Merge pull request #2694 from weaveworks/2647-testing-mvp

Testing MVP

Fixes #2647

.gitignore

@@ -68,3 +68,5 @@ test/tls/*.pem
 test/coverage
 test/coverage.*
 *qemu-*-static
+terraform.tfstate
+terraform.tfstate.backup

.lintignore

@@ -1,8 +1,27 @@
 # IMPORTANT: Please only use GLOBs to ignore files and directories.
 
-# Do not lint any bash script in Weave Net, in order to 
+# Do not lint the below bash scripts in Weave Net, in order to 
 # avoid breaking the build on make lint:
-*.sh
-bin/*
+bin/circle-deploy-issues
+bin/circle-deploy-master
+bin/circle-teardown-pre
+bin/circle-test-teardown
+bin/circle-test-unit
+bin/install-wordepress
+bin/multiweave
+bin/publish-site
+bin/release
+build/build.sh
+prog/weave-kube/launch.sh
 prog/weaveexec/symlink
+test/*_test.sh
+test/600_proxy_docker_py.sh
+test/assert.sh
+test/config.sh
+test/gce.sh
+test/gen_coverage_reports.sh
+test/run_all.sh
+test/sanity_check.sh
+test/setup.sh
+vendor/*.sh
 weave

Makefile

@@ -214,7 +214,7 @@ tests:
 	./tools/test -no-go-get -netgo -timeout 8m
 
 lint:
-	./tools/lint -nocomment -notestpackage .
+	./tools/lint -nocomment -notestpackage
 
 endif
 
@@ -359,3 +359,20 @@ build:
 
 run-smoketests: all testrunner
 	cd test && ./setup.sh && ./run_all.sh
+
+integration-tests: all testrunner
+# Usage:
+#   $ make \
+#     NAME="<prefix used to name VMs and other resources>" \
+#     PROVIDER="<provider among {vagrant|gcp|aws|do}>" \
+#     NUM_HOSTS="<# test machines>" \
+#     PLAYBOOK="<filename>" \
+#     RUNNER_ARGS="<...>" \
+#     TESTS="<...>" \  # Can be set to only run one or a few tests instead of the full test suite.
+#     DOCKER_VERSION=<...> \
+#     KUBERNETES_VERSION=<...> \
+#     KUBERNETES_CNI_VERSION=<...> \
+#     <...> # See also run-integration-test.sh for all variables and individual functions.
+#     integration-tests
+#
+	RUNNER_ARGS="-parallel" ./test/run-integration-tests.sh

Vagrantfile

@@ -1,45 +1,36 @@
-VAGRANTFILE_API_VERSION = "2"
-
-require './vagrant-common.rb'
+require File.expand_path(File.join(File.dirname(__FILE__), 'vagrant-common.rb'))
 
 vm_ip = "172.16.0.3" # arbitrary private IP
 
-pkgs = %w(
-  docker-engine=1.10.2-0~wily
-  aufs-tools
-  build-essential
-  ethtool
-  iputils-arping
-  libpcap-dev
-  git
-  mercurial
-  bc
-  jq
-)
-
 Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
 
-  config.vm.box = "ubuntu/wily64"
+  config.vm.box = VAGRANT_IMAGE
 
   config.vm.network "private_network", ip: vm_ip
   config.vm.provider :virtualbox do |vb|
     vb.memory = 2048
-    vb.customize ["modifyvm", :id, "--natdnshostresolver1", "off"]
-    vb.customize ["modifyvm", :id, "--natdnsproxy1", "off"]
+    configure_nat_dns(vb)    
   end
 
+  # Disable default Vagrant shared folder, which we don't need:
   config.vm.synced_folder ".", "/vagrant", disabled: true
+  # Keep Weave Net sources' in sync:
   config.vm.synced_folder ".", "/home/vagrant/src/github.com/weaveworks/weave"
+  # Create a convenience symlink to $HOME/src/github.com/weaveworks/weave
+  config.vm.provision :shell, :inline => 'ln -sf ~vagrant/src/github.com/weaveworks/weave ~vagrant/'
 
   # Set SSH keys up to be able to run smoke tests straightaway:
   config.vm.provision "file", source: "~/.vagrant.d/insecure_private_key", destination: "/home/vagrant/src/github.com/weaveworks/weave/test/insecure_private_key"
-
-  install_build_deps config.vm, pkgs
-  install_go_toochain config.vm
-  tweak_user_env config.vm
-  tweak_docker_daemon config.vm
+  # Grant permissions on sources:
+  config.vm.provision :shell, :inline => 'sudo chown -R vagrant:vagrant ~vagrant/src', :privileged => false
   cleanup config.vm
 
