Merge branch 'main' into pr/223

* main:
  Simplify domain language to just "boot" and unscoped config keys
  Retain a fixed number of containers when pruning
  Don't assume rolling back in message
  Check all hosts before rolling back
  Ensure Traefik service name is consistent
  Extend traefik delay by 1 second
  Include traefik access logs
  Check if we are still getting a 404
  Also dump load balancer logs
  Dump traefik logs when app not booted
  Fix missing for apt-get
  Report on container health after failure
  Fix the integration test healthcheck
  Allow percentage-based rolling deployments
  Move `group_limit` & `group_wait` under `boot`
  Limit rolling deployment to boot operation
  Allow performing boot & start operations in groups
This commit is contained in:
David Heinemeier Hansson
2023-05-02 14:43:17 +02:00
24 changed files with 204 additions and 44 deletions

View File

@@ -864,6 +864,24 @@ mrsk lock acquire -m "Doing maintanence"
mrsk lock release
```
## Rolling deployments
When deploying to large numbers of hosts, you might prefer not to restart your services on every host at the same time.
MRSK's default is to boot new containers on all hosts in parallel. But you can control this by configuring `boot/limit` and `boot/wait` as options:
```yaml
service: myservice
boot:
limit: 10 # Can also specify as a percentage of total hosts, such as "25%"
wait: 2
```
When `limit` is specified, containers will be booted on, at most, `limit` hosts at once. MRSK will pause for `wait` seconds between batches.
These settings only apply when booting containers (using `mrsk deploy`, or `mrsk app boot`). For other commands, MRSK continues to run commands in parallel across all hosts.
## Stage of development
This is beta software. Commands may still move around. But we're live in production at [37signals](https://37signals.com).

View File

@@ -11,7 +11,7 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
execute *MRSK.app.tag_current_as_latest
end
on(MRSK.hosts) do |host|
on(MRSK.hosts, **MRSK.boot_strategy) do |host|
roles = MRSK.roles_on(host)
roles.each do |role|

View File

@@ -236,15 +236,24 @@ class Mrsk::Cli::Main < Mrsk::Cli::Base
subcommand "lock", Mrsk::Cli::Lock
private
def container_available?(version, host: MRSK.primary_host)
available = nil
on(host) do
first_role = MRSK.roles_on(host).first
available = capture_with_info(*MRSK.app(role: first_role).container_id_for_version(version)).present?
def container_available?(version)
begin
on(MRSK.hosts) do
MRSK.roles_on(host).each do |role|
container_id = capture_with_info(*MRSK.app(role: role).container_id_for_version(version))
raise "Container not found" unless container_id.present?
end
end
rescue SSHKit::Runner::ExecuteError => e
if e.message =~ /Container not found/
say "Error looking for container version #{version}: #{e.message}"
return false
else
raise
end
end
available
true
end
def deploy_options

View File

@@ -7,7 +7,7 @@ class Mrsk::Cli::Prune < Mrsk::Cli::Base
end
end
desc "images", "Prune unused images older than 7 days"
desc "images", "Prune dangling images"
def images
with_lock do
on(MRSK.hosts) do
@@ -17,7 +17,7 @@ class Mrsk::Cli::Prune < Mrsk::Cli::Base
end
end
desc "containers", "Prune stopped containers older than 3 days"
desc "containers", "Prune all stopped containers, except the last 5"
def containers
with_lock do
on(MRSK.hosts) do

View File

@@ -51,6 +51,14 @@ class Mrsk::Commander
end
end
def boot_strategy
if config.boot.limit.present?
