Re: [PATCH v8 0/6] rcu: Add RCU stall diagnosis information

From: Paul E. McKenney
Date: Tue Nov 22 2022 - 19:27:22 EST


On Tue, Nov 22, 2022 at 12:59:28PM +0100, Frederic Weisbecker wrote:
> On Sat, Nov 19, 2022 at 05:25:02PM +0800, Zhen Lei wrote:
> > v7 --> v8:
> > 1. Change call jiffies64_to_msecs() to call jiffies_to_msecs().
> > 2. Mention that rcupdate.rcu_cpu_stall_cputime overrides
> > CONFIG_RCU_CPU_STALL_CPUTIME behaviour in the Kconfig help text.
> > 3. Fix a make htmldocs warning, change "|...|" to ":...:".
> >
> > v6 --> v7:
> > 1. Use kcpustat_field() to obtain the cputime.
> > 2. Make the output start with "\t" to match other related prints.
> > 3. Aligns the output of the last line of RCU stall.
> >
> > v5 --> v6:
> > 1. When there are more than two continuous RCU stallings, correctly handle the
> > value of the second and subsequent sampling periods. Update comments and
> > document.
> > Thanks to Elliott, Robert for the test.
> > 2. Change "rcu stall" to "RCU stall".
> >
> > v4 --> v5:
> > 1. Resolve a git am conflict. No code change.
> >
> > v3 --> v4:
> > 1. Rename rcu_cpu_stall_deep_debug to rcu_cpu_stall_cputime.
> >
> > v2 --> v3:
> > 1. Fix the return type of kstat_cpu_irqs_sum()
> > 2. Add Kconfig option CONFIG_RCU_CPU_STALL_DEEP_DEBUG and boot parameter
> > rcupdate.rcu_cpu_stall_deep_debug.
> > 3. Add comments and normalize local variable name
> >
> > v1 --> v2:
> > 1. Fixed a bug in the code. If the rcu stall is detected by another CPU,
> > kcpustat_this_cpu cannot be used.
> > @@ -451,7 +451,7 @@ static void print_cpu_stat_info(int cpu)
> > if (r->gp_seq != rdp->gp_seq)
> > return;
> >
> > - cpustat = kcpustat_this_cpu->cpustat;
> > + cpustat = kcpustat_cpu(cpu).cpustat;
> > 2. Move the start point of statistics from rcu_stall_kick_kthreads() to
> > rcu_implicit_dynticks_qs(), removing the dependency on irq_work.
> >
> > v1:
> > In some extreme cases, such as the I/O pressure test, the CPU usage may
> > be 100%, causing RCU stall. In this case, the printed information about
> > current is not useful. Displays the number and usage of hard interrupts,
> > soft interrupts, and context switches that are generated within half of
> > the CPU stall timeout, can help us make a general judgment. In other
> > cases, we can preliminarily determine whether an infinite loop occurs
> > when local_irq, local_bh or preempt is disabled.
> >
> > Zhen Lei (6):
> > genirq: Fix the return type of kstat_cpu_irqs_sum()
> > sched: Add helper kstat_cpu_softirqs_sum()
> > sched: Add helper nr_context_switches_cpu()
> > rcu: Add RCU stall diagnosis information
> > doc: Document CONFIG_RCU_CPU_STALL_CPUTIME=y stall information
> > rcu: Align the output of RCU stall
>
> Reviewed-by: Frederic Weisbecker <frederic@xxxxxxxxxx>

Applied, thank you!

Thanx, Paul

> Thanks!
>
> >
> > Documentation/RCU/stallwarn.rst | 88 +++++++++++++++++++
> > .../admin-guide/kernel-parameters.txt | 6 ++
> > include/linux/kernel_stat.h | 14 ++-
> > kernel/rcu/Kconfig.debug | 13 +++
> > kernel/rcu/rcu.h | 1 +
> > kernel/rcu/tree.c | 18 ++++
> > kernel/rcu/tree.h | 19 ++++
> > kernel/rcu/tree_stall.h | 35 +++++++-
> > kernel/rcu/update.c | 2 +
> > kernel/sched/core.c | 5 ++
> > 10 files changed, 198 insertions(+), 3 deletions(-)
> >
> > --
> > 2.25.1
> >