All of lore.kernel.org
 help / color / mirror / Atom feed
From: zwu.kernel@gmail.com
To: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, linux-btrfs@vger.kernel.org,
	linux-ext4@vger.kernel.org, linuxram@linux.vnet.ibm.com,
	viro@zeniv.linux.org.uk, cmm@us.ibm.com, tytso@mit.edu,
	marco.stornelli@gmail.com, david@fromorbit.com,
	stroetmann@ontolinux.com, diegocg@gmail.com, chris@csamuel.org,
	Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Subject: [RFC v2 08/10] vfs: add 3 new ioctl interfaces
Date: Sun, 23 Sep 2012 20:56:33 +0800	[thread overview]
Message-ID: <1348404995-14372-9-git-send-email-zwu.kernel@gmail.com> (raw)
In-Reply-To: <1348404995-14372-1-git-send-email-zwu.kernel@gmail.com>

From: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>

  FS_IOC_GET_HEAT_INFO: return a struct containing the various
metrics collected in btrfs_freq_data structs, and also return a
calculated data temperature based on those metrics. Optionally, retrieve
the temperature from the hot data hash list instead of recalculating it.

  FS_IOC_GET_HEAT_OPTS: return an integer representing the current
state of hot data tracking and migration:

0 = do nothing
1 = track frequency of access

  FS_IOC_SET_HEAT_OPTS: change the state of hot data tracking and
migration, as described above.

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 fs/compat_ioctl.c            |    8 +++
 fs/ioctl.c                   |  130 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h           |   11 ++++
 include/linux/hot_tracking.h |   12 ++++
 4 files changed, 161 insertions(+), 0 deletions(-)

diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index debdfe0..a88c7de 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1390,6 +1390,11 @@ COMPATIBLE_IOCTL(TIOCSTART)
 COMPATIBLE_IOCTL(TIOCSTOP)
 #endif
 
+/*Hot data tracking*/
+COMPATIBLE_IOCTL(FS_IOC_GET_HEAT_INFO)
+COMPATIBLE_IOCTL(FS_IOC_SET_HEAT_OPTS)
+COMPATIBLE_IOCTL(FS_IOC_GET_HEAT_OPTS)
+
 /* fat 'r' ioctls. These are handled by fat with ->compat_ioctl,
    but we don't want warnings on other file systems. So declare
    them as compatible here. */
@@ -1572,6 +1577,9 @@ asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
 	case FIBMAP:
 	case FIGETBSZ:
 	case FIONREAD:
+	case FS_IOC_GET_HEAT_INFO:
+	case FS_IOC_SET_HEAT_OPTS:
+	case FS_IOC_GET_HEAT_OPTS:
 		if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
 			break;
 		/*FALL THROUGH*/
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 29167be..394975e 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -15,6 +15,7 @@
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <linux/falloc.h>
+#include "hot_tracking.h"
 
