Skip to content
Merged
Changes from 1 commit
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,15 @@ function sed_in_place() {
esac
}

# run-api-test.sh starts the Server twice on the same configuration, and a
# key appended twice is read back as a list, so append each line only once
function append_once() {
local line=$1
local file=$2

grep -qxF "$line" "$file" || echo "$line" >> "$file"
}

case "$BACKEND" in
memory)
SERIALIZER=text
Expand All @@ -64,18 +73,18 @@ write_property "$CONF" "serializer" "$SERIALIZER"

# Set timeout for hbase
if [ "$BACKEND" == "hbase" ]; then
echo "restserver.request_timeout=200" >> $REST_CONF
echo "gremlinserver.timeout=200" >> $REST_CONF
append_once "restserver.request_timeout=200" "$REST_CONF"
append_once "gremlinserver.timeout=200" "$REST_CONF"
sed_in_place 's/evaluationTimeout.*/evaluationTimeout: 200000/' "$GREMLIN_CONF"
fi

# Set usePD=true for hstore
if [ "$BACKEND" == "hstore" ]; then
echo "usePD=true" >> $REST_CONF
append_once "usePD=true" "$REST_CONF"

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Minor: This line is the fix for the hstore job, but the CI of this PR never runs it: gh pr checks 3371 lists pd_store and compatibility / build-server-backends (hbase) as SKIPPED. .github/scripts/ci-policy.py maps a hugegraph-dist/ path to {server, docker, macos, macos_full} and adds hstore only when the path contains pd, store or distributed, so start-server.sh and run-api-test.sh never select hstore or hbase. That is how #3366 merged with the hstore API step broken, and the next change to these two scripts would hit the same blind spot. Requested change: add TRAVIS + "start-server.sh" and TRAVIS + "run-api-test.sh" to the planner with {hstore, hbase} (you offered this in the description; doing it here also lets this PR's own CI run the hstore API step instead of relying on the out-of-CI Ubuntu run).

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

effa296 covers these lines without the hstore and hbase jobs. test-start-server.sh runs start-server.sh twice per backend and checks that usePD=true (hstore), both timeouts (hbase) and schema.sync_deletion=true (all backends) each end up once, only for their backend, and that the second start changes nothing. It runs in the rocksdb job, which every hugegraph-dist change selects, and fails on master's script. Touching server-tests.yml also selects the hbase job, so this PR's CI now runs the real hbase API step with both starts. The planner change is not in this PR: it would add hstore and hbase runs to every change to these two scripts, so it is a separate decision.

fi

# Append schema.sync_deletion=true to config file
echo "schema.sync_deletion=true" >> $CONF
append_once "schema.sync_deletion=true" "$CONF"

JACOCO_OPTION=""
if [ -n "$JACOCO_PORT" ]; then
Expand Down
Loading