[PATCH] per-task-delay-accounting: setup

Initialization code related to collection of per-task "delay" statistics which
measure how long it had to wait for cpu, sync block io, swapping etc.  The
collection of statistics and the interface are in other patches.  This patch
sets up the data structures and allows the statistics collection to be
disabled through a kernel boot parameter.

Signed-off-by: Shailabh Nagar <nagar@watson.ibm.com>
Signed-off-by: Balbir Singh <balbir@in.ibm.com>
Cc: Jes Sorensen <jes@sgi.com>
Cc: Peter Chubb <peterc@gelato.unsw.edu.au>
Cc: Erich Focht <efocht@ess.nec.de>
Cc: Levent Serinol <lserinol@gmail.com>
Cc: Jay Lan <jlan@engr.sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

10 files changed, 207 insertions, 0 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 149f62b..e11f772 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -448,6 +448,8 @@ running once the system is up.
 			Format: <area>[,<node>]
 			See also Documentation/networking/decnet.txt.
 
+	delayacct	[KNL] Enable per-task delay accounting
+
 	dhash_entries=	[KNL]
 			Set number of hash buckets for dentry cache.
 
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
new file mode 100644
index 0000000..9572cfa
--- /dev/null
+++ b/include/linux/delayacct.h
@@ -0,0 +1,69 @@
+/* delayacct.h - per-task delay accounting
+ *
+ * Copyright (C) Shailabh Nagar, IBM Corp. 2006
+ *
+ * This program is free software;  you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY;  without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
+ * the GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_DELAYACCT_H
+#define _LINUX_DELAYACCT_H
+
+#include <linux/sched.h>
+
+#ifdef CONFIG_TASK_DELAY_ACCT
+
+extern int delayacct_on;	/* Delay accounting turned on/off */
+extern kmem_cache_t *delayacct_cache;
+extern void delayacct_init(void);
+extern void __delayacct_tsk_init(struct task_struct *);
+extern void __delayacct_tsk_exit(struct task_struct *);
+
+static inline void delayacct_set_flag(int flag)
+{
+	if (current->delays)
+		current->delays->flags |= flag;
+}
+
+static inline void delayacct_clear_flag(int flag)
+{
+	if (current->delays)
+		current->delays->flags &= ~flag;
+}
+
+static inline void delayacct_tsk_init(struct task_struct *tsk)
+{
+	/* reinitialize in case parent's non-null pointer was dup'ed*/
+	tsk->delays = NULL;
+	if (unlikely(delayacct_on))
+		__delayacct_tsk_init(tsk);
+}
+
+static inline void delayacct_tsk_exit(struct task_struct *tsk)
+{
+	if (tsk->delays)
+		__delayacct_tsk_exit(tsk);
+}
+
+#else
+static inline void delayacct_set_flag(int flag)
+{}
+static inline void delayacct_clear_flag(int flag)
+{}
+static inline void delayacct_init(void)
+{}
+static inline void delayacct_tsk_init(struct task_struct *tsk)
+{}
+static inline void delayacct_tsk_exit(struct task_struct *tsk)
+{}
+#endif /* CONFIG_TASK_DELAY_ACCT */
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1c876e2..7a54e62 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -552,6 +552,23 @@ struct sched_info {
 extern struct file_operations proc_schedstat_operations;
 #endif
 
+#ifdef CONFIG_TASK_DELAY_ACCT
+struct task_delay_info {
+	spinlock_t	lock;
+	unsigned int	flags;	/* Private per-task flags */
+
+	/* For each stat XXX, add following, aligned appropriately
+	 *
+	 * struct timespec XXX_start, XXX_end;
+	 * u64 XXX_delay;
+	 * u32 XXX_count;
+	 *
+	 * Atomicity of updates to XXX_delay, XXX_count protected by
+	 * single lock above (split into XXX_lock if contention is an issue).
+	 */
+};
+#endif
+
 enum idle_type
 {
 	SCHED_IDLE,
@@ -945,6 +962,9 @@ struct task_struct {
 	 * cache last used pipe for splice
 	 */
 	struct pipe_inode_info *splice_pipe;
+#ifdef	CONFIG_TASK_DELAY_ACCT
+	struct task_delay_info *delays;
+#endif
 };
 
 static inline pid_t process_group(struct task_struct *tsk)
diff --git a/include/linux/time.h b/include/linux/time.h
index c05f8bb..a5b7399 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -71,6 +71,18 @@ extern unsigned long mktime(const unsigned int year, const unsigned int mon,
 extern void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec);
 
 /*
+ * sub = lhs - rhs, in normalized form
+ */
+static inline struct timespec timespec_sub(struct timespec lhs,
+						struct timespec rhs)
+{
+	struct timespec ts_delta;
+	set_normalized_timespec(&ts_delta, lhs.tv_sec - rhs.tv_sec,
+				lhs.tv_nsec - rhs.tv_nsec);
+	return ts_delta;
+}
+
+/*
  * Returns true if the timespec is norm, false if denorm:
  */
 #define timespec_valid(ts) \
diff --git a/init/Kconfig b/init/Kconfig
index a5b073a..90498a3 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -158,6 +158,16 @@ config BSD_PROCESS_ACCT_V3
 	  for processing it. A preliminary version of these tools is available
 	  at <http://www.physik3.uni-rostock.de/tim/kernel/utils/acct/>.
 
