
+
+ /* Always lock hot_inode_item first */
+ spin_lock(&hot_inode->lock);
+ spin_lock(&hot_range->lock);
+ hot_debugfs_log(data, "inode #%lu, range start " \
+ "%llu (range len %llu) reads %u, writes %u, "
+ "avg read time %llu, avg write time %llu, temp %u\n",
+ hot_inode->i_ino,
+ hot_range->start,
+ hot_range->len,
+ freq_data->nr_reads,
+ freq_data->nr_writes,
+ freq_data->avg_delta_reads,
+ freq_data->avg_delta_writes,
+ freq_data->last_temperature);
+ spin_unlock(&hot_range->lock);
+ spin_unlock(&hot_inode->lock);
+}
+
+/*
+ * take the inode, find ranges associated with inode
+ * and print each range data struct
+ */
+static void __hot_debugfs_walk_range_tree(struct hot_inode_item *hot_inode,
+ struct debugfs_vol_data *data,
+ struct hot_info *root)
+{
+ struct hot_range_tree *inode_range_tree;
+ struct rb_node *node;
+ struct hot_range_item *current_range;
+
+ inode_range_tree = &hot_inode->hot_range_tree;
+ read_lock(&inode_range_tree->lock);
+ node = rb_first(&inode_range_tree->map);
+
+ /* Walk the hot_range_tree for inode */
+ while (node) {
+ current_range = rb_entry(node, struct hot_range_item, rb_node);
+ __hot_debugfs_print_range_freq_data(hot_inode,
+ current_range, data, root);
+ node = rb_next(node);
+ }
+ read_unlock(&inode_range_tree->lock);
+}
+
+/* Print frequency data for each freq data to log */
+static void __hot_debugfs_print_inode_freq_data(
+ struct hot_inode_item *hot_inode,
+ struct debugfs_vol_data *data,
+ struct hot_info *root)
+{
+ struct hot_freq_data *freq_data = &hot_inode->hot_freq_data;
+
+ spin_lock(&hot_inode->lock);
+ hot_debugfs_log(data, "inode #%lu, reads %u, writes %u, " \
+ "avg read time %llu, avg write time %llu, temp %u\n",
+ hot_inode->i_ino,
+ freq_data->nr_reads,
+ freq_data->nr_writes,
+ freq_data->avg_delta_reads,
+ freq_data->avg_delta_writes,
+ freq_data->last_temperature);
+ spin_unlock(&hot_inode->lock);
+}
+
+/* debugfs read file override from fops table */
+static ssize_t __hot_debugfs_range_read(struct file *file, char __user *user,
+ size_t count, loff_t *ppos)
+{
+ int err = 0;
+ struct hot_info *root;
+ struct hot_inode_item *current_hot_inode;
+ struct debugfs_vol_data *data;
+ struct lstring *debugfs_log;
+ unsigned long inode_num;
+
+ data = (struct debugfs_vol_data *) file->private_data;
+ root = &(data->sb->s_hotinfo);
+
+ if (!data->debugfs_log) {
+ /* initialize debugfs log corresponding to this volume*/
+ debugfs_log = kmalloc(sizeof(struct lstring),
+ GFP_KERNEL | GFP_NOFS);
+ debugfs_log->str = NULL,
+ debugfs_log->len = 0;
+ data->debugfs_log = debugfs_log;
+ hot_debugfs_log_init(data);
+ }
+
+ if ((unsigned long) *ppos > 0) {
+ /* caller is continuing a previous read, don't walk tree */
+ if ((unsigned long) *ppos >= data->debugfs_log->len)
+ goto clean_up;
+
+ goto print_to_user;
+ }
+
+ /* walk the inode tree */
+ current_hot_inode = hot_rb_find_next_hot_inode(root, 0);
+
+ while (current_hot_inode) {
+ /* walk ranges, print data to debugfs log */
+ __hot_debugfs_walk_range_tree(current_hot_inode, data, root);
+ inode_num = current_hot_inode->i_ino;
+ hot_rb_free_hot_inode_item(current_hot_inode);
