Skip to content

fix: improve must-gather resilience for SOS and container log collection #142

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
openshift-merge-bot merged 3 commits into from
Jun 29, 2026
+11 −8
Merged

fix: improve must-gather resilience for SOS and container log collection #142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6a1e2f4
fix: improve must-gather resilience for SOS and container log collection
lmiccini Jun 29, 2026
418e366
fix: add skip_missing_interpreters to tox.ini
lmiccini Jun 29, 2026
b2ea3c1
fix: use /host prefix for sos report --tmp-dir inside toolbox container
lmiccini Jun 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions collection-scripts/gather_ctlplane_resources
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,11 +69,11 @@ function gather_ctlplane_resources {
.metadata.name as $pod |
(.status |
(
if has("initContainerStatuses") then .initContainerStatuses[] else empty end |
if has("initContainerStatuses") then .initContainerStatuses[] | select(.state | has("running") or has("terminated")) else empty end |
"\($pod) \(.name) \(has("lastState") and (.lastState | has("terminated"))) true"
),
(
if has("containerStatuses") then .containerStatuses[] else empty end |
if has("containerStatuses") then .containerStatuses[] | select(.state | has("running") or has("terminated")) else empty end |
"\($pod) \(.name) \(has("lastState") and (.lastState | has("terminated"))) false"
)
)
Expand Down
14 changes: 8 additions & 6 deletions collection-scripts/gather_sos
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,7 @@ gather_node_sos () {
mkdir -p \"${TMPDIR}\" && \
sudo podman rm --force toolbox-osp; \
sudo --preserve-env podman pull --authfile /var/lib/kubelet/config.json $SUPPORT_TOOLS && \
toolbox sos report --batch --all-logs $SOS_LIMIT --tmp-dir=\"${TMPDIR}\" && \
toolbox sos report --batch --all-logs $SOS_LIMIT --tmp-dir=\"/host${TMPDIR}\" && \
if [[ \"\$(ls /var/log/pods/*/{*.log.*,*/*.log.*} 2>/dev/null)\" != '' ]]; then tar --ignore-failed-read --warning=no-file-changed -cJf \"${TMPDIR}/podlogs.tar.xz\" --transform 's,^,podlogs/,' /var/log/pods/*/{*.log.*,*/*.log.*} || true; fi"

# shellcheck disable=SC2181
Expand Down Expand Up @@ -118,11 +118,13 @@ gather_node_sos () {

# if we are decompressing the sos report, remove the original sos archive
if [[ ${SOS_DECOMPRESS} -eq 1 ]]; then
mkdir "${SOS_PATH_NODES}/sosreport-$node"
tar -i --one-top-level="${SOS_PATH_NODES}/sosreport-$node" --strip-components=1 --exclude='*/dev/null' -Jxf "${sos_file}"
rm "${sos_file}"
# Ensure write access to the sos reports directories so must-gather rsync doesn't fail
chmod +w -R "${SOS_PATH_NODES}/sosreport-$node/"
if tar -i -C "${SOS_PATH_NODES}" --one-top-level="sosreport-$node" --strip-components=1 --exclude='*/dev/null' -Jxf "${sos_file}"; then
rm "${sos_file}"
# Ensure write access to the sos reports directories so must-gather rsync doesn't fail
chmod +w -R "${SOS_PATH_NODES}/sosreport-$node/"
else
echo "Failed to decompress SOS report for ${node}, keeping compressed archive"
fi
fi

sleep 1
Expand Down
1 change: 1 addition & 0 deletions pyscripts/tox.ini
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ envlist =
mypy
stestr
pytest
skip_missing_interpreters = true
skipsdist = true
passenv =
LANG
Expand Down
Loading