Our custom nr_unint logic follows the kernel's one about the global
nr_uninterruptible one. One invariant that both share is that values
of nr_unint can go negative when a task is migrated from a CPU.
What's important is that when summed across all task groups they either result
in a positive numbe
BTW, do we need a similar patch for vz7 as well?
On 30.11.2022 13:29, Nikolay Borisov wrote:
Our custom nr_unint logic follows the kernel's one about the global
nr_uninterruptible one. One invariant that both share is that values
of nr_unint can go negative when a task is migrated from a CPU.
Wha
On 7.12.22 г. 20:02 ч., Konstantin Khorenko wrote:
BTW, do we need a similar patch for vz7 as well?
Looking at the vz7 kernel code I'd say yes since processes can still be
woken up on a different CPU than the one they went to sleep on. However,
I wonder why this issue hasn't manifested so f