+ current_hot_inode = hot_rb_find_next_hot_inode(root,
+ inode_num + 1);
+ }
+
+print_to_user:
+ if (data->debugfs_log->len) {
+ err = simple_read_from_buffer(user, count, ppos,
+ data->debugfs_log->str,
+ data->debugfs_log->len);
+ }
+
+ return err;
+
+clean_up:
+ /* Reader has finished the file, clean up */
+ hot_debugfs_log_exit(data);
+ kfree(data->debugfs_log);
+ data->debugfs_log = NULL;
+
+ return 0;
+}
+
+/* debugfs read file override from fops table */
+static ssize_t __hot_debugfs_inode_read(struct file *file, char __user *user,
+ size_t count, loff_t *ppos)
+{
+ int err = 0;
+ struct hot_info *root;
+ struct hot_inode_item *current_hot_inode;
+ struct debugfs_vol_data *data;
+ struct lstring *debugfs_log;
+ unsigned long inode_num;
+
+ data = (struct debugfs_vol_data *) file->private_data;
+ root = &(data->sb->s_hotinfo);
+
+ if (!data->debugfs_log) {
+ /* initialize debugfs log corresponding to this volume */
+ debugfs_log = kmalloc(sizeof(struct lstring),
+ GFP_KERNEL | GFP_NOFS);
+ debugfs_log->str = NULL,
+ debugfs_log->len = 0;
+ data->debugfs_log = debugfs_log;
+ hot_debugfs_log_init(data);
+ }
+
+ if ((unsigned long) *ppos > 0) {
+ /* caller is continuing a previous read, don't walk tree */
+ if ((unsigned long) *ppos >= data->debugfs_log->len)
+ goto clean_up;
+
+ goto print_to_user;
+ }
+
+ /* walk the inode tree */
+ current_hot_inode = hot_rb_find_next_hot_inode(root, 0);
+
+ while (current_hot_inode) {
+ /* walk ranges, print data to debugfs log */
+ __hot_debugfs_print_inode_freq_data(current_hot_inode,
+ data, root);
+ inode_num = current_hot_inode->i_ino;
+ hot_rb_free_hot_inode_item(current_hot_inode);
+ current_hot_inode = hot_rb_find_next_hot_inode(root,
+ inode_num+1);
+ }
+
+print_to_user:
+ if (data->debugfs_log->len) {
+ err = simple_read_from_buffer(user, count, ppos,
+ data->debugfs_log->str,
+ data->debugfs_log->len);
+ }
+
+ return err;
+
+clean_up:
+ /* reader has finished the file, clean up */
+ hot_debugfs_log_exit(data);
+ kfree(data->debugfs_log);
+ data->debugfs_log = NULL;
+
+ return 0;
+}
+
+/* fops to override for printing range data */
+static const struct file_operations hot_debugfs_range_fops = {
+ .read = __hot_debugfs_range_read,
+ .open = __hot_debugfs_open,
+};
+
+/* fops to override for printing inode data */
+static const struct file_operations hot_debugfs_inode_fops = {
+ .read = __hot_debugfs_inode_read,
+ .open = __hot_debugfs_open,
+};
+
+/* initialize debugfs at module init */
+int hot_debugfs_init(void)
+{
+ hot_debugfs_root_dentry = debugfs_create_dir(DEBUGFS_ROOT_NAME, NULL);
+ /*init list of debugfs data list */
+ INIT_LIST_HEAD(&hot_debugfs_vol_data_list);
+ /*init lock to list of debugfs data list */
+ spin_lock_init(&hot_debugfs_data_list_lock);
+ if (!hot_debugfs_root_dentry)
+ goto debugfs_error;
+
+ return 0;
+
+debugfs_error:
+ return -EIO;
+}
+
+/*
+ * on each volume mount, initialize the debugfs dentries and associated
+ * structures (debugfs_vol_data and debugfs_log)
+ */
+int hot_debugfs_volume_init(const char *uuid, struct super_block *sb)
+{
+ struct dentry *debugfs_volume_entry = NULL;
