[PATCH 2/2] vfs: Add a trace point in the mark_inode_dirty function

[amit.kucheria at canonical.com]

From: Arjan van de Ven <arjan at linux.intel.com>

PowerTOP would like to be able to show who is keeping the disk
busy by dirtying data. The most logical spot for this is in the vfs
in the mark_inode_dirty() function. Doing this on the block level
is not possible because by the time the IO hits the block layer the
guilty party can no longer be found ("kjournald" and "pdflush" are not
useful answers to "who caused this file to be dirty).

The trace point follows the same logic/style as the block_dump code
and pretty much dumps the same data, just not to dmesg (and thus to
/var/log/messages) but via the trace events streams.

Note: This patch was posted to lkml and might potentially go into 2.6.33 but I
have not seen which maintainer will take it.

Signed-of-by: Arjan van de Ven <arjan at linux.intel.com>
Signed-off-by: Amit Kucheria <amit.kucheria at canonical.com>
---
 fs/fs-writeback.c          |    3 ++
 fs/inode.c                 |    4 +++
 include/trace/events/vfs.h |   53 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 60 insertions(+), 0 deletions(-)
 create mode 100644 include/trace/events/vfs.h

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 9d5360c..4102f20 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -25,6 +25,7 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
+#include <trace/events/vfs.h>
 #include "internal.h"
 
 #define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
@@ -1071,6 +1072,8 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	if ((inode->i_state & flags) == flags)
 		return;
 
+	trace_dirty_inode(inode, current);
+
 	if (unlikely(block_dump))
 		block_dump___mark_inode_dirty(inode);
 
diff --git a/fs/inode.c b/fs/inode.c
index 4d8e3be..b89af38 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1624,3 +1624,7 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
 				  inode->i_ino);
 }
 EXPORT_SYMBOL(init_special_inode);
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/vfs.h>
+
diff --git a/include/trace/events/vfs.h b/include/trace/events/vfs.h
new file mode 100644
index 0000000..3c170f8
--- /dev/null
+++ b/include/trace/events/vfs.h
@@ -0,0 +1,53 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vfs
+
+#if !defined(_TRACE_VFS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_VFS_H
+
+/*
+ * Tracepoint for dirtying an inode:
+ */
+TRACE_EVENT(dirty_inode,
+
+	TP_PROTO(struct inode *inode, struct task_struct *task),
+
+	TP_ARGS(inode, task),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__array( char,  dev,    16		)
+		__array( char,  file,   32		)
+	),
+
+	TP_fast_assign(
+		if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
+			struct dentry *dentry;
+			const char *name = "?";
+
+			dentry = d_find_alias(inode);
+			if (dentry) {
+				spin_lock(&dentry->d_lock);
+				name = (const char *) dentry->d_name.name;
+			}
+
+			memcpy(__entry->comm, task->comm, TASK_COMM_LEN);
+			__entry->pid = task->pid;
+			strlcpy(__entry->file, name, 32);
+			strlcpy(__entry->dev, inode->i_sb->s_id, 16);
+
+			if (dentry) {
+				spin_unlock(&dentry->d_lock);
+				dput(dentry);
+			}
+		}
+	),
+
+	TP_printk("task=%i (%s) file=%s dev=%s",
+		__entry->pid, __entry->comm, __entry->file, __entry->dev)
+);
+
+#endif /* _TRACE_VFS_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
1.6.3.3