[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <b6ad043f-a742-46bc-a782-6ab2e1a6257f@intel.com>
Date: Wed, 24 Apr 2024 21:38:45 -0700
From: Reinette Chatre <reinette.chatre@...el.com>
To: Ilpo Järvinen <ilpo.jarvinen@...ux.intel.com>,
<linux-kselftest@...r.kernel.org>, Shuah Khan <shuah@...nel.org>, Babu Moger
<babu.moger@....com>, Maciej Wieczór-Retman
<maciej.wieczor-retman@...el.com>
CC: Fenghua Yu <fenghua.yu@...el.com>, <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v3 02/16] selftests/resctrl: Calculate resctrl FS derived
mem bw over sleep(1) only
Hi Ilpo,
On 4/8/2024 9:32 AM, Ilpo Järvinen wrote:
> For MBM/MBA tests, measure_vals() calls get_mem_bw_imc() that performs
> the measurement over a duration of sleep(1) call. The memory bandwidth
> numbers from IMC are derived over this duration. The resctrl FS derived
> memory bandwidth, however, is calculated inside measure_vals() and only
> takes delta between the previous value and the current one which
> besides the actual test, also samples inter-test noise.
>
> Rework the logic in measure_vals() and get_mem_bw_imc() such that the
> resctrl FS memory bandwidth section covers much shorter duration
> closely matching that of the IMC perf counters to improve measurement
> accuracy.
I do not know how much latency this adds but I think for the resctrl data
to reach this stated goal to closely match the IMC perf counters it
can keep the file descriptor open during the test and only read data
from the appropriate file instead of encurring the fopen()/fclose()
cost at each measurement.
Reinette
Powered by blists - more mailing lists