+ struct dentry *debugfs_range_entry = NULL;
+ struct dentry *debugfs_inode_entry = NULL;
+ struct debugfs_vol_data *range_data = NULL;
+ struct debugfs_vol_data *inode_data = NULL;
+ size_t dev_name_length = strlen(uuid);
+ char dev[NAME_MAX];
+
+ if (!hot_debugfs_root_dentry)
+ goto debugfs_error;
+
+ /* create debugfs folder for this volume by mounted dev name */
+ memcpy(dev, uuid + DEV_NAME_CHOP, dev_name_length - DEV_NAME_CHOP + 1);
+ debugfs_volume_entry = debugfs_create_dir(dev, hot_debugfs_root_dentry);
+
+ if (!debugfs_volume_entry)
+ goto debugfs_error;
+
+ /* malloc and initialize debugfs_vol_data for range_data */
+ range_data = kmalloc(sizeof(struct debugfs_vol_data),
+ GFP_KERNEL | GFP_NOFS);
+ memset(range_data, 0, sizeof(struct debugfs_vol_data));
+ range_data->debugfs_log = NULL;
+ range_data->sb = sb;
+ spin_lock_init(&range_data->log_lock);
+ range_data->log_alloc_size = 0;
+
+ /* malloc and initialize debugfs_vol_data for range_data */
+ inode_data = kmalloc(sizeof(struct debugfs_vol_data),
+ GFP_KERNEL | GFP_NOFS);
+ memset(inode_data, 0, sizeof(struct debugfs_vol_data));
+ inode_data->debugfs_log = NULL;
+ inode_data->sb = sb;
+ spin_lock_init(&inode_data->log_lock);
+ inode_data->log_alloc_size = 0;
+
+ /*
+ * add debugfs_vol_data for inode data and range data for
+ * volume to list
+ */
+ range_data->de = debugfs_volume_entry;
+ inode_data->de = debugfs_volume_entry;
+ spin_lock(&hot_debugfs_data_list_lock);
+ list_add(&range_data->node, &hot_debugfs_vol_data_list);
+ list_add(&inode_data->node, &hot_debugfs_vol_data_list);
+ spin_unlock(&hot_debugfs_data_list_lock);
+
+ /* create debugfs range_data file */
+ debugfs_range_entry = debugfs_create_file("range_data",
+ S_IFREG | S_IRUSR | S_IWUSR | S_IRUGO,
+ debugfs_volume_entry,
+ (void *) range_data,
+ &hot_debugfs_range_fops);
+ if (!debugfs_range_entry)
+ goto debugfs_error;
+
+ /* create debugfs inode_data file */
+ debugfs_inode_entry = debugfs_create_file("inode_data",
+ S_IFREG | S_IRUSR | S_IWUSR | S_IRUGO,
+ debugfs_volume_entry,
+ (void *) inode_data,
+ &hot_debugfs_inode_fops);
+
+ if (!debugfs_inode_entry)
+ goto debugfs_error;
+
+ return 0;
+
+debugfs_error:
+ kfree(range_data);
+ kfree(inode_data);
+
+ return -EIO;
+}
+
+/*
+ * find volume mounted (match by superblock) and remove
+ * debugfs dentry
+ */
+void hot_debugfs_volume_exit(struct super_block *sb)
+{
+ struct list_head *head;
+ struct list_head *pos;
+ struct debugfs_vol_data *data;
+
+ spin_lock(&hot_debugfs_data_list_lock);
+ head = &hot_debugfs_vol_data_list;
+ /* must clean up memory assicatied with superblock */
+ list_for_each(pos, head)
+ {
+ data = list_entry(pos, struct debugfs_vol_data, node);
+ if (data->sb == sb) {
+ list_del(pos);
+ debugfs_remove_recursive(data->de);
+ kfree(data);
+ data = NULL;
+ break;
+ }
+ }
+ spin_unlock(&hot_debugfs_data_list_lock);
+}
diff --git a/fs/hot_debugfs.h b/fs/hot_debugfs.h
new file mode 100644
index 0000000..977ad4c
--- /dev/null
+++ b/fs/hot_debugfs.h
@@ -0,0 +1,60 @@
+/*
+ * fs/debugfs.h
+ *
+ * Copyright (C) 2012 IBM Corp. All rights reserved.