+config TASK_DELAY_ACCT
+	bool "Enable per-task delay accounting (EXPERIMENTAL)"
+	help
+	  Collect information on time spent by a task waiting for system
+	  resources like cpu, synchronous block I/O completion and swapping
+	  in pages. Such statistics can help in setting a task's priorities
+	  relative to other tasks for cpu, io, rss limits etc.
+
+	  Say N if unsure.
+
 config SYSCTL
 	bool "Sysctl support" if EMBEDDED
 	default y
diff --git a/init/main.c b/init/main.c
index 628b8e9..9e8e8c1 100644
--- a/init/main.c
+++ b/init/main.c
@@ -41,6 +41,7 @@
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/efi.h>
+#include <linux/delayacct.h>
 #include <linux/unistd.h>
 #include <linux/rmap.h>
 #include <linux/mempolicy.h>
@@ -574,6 +575,7 @@ asmlinkage void __init start_kernel(void)
 	proc_root_init();
 #endif
 	cpuset_init();
+	delayacct_init();
 
 	check_bugs();
 
diff --git a/kernel/Makefile b/kernel/Makefile
index 47dbcd5..87bb34c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_RELAY) += relay.o
+obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
new file mode 100644
index 0000000..fbf7f22
--- /dev/null
+++ b/kernel/delayacct.c
@@ -0,0 +1,87 @@
+/* delayacct.c - per-task delay accounting
+ *
+ * Copyright (C) Shailabh Nagar, IBM Corp. 2006
+ *
+ * This program is free software;  you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU General Public License for more details.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/sysctl.h>
+#include <linux/delayacct.h>
+
+int delayacct_on __read_mostly;	/* Delay accounting turned on/off */
+kmem_cache_t *delayacct_cache;
+
+static int __init delayacct_setup_enable(char *str)
+{
+	delayacct_on = 1;
+	return 1;
+}
+__setup("delayacct", delayacct_setup_enable);
+
+void delayacct_init(void)
+{
+	delayacct_cache = kmem_cache_create("delayacct_cache",
+					sizeof(struct task_delay_info),
+					0,
+					SLAB_PANIC,
+					NULL, NULL);
+	delayacct_tsk_init(&init_task);
+}
+
+void __delayacct_tsk_init(struct task_struct *tsk)
+{
+	tsk->delays = kmem_cache_zalloc(delayacct_cache, SLAB_KERNEL);
+	if (tsk->delays)
+		spin_lock_init(&tsk->delays->lock);
+}
+
+void __delayacct_tsk_exit(struct task_struct *tsk)
+{
+	kmem_cache_free(delayacct_cache, tsk->delays);
+	tsk->delays = NULL;
+}
+
+/*
+ * Start accounting for a delay statistic using
+ * its starting timestamp (@start)
+ */
+
+static inline void delayacct_start(struct timespec *start)
+{
+	do_posix_clock_monotonic_gettime(start);
+}
+
+/*
+ * Finish delay accounting for a statistic using
+ * its timestamps (@start, @end), accumalator (@total) and @count
+ */
+
+static void delayacct_end(struct timespec *start, struct timespec *end,
+				u64 *total, u32 *count)
+{
+	struct timespec ts;
+	s64 ns;
+
+	do_posix_clock_monotonic_gettime(end);
+	ts = timespec_sub(*end, *start);
+	ns = timespec_to_ns(&ts);
+	if (ns < 0)
+		return;
+
+	spin_lock(&current->delays->lock);
+	*total += ns;
+	(*count)++;
+	spin_unlock(&current->delays->lock);
+}
+
diff --git a/kernel/exit.c b/kernel/exit.c
index 6664c08..3c2cf91 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -25,6 +25,7 @@
 #include <linux/mount.h>
 #include <linux/proc_fs.h>
 #include <linux/mempolicy.h>
+#include <linux/delayacct.h>
 #include <linux/cpuset.h>
 #include <linux/syscalls.h>
 #include <linux/signal.h>
@@ -900,6 +901,7 @@ fastcall NORET_TYPE void do_exit(long code)
 #endif
 	if (unlikely(tsk->audit_context))
 		audit_free(tsk);
+	delayacct_tsk_exit(tsk);
 	exit_mm(tsk);
 
 	if (group_dead)
diff --git a/kernel/fork.c b/kernel/fork.c
index 926e5a6..451cfd3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -43,6 +43,7 @@
 #include <linux/rmap.h>
 #include <linux/acct.h>
 #include <linux/cn_proc.h>
+#include <linux/delayacct.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -1000,6 +1001,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_put_domain;
 
 	p->did_exec = 0;
+	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
 	copy_flags(clone_flags, p);
 	p->pid = pid;
 	retval = -EFAULT;