feat(metrics): dockerized grafana dashboard to visualize node metrics #3568

Workflow file for this run

	name: Check before merge

	on:
	# tests must run for a PR to be valid and pass merge queue muster
	# on main, we want to know that all commits are passing at a glance, any deviation should help bisecting errors
	# the merge run checks should show on master and enable this clear test/passing history
	merge_group:
	branches: [main]
	pull_request:
	branches: ["*"]

	env:
	CARGO_INCREMENTAL: 0 # bookkeeping for incremental builds has overhead, not useful in CI.

	jobs:
	cargo-udeps:
	if: "!startsWith(github.event.head_commit.message, 'chore(release):')"
	name: Unused dependency check
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v3

	- name: Install Rust
	uses: dtolnay/rust-toolchain@stable
	with:
	#Needs nightly to distinguish between deps of different versions
	toolchain: nightly
	# we need rustfmt here while we have a build step
	components: rustfmt

	- name: Install cargo-udeps
	# TODO: (2023-07-03) This is a non-released version from udeps, which includes a bug fix:
	# https://github.com/est31/cargo-udeps/issues/180
	# Change this when this is released.
	run: cargo install --git=https://github.com/est31/cargo-udeps.git --rev=f7a4705 --locked
	- name: Run cargo-udeps
	run: cargo +nightly udeps --all-targets

	lint:
	runs-on: ubuntu-latest
	env:
	GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
	steps:
	- uses: actions/checkout@v3
	with:
	fetch-depth: 0
	- uses: wagoid/commitlint-github-action@f114310111fdbd07e99f47f9ca13d62b3ec98372

	checks:
	if: "!startsWith(github.event.head_commit.message, 'chore(release):')"
	name: various checks
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v3


	- name: Install Rust
	uses: dtolnay/rust-toolchain@stable
	with:
	toolchain: stable
	components: rustfmt, clippy

	- uses: Swatinem/rust-cache@v2

	- name: Check formatting
	run: cargo fmt --all -- --check

	- shell: bash
	run: cargo clippy --all-targets --all-features -- -Dwarnings

	- name: Check documentation
	# Deny certain `rustdoc` lints that are unwanted.
	# See https://doc.rust-lang.org/rustdoc/lints.html for lints that are 'warning' by default.
	run: RUSTDOCFLAGS="--deny=warnings" cargo doc --no-deps

	- name: Check local-discovery is not a default feature
	shell: bash
	run: if [[ ! $(cargo metadata --no-deps --format-version 1 \| jq -r '.packages[].features.default[]? \| select(. == "local-discovery")') ]]; then echo "local-discovery is not a default feature in any package."; else echo "local-discovery is a default feature in at least one package." && exit 1; fi

	- name: Check the whole workspace can build
	run: cargo build --all-targets --all-features

	unit:
	if: "!startsWith(github.event.head_commit.message, 'chore(release):')"
	name: Unit Tests
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	os: [ubuntu-latest, windows-latest, macos-latest]
	steps:
	- uses: actions/checkout@v3


	- name: Install Rust
	uses: dtolnay/rust-toolchain@stable
	with:
	toolchain: stable

	- uses: Swatinem/rust-cache@v2

	- name: Run testnet tests
	timeout-minutes: 25
	run: cargo test --release --package sn_testnet

	- name: Run network tests
	timeout-minutes: 25
	run: cargo test --release --package sn_networking

	- name: Run protocol tests
	timeout-minutes: 25
	run: cargo test --release --package sn_protocol

	- name: Run transfers tests
	timeout-minutes: 25
	run: cargo test --release --package sn_transfers

	- name: Run register tests
	timeout-minutes: 25
	run: cargo test --release --package sn_registers
	env:
	# this will speed up PR merge flows, while giving us a modicum
	# of proptesting
	# we do many more runs on the nightly run
	PROPTEST_CASES: 50

	e2e:
	if: "!startsWith(github.event.head_commit.message, 'chore(release):')"
	name: E2E tests
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	os: [ubuntu-latest, windows-latest, macos-latest]
	steps:
	- uses: actions/checkout@v3


	- name: Install Rust
	uses: dtolnay/rust-toolchain@stable
	with:
	toolchain: stable
	- uses: Swatinem/rust-cache@v2

