argus/src/sys/tests/scripts/07_logs_send_and_assert.sh

93 lines
3.6 KiB
Bash
Executable File

#!/usr/bin/env bash
set -euo pipefail
echo "[INFO] Sending logs via node-a/node-b and asserting ES counts..."
# 载入端口变量
TEST_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. && pwd)"
if [[ -f "$TEST_ROOT/.env" ]]; then
set -a; source "$TEST_ROOT/.env"; set +a
fi
# Robust count helper: tolerates 404/503 and non-JSON responses, returns integer >=0
get_count() {
local idx="$1"; local tmp; tmp=$(mktemp)
local code
code=$(curl -s -o "$tmp" -w "%{http_code}" "http://localhost:${ES_HTTP_PORT:-9200}/${idx}/_count?ignore_unavailable=true&allow_no_indices=true" || true)
if [[ "$code" == "200" ]]; then
local val
val=$(jq -r '(.count // 0) | tonumber? // 0' "$tmp" 2>/dev/null || echo 0)
echo "$val"
else
echo 0
fi
rm -f "$tmp"
}
train0=$(get_count "train-*")
infer0=$(get_count "infer-*")
base=$((train0 + infer0))
echo "[INFO] initial counts: train=${train0} infer=${infer0} total=${base}"
send_logs() {
local cname="$1"; local hosttag="$2"
docker exec "$cname" sh -lc 'mkdir -p /logs/train /logs/infer'
docker exec "$cname" sh -lc "ts=\$(date -u +%Y-%m-%dT%H:%M:%SZ); echo \"\$ts INFO [$hosttag] training step=1 loss=1.23 model=bert\" >> /logs/train/train-demo.log"
docker exec "$cname" sh -lc "ts=\$(date -u +%Y-%m-%dT%H:%M:%SZ); echo \"\$ts INFO [$hosttag] training step=2 loss=1.10 model=bert\" >> /logs/train/train-demo.log"
docker exec "$cname" sh -lc "ts=\$(date -u +%Y-%m-%dT%H:%M:%SZ); echo \"\$ts WARN [$hosttag] inference slow on batch=2 latency=1.9s\" >> /logs/infer/infer-demo.log"
}
# Determine container names
node_a=$(docker ps --format '{{.Names}}' | grep -E '^argus-node-a$|argus-sys-node-a-1' | head -n1)
node_b=$(docker ps --format '{{.Names}}' | grep -E '^argus-node-b$|argus-sys-node-b-1' | head -n1)
send_logs "$node_a" "host01"
send_logs "$node_b" "host02"
echo "[INFO] Waiting for ES to ingest..."
# Proactively refresh indices (ignore errors if not created yet)
curl -s -X POST "http://localhost:${ES_HTTP_PORT:-9200}/train-*/_refresh" >/dev/null 2>&1 || true
curl -s -X POST "http://localhost:${ES_HTTP_PORT:-9200}/infer-*/_refresh" >/dev/null 2>&1 || true
# Retry up to 120s for counts to increase and reach threshold (>=4)
final=0
threshold=4
for attempt in {1..60}; do
train1=$(get_count "train-*")
infer1=$(get_count "infer-*")
final=$((train1 + infer1))
if (( final > base && final >= threshold )); then
break
fi
echo "[..] waiting ES counts increase to >=${threshold} ($attempt/60) current=${final} base=${base}"
# refresh indices again to speed up visibility
curl -s -X POST "http://localhost:${ES_HTTP_PORT:-9200}/train-*/_refresh" >/dev/null 2>&1 || true
curl -s -X POST "http://localhost:${ES_HTTP_PORT:-9200}/infer-*/_refresh" >/dev/null 2>&1 || true
sleep 2
done
echo "[INFO] final counts: train=${train1} infer=${infer1} total=${final}"
if (( final <= base )); then
echo "[ERR] ES total did not increase (${base} -> ${final})" >&2
exit 1
fi
# Minimal threshold to be tolerant: expect at least 4 documents (2 train + 1 infer per node)
if (( final < 4 )); then
echo "[ERR] ES total below expected threshold: ${final} < 4" >&2
exit 1
fi
# Health endpoints
es_health=$(curl -s "http://localhost:${ES_HTTP_PORT:-9200}/_cluster/health" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
if [[ "$es_health" != "green" && "$es_health" != "yellow" ]]; then
echo "[ERR] ES health not green/yellow: $es_health" >&2
exit 1
fi
if ! curl -fs "http://localhost:${KIBANA_PORT:-5601}/api/status" >/dev/null 2>&1; then
echo "[WARN] Kibana status endpoint not available"
fi
echo "[OK] ES counts increased and services healthy"