Messages in this thread | | | Subject | Re: [PATCH 1/4] softirq: implement IRQ flood detection mechanism | From | Bart Van Assche <> | Date | Wed, 4 Sep 2019 12:47:13 -0700 |
| |
On 9/4/19 11:02 AM, Peter Zijlstra wrote: > On Wed, Sep 04, 2019 at 10:38:59AM -0700, Bart Van Assche wrote: >> I think it is widely known that rdtsc is a relatively slow x86 instruction. >> So I expect that using that instruction will cause a measurable overhead if >> it is called frequently enough. I'm not aware of any publicly available >> measurement data however. > > https://www.agner.org/optimize/instruction_tables.pdf > > RDTSC, Ryzen: ~36 > RDTSC, Skylake: ~20 > > Sadly those same tables don't list the cost of actual exceptions or even > IRET :/
Thanks Peter for having looked up these numbers. These numbers are much better than last time I checked. Ming, would CONFIG_IRQ_TIME_ACCOUNTING help your workload?
Does anyone know which CPUs the following text from Documentation/admin-guide/kernel-parameters.txt refers to?
tsc= [ ... ] [x86] noirqtime: Do not use TSC to do irq accounting. Used to run time disable IRQ_TIME_ACCOUNTING on any platforms where RDTSC is slow and this accounting can add overhead.
Bart.
| |