{ in: :groups, limit: config.boot.limit, wait: config.boot.wait }
else
{}
end
end
def roles_on(host)
roles.select { |role| role.hosts.include?(host.to_s) }.map(&:name)
end

View File

@@ -2,11 +2,19 @@ require "active_support/duration"
require "active_support/core_ext/numeric/time"
class Mrsk::Commands::Prune < Mrsk::Commands::Base
def images(until_hours: 7.days.in_hours.to_i)
docker :image, :prune, "--all", "--force", "--filter", "label=service=#{config.service}", "--filter", "until=#{until_hours}h"
def images
docker :image, :prune, "--all", "--force", "--filter", "label=service=#{config.service}", "--filter", "dangling=true"
end
def containers(until_hours: 3.days.in_hours.to_i)
docker :container, :prune, "--force", "--filter", "label=service=#{config.service}", "--filter", "until=#{until_hours}h"
def containers(keep_last: 5)
pipe \
docker(:ps, "-q", "-a", "--filter", "label=service=#{config.service}", *stopped_containers_filters),
"tail -n +#{keep_last + 1}",
"while read container_id; do docker rm $container_id; done"
end
private
def stopped_containers_filters
[ "created", "exited", "dead" ].flat_map { |status| ["--filter", "status=#{status}"] }
end
end

View File

@@ -87,6 +87,10 @@ class Mrsk::Configuration
roles.select(&:running_traefik?).flat_map(&:hosts).uniq
end
def boot
Mrsk::Configuration::Boot.new(config: self)
end
def repository
[ raw_config.registry["server"], image ].compact.join("/")

View File

@@ -0,0 +1,20 @@
class Mrsk::Configuration::Boot
def initialize(config:)
@options = config.raw_config.boot || {}
@host_count = config.all_hosts.count
end
def limit
limit = @options["limit"]
if limit.to_s.end_with?("%")
@host_count * limit.to_i / 100
else
limit
end
end
def wait
@options["wait"]
end
end

View File

@@ -89,6 +89,9 @@ class Mrsk::Configuration::Role
def traefik_labels
if running_traefik?
{
# Setting a service property ensures that the generated service name will be consistent between versions
"traefik.http.services.#{traefik_service}.loadbalancer.server.scheme" => "http",
"traefik.http.routers.#{traefik_service}.rule" => "PathPrefix(`/`)",
"traefik.http.middlewares.#{traefik_service}-retry.retry.attempts" => "5",
"traefik.http.middlewares.#{traefik_service}-retry.retry.initialinterval" => "500ms",

View File

@@ -1,5 +1,5 @@
class Mrsk::Utils::HealthcheckPoller
TRAEFIK_HEALTHY_DELAY = 1
TRAEFIK_HEALTHY_DELAY = 2
class HealthcheckError < StandardError; end

View File

@@ -40,6 +40,16 @@ class CliAppTest < CliTestCase
Thread.report_on_exception = true
end
test "boot uses group strategy when specified" do
Mrsk::Cli::App.any_instance.stubs(:on).with("1.1.1.1").twice # acquire & release lock
Mrsk::Cli::App.any_instance.stubs(:on).with([ "1.1.1.1" ]) # tag container
# Strategy is used when booting the containers
Mrsk::Cli::App.any_instance.expects(:on).with([ "1.1.1.1" ], in: :groups, limit: 3, wait: 2).with_block_given
run_command("boot", config: :with_boot_strategy)
end
test "start" do
run_command("start").tap do |output|
assert_match "docker start app-web-999", output
@@ -158,7 +168,7 @@ class CliAppTest < CliTestCase
end
private
def run_command(*command)
stdouted { Mrsk::Cli::App.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml", "--hosts", "1.1.1.1"]) }
def run_command(*command, config: :with_accessories)
stdouted { Mrsk::Cli::App.start([*command, "-c", "test/fixtures/deploy_#{config}.yml", "--hosts", "1.1.1.1"]) }
end
end

View File

@@ -145,7 +145,8 @@ class CliMainTest < CliTestCase
end
test "rollback bad version" do
# Mrsk::Cli::Main.any_instance.stubs(:container_available?).returns(false)
Thread.report_on_exception = false
run_command("details") # Preheat MRSK const
run_command("rollback", "nonsense").tap do |output|
@@ -155,9 +156,19 @@ class CliMainTest < CliTestCase
end
test "rollback good version" do
Mrsk::Cli::Main.any_instance.stubs(:container_available?).returns(true)
SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info).with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=web", "--filter", "status=running", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-").returns("version-to-rollback\n").at_least_once
SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info).with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=workers", "--filter", "status=running", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-").returns("version-to-rollback\n").at_least_once
SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
.with(:docker, :container, :ls, "--all", "--filter", "name=^app-web-123$", "--quiet")
.returns("version-to-rollback\n").at_least_once
SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
.with(:docker, :container, :ls, "--all", "--filter", "name=^app-workers-123$", "--quiet")
.returns("version-to-rollback\n").at_least_once
SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
