Re: Can RCU stall lead to hard lockups?

2018-02-06 Thread Paul E. McKenney
On Tue, Feb 06, 2018 at 08:55:04PM -0600, Serge E. Hallyn wrote: > On Tue, Feb 06, 2018 at 06:53:37PM -0800, Paul E. McKenney wrote: > > On Tue, Feb 06, 2018 at 08:33:03PM -0600, Serge E. Hallyn wrote: > > > On Sat, Feb 03, 2018 at 12:50:32PM -0800, Paul E. McKenney wrote: > > > > On Fri, Feb 02, 2

Re: Can RCU stall lead to hard lockups?

2018-02-06 Thread Serge E. Hallyn
On Tue, Feb 06, 2018 at 06:53:37PM -0800, Paul E. McKenney wrote: > On Tue, Feb 06, 2018 at 08:33:03PM -0600, Serge E. Hallyn wrote: > > On Sat, Feb 03, 2018 at 12:50:32PM -0800, Paul E. McKenney wrote: > > > On Fri, Feb 02, 2018 at 05:44:30PM -0600, Serge E. Hallyn wrote: > > > > Quoting Paul E. M

Re: Can RCU stall lead to hard lockups?

2018-02-06 Thread Paul E. McKenney
On Tue, Feb 06, 2018 at 08:33:03PM -0600, Serge E. Hallyn wrote: > On Sat, Feb 03, 2018 at 12:50:32PM -0800, Paul E. McKenney wrote: > > On Fri, Feb 02, 2018 at 05:44:30PM -0600, Serge E. Hallyn wrote: > > > Quoting Paul E. McKenney (paul...@linux.vnet.ibm.com): > > > > On Tue, Jan 09, 2018 at 06:1

Re: Can RCU stall lead to hard lockups?

2018-02-06 Thread Serge E. Hallyn
On Sat, Feb 03, 2018 at 12:50:32PM -0800, Paul E. McKenney wrote: > On Fri, Feb 02, 2018 at 05:44:30PM -0600, Serge E. Hallyn wrote: > > Quoting Paul E. McKenney (paul...@linux.vnet.ibm.com): > > > On Tue, Jan 09, 2018 at 06:11:14AM -0800, Tejun Heo wrote: > > > > Hello, Paul. > > > > > > > > On M

Re: Can RCU stall lead to hard lockups?

2018-02-03 Thread Paul E. McKenney
On Fri, Feb 02, 2018 at 05:44:30PM -0600, Serge E. Hallyn wrote: > Quoting Paul E. McKenney (paul...@linux.vnet.ibm.com): > > On Tue, Jan 09, 2018 at 06:11:14AM -0800, Tejun Heo wrote: > > > Hello, Paul. > > > > > > On Mon, Jan 08, 2018 at 08:24:25PM -0800, Paul E. McKenney wrote: > > > > > I don'

Re: Can RCU stall lead to hard lockups?

2018-02-02 Thread Serge E. Hallyn
Quoting Paul E. McKenney (paul...@linux.vnet.ibm.com): > On Tue, Jan 09, 2018 at 06:11:14AM -0800, Tejun Heo wrote: > > Hello, Paul. > > > > On Mon, Jan 08, 2018 at 08:24:25PM -0800, Paul E. McKenney wrote: > > > > I don't know the RCU code at all but it *looks* like the first CPU is > > > > takin

Re: Can RCU stall lead to hard lockups?

2018-01-09 Thread Paul E. McKenney
On Tue, Jan 09, 2018 at 06:11:14AM -0800, Tejun Heo wrote: > Hello, Paul. > > On Mon, Jan 08, 2018 at 08:24:25PM -0800, Paul E. McKenney wrote: > > > I don't know the RCU code at all but it *looks* like the first CPU is > > > taking a sweet while flushing printk buffer while holding a lock (the >

Re: Can RCU stall lead to hard lockups?

2018-01-09 Thread Tejun Heo
Hello, Paul. On Mon, Jan 08, 2018 at 08:24:25PM -0800, Paul E. McKenney wrote: > > I don't know the RCU code at all but it *looks* like the first CPU is > > taking a sweet while flushing printk buffer while holding a lock (the > > console is IPMI serial console, which faithfully emulates 115200 ba

Re: Can RCU stall lead to hard lockups?

2018-01-08 Thread Paul E. McKenney
On Mon, Jan 08, 2018 at 07:52:07PM -0800, Tejun Heo wrote: > Hello, Paul. > > So, I was looking at a machine which triggered crashdump from NMI hard > lockup. The dmesg was filled up with backtraces - many were stuck in > reclaim path, which seems to be the culprit, the others were stuck in > RCU

Can RCU stall lead to hard lockups?

2018-01-08 Thread Tejun Heo
Hello, Paul. So, I was looking at a machine which triggered crashdump from NMI hard lockup. The dmesg was filled up with backtraces - many were stuck in reclaim path, which seems to be the culprit, the others were stuck in RCU path. It looks like by the time crashdump was created, all CPUs got s