Re: [PATCH v2 5/6] perf stat: Enable iiostat mode for x86 platforms

[Namhyung Kim]

On Wed, Dec 23, 2020 at 10:03 PM Alexander Antonov
<alexander.antonov@xxxxxxxxxxxxxxx> wrote:
>
> This functionality is based on recently introduced sysfs attributes
> for Intel® Xeon® Scalable processor family (code name Skylake-SP):
> Commit bb42b3d39781 ("perf/x86/intel/uncore: Expose an Uncore unit to
> IIO PMON mapping")
>
> Mode is intended to provide four I/O performance metrics in MB per each
> IIO stack:
>  - Inbound Read: I/O devices below IIO stack read from the host memory
>  - Inbound Write: I/O devices below IIO stack write to the host memory
>  - Outbound Read: CPU reads from I/O devices below IIO stack
>  - Outbound Write: CPU writes to I/O devices below IIO stack
>
> Each metric requiries only one IIO event which increments at every 4B
> transfer in corresponding direction. The formulas to compute metrics
> are generic:
>     #EventCount * 4B / (1024 * 1024)

Hmm.. maybe we can do this with JSON metrics, no?

>
> Signed-off-by: Alexander Antonov <alexander.antonov@xxxxxxxxxxxxxxx>
> ---
>  tools/perf/Documentation/perf-iiostat.txt |  89 ++++++
>  tools/perf/Makefile.perf                  |   5 +-
>  tools/perf/arch/x86/util/Build            |   1 +
>  tools/perf/arch/x86/util/iiostat.c        | 337 ++++++++++++++++++++++
>  tools/perf/command-list.txt               |   1 +
>  tools/perf/perf-iiostat.sh                |  12 +
>  6 files changed, 444 insertions(+), 1 deletion(-)
>  create mode 100644 tools/perf/Documentation/perf-iiostat.txt
>  create mode 100644 tools/perf/perf-iiostat.sh
>
> diff --git a/tools/perf/Documentation/perf-iiostat.txt b/tools/perf/Documentation/perf-iiostat.txt
> new file mode 100644
> index 000000000000..38b5697b0d85
> --- /dev/null
> +++ b/tools/perf/Documentation/perf-iiostat.txt
> @@ -0,0 +1,89 @@
> +perf-iiostat(1)
> +===============
> +
> +NAME
> +----
> +perf-iiostat - Show I/O performance metrics
> +
> +SYNOPSIS
> +--------
> +[verse]
> +'perf iiostat' show
> +'perf iiostat' <ports> -- <command> [<options>]
> +
> +DESCRIPTION
> +-----------
> +Mode is intended to provide four I/O performance metrics per each IIO
> +stack (PCIe root port):
> +
> +- Inbound Read   - I/O devices below IIO stack read from the host memory, in MB
> +
> +- Inbound Write  - I/O devices below IIO stack write to the host memory, in MB
> +
> +- Outbound Read  - CPU reads from I/O devices below IIO stack, in MB
> +
> +- Outbound Write - CPU writes to I/O devices below IIO stack, in MB
> +
> +OPTIONS
> +-------
> +<command>...::
> +       Any command you can specify in a shell.
> +
> +show::
> +       List all IIO stacks.

I'd prefer 'list' for this, but not a strong opinion..

> +
> +<ports>::
> +       Select the root ports for monitoring. Comma-separated list is supported.
> +
> +EXAMPLES
> +--------
> +
> +1. List all IIO stacks (example for 2-S platform):
> +
> +   $ perf iiostat show
> +   S0-uncore_iio_0<0000:00>
> +   S1-uncore_iio_0<0000:80>
> +   S0-uncore_iio_1<0000:17>
> +   S1-uncore_iio_1<0000:85>
> +   S0-uncore_iio_2<0000:3a>
> +   S1-uncore_iio_2<0000:ae>
> +   S0-uncore_iio_3<0000:5d>
> +   S1-uncore_iio_3<0000:d7>
> +
> +2. Collect metrics for all I/O stacks:
> +
> +   $ perf iiostat -- dd if=/dev/zero of=/dev/nvme0n1 bs=1M oflag=direct
> +   357708+0 records in
> +   357707+0 records out
> +   375083606016 bytes (375 GB, 349 GiB) copied, 215.974 s, 1.7 GB/s
> +
> +    Performance counter stats for 'system wide':
> +
> +      port             Inbound Read(MB)    Inbound Write(MB)    Outbound Read(MB)   Outbound Write(MB)
> +   0000:00                    1                    0                    2                    3
> +   0000:80                    0                    0                    0                    0
> +   0000:17               352552                   43                    0                   21
> +   0000:85                    0                    0                    0                    0
> +   0000:3a                    3                    0                    0                    0
> +   0000:ae                    0                    0                    0                    0
> +   0000:5d                    0                    0                    0                    0
> +   0000:d7                    0                    0                    0                    0
> +
> +3. Collect metrics for comma-separated list of I/O stacks:
> +
> +   $ perf iiostat 0000:17,0:3a -- dd if=/dev/zero of=/dev/nvme0n1 bs=1M oflag=direct
> +   357708+0 records in
> +   357707+0 records out
> +   375083606016 bytes (375 GB, 349 GiB) copied, 197.08 s, 1.9 GB/s
> +
> +    Performance counter stats for 'system wide':
> +
> +      port             Inbound Read(MB)    Inbound Write(MB)    Outbound Read(MB)   Outbound Write(MB)
> +   0000:17               358559                   44                    0                   22
> +   0000:3a                    3                    2                    0                    0
> +
> +        197.081983474 seconds time elapsed
> +
> +SEE ALSO
> +--------
> +linkperf:perf-stat[1]
> \ No newline at end of file

[SNIP]
> diff --git a/tools/perf/perf-iiostat.sh b/tools/perf/perf-iiostat.sh
> new file mode 100644
> index 000000000000..2c5168d2550b
> --- /dev/null
> +++ b/tools/perf/perf-iiostat.sh
> @@ -0,0 +1,12 @@
> +#!/bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +# perf iiostat
> +# Alexander Antonov <alexander.antonov@xxxxxxxxxxxxxxx>
> +
> +if [[ "$1" == "show" ]] || [[ "$1" =~ ([a-f0-9A-F]{1,}):([a-f0-9A-F]{1,2})(,)? ]]; then
> +        DELIMITER="="
> +else
> +        DELIMITER=" "
> +fi
> +
> +perf stat --iiostat$DELIMITER$*

Why is this needed?

Thanks,
Namhyung


> \ No newline at end of file
> --
> 2.19.1
>