Skip to content

Fix/healtcheck-ci script #39

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
Shayan-Ghani merged 2 commits into from
Jun 1, 2025
Merged

Fix/healtcheck-ci script #39

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f5ed93a
refactor: improved metrics naming
Shayan-Ghani Jun 1, 2025
a6e5bc2
fix: healthcheck ci doesn't list metrics without container_name label
Shayan-Ghani Jun 1, 2025
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
24 changes: 12 additions & 12 deletions container_exporter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,12 +37,12 @@ async def lifespan(app: FastAPI):
gauge_memory_percentage = Gauge('cxp_memory_percentage', 'Docker container memory usage in percent', ['container_name'])
gauge_memory_bytes = Gauge('cxp_memory_bytes_total', 'Docker container memory usage in bytes', ['container_name'])

counter_disk_read = Gauge("cxp_disk_io_read_bytes_total", "Total bytes read from disk", ['container_name'])
counter_disk_write = Gauge("cxp_disk_io_write_bytes_total", "Total bytes written to disk", ['container_name'])
counter_net_rx = Gauge("cxp_network_rx_bytes_total", "Total bytes received over network", ['container_name'])
counter_net_tx = Gauge("cxp_network_tx_bytes_total", "Total bytes sent over network", ['container_name'])
gauge_disk_read = Gauge("cxp_disk_io_read_bytes_total", "Total bytes read from disk", ['container_name'])
gauge_disk_write = Gauge("cxp_disk_io_write_bytes_total", "Total bytes written to disk", ['container_name'])
gauge_net_rx = Gauge("cxp_network_rx_bytes_total", "Total bytes received over network", ['container_name'])
gauge_net_tx = Gauge("cxp_network_tx_bytes_total", "Total bytes sent over network", ['container_name'])

counter_running_containers_total = Gauge("cxp_running_cotainers_total", "Total number of running containers")
gauge_running_containers_total = Gauge("cxp_running_cotainers_total", "Total number of running containers")

async def get_containers(all=False) -> list[DockerContainer]:
return await docker_client.containers.list(all=all)
Expand All @@ -62,7 +62,7 @@ async def container_stats(running_containers: list[DockerContainer]):
all_stats = await stat.get_containers_stats(running_containers)
running_containers_total = len(running_containers)

counter_running_containers_total.set(running_containers_total)
gauge_running_containers_total.set(running_containers_total)

for stats in all_stats:
name = stats[0].get('name', stats[0].get('id', 'Unkown').lstrip("/")).lstrip("/")
Expand All @@ -73,20 +73,20 @@ async def container_stats(running_containers: list[DockerContainer]):
disk_read, disk_write = stat.calculate_disk_io(stats[0])
net_rx, net_tx = stat.calculate_network_io(stats[0])

counter_disk_read.labels(container_name=name).set(disk_read)
counter_disk_write.labels(container_name=name).set(disk_write)
counter_net_rx.labels(container_name=name).set(net_rx)
counter_net_tx.labels(container_name=name).set(net_tx)
gauge_disk_read.labels(container_name=name).set(disk_read)
gauge_disk_write.labels(container_name=name).set(disk_write)
gauge_net_rx.labels(container_name=name).set(net_rx)
gauge_net_tx.labels(container_name=name).set(net_tx)

# List of metrics we want to prune (performance counters)
prunable_metrics: list[PromMetric] = [
gauge_cpu_percentage, gauge_memory_percentage, gauge_memory_bytes,
counter_disk_read, counter_disk_write, counter_net_rx, counter_net_tx
gauge_disk_read, gauge_disk_write, gauge_net_rx, gauge_net_tx
]

# Metrics we want to always keep, and set to 0 instead
persistent_metrics: list[Gauge] = [
gauge_container_status, counter_running_containers_total
gauge_container_status, gauge_running_containers_total
]


Expand Down
4 changes: 2 additions & 2 deletions scripts/healthcheck-ci.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ fi

log "Displaying container-related metrics:"
echo -e "\n${GREEN}--- Metrics with container added ---${NC}"
grep 'container_name' "${log_dir}/metrics.txt" | sort | uniq || echo "(No container metrics found)"
grep -e '^cxp' "${log_dir}/metrics.txt" | sort | uniq || echo "(No container metrics found)"

log "Removing test container..."
docker rm -f "$container_name" >/dev/null || fail "Failed to remove test container"
Expand All @@ -66,7 +66,7 @@ fi

log "Displaying container-related metrics after removal:"
echo -e "\n${GREEN}--- Metrics after container removed ---${NC}"
grep 'container_name' "${log_dir}/metrics_post_remove.txt" | sort | uniq || echo "(No container metrics found)"
grep '^cxp' "${log_dir}/metrics_post_remove.txt" | sort | uniq || echo "(No container metrics found)"

pass "Full Healthcheck Completed Successfully."

Expand Down
Loading