From ca74e92b4698276b6696f15a801759f50944f387 Mon Sep 17 00:00:00 2001 From: Shailabh Nagar Date: Fri, 14 Jul 2006 00:24:36 -0700 Subject: [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 Signed-off-by: Balbir Singh Cc: Jes Sorensen Cc: Peter Chubb Cc: Erich Focht Cc: Levent Serinol Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1c876e27ff93..7a54e62763c5 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) -- cgit v1.2.2 From 0ff922452df86f3e9a2c6f705c4588ec62d096a7 Mon Sep 17 00:00:00 2001 From: Shailabh Nagar Date: Fri, 14 Jul 2006 00:24:37 -0700 Subject: [PATCH] per-task-delay-accounting: sync block I/O and swapin delay collection Unlike earlier iterations of the delay accounting patches, now delays are only collected for the actual I/O waits rather than try and cover the delays seen in I/O submission paths. Account separately for block I/O delays incurred as a result of swapin page faults whose frequency can be affected by the task/process' rss limit. Hence swapin delays can act as feedback for rss limit changes independent of I/O priority changes. Signed-off-by: Shailabh Nagar Signed-off-by: Balbir Singh Cc: Jes Sorensen Cc: Peter Chubb Cc: Erich Focht Cc: Levent Serinol Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 7a54e62763c5..2f43f1fb7de7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -566,6 +566,19 @@ struct task_delay_info { * Atomicity of updates to XXX_delay, XXX_count protected by * single lock above (split into XXX_lock if contention is an issue). */ + + /* + * XXX_count is incremented on every XXX operation, the delay + * associated with the operation is added to XXX_delay. + * XXX_delay contains the accumulated delay time in nanoseconds. + */ + struct timespec blkio_start, blkio_end; /* Shared by blkio, swapin */ + u64 blkio_delay; /* wait for sync block io completion */ + u64 swapin_delay; /* wait for swapin block io completion */ + u32 blkio_count; /* total count of the number of sync block */ + /* io operations performed */ + u32 swapin_count; /* total count of the number of swapin block */ + /* io operations performed */ }; #endif -- cgit v1.2.2 From 52f17b6c2bd443e7806a161e9d10a983650db01d Mon Sep 17 00:00:00 2001 From: Chandra Seetharaman Date: Fri, 14 Jul 2006 00:24:38 -0700 Subject: [PATCH] per-task-delay-accounting: cpu delay collection via schedstats Make the task-related schedstats functions callable by delay accounting even if schedstats collection isn't turned on. This removes the dependency of delay accounting on schedstats. Signed-off-by: Chandra Seetharaman Signed-off-by: Shailabh Nagar Signed-off-by: Balbir Singh Cc: Jes Sorensen Cc: Peter Chubb Cc: Erich Focht Cc: Levent Serinol Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2f43f1fb7de7..f751062d89a2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -537,7 +537,7 @@ extern struct user_struct root_user; struct backing_dev_info; struct reclaim_state; -#ifdef CONFIG_SCHEDSTATS +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info { /* cumulative counters */ unsigned long cpu_time, /* time spent on the cpu */ @@ -548,9 +548,11 @@ struct sched_info { unsigned long last_arrival, /* when we last ran on a cpu */ last_queued; /* when we were last queued to run */ }; +#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ +#ifdef CONFIG_SCHEDSTATS extern struct file_operations proc_schedstat_operations; -#endif +#endif /* CONFIG_SCHEDSTATS */ #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { @@ -580,7 +582,19 @@ struct task_delay_info { u32 swapin_count; /* total count of the number of swapin block */ /* io operations performed */ }; +#endif /* CONFIG_TASK_DELAY_ACCT */ + +static inline int sched_info_on(void) +{ +#ifdef CONFIG_SCHEDSTATS + return 1; +#elif defined(CONFIG_TASK_DELAY_ACCT) + extern int delayacct_on; + return delayacct_on; +#else + return 0; #endif +} enum idle_type { @@ -777,7 +791,7 @@ struct task_struct { cpumask_t cpus_allowed; unsigned int time_slice, first_time_slice; -#ifdef CONFIG_SCHEDSTATS +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; #endif -- cgit v1.2.2 From 6f44993fe1d7b2b097f6ac60cd5835c6f5ca0874 Mon Sep 17 00:00:00 2001 From: Shailabh Nagar Date: Fri, 14 Jul 2006 00:24:41 -0700 Subject: [PATCH] per-task-delay-accounting: delay accounting usage of taskstats interface Usage of taskstats interface by delay accounting. Signed-off-by: Shailabh Nagar Signed-off-by: Balbir Singh Cc: Jes Sorensen Cc: Peter Chubb Cc: Erich Focht Cc: Levent Serinol Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index f751062d89a2..3c5610ca0c92 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -990,6 +990,7 @@ struct task_struct { */ struct pipe_inode_info *splice_pipe; #ifdef CONFIG_TASK_DELAY_ACCT + spinlock_t delays_lock; struct task_delay_info *delays; #endif }; -- cgit v1.2.2 From ad4ecbcba72855a2b5319b96e2a3a65ed1ca3bfd Mon Sep 17 00:00:00 2001 From: Shailabh Nagar Date: Fri, 14 Jul 2006 00:24:44 -0700 Subject: [PATCH] delay accounting taskstats interface send tgid once Send per-tgid data only once during exit of a thread group instead of once with each member thread exit. Currently, when a thread exits, besides its per-tid data, the per-tgid data of its thread group is also sent out, if its thread group is non-empty. The per-tgid data sent consists of the sum of per-tid stats for all *remaining* threads of the thread group. This patch modifies this sending in two ways: - the per-tgid data is sent only when the last thread of a thread group exits. This cuts down heavily on the overhead of sending/receiving per-tgid data, especially when other exploiters of the taskstats interface aren't interested in per-tgid stats - the semantics of the per-tgid data sent are changed. Instead of being the sum of per-tid data for remaining threads, the value now sent is the true total accumalated statistics for all threads that are/were part of the thread group. The patch also addresses a minor issue where failure of one accounting subsystem to fill in the taskstats structure was causing the send of taskstats to not be sent at all. The patch has been tested for stability and run cerberus for over 4 hours on an SMP. [akpm@osdl.org: bugfixes] Signed-off-by: Shailabh Nagar Signed-off-by: Balbir Singh Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3c5610ca0c92..6afa72e080cb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -463,6 +463,10 @@ struct signal_struct { #ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct; /* per-process accounting information */ #endif +#ifdef CONFIG_TASKSTATS + spinlock_t stats_lock; + struct taskstats *stats; +#endif }; /* Context switch must be unlocked if interrupts are to be enabled */ -- cgit v1.2.2 From a7ef7878ea7c8bca9b624db3f61223cdadda2a0a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 5 Aug 2006 12:13:42 -0700 Subject: [PATCH] Make suspend possible with a traced process at a breakpoint It should be possible to suspend, either to RAM or to disk, if there's a traced process that has just reached a breakpoint. However, this is a special case, because its parent process might have been frozen already and then we are unable to deliver the "freeze" signal to the traced process. If this happens, it's better to cancel the freezing of the traced process. Ref. http://bugzilla.kernel.org/show_bug.cgi?id=6787 Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6afa72e080cb..6674fc1e51bf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1557,6 +1557,14 @@ static inline void freeze(struct task_struct *p) p->flags |= PF_FREEZE; } +/* + * Sometimes we may need to cancel the previous 'freeze' request + */ +static inline void do_not_freeze(struct task_struct *p) +{ + p->flags &= ~PF_FREEZE; +} + /* * Wake up a frozen process */ -- cgit v1.2.2