Re: Please, put 64-bit counter per task and incr.by.one each ctxt switch.

["J.C. Pizarro" <jcpiza@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 2436 bytes --]

On 2008/2/24, Rik van Riel <riel@redhat.com> wrote:
> On Sun, 24 Feb 2008 04:08:38 +0100
>  "J.C. Pizarro" <jcpiza@gmail.com> wrote:
>
>  > We will need 64 bit counters of the slow context switches,
>  >   one counter for each new created task (e.g. u64 ctxt_switch_counts;)
>
>
> Please send a patch ...

diff -ur linux-2.6_git-20080224.orig/include/linux/sched.h
linux-2.6_git-20080224/include/linux/sched.h
--- linux-2.6_git-20080224.orig/include/linux/sched.h   2008-02-24
01:04:18.000000000 +0100
+++ linux-2.6_git-20080224/include/linux/sched.h        2008-02-24
04:50:18.000000000 +0100
@@ -1007,6 +1007,12 @@
        struct hlist_head preempt_notifiers;
 #endif

+       unsigned long long ctxt_switch_counts; /* 64-bit switches' count */
+       /* ToDo:
+        *  To implement a poller/clock for CPU-scheduler that only reads
+        *   these counts of context switches of the runqueue's tasks.
+        *  No problem if this poller/clock is not implemented. */
+
        /*
         * fpu_counter contains the number of consecutive context switches
         * that the FPU is used. If this is over a threshold, the lazy fpu
diff -ur linux-2.6_git-20080224.orig/kernel/sched.c
linux-2.6_git-20080224/kernel/sched.c
--- linux-2.6_git-20080224.orig/kernel/sched.c  2008-02-24
01:04:19.000000000 +0100
+++ linux-2.6_git-20080224/kernel/sched.c       2008-02-24
04:33:57.000000000 +0100
@@ -2008,6 +2008,8 @@
        BUG_ON(p->state != TASK_RUNNING);
        update_rq_clock(rq);

+       p->ctxt_switch_counts = 0ULL; /* task's 64-bit counter inited 0 */
+
        p->prio = effective_prio(p);

        if (!p->sched_class->task_new || !current->se.on_rq) {
@@ -2189,8 +2191,14 @@
 context_switch(struct rq *rq, struct task_struct *prev,
               struct task_struct *next)
 {
+       unsigned long flags;
+       struct rq *rq_prev;
        struct mm_struct *mm, *oldmm;

+       rq_prev = task_rq_lock(prev, &flags); /* locking the prev task */
+       prev->ctxt_switch_counts++; /* incr.+1 the task's 64-bit counter */
+       task_rq_unlock(rq_prev, &flags); /* unlocking the prev task */
+
        prepare_task_switch(rq, prev, next);
        mm = next->mm;
        oldmm = prev->active_mm;

>  > I will explain your later why of it.
>
>
> ... and explain exactly why the kernel needs this extra code.

One reason: for the objective of gain interactivity, it's an issue that
 CFS fair scheduler lacks it.

    o:)

[-- Attachment #2: linux-2.6_git-20080224_ctxt_switch_counts.patch --]
[-- Type: application/octet-stream, Size: 1754 bytes --]

diff -ur linux-2.6_git-20080224.orig/include/linux/sched.h linux-2.6_git-20080224/include/linux/sched.h
--- linux-2.6_git-20080224.orig/include/linux/sched.h	2008-02-24 01:04:18.000000000 +0100
+++ linux-2.6_git-20080224/include/linux/sched.h	2008-02-24 04:50:18.000000000 +0100
@@ -1007,6 +1007,12 @@
 	struct hlist_head preempt_notifiers;
 #endif
 
+	unsigned long long ctxt_switch_counts; /* 64-bit switches' count */
+	/* ToDo:
+	 *  To implement a poller/clock for CPU-scheduler that only reads
+	 *   these counts of context switches of the runqueue's tasks.
+	 *  No problem if this poller/clock is not implemented. */
+	
 	/*
 	 * fpu_counter contains the number of consecutive context switches
 	 * that the FPU is used. If this is over a threshold, the lazy fpu
diff -ur linux-2.6_git-20080224.orig/kernel/sched.c linux-2.6_git-20080224/kernel/sched.c
--- linux-2.6_git-20080224.orig/kernel/sched.c	2008-02-24 01:04:19.000000000 +0100
+++ linux-2.6_git-20080224/kernel/sched.c	2008-02-24 04:33:57.000000000 +0100
@@ -2008,6 +2008,8 @@
 	BUG_ON(p->state != TASK_RUNNING);
 	update_rq_clock(rq);
 
+	p->ctxt_switch_counts = 0ULL; /* task's 64-bit counter inited 0 */
+	
 	p->prio = effective_prio(p);
 
 	if (!p->sched_class->task_new || !current->se.on_rq) {
@@ -2189,8 +2191,14 @@
 context_switch(struct rq *rq, struct task_struct *prev,
 	       struct task_struct *next)
 {
+	unsigned long flags;
+	struct rq *rq_prev;
 	struct mm_struct *mm, *oldmm;
 
+	rq_prev = task_rq_lock(prev, &flags); /* locking the prev task */
+	prev->ctxt_switch_counts++; /* incr.+1 the task's 64-bit counter */
+	task_rq_unlock(rq_prev, &flags); /* unlocking the prev task */
+	
 	prepare_task_switch(rq, prev, next);
 	mm = next->mm;
 	oldmm = prev->active_mm;