+ * Written by Zhi Yong Wu <wu...@linux.vnet.ibm.com>
+ * Ben Chociej <bchoc...@gmail.com>
+ *
+ * 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_DEBUGFS__
+#define __HOT_DEBUGFS__
+
+#include <linux/fs.h>
+#include "hot_rb.h"
+#include "hot_hash.h"
+
+/* size of log to vmalloc */
+#define INIT_LOG_ALLOC_SIZE (PAGE_SIZE * 10)
+#define LOG_PAGE_SIZE (PAGE_SIZE * 10)
+
+/*
+ * number of chars of device name of chop off for making debugfs folder
+ * e.g. /dev/sda -> sda
+ *
+ * TODO: use something better for this
+ */
+#define DEV_NAME_CHOP 5
+
+/*
+ * Name for VFS data in debugfs directory
+ * e.g. /sys/kernel/debug/hot_track
+ */
+#define DEBUGFS_ROOT_NAME "hot_track"
+
+/* log to output to userspace in debugfs files */
+struct lstring {
+ char *str;
+ unsigned long len;
+};
+
+/* debugfs_vol_data is a struct of items that is passed to the debugfs */
+struct debugfs_vol_data {
+ struct list_head node; /* protected by data_list_lock */
+ struct lstring *debugfs_log;
+ struct super_block *sb;
+ struct dentry *de;
+ spinlock_t log_lock; /* protects debugfs_log */
+ char log_work_buff[1024];
+ uint log_alloc_size;
+};
+
+int hot_debugfs_init(void);
+void hot_debugfs_exit(void);
+int hot_debugfs_volume_init(const char *, struct super_block *);
+void hot_debugfs_volume_exit(struct super_block *);
+
+#endif /* __HOT_DEBUGFS__ */
diff --git a/fs/hot_track.c b/fs/hot_track.c
index be5bae4..ae113db 100644
--- a/fs/hot_track.c
+++ b/fs/hot_track.c
@@ -81,4 +81,5 @@ void hot_track_exit(struct super_block *sb)
sb->s_hotinfo.mount_opt &= ~HOT_MOUNT_HOT_TRACK;
hot_hash_free_heat_hash_list(&sb->s_hotinfo);
hot_rb_free_hot_inode_tree(&sb->s_hotinfo);
+ hot_debugfs_volume_exit(sb);
}
diff --git a/fs/hot_track.h b/fs/hot_track.h
index e137142..3cb5a01 100644
--- a/fs/hot_track.h
+++ b/fs/hot_track.h
@@ -13,8 +13,7 @@
#ifndef __HOT_TRACK__
#define __HOT_TRACK__
-#include "hot_rb.h"
-#include "hot_hash.h"
+#include "hot_debugfs.h"
bool hot_track_parse_options(char *options);
void __init hot_track_item_cache_init(void);
diff --git a/fs/namespace.c b/fs/namespace.c
index 90c958a..6843489 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2629,6 +2629,12 @@ void __init mnt_init(void)
fs_kobj = kobject_create_and_add("fs", NULL);
if (!fs_kobj)
printk(KERN_WARNING "%s: kobj create error\n", __func__);
+
+ err = hot_debugfs_init();
+ if (err)
+ printk(KERN_WARNING "%s: sysfs_init error: %d\n",
+ __func__, err);
+
init_rootfs();
init_mount_tree();
}
--
1.7.6.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
