物理修复(400 失败点归因,见 docs/failed400_nan_pseudo_convergence_2026_08_17.md): - runner: 阶段 converged 后复查 fort.7,含 NaN/Inf 即否决(fort.9 全零伪收敛, 曾致 261 点误跳过 nl_direct 回退);否决阶段不产出种子,阻断污染传播 - runner: nl_tight 回退——仅能量边际失败时以 CHMAX 收紧 10× 从自身模型续迭代, 残差降幅 ~10×;execute_tlusty_stage 抽取供主链与回退共用 - conv_check: fort.14 为 Eddington 通量 Hλ,积分需乘 4π 再比 σTeff⁴ (旧版 ratio 稳定 0.0796=1/4π,全点系统性假阳性)+ 回归测试 - nst_writer: 单行超 80 字符被 TLUSTY 静默截断,IFALI/JALI/TRAD 等从未生效; 按 75 字符自动换行 - seed_finder: Teff 容忍度改含边界 <=,相邻 5000K 档恢复互为种子 + 回归测试 谱线表与网格: - 默认线表 gfVIS99 → gfATO(全波段 18-23000Å),TaskSpec.linelist 支持工作流 级覆盖,节点按需下载(进程互斥锁防并发重复下载 238MB) - sdB_cno Teff 加密至 5000K 步长,432 → 9216 点;tlusty/synspec 静态二进制更新 统计与部署: - grid 汇总改按 tlusty_status/synspec_status 分项计数,新增 tlusty_failed/ synspec_failed/synspec_pending,前端详情页双视图适配 - deploy/fetch_results 支持跳板机 ProxyJump 与 SSH 主连接复用,fetch 新增 --force; - Docker 构建支持 CARGO_MIRROR/USE_MIRRORS 国内镜像参数;移除 tools/ 拷贝 - 新增 tlusty-synspec-test skill 与 6 篇根因分析/验证文档
91 lines
3.6 KiB
Bash
Executable File
91 lines
3.6 KiB
Bash
Executable File
#!/bin/bash
|
||
# ============================================================
|
||
# SYNSPEC 执行模板 — 由 new_test.sh 拷为 scripts/run.sh
|
||
# 规范: docs/testing_workflow_2026_08_11.md §四;references/synspec-inputs.md
|
||
# 输入: fort.5(stdin) fort.55(控制卡) fort.8(收敛大气) + fort.19/data 软链
|
||
# 用法: bash scripts/run.sh [timeout_sec]
|
||
# 产物: outputs/{name}.spec/.cont/.iden/.lindat + synspec.log
|
||
# ============================================================
|
||
set -uo pipefail
|
||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||
TEST_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
|
||
INPUTS="$TEST_DIR/inputs"; RUN="$TEST_DIR/run"; OUTPUTS="$TEST_DIR/outputs"
|
||
|
||
SYNSPEC="/home/fmq/program/tlusty/tl208-s54/dcts/assets/synspec_static"
|
||
RUNTIME_DATA="/home/fmq/program/tlusty/tl208-s54/dcts/assets/data"
|
||
TIMEOUT_SEC="${1:-1200}"
|
||
OUT_NAME="${OUT_NAME:-spectrum}" # 产物名前缀,可环境变量覆盖
|
||
|
||
# --- 1. 切 run/,清理上轮 ---
|
||
mkdir -p "$RUN" "$OUTPUTS"
|
||
cd "$RUN"
|
||
rm -f fort.* *.spec *.cont *.iden *.lindat *.log *.err
|
||
|
||
# --- 2. 复制输入 ---
|
||
[ -f "$INPUTS/fort.5" ] || { echo "❌ 缺 inputs/fort.5"; exit 1; }
|
||
[ -f "$INPUTS/fort.55" ] || { echo "❌ 缺 inputs/fort.55"; exit 1; }
|
||
[ -f "$INPUTS/fort.8" ] || { echo "❌ 缺 inputs/fort.8 (收敛大气)"; exit 1; }
|
||
