linux-kernel - Re: INFO: rcu_sched self-detected stall on CPU

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 4 Jan 2017 08:17:12 -0800
From:   "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
To:     Steven Rostedt <rostedt@...dmis.org>
Cc:     Enrico Mioso <mrkiko.rs@...il.com>, linux-kernel@...r.kernel.org,
        Josh Triplett <josh@...htriplett.org>,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Subject: Re: INFO: rcu_sched self-detected stall on CPU

On Wed, Jan 04, 2017 at 09:16:31AM -0500, Steven Rostedt wrote:
> On Wed, 4 Jan 2017 05:46:08 -0800
> "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com> wrote:
> 
> > I suggest enabling tracing for timers with a goal of working out why
> > the rcu_sched task is not being awakened regularly -- during a grace
> > period, it should be awakened every three jiffies or so (depending on
> > the value of HZ).
> 
> Perhaps enable events for rcu, sched and irqs as well?

Good point -- but you will need to build with CONFIG_RCU_TRACE=y
to get most of the RCU events.

							Thanx, Paul