Add multinode NCCL PDF matrix runner

This commit is contained in:
cs 2026-05-23 19:21:58 +08:00
parent bdffd7e616
commit 8ff5021385
9 changed files with 176 additions and 6 deletions

View File

@ -23,7 +23,7 @@ multinode_nccl:
- /usr/mpi/gcc/openmpi-4.1.9a1/lib
- /tmp/nccl-2.27.7-cuda12.4/usr/lib/x86_64-linux-gnu
- /usr/local/cuda-12.4/targets/x86_64-linux/lib
nccl_tests_dir: null
nccl_tests_dir: /data/nccl-tests-latest/build
tests:
- all_reduce_perf
- alltoall_perf

View File

@ -23,7 +23,7 @@ multinode_nccl:
- /usr/mpi/gcc/openmpi-4.1.9a1/lib
- /tmp/nccl-2.27.7-cuda12.4/usr/lib/x86_64-linux-gnu
- /usr/local/cuda-12.4/targets/x86_64-linux/lib
nccl_tests_dir: null
nccl_tests_dir: /data/nccl-tests-latest/build
tests:
- all_reduce_perf
- alltoall_perf

View File

@ -23,7 +23,7 @@ multinode_nccl:
- /usr/mpi/gcc/openmpi-4.1.9a1/lib
- /tmp/nccl-2.27.7-cuda12.4/usr/lib/x86_64-linux-gnu
- /usr/local/cuda-12.4/targets/x86_64-linux/lib
nccl_tests_dir: null
nccl_tests_dir: /data/nccl-tests-latest/build
tests:
- all_reduce_perf
- alltoall_perf

View File

@ -23,7 +23,7 @@ multinode_nccl:
- /usr/mpi/gcc/openmpi-4.1.9a1/lib
- /tmp/nccl-2.27.7-cuda12.4/usr/lib/x86_64-linux-gnu
- /usr/local/cuda-12.4/targets/x86_64-linux/lib
nccl_tests_dir: null
nccl_tests_dir: /data/nccl-tests-latest/build
tests:
- all_reduce_perf
- alltoall_perf

View File

@ -23,7 +23,7 @@ multinode_nccl:
- /usr/mpi/gcc/openmpi-4.1.9a1/lib
- /tmp/nccl-2.27.7-cuda12.4/usr/lib/x86_64-linux-gnu
- /usr/local/cuda-12.4/targets/x86_64-linux/lib
nccl_tests_dir: null
nccl_tests_dir: /data/nccl-tests-latest/build
tests:
- all_reduce_perf
- alltoall_perf

View File

@ -24,6 +24,16 @@ bash scripts/multinode_nccl_deep_diagnose.sh preflight
bash scripts/multinode_nccl_deep_diagnose.sh all
```
如果要按 PDF 参考矩阵跑正式多机多卡报告,使用:
```bash
cd /root/test_gpu_scripts
bash scripts/run_multinode_nccl_pdf_matrix.sh
```
它会跑 2 机 x 1/2/4/8 GPU per node 的 `all_reduce_perf``alltoall_perf`,输出到
`reports/multinode_nccl_pdf_matrix_YYYYMMDD_HHMMSS.md`
默认输出目录为:
```text
@ -63,7 +73,7 @@ bash scripts/multinode_nccl_deep_diagnose.sh all
如果 nccl-tests 或 NCCL 运行库路径变化:
```bash
NCCL_TESTS_DIR=/opt/gpu-test-tools/nccl-tests/build \
NCCL_TESTS_DIR=/data/nccl-tests-latest/build \
NCCL_LD_LIBRARY_PATH=/usr/mpi/gcc/openmpi-4.1.9a1/lib:/path/to/nccl/lib:/usr/local/cuda/lib64 \
bash scripts/multinode_nccl_deep_diagnose.sh graph
```

View File

@ -119,6 +119,13 @@ cd /root/test_gpu_scripts
bash scripts/run_h100_single_node_all.sh
```
### 多机多卡 PDF 矩阵
```bash
cd /root/test_gpu_scripts
bash scripts/run_multinode_nccl_pdf_matrix.sh
```
### 完整深度诊断
```bash
@ -155,6 +162,8 @@ OUT_DIR=/root/test_gpu_scripts/reports/nccl_deep_diag_plugin_check_$(date +%Y%m%
| `scripts/multinode_nccl_deep_diagnose.sh` | 可复跑诊断脚本 |
| `scripts/nccl_environment_snapshot.sh` | 单节点 HCA/plugin/topo 快照脚本 |
| `scripts/run_h100_single_node_all.sh` | 单节点原始 `test all` 报告入口 |
| `scripts/run_multinode_nccl_pdf_matrix.sh` | 多机多卡 PDF 矩阵报告入口 |
| `configs/multinode_nccl_nccl227_pdf_matrix.yaml` | 多机多卡 PDF 矩阵配置 |
## 当前建议

View File

@ -28,8 +28,17 @@
| `scripts/multinode_nccl_deep_diagnose.sh` | 可复跑的多节点 NCCL 深度诊断脚本 |
| `scripts/nccl_environment_snapshot.sh` | 单节点 NCCL/RDMA 环境等价性快照脚本,不启动 NCCL workload |
| `scripts/run_h100_single_node_all.sh` | 单节点 H100 `test all` 原始报告入口,默认同时采环境快照 |
| `scripts/run_multinode_nccl_pdf_matrix.sh` | 多机多卡 PDF 矩阵入口,跑 2 机 x 1/2/4/8 GPU per node 的 allreduce/alltoall |
| `configs/multinode_nccl_nccl227_pdf_matrix.yaml` | 多机多卡 PDF 矩阵配置,固定 NCCL 2.27.7 和 `/data/nccl-tests-latest/build` |
| `docs/multinode_nccl_deep_diagnose_runbook.md` | 诊断脚本中文 runbook |
多机多卡 PDF 矩阵:
```bash
cd /root/test_gpu_scripts
bash scripts/run_multinode_nccl_pdf_matrix.sh
```
单节点 H100 原始 all 报告:
```bash

View File

@ -0,0 +1,142 @@
#!/usr/bin/env bash
set -uo pipefail
# Run the formal cross-node NCCL PDF matrix for the current two-node H100 pair.
# This wrapper standardizes the command, output naming, and preflight hook; the
# actual benchmark implementation remains in gpu_tester.py / MultiNodeNCCLTest.
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" >/dev/null 2>&1 && pwd)"
PROJECT_DIR="$(cd -- "$SCRIPT_DIR/.." >/dev/null 2>&1 && pwd)"
PYTHON_BIN="${PYTHON_BIN:-/root/gpu-test-venv/bin/python}"
CONFIG_FILE="${CONFIG_FILE:-$PROJECT_DIR/configs/multinode_nccl_nccl227_pdf_matrix.yaml}"
OUT_DIR="${OUT_DIR:-$PROJECT_DIR/reports}"
FORMAT="${FORMAT:-md}"
DRY_RUN=0
RUN_PREFLIGHT=1
PREFLIGHT_ONLY=0
usage() {
cat <<'EOF'
Usage: run_multinode_nccl_pdf_matrix.sh [options]
Options:
--python PATH Python executable (default: /root/gpu-test-venv/bin/python)
--config PATH Matrix config file (default: configs/multinode_nccl_nccl227_pdf_matrix.yaml)
--out-dir PATH Report output directory (default: reports)
--format FORMAT Report format: md, json, or html (default: md)
--no-preflight Skip scripts/multinode_nccl_deep_diagnose.sh preflight
--preflight-only Run only the preflight check, not the matrix workload
--dry-run Print commands without running them
-h, --help Show this help
EOF
}
while (($#)); do
case "$1" in
--python)
PYTHON_BIN="$2"
shift 2
;;
--config)
CONFIG_FILE="$2"
shift 2
;;
--out-dir)
OUT_DIR="$2"
shift 2
;;
--format)
FORMAT="$2"
shift 2
;;
--no-preflight)
RUN_PREFLIGHT=0
shift
;;
--preflight-only)
PREFLIGHT_ONLY=1
shift
;;
--dry-run)
DRY_RUN=1
shift
;;
-h|--help)
usage
exit 0
;;
*)
echo "Unknown argument: $1" >&2
usage >&2
exit 2
;;
esac
done
if [[ "$FORMAT" != "md" && "$FORMAT" != "json" && "$FORMAT" != "html" ]]; then
echo "Unsupported format: $FORMAT" >&2
exit 2
fi
if [[ ! -x "$PYTHON_BIN" ]]; then
PYTHON_BIN="$(command -v python3 || true)"
fi
if [[ -z "$PYTHON_BIN" || ! -x "$PYTHON_BIN" ]]; then
echo "Python executable not found. Set --python or PYTHON_BIN." >&2
exit 1
fi
TS="$(date +%Y%m%d_%H%M%S)"
mkdir -p "$OUT_DIR"
REPORT_FILE="$OUT_DIR/multinode_nccl_pdf_matrix_${TS}.${FORMAT}"
PREFLIGHT_CMD=(bash "$PROJECT_DIR/scripts/multinode_nccl_deep_diagnose.sh" preflight)
MATRIX_CMD=(
"$PYTHON_BIN" "$PROJECT_DIR/gpu_tester.py"
--config "$CONFIG_FILE"
--test multinode-nccl
--report
--format "$FORMAT"
--output "$REPORT_FILE"
)
echo "Project: $PROJECT_DIR"
echo "Config: $CONFIG_FILE"
echo "Report: $REPORT_FILE"
echo "Matrix: 2 nodes x {1,2,4,8} GPUs per node; all_reduce_perf + alltoall_perf; 16G"
if ((DRY_RUN)); then
if ((RUN_PREFLIGHT)); then
printf 'DRY RUN preflight:'
printf ' %q' "${PREFLIGHT_CMD[@]}"
printf '\n'
fi
if ((PREFLIGHT_ONLY)); then
exit 0
fi
printf 'DRY RUN matrix:'
printf ' %q' "${MATRIX_CMD[@]}"
printf '\n'
exit 0
fi
if ((RUN_PREFLIGHT)); then
"${PREFLIGHT_CMD[@]}"
preflight_status=$?
if ((preflight_status != 0)); then
echo "Preflight failed with exit code $preflight_status" >&2
exit "$preflight_status"
fi
fi
if ((PREFLIGHT_ONLY)); then
exit 0
fi
"${MATRIX_CMD[@]}"
status=$?
echo "Report written to: $REPORT_FILE"
exit "$status"