Skip to content

Commit 68fca6f

Browse files
committed
update workflow yaml
1 parent dca07fb commit 68fca6f

1 file changed

Lines changed: 36 additions & 11 deletions

File tree

.github/workflows/sandbox-validation.yml

Lines changed: 36 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -34,7 +34,7 @@
3434
# - On changes to sandbox-related files
3535
#
3636
# --------------------------------------------------------------------
37-
name: Sandbox Weekly Validation
37+
name: Sandbox Validation
3838

3939
on:
4040
# Run every Monday at 02:00 UTC (weekly validation)
@@ -92,18 +92,26 @@ jobs:
9292
cd devops/sandbox
9393
./run.sh -c ${{ matrix.version }}
9494
95-
echo "Waiting for deployment to complete..."
96-
for i in {1..30}; do
95+
echo "Waiting for container to initialize (30s)..."
96+
sleep 30
97+
98+
echo "Waiting for deployment to complete (up to 6 minutes)..."
99+
for i in {1..36}; do
97100
if docker logs cbdb-cdw 2>&1 | grep -q "DEPLOYMENT SUCCESSFUL"; then
98101
echo "✅ Deployment completed successfully"
99102
break
100103
fi
104+
if docker logs cbdb-cdw 2>&1 | grep -q "Postgres version does not match"; then
105+
echo "ERROR: Postgres version mismatch detected"
106+
docker logs cbdb-cdw
107+
exit 1
108+
fi
101109
if ! docker ps | grep -q cbdb-cdw; then
102110
echo "ERROR: Container stopped unexpectedly"
103111
docker logs cbdb-cdw
104112
exit 1
105113
fi
106-
[ $i -eq 30 ] && echo "ERROR: Deployment timeout" && docker logs cbdb-cdw && exit 1
114+
[ $i -eq 36 ] && echo "ERROR: Deployment timeout after 6 minutes" && docker logs cbdb-cdw && exit 1
107115
sleep 10
108116
done
109117
timeout-minutes: 30
@@ -172,28 +180,45 @@ jobs:
172180
cd devops/sandbox
173181
./run.sh -c ${{ matrix.version }} -m
174182
175-
echo "Waiting for Apache Cloudberry multi-node deployment to complete..."
176-
for i in {1..24}; do
183+
echo "Waiting for all containers to fully initialize (90s)..."
184+
sleep 90
185+
186+
echo "Checking all containers are running..."
187+
for container in cbdb-cdw cbdb-scdw cbdb-sdw1 cbdb-sdw2; do
188+
if ! docker ps | grep -q $container; then
189+
echo "ERROR: Container $container not running"
190+
docker ps -a
191+
exit 1
192+
fi
193+
done
194+
195+
echo "Waiting for multi-node deployment to complete (up to 8 minutes)..."
196+
for i in {1..32}; do
177197
if docker logs cbdb-cdw 2>&1 | grep -q "DEPLOYMENT SUCCESSFUL"; then
178198
echo "✅ Multi-node deployment completed"
179199
break
180200
fi
201+
if docker logs cbdb-cdw 2>&1 | grep -q "Timeout waiting for SSH"; then
202+
echo "ERROR: SSH timeout detected"
203+
docker logs cbdb-cdw
204+
exit 1
205+
fi
181206
if ! docker ps | grep -q cbdb-cdw; then
182207
echo "ERROR: Coordinator stopped unexpectedly"
183208
docker logs cbdb-cdw
184209
exit 1
185210
fi
186-
[ $i -eq 24 ] && echo "ERROR: Deployment timeout" && docker logs cbdb-cdw && exit 1
211+
[ $i -eq 32 ] && echo "ERROR: Deployment timeout after 8 minutes" && docker logs cbdb-cdw && exit 1
187212
sleep 15
188213
done
189-
timeout-minutes: 30
214+
timeout-minutes: 35
190215

191216
- name: Test SSH connectivity between nodes
192217
run: |
193218
echo "Testing SSH connectivity from coordinator to all nodes..."
194-
docker exec -u gpadmin cbdb-cdw bash -l -c "ssh -o StrictHostKeyChecking=no -o ConnectTimeout=10 sdw1 'hostname'"
195-
docker exec -u gpadmin cbdb-cdw bash -l -c "ssh -o StrictHostKeyChecking=no -o ConnectTimeout=10 sdw2 'hostname'"
196-
docker exec -u gpadmin cbdb-cdw bash -l -c "ssh -o StrictHostKeyChecking=no -o ConnectTimeout=10 scdw 'hostname'"
219+
docker exec -u gpadmin cbdb-cdw bash -l -c "ssh -o StrictHostKeyChecking=no -o ConnectTimeout=20 sdw1 'hostname'"
220+
docker exec -u gpadmin cbdb-cdw bash -l -c "ssh -o StrictHostKeyChecking=no -o ConnectTimeout=20 sdw2 'hostname'"
221+
docker exec -u gpadmin cbdb-cdw bash -l -c "ssh -o StrictHostKeyChecking=no -o ConnectTimeout=20 scdw 'hostname'"
197222
echo "✅ SSH connectivity verified"
198223
199224
- name: Test database operations

0 commit comments

Comments
 (0)