	- name: Build node and client
	run: cargo build --release --bin safenode --bin safe --bin faucet
	timeout-minutes: 30

	- name: Start a local network
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: start
	interval: 2000
	node-path: target/release/safenode
	faucet-path: target/release/faucet
	platform: ${{ matrix.os }}

	- name: Check SAFE_PEERS was set
	shell: bash
	run: \|
	if [[ -z "$SAFE_PEERS" ]]; then
	echo "The SAFE_PEERS variable has not been set"
	exit 1
	else
	echo "SAFE_PEERS has been set to $SAFE_PEERS"
	fi

	- name: Create and fund a wallet to pay for files storage
	run: \|
	cargo run --bin faucet --release -- --log-output-dest=data-dir send 1000000 $(cargo run --bin safe --release -- --log-output-dest=data-dir wallet address \| tail -n 1) \| tail -n 1 > transfer_hex
	cargo run --bin safe --release -- --log-output-dest=data-dir wallet receive --file transfer_hex
	env:
	SN_LOG: "all"
	timeout-minutes: 5

	- name: Start a client to pay for files storage
	run: cargo run --bin safe --release -- --log-output-dest=data-dir wallet pay "./resources"
	env:
	SN_LOG: "all"
	timeout-minutes: 10

	- name: Start a client to upload files
	run: cargo run --bin safe --release -- --log-output-dest=data-dir files upload -- "./resources"
	env:
	SN_LOG: "all"
	timeout-minutes: 15

	- name: Start a client to download files
	run: cargo run --bin safe --release -- --log-output-dest=data-dir files download
	env:
	SN_LOG: "all"
	timeout-minutes: 2

	- name: Start a client to create a register
	run: cargo run --bin safe --release -- --log-output-dest=data-dir register create baobao
	env:
	SN_LOG: "all"
	timeout-minutes: 10

	- name: Start a client to get a register
	run: cargo run --bin safe --release -- --log-output-dest=data-dir register get -n baobao
	env:
	SN_LOG: "all"
	timeout-minutes: 2

	- name: Start a client to edit a register
	run: cargo run --bin safe --release -- --log-output-dest=data-dir register edit -n baobao wood
	env:
	SN_LOG: "all"
	timeout-minutes: 10

	- name: Stop the local network and upload logs
	if: always()
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: stop
	log_file_prefix: safe_test_logs_e2e
	platform: ${{ matrix.os }}

	gossipsub:
	if: "!startsWith(github.event.head_commit.message, 'chore(release):')"
	name: Gossipsub E2E tests
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	os: [ubuntu-latest, windows-latest, macos-latest]
	steps:
	- uses: actions/checkout@v3

	- name: Install Rust
	uses: dtolnay/rust-toolchain@stable
	with:
	toolchain: stable
	- uses: Swatinem/rust-cache@v2

	- name: Build node
	run: cargo build --release --bin safenode
	timeout-minutes: 30

	- name: Build gossipsub testing executable
	run: cargo test --release -p sn_node --features=local-discovery --test msgs_over_gossipsub --no-run
	timeout-minutes: 30

	- name: Start a local network
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: start
	interval: 2000
	node-path: target/release/safenode
	faucet-path: target/release/faucet
	platform: ${{ matrix.os }}

	- name: Gossipsub - nodes to subscribe to topics, and publish messages
	run: cargo test --release -p sn_node --features local-discovery msgs_over_gossipsub -- --nocapture
	timeout-minutes: 20

	- name: Stop the local network and upload logs
	if: always()
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: stop
	log_file_prefix: safe_test_logs_e2e
	platform: ${{ matrix.os }}

	spend_test:
	if: "!startsWith(github.event.head_commit.message, 'chore(release):')"
	name: spend tests against network
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	os: [ubuntu-latest, windows-latest, macos-latest]
	steps:
	- uses: actions/checkout@v3


	- name: Install Rust
	uses: dtolnay/rust-toolchain@stable
	with:
	toolchain: stable

	- uses: Swatinem/rust-cache@v2

	- name: Build safe bins
	run: cargo build --release --features local-discovery --bin safenode --bin faucet
	timeout-minutes: 30

	- name: Build testing executable
	run: cargo test --release -p sn_node --features=local-discovery --test sequential_transfers --test storage_payments --test nodes_rewards --no-run
	timeout-minutes: 30

