Re: [PATCH v7 0/4] Add lcore poll busyness telemetry

[Kevin Laatz <kevin.laatz@intel.com>]

[-- Attachment #1: Type: text/plain, Size: 1520 bytes --]

On 16/09/2022 13:35, Kevin Laatz wrote:
> On 14/09/2022 15:33, Stephen Hemminger wrote:
>> On Wed, 14 Sep 2022 10:29:25 +0100
>> Kevin Laatz <kevin.laatz@intel.com> wrote:
>>
>>> Currently, there is no way to measure lcore polling busyness in a 
>>> passive
>>> way, without any modifications to the application. This patchset 
>>> adds a new
>>> EAL API that will be able to passively track core polling busyness. 
>>> As part
>>> of the set, new telemetry endpoints are added to read the generate 
>>> metrics.
>> How much does measuring busyness impact performance??
>>
>> In the past, calling rte_rdsc() would slow down packet rate
>> because it is stops CPU pipeline. Maybe better on more modern
>> processors, haven't measured it lately.
>
> Hi Stephen,
>
> I've run some 0.001% loss tests using 2x 100G ports, with 64B packets 
> using testpmd for forwarding. Those tests show a ~2.7% performance 
> impact when the lcore poll busyness feature is enabled vs compile-time 
> disabled.
> Applications with more compute intensive workloads should see less 
> performance impact since the proportion of time spent time-stamping 
> will be smaller.
>
> In addition, a performance autotest has been added in this patchset 
> which measures the cycles cost of calling the timestamp macro. Please 
> feel free to test it on your system (lcore_poll_busyness_perf_autotest).
>
Worth mentioning as well, is that when lcore poll busyness is enabled at 
compile-time and disabled at run-time, we see *zero *performance impact.

[-- Attachment #2: Type: text/html, Size: 2346 bytes --]