Skip to content
reconverse-ci

9.3: wire examples and change CI #41

Sign in to view logs

9.3: wire examples and change CI

9.3: wire examples and change CI #41

Workflow file for this run

.github/workflows/reconverse-ci.yaml at befd59e
name: reconverse-ci
# CI for the reviewed reconverse line. The tier below defines what CI
# GUARANTEES; it is a floor, not the support surface. Features without a
# test here are supported with coverage debt -- the tier is meant to GROW
# toward them, and dropping support for anything is an explicit reviewed
# act (a tombstone commit deleting its test), never a side effect of a
# test not yet existing. Correctness-gated only -- never timing-gated:
# hosted runners are noisy. Real-fabric behavior (IB, Slingshot) is NOT
# covered here; runtime-core PRs get a manual run on an HPC site by a
# reviewer (see PR template) until a sanctioned site runner exists.
on:
push:
branches: [reviewed-with-reconverse]
pull_request:
branches: [reviewed-with-reconverse]
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
env:
# Pin the OFI provider. LCI takes the FIRST fi_getinfo() match, and which
# provider ranks first is a property of the runner's host, not of this
# repo: a hosted VM that exposes an RDMA-capable NIC gets a hardware
# provider ahead of tcp, and fi_enable() then fails with ENOMEM
# (lci/src/network/ofi/backend_ofi.cpp:273) inside ConverseInit, before
# any test code runs. That is a runner lottery, not a regression -- it is
# why identical commits pass one day and abort the next, and why one
# ubuntu-latest job can pass while its sibling aborts in the same run.
# Hosted runners never covered a real fabric anyway (see the header: IB
# and Slingshot are the manual HPC-site run's job), so pinning tcp costs
# no coverage and makes every runner in the pool behave identically.
# Shrinking the queues (LCI_ATTR_NET_MAX_CQES) does NOT help: the failure
# is provider selection, not queue size.
FI_PROVIDER: tcp
# Curated test tier. Grows one reviewed PR at a time; every tests/ dir NOT
# listed here is by definition unsupported-on-reconverse until added (the
# parity matrix mirrors this list).
TEST_DIRS: >-
tests/charm++/megatest
tests/charm++/simplearrayhello
tests/charm++/anytime_migration
tests/charm++/anytime_bcastred
tests/charm++/qd
jobs:
reconverse-linux-x86_64:
timeout-minutes: 90
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v5
- name: install dependencies
run: sudo apt-get update && sudo apt-get install -y cmake libfabric-dev
- name: build
run: ./build charm++ reconverse-linux-x86_64 -j4 -g
- name: build tests
run: |
set -e
B=$PWD/reconverse-linux-x86_64
for d in $TEST_DIRS; do make -C $d CHARMC=$B/bin/charmc; done
- name: test (single process)
run: |
set -e
for d in $TEST_DIRS; do make -C $d test; done
- name: test (2 processes, lcrun)
run: |
set -e
for d in $TEST_DIRS; do TESTRUN_PROCS=2 make -C $d test; done
# ARM64 Linux (Grace-class systems). Replaces the coverage CircleCI's
# arm.medium jobs provided on the classic line; -Werror=vla carried over
# from those jobs.
reconverse-linux-arm8:
timeout-minutes: 90
runs-on: ubuntu-24.04-arm
steps:
- uses: actions/checkout@v5
- name: install dependencies
run: sudo apt-get update && sudo apt-get install -y cmake libfabric-dev
- name: build
run: ./build charm++ reconverse-linux-arm8 -j4 -g -Werror=vla
- name: build tests
run: |
set -e
B=$PWD/reconverse-linux-arm8
for d in $TEST_DIRS; do make -C $d CHARMC=$B/bin/charmc; done
- name: test (single process)
run: |
set -e
for d in $TEST_DIRS; do make -C $d test; done
- name: test (2 processes, lcrun)
run: |
set -e
for d in $TEST_DIRS; do TESTRUN_PROCS=2 make -C $d test; done
reconverse-darwin-arm64:
timeout-minutes: 90
runs-on: macos-latest # Apple Silicon
steps:
- uses: actions/checkout@v5
- name: install dependencies
run: brew install libfabric
- name: build
run: ./build charm++ reconverse-darwin-arm8 -j4 -g
- name: build tests
run: |
set -e
B=$PWD/reconverse-darwin-arm8
for d in $TEST_DIRS; do make -C $d CHARMC=$B/bin/charmc; done
- name: test (single process)
run: |
set -e
for d in $TEST_DIRS; do make -C $d test; done
- name: test (2 processes, lcrun)
run: |
set -e
for d in $TEST_DIRS; do TESTRUN_PROCS=2 make -C $d test; done
# Race/stress tier: error checking live (CkEnforce-heavy tests with teeth),
# heavy anytime-migration stress (the #3939 regression class), QD settles,
# both process shapes. This is the job that hunts the bug class this line's
# hardening exists for.
reconverse-linux-stress:
timeout-minutes: 90
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v5
- name: install dependencies
run: sudo apt-get update && sudo apt-get install -y cmake libfabric-dev
- name: build (error checking on)
run: ./build charm++ reconverse-linux-x86_64 -j4 -g --enable-error-checking
- name: build stress tests
run: |
set -e
B=$PWD/reconverse-linux-x86_64
make -C tests/charm++/anytime_bcastred CHARMC=$B/bin/charmc
make -C tests/charm++/qd CHARMC=$B/bin/charmc
make -C tests/charm++/megatest CHARMC=$B/bin/charmc
# Heavy migration config (-m 1 -c 8): every step migrates 8 of the 8
# elements. Exercises the #3939 class (obligation-free PEs vs reduction
# tree) that this line's reduction fix closes; hangs without it.
- name: anytime migration stress (single process)
run: |
set -e
cd tests/charm++/anytime_bcastred
B=$PWD/../../../reconverse-linux-x86_64
for S in 1 2 3; do
env LD_LIBRARY_PATH=$B/lib ./bcastred +pe 4 -n 8 -i 500 -m 1 -c 8 -S $S -w 30
done
- name: anytime migration stress (2 processes)
run: |
set -e
cd tests/charm++/anytime_bcastred
B=$PWD/../../../reconverse-linux-x86_64
for S in 4 5; do
$B/_deps/lci-src/lcrun -n 2 env LD_LIBRARY_PATH=$B/lib ./bcastred +pe 4 -n 8 -i 500 -m 1 -c 8 -S $S -w 30
done
- name: qd + megatest multi-process
run: |
set -e
B=$PWD/reconverse-linux-x86_64
cd tests/charm++/qd
$B/_deps/lci-src/lcrun -n 2 env LD_LIBRARY_PATH=$B/lib ./qdbench +pe 4
cd ../megatest
$B/_deps/lci-src/lcrun -n 2 env LD_LIBRARY_PATH=$B/lib ./megatest +pe 4