 #include <asm/ioctls.h>
 
@@ -537,6 +538,126 @@ static int ioctl_fsthaw(struct file *filp)
 }
 
 /*
+ * Retrieve information about access frequency for the given file. Return it in
+ * a userspace-friendly struct for btrfsctl (or another tool) to parse.
+ *
+ * The temperature that is returned can be "live" -- that is, recalculated when
+ * the ioctl is called -- or it can be returned from the hashtable, reflecting
+ * the (possibly old) value that the system will use when considering files
+ * for migration. This behavior is determined by hot_heat_info->live.
+ */
+static int ioctl_heat_info(struct file *file, void __user *argp)
+{
+	struct inode *mnt_inode = file->f_path.dentry->d_inode;
+	struct inode *file_inode;
+	struct file *file_filp;
+	struct hot_info *root = &(mnt_inode->i_sb->s_hotinfo);
+	struct hot_heat_info *heat_info;
+	struct hot_inode_tree *hitree;
+	struct hot_inode_item *he;
+	int ret;
+
+	heat_info = kmalloc(sizeof(struct hot_heat_info),
+				GFP_KERNEL | GFP_NOFS);
+
+	if (copy_from_user((void *) heat_info,
+			argp,
+			sizeof(struct hot_heat_info)) != 0) {
+		ret = -EFAULT;
+		goto err;
+	}
+
+	file_filp = filp_open(heat_info->filename, O_RDONLY, 0);
+	file_inode = file_filp->f_dentry->d_inode;
+	filp_close(file_filp, NULL);
+
+	hitree = &root->hot_inode_tree;
+	read_lock(&hitree->lock);
+	he = hot_rb_lookup_hot_inode_item(hitree, file_inode->i_ino);
+	read_unlock(&hitree->lock);
+	if (!he) {
+		/* we don't have any info on this file yet */
+		ret = -ENODATA;
+		goto err;
+	}
+
+	spin_lock(&he->lock);
+	heat_info->avg_delta_reads =
+			(__u64) he->hot_freq_data.avg_delta_reads;
+	heat_info->avg_delta_writes =
+			(__u64) he->hot_freq_data.avg_delta_writes;
+	heat_info->last_read_time =
+			(__u64) timespec_to_ns(&he->hot_freq_data.last_read_time);
+	heat_info->last_write_time =
+			(__u64) timespec_to_ns(&he->hot_freq_data.last_write_time);
+	heat_info->num_reads =
+			(__u32) he->hot_freq_data.nr_reads;
+	heat_info->num_writes =
+			(__u32) he->hot_freq_data.nr_writes;
+
+	if (heat_info->live > 0) {
+		/* got a request for live temperature,
+		 * call hot_hash_calc_temperature to recalculate
+		 */
+		heat_info->temperature =
+			hot_hash_calc_temperature(&he->hot_freq_data);
+	} else {
+		/* not live temperature, get it from the hashlist */
+		read_lock(&he->heat_node->hlist->rwlock);
+		heat_info->temperature = he->heat_node->hlist->temperature;
+		read_unlock(&he->heat_node->hlist->rwlock);
+	}
+	spin_unlock(&he->lock);
+
+	hot_rb_free_hot_inode_item(he);
+
+	if (copy_to_user(argp, (void *) heat_info,
+			sizeof(struct hot_heat_info))) {
+		ret = -EFAULT;
+		goto err;
+	}
+
+	kfree(heat_info);
+	return 0;
+
+err:
+	kfree(heat_info);
+	return ret;
+}
+
+static int ioctl_heat_opts(struct file *file, void __user *argp, int set)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	int arg, ret = 0;
+
+	if (!set) {
+		arg = TRACK_THIS_INODE(inode) ? 1 : 0;
+
+		if (copy_to_user(argp, (void *) &arg, sizeof(int)) != 0)
+			ret = -EFAULT;
+	} else {
+		if (copy_from_user((void *) &arg, argp, sizeof(int)) != 0) {
+			ret = -EFAULT;
+		} else {
+			switch (arg) {
+			case 0: /* track nothing */
+				/* set S_NOHOTDATATRACK */
+				inode->i_flags |= S_NOHOTDATATRACK;
+				break;
+			case 1: /* do tracking */
+				/* clear S_NOHOTDATATRACK */
+				inode->i_flags &= ~S_NOHOTDATATRACK;
+				break;
+			default:
+				ret = -EINVAL;
+			}
+		}
+	}
+
+	return ret;
+}
+
+/*
  * When you add any new common ioctls to the switches above and below
  * please update compat_sys_ioctl() too.
  *
@@ -591,6 +712,15 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 	case FIGETBSZ:
 		return put_user(inode->i_sb->s_blocksize, argp);
 
+	case FS_IOC_GET_HEAT_INFO:
+		return ioctl_heat_info(filp, argp);
+
+	case FS_IOC_SET_HEAT_OPTS:
+		return ioctl_heat_opts(filp, argp, 1);
+
+	case FS_IOC_GET_HEAT_OPTS:
+		return ioctl_heat_opts(filp, argp, 0);
+
 	default:
 		if (S_ISREG(inode->i_mode))
 			error = file_ioctl(filp, cmd, arg);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index db1a144..277791f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -256,6 +256,7 @@ struct inodes_stat_t {
 #define S_IMA		1024	/* Inode has an associated IMA struct */
 #define S_AUTOMOUNT	2048	/* Automount/referral quasi-directory */
 #define S_NOSEC		4096	/* no suid or xattr security attributes */
+#define S_NOHOTDATATRACK (1 << 13)	/* hot data tracking */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
@@ -354,6 +355,16 @@ struct inodes_stat_t {
 #define FS_IOC32_SETVERSION		_IOW('v', 2, int)
 
