[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1493023382.6266.9.camel@gmx.de>
Date: Mon, 24 Apr 2017 10:43:02 +0200
From: Mike Galbraith <efault@....de>
To: paulmck@...ux.vnet.ibm.com
Cc: LKML <linux-kernel@...r.kernel.org>
Subject: Re: TREE_SRCU slows hotplug by factor ~16
On Mon, 2017-04-24 at 09:35 +0200, Mike Galbraith wrote:
> # tracer: nop
> #
> # entries-in-buffer/entries-written: 229332/229332 #P:8
> #
> # _-----=> irqs-off
> # / _----=> need-resched
> # | / _---=> hardirq/softirq
> # || / _--=> preempt-depth
> # ||| / delay
> # TASK-PID CPU# |||| TIMESTAMP FUNCTION
> # | | | |||| | |
> stress-cpu-hotp-2443 [004] .... 144.123608: synchronize_srcu: enter
> stress-cpu-hotp-2443 [004] .... 144.123610: call_srcu: enter
> stress-cpu-hotp-2443 [004] .... 144.123612: call_srcu: exit
> stress-cpu-hotp-2443 [005] .... 144.139528: synchronize_srcu: exit
I probably could have sent a LOT less trace.
classic:
# tracer: nop
#
# entries-in-buffer/entries-written: 114688/114688 #P:8
#
# _-----=> irqs-off
# / _----=> need-resched
# | / _---=> hardirq/softirq
# || / _--=> preempt-depth
# ||| / delay
# TASK-PID CPU# |||| TIMESTAMP FUNCTION
# | | | |||| | |
stress-cpu-hotp-4337 [007] .... 174.082801: synchronize_srcu: enter
stress-cpu-hotp-4337 [007] .... 174.082802: synchronize_srcu: exit
stress-cpu-hotp-4337 [007] .... 174.082896: synchronize_srcu: enter
stress-cpu-hotp-4337 [007] .... 174.082896: synchronize_srcu: exit
stress-cpu-hotp-4337 [007] .... 174.082975: synchronize_srcu: enter
stress-cpu-hotp-4337 [007] .... 174.082975: synchronize_srcu: exit
stress-cpu-hotp-4337 [007] .... 174.083051: synchronize_srcu: enter
stress-cpu-hotp-4337 [007] .... 174.083051: synchronize_srcu: exit
....
Powered by blists - more mailing lists