I haven't looked into the commit yet, but the bisect ended at:
0e576acbc1d9600cf2d9b4a141a2554639959d50 is the first bad commit
commit 0e576acbc1d9600cf2d9b4a141a2554639959d50
Author: Thomas Gleixner <email address hidden>
Date: Fri Nov 29 12:18:13 2013 +0100
nohz: Fix another inconsistency between CONFIG_NO_HZ=n and nohz=off
If CONFIG_NO_HZ=n tick_nohz_get_sleep_length() returns NSEC_PER_SEC/HZ.
If CONFIG_NO_HZ=y and the nohz functionality is disabled via the
command line option "nohz=off" or not enabled due to missing hardware
support, then tick_nohz_get_sleep_length() returns 0. That happens
because ts->sleep_length is never set in that case.
Set it to NSEC_PER_SEC/HZ when the NOHZ mode is inactive.
Reported-by: Michal Hocko <email address hidden>
Reported-by: Borislav Petkov <email address hidden>
Signed-off-by: Thomas Gleixner <email address hidden>
:040000 040000 e98d34fcc56a28e516d6282265f2de29bc0f4ad6 ec91edd6b6c6548dc58410a052c5fbc59f12690b M kernel
I haven't looked into the commit yet, but the bisect ended at:
0e576acbc1d9600 cf2d9b4a141a255 4639959d50 is the first bad commit cf2d9b4a141a255 4639959d50
commit 0e576acbc1d9600
Author: Thomas Gleixner <email address hidden>
Date: Fri Nov 29 12:18:13 2013 +0100
nohz: Fix another inconsistency between CONFIG_NO_HZ=n and nohz=off
If CONFIG_NO_HZ=n tick_nohz_ get_sleep_ length( ) returns NSEC_PER_SEC/HZ.
If CONFIG_NO_HZ=y and the nohz functionality is disabled via the get_sleep_ length( ) returns 0. That happens
command line option "nohz=off" or not enabled due to missing hardware
support, then tick_nohz_
because ts->sleep_length is never set in that case.
Set it to NSEC_PER_SEC/HZ when the NOHZ mode is inactive.
Reported-by: Michal Hocko <email address hidden>
Reported-by: Borislav Petkov <email address hidden>
Signed-off-by: Thomas Gleixner <email address hidden>
:040000 040000 e98d34fcc56a28e 516d6282265f2de 29bc0f4ad6 ec91edd6b6c6548 dc58410a052c5fb c59f12690b M kernel