Messages in this thread | | | From | Thomas Gleixner <> | Subject | Re: [PATCH 1/3] timekeeping: NMI safe converter from a given time to monotonic | Date | Fri, 27 Jan 2023 14:30:20 +0100 |
| |
On Tue, Jan 24 2023 at 01:10, Stephane Eranian wrote: > On Tue, Jan 24, 2023 at 12:52 AM Thomas Gleixner <tglx@linutronix.de> wrote: >> > It's useful to provide a NMI safe function to convert a given time to >> > monotonic. For example, the perf_event subsystem wants to convert a TSC >> > of a PEBS record to a monotonic clock in a NMI handler. >> >> Why? That's a postprocessing problem, really. >> > Because you want to correlate samples captured by PEBS with samples > from applications timestamped with a user available clock such as > CLOCK_MONOTONIC, for instance.
Sure. Postprocessing can do that if the kernel provides the relevant conversion information. Absolutely no need for doing this in the kernel.
> When I create a perf_event event and I stipulate that > event_attr.clockid=MONOTONIC, I expect all the samples from that event > to be timestamped using the same clock source, regardless of PEBS or > IBS.
Just because the kernel can do the conversion, there is no requirement to actually do so. Instrumentation has to be as lightweight as possible and a lot of instrumentation goes the extra mile of doing postprocessing exactly for this reason.
So if we implement this conversion in the kernel then there needs to be a compelling technical reason to do so.
So far the provided arguments are in the 'I want a pony' realm.
Thanks,
tglx
| |