From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ian Rogers <irogers@google.com>
Cc: namhyung@kernel.org, ak@kernel.org, ak@linux.intel.com,
andi@firstfloor.org, linux-perf-users@vger.kernel.org
Subject: Re: [PATCH v4 0/9] perf report/top: Add opt-in --hybrid-merge
Date: Fri, 18 Sep 2026 18:58:24 -0300 [thread overview]
Message-ID: <aq20APrOz60O4n8B@x2> (raw)
In-Reply-To: <aq2hq_Fw6fn0rGkm@x2>
On Fri, Sep 18, 2026 at 05:40:15PM -0300, Arnaldo Carvalho de Melo wrote:
> On Wed, Sep 16, 2026 at 10:06:59PM -0700, Ian Rogers wrote:
> > On a hybrid machine a wildcard event expands to one event per core
> > PMU, so "perf record -e cycles" records cpu_core/cycles/ and
> > cpu_atom/cycles/. perf report and perf top then show one histogram per
> > PMU, and a symbol that ran on both kinds of core is split across them,
> > with each percentage relative to its own PMU's total. There is no way
> > to ask for the single combined profile.
> >
> > Add --hybrid-merge to perf report and perf top, which merges the
> > histograms of the events that came from the same wildcard into one,
> > with percentages taken against the summed period.
> >
> > Merging is opt-in because it isn't always the right thing to do. The
> > cores differ in performance, so a merged cycles count mixes work done
> > at different rates and a merged IPC is not the IPC of either core
> > type. perf-tips notes this. When merging is possible but wasn't asked
> > for, the TUI says so, rather than merging silently.
> >
> > core.hybrid-merge in .perfconfig turns it on by default. As a default
> > rather than an explicit request it yields to the command line: with
> > --hierarchy it is ignored with a warning, whereas asking for both
> > --hierarchy and --hybrid-merge on the command line is an error. For
> > the same reason it is silent when there is nothing to merge, so it
> > doesn't warn on every invocation on a machine with a single core PMU.
> >
> > perf stat is deliberately untouched. Counting already has its own
> > merging options, and this is aimed at sampling.
> >
> > The events to merge are found with first_wildcard_match, which parsing
> > fills in. perf report reads events from a file rather than parsing
> > them, so there the wildcard grouping is recovered by matching event
> > names, and core PMUs are identified from the perf.data header topology
> > so that a file recorded on another machine is read correctly.
>
> Thanks, applied to perf-tools-next, for v7.4.
I tried 'perf top --hybrid-merge" on this machine:
acme@x2:~/git/perf-tools-next$ grep -m1 "model name" /proc/cpuinfo
model name : Intel(R) Core(TM) i7-8650U CPU @ 1.90GHz
acme@x2:~/git/perf-tools-next$
That is hybrid and it didn't merge anything, just told me that:
┌─Warning:──────────────────────────────────────────┐
│--hybrid-merge: no events to merge across core PMUs│
│ │
│ │
│Press any key... │
└───────────────────────────────────────────────────┘
What am I missing?
I merged this, so we can continue from there,
- Arnaldo
next prev parent reply other threads:[~2026-09-18 21:58 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-16 6:52 [PATCH v2 0/9] perf report/top: Add opt-in --hybrid-merge Ian Rogers
2026-09-16 6:52 ` [PATCH v2 1/9] perf evlist: Implement evlist__can_merge_hybrid using first_wildcard_match Ian Rogers
2026-09-16 7:02 ` sashiko-bot
2026-09-16 6:52 ` [PATCH v2 2/9] perf ui hist: Add support for aggregated total_period and merging entries Ian Rogers
2026-09-16 7:04 ` sashiko-bot
2026-09-16 6:52 ` [PATCH v2 3/9] perf tools: Expose opt-in --hybrid-merge Ian Rogers
2026-09-16 7:04 ` sashiko-bot
2026-09-16 6:52 ` [PATCH v2 4/9] perf Documentation: Add tip for hybrid event merging Ian Rogers
2026-09-16 6:59 ` sashiko-bot
2026-09-16 6:52 ` [PATCH v2 5/9] perf evlist: Toggle merged_hybrid_group properly in enable/disable Ian Rogers