cp "$INPUTS/fort.5" fort.5
|
||
cp "$INPUTS/fort.55" fort.55
|
||
cp "$INPUTS/fort.8" fort.8
|
||
# fort.19 / data: 软链(优先用 inputs 里已有的,否则指 assets)
|
||
if [ -e "$INPUTS/fort.19" ]; then
|
||
ln -sfn "$(readlink -f "$INPUTS/fort.19")" fort.19
|
||
else
|
||
ln -sfn "$RUNTIME_DATA/gfATO.dat" fort.19 # 全波段默认
|
||
fi
|
||
ln -sfn "$RUNTIME_DATA" data
|
||
|
||
# --- 3. 执行前自检 ---
|
||
echo "=== 执行前自检 ==="
|
||
echo "fort.5 第1行 TEFF/GRAV: $(sed -n '1p' fort.5)"
|
||
echo "fort.55 第6行 波长范围: $(sed -n '6p' fort.55)"
|
||
echo "fort.8 行数: $(wc -l < fort.8)"
|
||
echo "fort.8 NaN/坏行: $(grep -ciE 'nan|inf|\*{3,}' fort.8 || true)"
|
||
echo "fort.19 -> $(readlink fort.19)"
|
||
echo "data -> $(readlink data)"
|
||
echo ""
|
||
|
||
# --- 4. 执行 SYNSPEC ---
|
||
echo "=== 执行 SYNSPEC (timeout ${TIMEOUT_SEC}s) ==="
|
||
T0=$(date +%s)
|
||
set +e
|
||
timeout "$TIMEOUT_SEC" "$SYNSPEC" < fort.5 > synspec.log 2> synspec.err
|
||
RC=$?
|
||
set -e
|
||
T1=$(date +%s)
|
||
echo "rc=$RC, elapsed=$((T1-T0))s"
|
||
# rc=124 = timeout 杀死。SYNSPEC 大线表全波段易超时,产物可能不完整。
|
||
if [ "$RC" -eq 124 ]; then
|
||
echo "⚠⚠ SYNSPEC TIMEOUT (rc=124, 超过 ${TIMEOUT_SEC}s 被 kill —— spec 可能不完整/被截断)"
|
||
touch "$OUTPUTS/SYNSPEC.TIMEOUT"
|
||
fi
|
||
|
||
# --- 5. 产物重命名 ---
|
||
# SYNSPEC: fort.7=spectrum, fort.17=continuum, fort.12=line IDs, fort.11=line data
|
||
[ -f fort.7 ] && cp fort.7 "$OUTPUTS/${OUT_NAME}.spec"
|
||
[ -f fort.17 ] && cp fort.17 "$OUTPUTS/${OUT_NAME}.cont"
|
||
[ -f fort.12 ] && cp fort.12 "$OUTPUTS/${OUT_NAME}.iden"
|
||
[ -f fort.11 ] && cp fort.11 "$OUTPUTS/${OUT_NAME}.lindat"
|
||
cp synspec.log "$OUTPUTS/synspec.log" 2>/dev/null || true
|
||
cp synspec.err "$OUTPUTS/synspec.err" 2>/dev/null || true
|
||
|
||
# --- 6. 立即数值审查 ---
|
||
echo ""
|
||
echo "=== 数值审查 ==="
|
||
SPEC="$OUTPUTS/${OUT_NAME}.spec"
|
||
if [ -f "$SPEC" ]; then
|
||
ROWS=$(wc -l < "$SPEC")
|
||
FIRST=$(head -1 "$SPEC" | awk '{print $1}')
|
||
LAST=$(tail -1 "$SPEC" | awk '{print $1}')
|
||
NAN=$(grep -ciE 'nan|inf|\*{3,}' "$SPEC" || true)
|
||
echo "spec 行数: $ROWS"
|
||
echo "波长范围: $FIRST - $LAST Å"
|
||
echo "NaN/Inf/坏行: $NAN $([ "$NAN" = 0 ] && echo '✅' || echo '❌')"
|
||
else
|
||
echo "!! 未生成 ${OUT_NAME}.spec(SYNSPEC 失败,rc=$RC)"
|
||
fi
|
||
echo ""
|
||
echo "synspec.log 尾 15 行:"
|
||
tail -15 "$OUTPUTS/synspec.log" 2>/dev/null || echo "(无 log)"
|