[PATCH RFC 3/3] arm64: Add HOTPLUG_PARALLEL support for secondary CPUs

[Thomas Gleixner]

On Mon, Jun 15 2026 at 17:57, Jinjie Ruan wrote:
> On 6/12/2026 11:45 PM, Michael Kelley wrote:
>
> - Default (no patch): Slowest HVC64 handling (126 μs), highest WFx count
> (85k), and most total VM‑exits.
>
> - cpuhp.parallel=1: HVC64 latency improved to 78 μs (close to
> cpuhp.parallel=0), but IRQ exits increased dramatically (12.9k, 2.7×
> that of `cpuhp.parallel=0`), accounting for 95% of event time and
> becoming the new bottleneck.
>
> - cpuhp.parallel=0: Fastest HVC64 (69 μs), lowest IRQ exits (4.8k), and
> lowest total samples, delivering the best overall boot performance.
>
> Therefor, `cpuhp.parallel=1` reduces HVC cost but suffers from a massive
> increase in IRQ exits, while `cpuhp.parallel=0` avoids this interrupt
> storm and therefore performs best in a KVM guest.

What's the cause for having this massive interrupt exit rate in parallel
mode? Just because parallel does not give a useful explanation.

Thanks,

        tglx