	- name: Start a local network
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: start
	interval: 2000
	node-path: target/release/safenode
	faucet-path: target/release/faucet
	platform: ${{ matrix.os }}

	- name: Check SAFE_PEERS was set
	shell: bash
	run: \|
	if [[ -z "$SAFE_PEERS" ]]; then
	echo "The SAFE_PEERS variable has not been set"
	exit 1
	else
	echo "SAFE_PEERS has been set to $SAFE_PEERS"
	fi

	# This should be first to avoid slow reward acceptance etc
	- name: execute the nodes rewards tests
	run: cargo test --release -p sn_node --features="local-discovery" --test nodes_rewards -- --nocapture --test-threads=1
	env:
	SN_LOG: "all"
	timeout-minutes: 25

	- name: execute the spend tests
	run: cargo test --release -p sn_node --features="local-discovery" --test sequential_transfers -- --nocapture
	env:
	SN_LOG: "all"
	timeout-minutes: 25

	- name: execute the storage payment tests
	run: cargo test --release -p sn_node --features="local-discovery" --test storage_payments -- --nocapture --test-threads=1
	env:
	SN_LOG: "all"
	timeout-minutes: 25


	- name: Stop the local network and upload logs
	if: always()
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: stop
	log_file_prefix: safe_test_logs_spend
	platform: ${{ matrix.os }}

	churn:
	if: "!startsWith(github.event.head_commit.message, 'chore(release):')"
	name: Network churning tests
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	include:
	- os: ubuntu-latest
	node_data_path: /home/runner/.local/share/safe/node
	- os: windows-latest
	node_data_path: C:\\Users\\runneradmin\\AppData\\Roaming\\safe\\node
	- os: macos-latest
	node_data_path: /Users/runner/Library/Application Support/safe/node
	steps:
	- uses: actions/checkout@v3

	- uses: dtolnay/rust-toolchain@stable
	with:
	toolchain: stable

	- uses: Swatinem/rust-cache@v2

	- name: Build safe bins
	run: cargo build --release --features local-discovery --bin safenode --bin faucet
	timeout-minutes: 30

	- name: Build churn tests
	run: cargo test --release -p sn_node --features=local-discovery --test data_with_churn --no-run
	timeout-minutes: 30

	- name: Start a local network
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: start
	interval: 2000
	node-path: target/release/safenode
	faucet-path: target/release/faucet
	platform: ${{ matrix.os }}

	- name: Check SAFE_PEERS was set
	shell: bash
	run: \|
	if [[ -z "$SAFE_PEERS" ]]; then
	echo "The SAFE_PEERS variable has not been set"
	exit 1
	else
	echo "SAFE_PEERS has been set to $SAFE_PEERS"
	fi

	- name: Chunks data integrity during nodes churn
	run: cargo test --release -p sn_node --features="local-discovery" --test data_with_churn -- --nocapture
	env:
	TEST_DURATION_MINS: 5
	TEST_TOTAL_CHURN_CYCLES: 15
	SN_LOG: "all"
	timeout-minutes: 30

	- name: Verify restart of nodes using rg
	shell: bash
	timeout-minutes: 1
	# get the counts, then the specific line, and then the digit count only
	# then check we have an expected level of restarts
	# TODO: make this use an env var, or relate to testnet size
	run : \|
	restart_count=$(rg "Node is restarting in" "${{ matrix.node_data_path }}" -c --stats \| \
	rg "(\d+) matches" \| rg "\d+" -o)
	echo "Restart $restart_count nodes"
	peer_removed=$(rg "PeerRemovedFromRoutingTable" "${{ matrix.node_data_path }}" -c --stats \| \
	rg "(\d+) matches" \| rg "\d+" -o)
	echo "PeerRemovedFromRoutingTable $peer_removed times"
	if [ $peer_removed -lt $restart_count ]; then
	echo "PeerRemovedFromRoutingTable times of: $peer_removed is less than the restart count of: $restart_count"
	exit 1
	fi
	node_count=$(ls "${{ matrix.node_data_path }}" \| wc -l)
	echo "Node dir count is $node_count"