 /*
+ * Hot data tracking ioctls:
+ *
+ * HOT_INFO - retrieve info on frequency of access
+ */
+#define FS_IOC_GET_HEAT_INFO _IOR('f', 17, \
+				struct hot_heat_info)
+#define FS_IOC_SET_HEAT_OPTS _IOW('f', 18, int)
+#define FS_IOC_GET_HEAT_OPTS _IOR('f', 19, int)
+
+/*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
  */
 #define	FS_SECRM_FL			0x00000001 /* Secure deletion */
diff --git a/include/linux/hot_tracking.h b/include/linux/hot_tracking.h
index 1ec90a6..b0a2705 100644
--- a/include/linux/hot_tracking.h
+++ b/include/linux/hot_tracking.h
@@ -63,6 +63,18 @@ struct hot_freq_data {
 	u32 last_temperature;
 };
 
+struct hot_heat_info {
+	__u64 avg_delta_reads;
+	__u64 avg_delta_writes;
+	__u64 last_read_time;
+	__u64 last_write_time;
+	__u32 num_reads;
+	__u32 num_writes;
+	__u32 temperature;
+	__u8 live;
+	char filename[PATH_MAX];
+};
+
 /* Hash list heads for hot hash table */
 struct hot_hash_head {
 	struct hlist_head hashhead;
-- 
1.7.6.5


  parent reply	other threads:[~2012-09-23 12:57 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-09-23 12:56 [RFC v2 00/10] vfs: hot data tracking zwu.kernel
2012-09-23 12:56 ` [RFC v2 01/10] vfs: introduce private rb structures zwu.kernel
2012-09-25  7:37   ` Dave Chinner
2012-09-25  7:57     ` Zhi Yong Wu
2012-09-25  8:00     ` Zhi Yong Wu
2012-09-25 10:20   ` Ram Pai
2012-09-26  3:20     ` Zhi Yong Wu
2012-09-23 12:56 ` [RFC v2 02/10] vfs: add support for updating access frequency zwu.kernel
2012-09-25  9:17   ` Dave Chinner
2012-09-26  2:53     ` Zhi Yong Wu
2012-09-27  2:19       ` Dave Chinner
2012-09-27  2:30         ` Zhi Yong Wu
2012-09-23 12:56 ` [RFC v2 03/10] vfs: add one new mount option '-o hottrack' zwu.kernel
2012-09-25  9:28   ` Dave Chinner
2012-09-26  2:56     ` Zhi Yong Wu
2012-09-27  2:20       ` Dave Chinner
2012-09-27  2:30         ` Zhi Yong Wu
2012-09-27  5:25     ` Zhi Yong Wu
2012-09-27  7:05       ` Dave Chinner
2012-09-27  7:21         ` Zhi Yong Wu
2012-09-23 12:56 ` [RFC v2 04/10] vfs: add init and exit support zwu.kernel
2012-09-27  2:27   ` Dave Chinner
2012-09-23 12:56 ` [RFC v2 05/10] vfs: introduce one hash table zwu.kernel
2012-09-25  9:54   ` Ram Pai
2012-09-26  4:08     ` Zhi Yong Wu
2012-09-27  3:43   ` Dave Chinner
2012-09-27  6:23     ` Zhi Yong Wu
2012-09-27  6:57       ` Dave Chinner
2012-09-27  7:10         ` Zhi Yong Wu
2012-09-23 12:56 ` [RFC v2 06/10] vfs: enable hot data tracking zwu.kernel
2012-09-27  3:54   ` Dave Chinner
2012-09-27  6:28     ` Zhi Yong Wu
2012-09-27  6:59       ` Dave Chinner
2012-09-27  7:12         ` Zhi Yong Wu
2012-09-23 12:56 ` [RFC v2 07/10] vfs: fork one kthread to update data temperature zwu.kernel
2012-09-27  4:03   ` Dave Chinner
2012-09-27  6:54     ` Zhi Yong Wu
2012-09-27  7:01       ` Dave Chinner
2012-09-27  7:19         ` Zhi Yong Wu
2012-09-23 12:56 ` zwu.kernel [this message]
2012-09-23 12:56 ` [RFC v2 09/10] vfs: add debugfs support zwu.kernel
2012-09-23 12:56 ` [RFC v2 10/10] vfs: add documentation zwu.kernel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1348404995-14372-9-git-send-email-zwu.kernel@gmail.com \
    --to=zwu.kernel@gmail.com \
    --cc=chris@csamuel.org \
    --cc=cmm@us.ibm.com \
    --cc=david@fromorbit.com \
    --cc=diegocg@gmail.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxram@linux.vnet.ibm.com \
    --cc=marco.stornelli@gmail.com \
    --cc=stroetmann@ontolinux.com \
    --cc=tytso@mit.edu \
    --cc=viro@zeniv.linux.org.uk \
    --cc=wuzhy@linux.vnet.ibm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.