Re: [PATCH 1/1] sched/cputime: do not decrease steal time after live migration on xen

["Jan Beulich" <JBeulich@suse.com>]

>>> On 10.10.17 at 11:14, <dongli.zhang@oracle.com> wrote:
> --- a/kernel/sched/cputime.c
> +++ b/kernel/sched/cputime.c
> @@ -238,10 +238,17 @@ static __always_inline u64 steal_account_process_time(u64 maxtime)
>  {
>  #ifdef CONFIG_PARAVIRT
>  	if (static_key_false(&paravirt_steal_enabled)) {
> -		u64 steal;
> +		u64 steal, steal_time;
> +		s64 steal_delta;
> +
> +		steal_time = paravirt_steal_clock(smp_processor_id());
> +		steal = steal_delta = steal_time - this_rq()->prev_steal_time;
> +
> +		if (unlikely(steal_delta < 0)) {
> +			this_rq()->prev_steal_time = steal_time;
> +			return 0;
> +		}
>  
> -		steal = paravirt_steal_clock(smp_processor_id());
> -		steal -= this_rq()->prev_steal_time;
>  		steal = min(steal, maxtime);
>  		account_steal_time(steal);
>  		this_rq()->prev_steal_time += steal;

While I can see this making the issue less pronounced, I don't see
how it fully addresses it: Why would only a negative delta represent
a discontinuity? In our old XenoLinux derived kernel we had the
change below (unlikely to be upstreamable as is, so just to give you
an idea).

Jan

--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -112,6 +112,47 @@ static inline void task_group_account_fi
 	cpuacct_account_field(p, index, tmp);
 }
 
+#if !defined(CONFIG_XEN) || defined(CONFIG_VIRT_CPU_ACCOUNTING)
+# define _cputime_adjust(t) (t)
+#else
+# include <linux/syscore_ops.h>
+# define NS_PER_TICK (1000000000 / HZ)
+
+static DEFINE_PER_CPU(u64, steal_snapshot);
+static DEFINE_PER_CPU(unsigned int, steal_residual);
+
+static u64 _cputime_adjust(u64 t)
+{
+	u64 s = this_vcpu_read(runstate.time[RUNSTATE_runnable]);
+	unsigned long adj = div_u64_rem(s - __this_cpu_read(steal_snapshot)
+					  + __this_cpu_read(steal_residual),
+					NS_PER_TICK,
+					this_cpu_ptr(&steal_residual));
+
+	__this_cpu_write(steal_snapshot, s);
+	if (t < jiffies_to_nsecs(adj))
+		return 0;
+
+	return t - jiffies_to_nsecs(adj);
+}
+
+static void steal_resume(void)
+{
+	_cputime_adjust((1ULL << 63) - 1);
+}
+
+static struct syscore_ops steal_syscore_ops = {
+	.resume	= steal_resume,
+};
+
+static int __init steal_register(void)
+{
+	register_syscore_ops(&steal_syscore_ops);
+	return 0;
+}
+core_initcall(steal_register);
+#endif
+
 /*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
@@ -128,7 +169,7 @@ void account_user_time(struct task_struc
 	index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
 
 	/* Add user time to cpustat. */
-	task_group_account_field(p, index, cputime);
+	task_group_account_field(p, index, _cputime_adjust(cputime));
 
 	/* Account for user time used */
 	acct_account_cputime(p);
@@ -172,7 +213,7 @@ void account_system_index_time(struct ta
 	account_group_system_time(p, cputime);
 
 	/* Add system time to cpustat. */
-	task_group_account_field(p, index, cputime);
+	task_group_account_field(p, index, _cputime_adjust(cputime));
 
 	/* Account for system time used */
 	acct_account_cputime(p);
@@ -224,9 +265,9 @@ void account_idle_time(u64 cputime)
 	struct rq *rq = this_rq();
 
 	if (atomic_read(&rq->nr_iowait) > 0)
-		cpustat[CPUTIME_IOWAIT] += cputime;
+		cpustat[CPUTIME_IOWAIT] += _cputime_adjust(cputime);
 	else
-		cpustat[CPUTIME_IDLE] += cputime;
+		cpustat[CPUTIME_IDLE] += _cputime_adjust(cputime);
 }
 
 /*





_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel