Skip to content

docs: bring the 5.10.5 benchmark to main - #1949

Merged
Jaro-c merged 1 commit into
mainfrom
develop
Sep 27, 2026
Merged

Jaro-c merged 1 commit into
mainfrom
develop

Conversation

@Jaro-c

@Jaro-c Jaro-c commented Sep 27, 2026

Copy link
Copy Markdown
Member

Brings #1948 to main, so the benchmark page and the README section people see on the default branch carry the 5.10.5 measurements instead of the 5.7.1 ones. Documentation and the chart script only; the binary is unchanged, so there is no version bump and no tag.

Signed-off-by: Jaro-c 75870284+Jaro-c@users.noreply.github.com

I re-ran the suite on the published 5.10.5 asset against podman-compose
1.6.0 and docker-compose 5.5.1, with docker-compose both on the Podman
socket and on Docker 29.8.1: 1392 timed runs, none failed.

The page now carries both comparisons, the host description the harness
records, and why these latencies cannot be subtracted from the 5.7.1
table: the engine on this host got two to three times slower on the
multi-container rows, and the 5.7.1 and 5.10.5 binaries run against each
other take the same time. It names the one row podup loses (#1947) and
the memory growth since 5.7.1 (#1946).

chart.py reads the renamed docker-compose-podman column and no longer
claims podup leads every scenario.

Signed-off-by: Jaro-c <75870284+Jaro-c@users.noreply.github.com>

Refs #1946, #1947

Signed-off-by: Jaro-c <75870284+Jaro-c@users.noreply.github.com>
@Jaro-c Jaro-c added type:docs Documentation prio:P3 Low priority effort:XS Extra small area:ci Subsystem: ci labels Sep 27, 2026
@Jaro-c
Jaro-c enabled auto-merge September 27, 2026 21:46
@Jaro-c
Jaro-c merged commit fde2d49 into main Sep 27, 2026
58 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area:ci Subsystem: ci effort:XS Extra small prio:P3 Low priority type:docs Documentation

Development

Successfully merging this pull request may close these issues.

1 participant