+  config.vm.provision 'ansible' do |ansible|
+    ansible.playbook = 'tools/config_management/setup_weave-net_dev.yml'
+    ansible.extra_vars = {
+      go_version: GO_VERSION
+    }
+  end
 end
 
 begin

bin/circle-dependencies-post

@@ -2,45 +2,16 @@
 
 set -e
 
-echo "TEST_AND_PUBLISH=1" > "$STATE"
-
-# Avoid doing a full build if we can.  Note if the PR doesn't exist
-# when the build is kicked off, we can't run this check so we do a
-# full build.  Subsequent pushes to the same branch will have the desired behaviour
-if [ -n "$CI_PULL_REQUEST" -a "$CI_PULL_REQUEST" = "$CI_PULL_REQUESTS" ] ; then
-    if PR=$(echo "$CI_PULL_REQUEST" | grep -oP '(?<=^https://github.com/weaveworks/weave/pull/)[0-9]+$') ; then
-        echo "GH_PR=$PR" >> "$STATE"
-        if FILES=$(curl -s https://api.github.com/repos/weaveworks/weave/pulls/$PR/files | jq -r '.[]|.filename') ; then
-            echo "PR touches [$FILES]"
-            if ! echo "$FILES" | grep -v ^site/ ; then
-                echo "PR contains site changes only - skipping tests"
-                echo "TEST_AND_PUBLISH=" >> "$STATE"
-            else
-                echo "PR contains non-site changes - running tests"
-            fi
-        else
-            echo "Unable to get files for PR $PR" >&2
-        fi
-    else
-        echo "Unable to extract PR number from $CI_PULL_REQUEST" >&2
-    fi
-fi
-
 source "$STATE"
 
-mkdir -p $(dirname $SRCDIR) && cp -r $(pwd)/ $SRCDIR
-
-if [ -n "$TEST_AND_PUBLISH" ] ; then
-    [ -z "$SECRET_PASSWORD" ] || bin/setup-circleci-secrets "$SECRET_PASSWORD"
-    cd $SRCDIR; git submodule update --init
-    if [ "$CIRCLE_NODE_INDEX" = "0" -a -n "$SECRET_PASSWORD" ] ; then
-        cd $SRCDIR/test; ./gce.sh make_template
-    fi
-    cd $SRCDIR/build
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    cd "$SRCDIR"
+    git submodule update --init
+    cd "$SRCDIR/build"
     ../tools/rebuild-image weaveworks/weavebuild . Dockerfile build.sh
-    touch $SRCDIR/.build.uptodate
+    touch "$SRCDIR/.build.uptodate"
     sudo chown -R ubuntu /usr/local/go
-    cd $SRCDIR
+    cd "$SRCDIR"
     make testrunner
     make COVERAGE=true RM= exes all
 fi

bin/circle-dependencies-post-sources

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+set -e
+
+echo "TEST_AND_PUBLISH=1" >"$STATE"
+
+# Avoid doing a full build if we can.  Note if the PR doesn't exist
+# when the build is kicked off, we can't run this check so we do a
+# full build.  Subsequent pushes to the same branch will have the desired behaviour
+if [ -n "$CI_PULL_REQUEST" -a "$CI_PULL_REQUEST" = "$CI_PULL_REQUESTS" ]; then
+    if PR=$(echo "$CI_PULL_REQUEST" | grep -oP '(?<=^https://github.com/weaveworks/weave/pull/)[0-9]+$'); then
+        echo "GH_PR=$PR" >>"$STATE"
+        if FILES=$(curl -s "https://api.github.com/repos/weaveworks/weave/pulls/$PR/files" | jq -r '.[]|.filename'); then
+            echo "PR touches [$FILES]"
+            if ! echo "$FILES" | grep -v ^site/; then
+                echo "PR contains site changes only - skipping tests"
+                echo "TEST_AND_PUBLISH=" >>"$STATE"
+            else
+                echo "PR contains non-site changes - running tests"
+            fi
+        else
+            echo "Unable to get files for PR $PR" >&2
+        fi
+    else
+        echo "Unable to extract PR number from $CI_PULL_REQUEST" >&2
+    fi
+fi
+
+source "$STATE"
+
+mkdir -p "$(dirname "$SRCDIR")" && cp -r "$(pwd)/" "$SRCDIR"
+
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    cd "$SRCDIR"
+    git submodule update --init
+fi

bin/circle-test-pre

@@ -2,9 +2,29 @@
 
 set -e
 
+# Signal failures in lock file, in order to fail fast:
+function signal_failure() {
+    echo "KO" >"$TEST_VMS_READY_LOCK_FILE"
+    exit 1
+}
+trap signal_failure ERR
+
 source "$STATE"
+source "$(dirname "$0")/wait_for.sh"
+
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    [ -n "$SECRET_KEY" ] || {
+        echo "Cannot run smoke tests: no secret key"
+        exit 1
+    }
+
+    # Provisioning from image typically take 90 seconds, 
+    # but if we are creating a GCP image, it can take more than 10 minutes:
+    wait_for 900 "$TEST_VMS_PROV_AND_CONF_LOCK_FILE"
 