	# TODO: reenable this once the testnet dir creation is tidied up to avoid a large count here
	# if [ $restart_count -lt $node_count ]; then
	# echo "Restart count of: $restart_count is less than the node count of: $node_count"
	# exit 1
	# fi

	- name: Verify data replication using rg
	shell: bash
	timeout-minutes: 1
	# get the counts, then the specific line, and then the digit count only
	# then check we have an expected level of replication
	# TODO: make this use an env var, or relate to testnet size
	run : \|
	fetching_attempt_count=$(rg "FetchingKeysForReplication" "${{ matrix.node_data_path }}" -c --stats \| \
	rg "(\d+) matches" \| rg "\d+" -o)
	echo "Carried out $fetching_attempt_count fetching attempts"
	node_count=$(ls "${{ matrix.node_data_path }}" \| wc -l)
	if [ $fetching_attempt_count -lt $node_count ]; then
	echo "Replication fetching attempts of: $fetching_attempt_count is less than the node count of: $node_count"
	exit 1
	fi

	- name: Stop the local network and upload logs
	if: always()
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: stop
	log_file_prefix: safe_test_logs_churn
	platform: ${{ matrix.os }}

	verify_data_location:
	if: "!startsWith(github.event.head_commit.message, 'chore(release):')"
	name: Verify data location
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	include:
	- os: ubuntu-latest
	node_data_path: /home/runner/.local/share/safe/node
	- os: windows-latest
	node_data_path: C:\\Users\\runneradmin\\AppData\\Roaming\\safe\\node
	- os: macos-latest
	node_data_path: /Users/runner/Library/Application Support/safe/node
	steps:
	- uses: actions/checkout@v3

	- uses: dtolnay/rust-toolchain@stable
	with:
	toolchain: stable

	- uses: Swatinem/rust-cache@v2

	- name: Build safe bins
	run: cargo build --release --features local-discovery --bin safenode --bin faucet
	timeout-minutes: 30

	- name: Build data location test
	run: cargo test --release -p sn_node --features=local-discovery --test verify_data_location --no-run
	timeout-minutes: 30

	- name: Start a local network
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: start
	interval: 2000
	node-path: target/release/safenode
	faucet-path: target/release/faucet
	platform: ${{ matrix.os }}

	- name: Check SAFE_PEERS was set
	shell: bash
	run: \|
	if [[ -z "$SAFE_PEERS" ]]; then
	echo "The SAFE_PEERS variable has not been set"
	exit 1
	else
	echo "SAFE_PEERS has been set to $SAFE_PEERS"
	fi

	- name: Verify the location of the data on the network (4 * 5 mins)
	run: cargo test --release -p sn_node --features="local-discovery" --test verify_data_location -- --nocapture
	env:
	CHURN_COUNT: 3
	SN_LOG: "all"
	timeout-minutes: 30

	- name: Verify restart of nodes using rg
	shell: bash
	timeout-minutes: 1
	# get the counts, then the specific line, and then the digit count only
	# then check we have an expected level of restarts
	# TODO: make this use an env var, or relate to testnet size
	run : \|
	restart_count=$(rg "Node is restarting in" "${{ matrix.node_data_path }}" -c --stats \| \
	rg "(\d+) matches" \| rg "\d+" -o)
	echo "Restart $restart_count nodes"
	peer_removed=$(rg "PeerRemovedFromRoutingTable" "${{ matrix.node_data_path }}" -c --stats \| \
	rg "(\d+) matches" \| rg "\d+" -o)
	echo "PeerRemovedFromRoutingTable $peer_removed times"
	if [ $peer_removed -lt $restart_count ]; then
	echo "PeerRemovedFromRoutingTable times of: $peer_removed is less than the restart count of: $restart_count"
	exit 1
	fi
	node_count=$(ls "${{ matrix.node_data_path }}" \| wc -l)
	echo "Node dir count is $node_count"

	- name: Stop the local network and upload logs
	if: always()
	uses: maidsafe/sn-local-testnet-action@main
	with:
	action: stop
	log_file_prefix: safe_test_logs_data_location
	platform: ${{ matrix.os }}

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(metrics): dockerized grafana dashboard to visualize node metrics #3568

Workflow file

feat(metrics): dockerized grafana dashboard to visualize node metrics #3568

Jobs

Run details

Workflow file for this run