Re: [REGRESSION] core scheduling latency with idle load

From: Mihail Mihov

Date: Tue Nov 17 2026 - 06:11:59 EST


Hi Prateek,

On Tue, Nov 17, 2026 at 03:52:15PM +0530, K Prateek Nayak wrote:
> That said, perhaps se_fi_update() could itself be optimized now with
> flattened pick. Could you try below changes a try:

With this on top of v7.4-rc3 the reproducer gives:

kernel no cookie cookie
v7.4-rc3 53 3290
v7.4-rc3 + patch 53 54

(p99 in us, same machine and config as in the report.)

Tested-by: Mihail Mihov <mihovmihailp@xxxxxxxxx>

Thanks,
Mihail