-if [ -n "$TEST_AND_PUBLISH" ] ; then
-    cd $SRCDIR/test
-    [ -z "$SECRET_PASSWORD" ] || (./gce.sh setup && eval $(./gce.sh hosts) && ./setup.sh)
+    # Upload built binaries to testing VMs:
+    cd "$SRCDIR/test" # Ensures we generate Terraform state files in the right folder, for later use by integration tests.
+    ./run-integration-tests.sh setup >>"$TEST_VMS_SETUP_OUTPUT_FILE" 2>&1
+    echo "OK" >"$TEST_VMS_READY_LOCK_FILE"
+    echo "Test VMs now ready. $(date)." >>"$TEST_VMS_SETUP_OUTPUT_FILE"
 fi

bin/circle-test-smoke

@@ -3,12 +3,21 @@
 set -e
 
 source "$STATE"
+source "$(dirname "$0")/wait_for.sh"
 
-if [ -n "$TEST_AND_PUBLISH" ] ; then
-    [ -n "$SECRET_PASSWORD" ] || { echo "Cannot run smoke tests: no secret key"; exit 1; }
-    cd $SRCDIR/test
-    eval $(./gce.sh hosts)
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    [ -n "$SECRET_KEY" ] || {
+        echo "Cannot run smoke tests: no secret key"
+        exit 1
+    }
+
+    # Provisioning from image typically take 90 seconds, 
+    # but if we are creating a GCP image, it can take more than 10 minutes:
+    wait_for 900 "$TEST_VMS_READY_LOCK_FILE"
+
+    # Run integration tests:
     export COVERAGE=true
     export WEAVE_NET_SANITY_CHECKS_FILES="$CIRCLE_ARTIFACTS/weave_net_sanity_check_*.log"
-    ./run_all.sh
+    cd "$SRCDIR/test" # Ensures we generate code coverage files in the right folder, and use the Terraform state of previously provisionned VMs.
+    ./run-integration-tests.sh test
 fi

bin/circle-test-teardown

@@ -6,6 +6,5 @@ source "$STATE"
 
 if [ -n "$TEST_AND_PUBLISH" ] ; then
     cd $SRCDIR/test
-    [ -z "$SECRET_PASSWORD" ] || ./gce.sh destroy
     test "$CIRCLE_NODE_INDEX" != "0" || (cd $SRCDIR/test; ./gen_coverage_reports.sh)
 fi

bin/provision_test_vms.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+
+set -e
+
+# Signal failures in lock file, in order to fail fast:
+function signal_failure() {
+    echo "KO" >"$TEST_VMS_PROV_AND_CONF_LOCK_FILE"
+    exit 1
+}
+trap signal_failure ERR
+
+source "$STATE"
+
+function install_terraform() {
+    curl -fsS https://releases.hashicorp.com/terraform/0.8.5/terraform_0.8.5_linux_amd64.zip | gunzip >terraform && chmod +x terraform && sudo mv terraform /usr/bin
+}
+
+function install_ansible() {
+    sudo apt-get update || true
+    sudo apt-get install -qq -y python-pip python-dev libffi-dev libssl-dev && pip install --user -U cffi && pip install --user ansible
+    export PATH="$PATH:$HOME/.local/bin"
+}
+
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    [ -n "$SECRET_KEY" ] || {
+        echo "Cannot run smoke tests: no secret key"
+        exit 1
+    }
+
+    install_terraform >>"$TEST_VMS_SETUP_OUTPUT_FILE" 2>&1
+    install_ansible >>"$TEST_VMS_SETUP_OUTPUT_FILE" 2>&1
+
+    # Only attempt to create GCP image in first container, wait for it to be created otherwise:
+    [ "$CIRCLE_NODE_INDEX" != "0" ] && export CREATE_IMAGE=0
+
+    # Provision and configure testing VMs:
+    cd "$SRCDIR/test" # Ensures we generate Terraform state files in the right folder, for later use by integration tests.
+    ./run-integration-tests.sh configure >>"$TEST_VMS_SETUP_OUTPUT_FILE" 2>&1
+    echo "OK" >"$TEST_VMS_PROV_AND_CONF_LOCK_FILE"
+    echo "Test VMs now provisioned and configured. $(date)." >>"$TEST_VMS_SETUP_OUTPUT_FILE"
+fi