2026-09-16 7:06 ` sashiko-bot
2026-09-16 6:52 ` [PATCH v2 6/9] perf tools: Add TUI hints for --hybrid-merge Ian Rogers
2026-09-16 7:01 ` sashiko-bot
2026-09-16 6:52 ` [PATCH v2 7/9] perf config: Add core.hybrid-merge to configure event merging Ian Rogers
2026-09-16 6:59 ` sashiko-bot
2026-09-16 6:52 ` [PATCH v2 8/9] perf test: Expand tests for --hybrid-merge Ian Rogers
2026-09-16 7:04 ` sashiko-bot
2026-09-16 6:52 ` [PATCH v2 9/9] perf test: Isolate test suite from user .perfconfig natively Ian Rogers
2026-09-16 7:08 ` sashiko-bot
2026-09-16 23:46 ` [PATCH v3 0/9] perf report/top: Add opt-in --hybrid-merge Ian Rogers
2026-09-16 23:46 ` [PATCH v3 1/9] perf evlist: Implement evlist__can_merge_hybrid using first_wildcard_match Ian Rogers
2026-09-16 23:58 ` sashiko-bot
2026-09-16 23:46 ` [PATCH v3 2/9] perf ui hist: Add support for aggregated total_period and merging entries Ian Rogers
2026-09-16 23:57 ` sashiko-bot
2026-09-16 23:46 ` [PATCH v3 3/9] perf tools: Expose opt-in --hybrid-merge Ian Rogers
2026-09-16 23:57 ` sashiko-bot
2026-09-16 23:46 ` [PATCH v3 4/9] perf Documentation: Add tip for hybrid event merging Ian Rogers
2026-09-16 23:48 ` sashiko-bot
2026-09-16 23:46 ` [PATCH v3 5/9] perf evlist: Toggle merged_hybrid_group properly in enable/disable Ian Rogers
2026-09-16 23:53 ` sashiko-bot
2026-09-16 23:46 ` [PATCH v3 6/9] perf tools: Add TUI hints for --hybrid-merge Ian Rogers
2026-09-16 23:53 ` sashiko-bot
2026-09-16 23:46 ` [PATCH v3 7/9] perf config: Add core.hybrid-merge to configure event merging Ian Rogers
2026-09-16 23:57 ` sashiko-bot
2026-09-16 23:46 ` [PATCH v3 8/9] perf test: Expand tests for --hybrid-merge Ian Rogers
2026-09-16 23:53 ` sashiko-bot
2026-09-16 23:46 ` [PATCH v3 9/9] perf test: Isolate test suite from user .perfconfig natively Ian Rogers
2026-09-16 23:57 ` sashiko-bot
2026-09-17 5:06 ` [PATCH v4 0/9] perf report/top: Add opt-in --hybrid-merge Ian Rogers
2026-09-17 5:07 ` [PATCH v4 1/9] perf evlist: Implement evlist__can_merge_hybrid using first_wildcard_match Ian Rogers
2026-09-17 5:14 ` sashiko-bot
2026-09-17 5:07 ` [PATCH v4 2/9] perf ui hist: Add support for aggregated total_period and merging entries Ian Rogers
2026-09-17 5:16 ` sashiko-bot
2026-09-17 5:07 ` [PATCH v4 3/9] perf tools: Expose opt-in --hybrid-merge Ian Rogers
2026-09-17 5:16 ` sashiko-bot
2026-09-18 20:31 ` Arnaldo Carvalho de Melo
2026-09-18 20:51 ` Ian Rogers
2026-09-17 5:07 ` [PATCH v4 4/9] perf Documentation: Add tip for hybrid event merging Ian Rogers
2026-09-17 5:10 ` sashiko-bot
2026-09-17 5:07 ` [PATCH v4 5/9] perf evlist: Toggle merged_hybrid_group properly in enable/disable Ian Rogers
2026-09-17 5:13 ` sashiko-bot
2026-09-17 5:07 ` [PATCH v4 6/9] perf tools: Add TUI hints for --hybrid-merge Ian Rogers
2026-09-17 5:14 ` sashiko-bot
2026-09-17 5:07 ` [PATCH v4 7/9] perf config: Add core.hybrid-merge to configure event merging Ian Rogers
2026-09-17 5:16 ` sashiko-bot
2026-09-17 5:07 ` [PATCH v4 8/9] perf test: Expand tests for --hybrid-merge Ian Rogers
2026-09-17 5:18 ` sashiko-bot
2026-09-17 5:07 ` [PATCH v4 9/9] perf test: Isolate test suite from user .perfconfig natively Ian Rogers
2026-09-17 5:17 ` sashiko-bot
2026-09-18 20:40 ` [PATCH v4 0/9] perf report/top: Add opt-in --hybrid-merge Arnaldo Carvalho de Melo
2026-09-18 21:58 ` Arnaldo Carvalho de Melo [this message]
2026-09-18 22:07 ` Ian Rogers
2026-09-18 22:11 ` Ian Rogers
2026-09-18 23:04 ` Arnaldo Melo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=aq20APrOz60O4n8B@x2 \
--to=acme@kernel.org \
--cc=ak@kernel.org \
--cc=ak@linux.intel.com \
--cc=andi@firstfloor.org \
--cc=irogers@google.com \
--cc=linux-perf-users@vger.kernel.org \
--cc=namhyung@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox