fix: use smaller timeouts for circuit relay connections #7894
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: PR Benchmarks | |
| on: pull_request | |
| env: | |
| CARGO_INCREMENTAL: "0" | |
| RUST_BACKTRACE: 1 | |
| CLIENT_DATA_PATH: /home/runner/.local/share/autonomi/client | |
| NODE_DATA_PATH: /home/runner/.local/share/autonomi/node | |
| jobs: | |
| benchmark-cli: | |
| name: Compare autonomi_cli benchmarks to main | |
| # right now only ubuntu, running on multiple systems would require many pushes...\ | |
| # perhaps this can be done with one consolidation action in the future, pulling down all results and pushing | |
| # once to the branch.. | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@stable | |
| with: | |
| components: rustfmt, clippy | |
| - uses: Swatinem/rust-cache@v2 | |
| continue-on-error: true | |
| ######################## | |
| ### Setup ### | |
| ######################## | |
| - run: cargo install cargo-criterion | |
| - name: install ripgrep | |
| run: sudo apt-get -y install ripgrep | |
| - name: Download 95mb file to be uploaded with the safe client | |
| shell: bash | |
| run: wget https://sn-node.s3.eu-west-2.amazonaws.com/the-test-data.zip | |
| # As normal user won't care much about initial client startup, | |
| # but be more alerted on communication speed during transmission. | |
| # Meanwhile the criterion testing code includes the client startup as well, | |
| # it will be better to execute bench test with `local`, | |
| # to make the measurement results reflect speed improvement or regression more accurately. | |
| - name: Build binaries | |
| run: cargo build --release --features local --bin antnode --bin ant | |
| timeout-minutes: 30 | |
| - name: Start a local network | |
| uses: maidsafe/ant-local-testnet-action@main | |
| env: | |
| ANT_LOG: "all" | |
| with: | |
| action: start | |
| enable-evm-testnet: true | |
| node-path: target/release/antnode | |
| platform: ubuntu-latest | |
| build: true | |
| - name: Check ANT_PEERS was set | |
| shell: bash | |
| run: echo "The ANT_PEERS variable has been set to $ANT_PEERS" | |
| - name: export default secret key | |
| run: echo "SECRET_KEY=0xac0974bec39a17e36ba4a6b4d238ff944bacb478cbed5efcae784d7bf4f2ff80" >> $GITHUB_ENV | |
| shell: bash | |
| ######################### | |
| ### Upload large file ### | |
| ######################### | |
| - name: Start a client instance to compare memory usage | |
| shell: bash | |
| run: ./target/release/ant --log-output-dest=data-dir file upload "./the-test-data.zip" | |
| env: | |
| ANT_LOG: "all" | |
| timeout-minutes: 5 | |
| - name: Cleanup uploaded_files folder to avoid pollute download benchmark | |
| shell: bash | |
| run: | | |
| ls -l $CLIENT_DATA_PATH | |
| rm -rf $CLIENT_DATA_PATH/uploaded_files | |
| ########################### | |
| ### Client Mem Analysis ### | |
| ########################### | |
| ### The peak limit shall be restored back to 50MB, | |
| ### Once client side chunking/quoting flow got re-examined. | |
| - name: Check client memory usage | |
| shell: bash | |
| run: | | |
| client_peak_mem_limit_mb="1500" # mb | |
| client_avg_mem_limit_mb="512" # mb | |
| peak_mem_usage=$( | |
| rg '"memory_used_mb":[^,]*' $CLIENT_DATA_PATH/logs --glob ant.* -o --no-line-number --no-filename | | |
| awk -F':' '/"memory_used_mb":/{print $2}' | | |
| sort -n | | |
| tail -n 1 | |
| ) | |
| echo "Peak memory usage: $peak_mem_usage MB" | |
| if (( $(echo "$peak_mem_usage > $client_peak_mem_limit_mb" | bc -l) )); then | |
| echo "Client peak memory usage exceeded threshold: $client_peak_mem_limit_mb MB" | |
| exit 1 | |
| fi | |
| total_mem=$( | |
| rg '"memory_used_mb":[^,]*' $CLIENT_DATA_PATH/logs --glob ant.* -o --no-line-number --no-filename | | |
| awk -F':' '/"memory_used_mb":/ {sum += $2} END {printf "%.0f\n", sum}' | |
| ) | |
| num_of_times=$( | |
| rg "\"memory_used_mb\"" $CLIENT_DATA_PATH/logs --glob ant.* -c --stats | | |
| rg "(\d+) matches" | | |
| rg "\d+" -o | |
| ) | |
| echo "num_of_times: $num_of_times" | |
| echo "Total memory is: $total_mem" | |
| average_mem=$(($total_mem/$(($num_of_times)))) | |
| echo "Average memory is: $average_mem" | |
| if (( $(echo "$average_mem > $client_avg_mem_limit_mb" | bc -l) )); then | |
| echo "Client average memory usage exceeded threshold: $client_avg_mem_limit_mb MB" | |
| exit 1 | |
| fi | |
| # Write the client memory usage to a file | |
| echo '[ | |
| { | |
| "name": "client-peak-memory-usage-during-upload", | |
| "value": '$peak_mem_usage', | |
| "unit": "MB" | |
| }, | |
| { | |
| "name": "client-average-memory-usage-during-upload", | |
| "value": '$average_mem', | |
| "unit": "MB" | |
| } | |
| ]' > client_memory_usage.json | |
| - name: check client_memory_usage.json | |
| shell: bash | |
| run: cat client_memory_usage.json | |
| - name: Alert for client memory usage | |
| uses: benchmark-action/github-action-benchmark@v1 | |
| with: | |
| name: "Memory Usage of Client during uploading large file" | |
| tool: "customSmallerIsBetter" | |
| output-file-path: client_memory_usage.json | |
| # Where the previous data file is stored | |
| external-data-json-path: ./cache/client-mem-usage.json | |
| # Workflow will fail when an alert happens | |
| fail-on-alert: true | |
| # GitHub API token to make a commit comment | |
| github-token: ${{ secrets.GITHUB_TOKEN }} | |
| # Enable alert commit comment | |
| comment-on-alert: true | |
| # 200% regression will result in alert | |
| alert-threshold: "200%" | |
| # Enable Job Summary for PRs | |
| summary-always: true | |
| # ######################## | |
| # ### Benchmark ### | |
| # ######################## | |
| # - name: Bench `safe` cli | |
| # shell: bash | |
| # # Criterion outputs the actual bench results to stderr "2>&1 tee output.txt" takes stderr, | |
| # # passes to tee which displays it in the terminal and writes to output.txt | |
| # run: | | |
| # cargo criterion --features=local --message-format=json 2>&1 -p sn_cli | tee -a output.txt | |
| # cat output.txt | rg benchmark-complete | jq -s 'map({ | |
| # name: (.id | split("/"))[-1], | |
| # unit: "MiB/s", | |
| # value: ((if .throughput[0].unit == "KiB/s" then (.throughput[0].per_iteration / (1024*1024*1024)) else (.throughput[0].per_iteration / (1024*1024)) end) / (.mean.estimate / 1e9)) | |
| # })' > files-benchmark.json | |
| # timeout-minutes: 15 | |
| # - name: Confirming the number of files uploaded and downloaded during the benchmark test | |
| # shell: bash | |
| # run: | | |
| # ls -l $CLIENT_DATA_PATH | |
| # ls -l $CLIENT_DATA_PATH/uploaded_files | |
| # ls -l $CLIENT_DATA_PATH/safe_files | |
| # - name: Store benchmark result | |
| # uses: benchmark-action/github-action-benchmark@v1 | |
| # with: | |
| # # What benchmark tool the output.txt came from | |
| # tool: "customBiggerIsBetter" | |
| # output-file-path: files-benchmark.json | |
| # # Where the previous data file is stored | |
| # external-data-json-path: ./cache/benchmark-data.json | |
| # # Workflow will fail when an alert happens | |
| # fail-on-alert: true | |
| # # GitHub API token to make a commit comment | |
| # github-token: ${{ secrets.GITHUB_TOKEN }} | |
| # # Enable alert commit comment | |
| # comment-on-alert: true | |
| # # 200% regression will result in alert | |
| # alert-threshold: "200%" | |
| # # Enable Job Summary for PRs | |
| # summary-always: true | |
| # - name: Start a client to carry out download to output the logs | |
| # shell: bash | |
| # run: target/release/safe --log-output-dest=data-dir files download --retry-strategy quick | |
| # - name: Start a client to simulate criterion upload | |
| # shell: bash | |
| # run: | | |
| # ls -l target/release | |
| # target/release/safe --log-output-dest=data-dir files upload target/release/faucet --retry-strategy quick | |
| ######################### | |
| ### Stop Network ### | |
| ######################### | |
| - name: Stop the local network | |
| if: always() | |
| uses: maidsafe/ant-local-testnet-action@main | |
| with: | |
| action: stop | |
| log_file_prefix: safe_test_logs_benchmark | |
| platform: ubuntu-latest | |
| build: true | |
| ######################### | |
| ### Node Mem Analysis ### | |
| ######################### | |
| # The large file uploaded will increase node's peak mem usage a lot | |
| - name: Check node memory usage | |
| shell: bash | |
| run: | | |
| node_peak_mem_limit_mb="250" # mb | |
| peak_mem_usage=$( | |
| rg '"memory_used_mb":[^,]*' $NODE_DATA_PATH/*/logs/* -o --no-line-number --no-filename | | |
| awk -F':' '/"memory_used_mb":/{print $2}' | | |
| sort -n | | |
| tail -n 1 | |
| ) | |
| echo "Memory usage: $peak_mem_usage MB" | |
| if (( $(echo "$peak_mem_usage > $node_peak_mem_limit_mb" | bc -l) )); then | |
| echo "Node memory usage exceeded threshold: $peak_mem_usage MB" | |
| exit 1 | |
| fi | |
| # Write the node memory usage to a file | |
| echo '[ | |
| { | |
| "name": "node-memory-usage-through-safe-benchmark", | |
| "value": '$peak_mem_usage', | |
| "unit": "MB" | |
| } | |
| ]' > node_memory_usage.json | |
| - name: check node_memory_usage.json | |
| shell: bash | |
| run: cat node_memory_usage.json | |
| - name: Alert for node memory usage | |
| uses: benchmark-action/github-action-benchmark@v1 | |
| with: | |
| tool: "customSmallerIsBetter" | |
| output-file-path: node_memory_usage.json | |
| # Where the previous data file is stored | |
| external-data-json-path: ./cache/node-mem-usage.json | |
| # Workflow will fail when an alert happens | |
| fail-on-alert: true | |
| # GitHub API token to make a commit comment | |
| github-token: ${{ secrets.GITHUB_TOKEN }} | |
| # Enable alert commit comment | |
| comment-on-alert: true | |
| # Comment on the PR | |
| comment-always: true | |
| # 200% regression will result in alert | |
| alert-threshold: "200%" | |
| # Enable Job Summary for PRs | |
| summary-always: true | |
| ########################################### | |
| ### Swarm_driver handling time Analysis ### | |
| ########################################### | |
| - name: Check swarm_driver handling time | |
| shell: bash | |
| run: | | |
| num_of_times=$( | |
| rg "SwarmCmd handled in [0-9.]+ms:" $NODE_DATA_PATH/*/logs/* --glob antnode.* -c --stats | | |
| rg "(\d+) matches" | | |
| rg "\d+" -o | |
| ) | |
| echo "Number of long cmd handling times: $num_of_times" | |
| total_long_handling_ms=$( | |
| rg "SwarmCmd handled in [0-9.]+ms:" $NODE_DATA_PATH/*/logs/* --glob antnode.* -o --no-line-number --no-filename | | |
| awk -F' |ms:' '{sum += $4} END {printf "%.0f\n", sum}' | |
| ) | |
| echo "Total cmd long handling time is: $total_long_handling_ms ms" | |
| average_handling_ms=$(($total_long_handling_ms/$(($num_of_times)))) | |
| echo "Average cmd long handling time is: $average_handling_ms ms" | |
| total_long_handling=$(($total_long_handling_ms)) | |
| total_num_of_times=$(($num_of_times)) | |
| num_of_times=$( | |
| rg "SwarmEvent handled in [0-9.]+ms:" $NODE_DATA_PATH/*/logs/* --glob antnode.* -c --stats | | |
| rg "(\d+) matches" | | |
| rg "\d+" -o | |
| ) | |
| echo "Number of long event handling times: $num_of_times" | |
| total_long_handling_ms=$( | |
| rg "SwarmEvent handled in [0-9.]+ms:" $NODE_DATA_PATH/*/logs/* --glob antnode.* -o --no-line-number --no-filename | | |
| awk -F' |ms:' '{sum += $4} END {printf "%.0f\n", sum}' | |
| ) | |
| echo "Total event long handling time is: $total_long_handling_ms ms" | |
| average_handling_ms=$(($total_long_handling_ms/$(($num_of_times)))) | |
| echo "Average event long handling time is: $average_handling_ms ms" | |
| total_long_handling=$(($total_long_handling_ms+$total_long_handling)) | |
| total_num_of_times=$(($num_of_times+$total_num_of_times)) | |
| average_handling_ms=$(($total_long_handling/$(($total_num_of_times)))) | |
| echo "Total swarm_driver long handling times is: $total_num_of_times" | |
| echo "Total swarm_driver long handling duration is: $total_long_handling ms" | |
| echo "Total average swarm_driver long handling duration is: $average_handling_ms ms" | |
| total_num_of_times_limit_hits="30000" # hits | |
| total_long_handling_limit_ms="400000" # ms | |
| average_handling_limit_ms="20" # ms | |
| if (( $(echo "$total_num_of_times > $total_num_of_times_limit_hits" | bc -l) )); then | |
| echo "Swarm_driver long handling times exceeded threshold: $total_num_of_times hits" | |
| exit 1 | |
| fi | |
| if (( $(echo "$total_long_handling > $total_long_handling_limit_ms" | bc -l) )); then | |
| echo "Swarm_driver total long handling duration exceeded threshold: $total_long_handling ms" | |
| exit 1 | |
| fi | |
| if (( $(echo "$average_handling_ms > $average_handling_limit_ms" | bc -l) )); then | |
| echo "Swarm_driver average long handling time exceeded threshold: $average_handling_ms ms" | |
| exit 1 | |
| fi | |
| # Write the node memory usage to a file | |
| echo '[ | |
| { | |
| "name": "swarm_driver long handling times", | |
| "value": '$total_num_of_times', | |
| "unit": "hits" | |
| }, | |
| { | |
| "name": "swarm_driver long handling total_time", | |
| "value": '$total_long_handling', | |
| "unit": "ms" | |
| }, | |
| { | |
| "name": "swarm_driver average long handling time", | |
| "value": '$average_handling_ms', | |
| "unit": "ms" | |
| } | |
| ]' > swarm_driver_long_handlings.json | |
| - name: check swarm_driver_long_handlings.json | |
| shell: bash | |
| run: cat swarm_driver_long_handlings.json | |
| - name: Alert for swarm_driver long handlings | |
| uses: benchmark-action/github-action-benchmark@v1 | |
| with: | |
| tool: "customSmallerIsBetter" | |
| output-file-path: swarm_driver_long_handlings.json | |
| # Where the previous data file is stored | |
| external-data-json-path: ./cache/swarm_driver_long_handlings.json | |
| # Workflow will fail when an alert happens | |
| fail-on-alert: true | |
| # GitHub API token to make a commit comment | |
| github-token: ${{ secrets.GITHUB_TOKEN }} | |
| # Enable alert commit comment | |
| comment-on-alert: true | |
| # Comment on the PR | |
| comment-always: true | |
| # 200% regression will result in alert | |
| alert-threshold: "200%" | |
| # Enable Job Summary for PRs | |
| summary-always: true |