.with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=web", "--filter", "status=running", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-")
.returns("version-to-rollback\n").at_least_once
SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
.with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=workers", "--filter", "status=running", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-")
.returns("version-to-rollback\n").at_least_once
run_command("rollback", "123", config_file: "deploy_with_accessories").tap do |output|
assert_match "Start version 123", output

View File

@@ -10,13 +10,13 @@ class CliPruneTest < CliTestCase
test "images" do
run_command("images").tap do |output|
assert_match /docker image prune --all --force --filter label=service=app --filter until=168h on 1.1.1.\d/, output
assert_match /docker image prune --all --force --filter label=service=app --filter dangling=true on 1.1.1.\d/, output
end
end
test "containers" do
run_command("containers").tap do |output|
assert_match /docker container prune --force --filter label=service=app --filter until=72h on 1.1.1.\d/, output
assert_match /docker ps -q -a --filter label=service=app --filter status=created --filter status=exited --filter status=dead | tail -n +6 | while read container_id; do docker rm $container_id; done on 1.1.1.\d/, output
end
end

View File

@@ -2,9 +2,7 @@ require "test_helper"
class CommanderTest < ActiveSupport::TestCase
setup do
@mrsk = Mrsk::Commander.new.tap do |mrsk|
mrsk.configure config_file: Pathname.new(File.expand_path("fixtures/deploy_with_roles.yml", __dir__))
end
configure_with(:deploy_with_roles)
end
test "lazy configuration" do
@@ -55,4 +53,27 @@ class CommanderTest < ActiveSupport::TestCase
assert_equal [ "web" ], @mrsk.roles_on("1.1.1.1")
assert_equal [ "workers" ], @mrsk.roles_on("1.1.1.3")
end
test "default group strategy" do
assert_empty @mrsk.boot_strategy
end
test "specific limit group strategy" do
configure_with(:deploy_with_boot_strategy)
assert_equal({ in: :groups, limit: 3, wait: 2 }, @mrsk.boot_strategy)
end
test "percentage-based group strategy" do
configure_with(:deploy_with_precentage_boot_strategy)
assert_equal({ in: :groups, limit: 1, wait: 2 }, @mrsk.boot_strategy)
end
private
def configure_with(variant)
@mrsk = Mrsk::Commander.new.tap do |mrsk|
mrsk.configure config_file: Pathname.new(File.expand_path("fixtures/#{variant}.yml", __dir__))
end
end
end

View File

@@ -13,7 +13,7 @@ class CommandsAppTest < ActiveSupport::TestCase
test "run" do
assert_equal \
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
new_command.run.join(" ")
end
@@ -21,7 +21,7 @@ class CommandsAppTest < ActiveSupport::TestCase
@config[:volumes] = ["/local/path:/container/path" ]
assert_equal \
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --volume /local/path:/container/path --label service=\"app\" --label role=\"web\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --volume /local/path:/container/path --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
new_command.run.join(" ")
end
@@ -29,7 +29,7 @@ class CommandsAppTest < ActiveSupport::TestCase
@config[:healthcheck] = { "path" => "/healthz" }
assert_equal \
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/healthz || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/healthz || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
new_command.run.join(" ")
end
@@ -37,7 +37,7 @@ class CommandsAppTest < ActiveSupport::TestCase
@config[:healthcheck] = { "cmd" => "/bin/up" }
assert_equal \
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"/bin/up\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"/bin/up\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
new_command.run.join(" ")
end
@@ -45,7 +45,7 @@ class CommandsAppTest < ActiveSupport::TestCase
@config[:servers] = { "web" => { "hosts" => [ "1.1.1.1" ], "healthcheck" => { "cmd" => "/bin/healthy" } } }
assert_equal \
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"/bin/healthy\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"/bin/healthy\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
new_command.run.join(" ")
end
@@ -60,7 +60,7 @@ class CommandsAppTest < ActiveSupport::TestCase
@config[:logging] = { "driver" => "local", "options" => { "max-size" => "100m", "max-file" => "3" } }
assert_equal \
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-driver \"local\" --log-opt max-size=\"100m\" --log-opt max-file=\"3\" --label service=\"app\" --label role=\"web\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
"docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-driver \"local\" --log-opt max-size=\"100m\" --log-opt max-file=\"3\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
new_command.run.join(" ")
end

View File

@@ -10,13 +10,13 @@ class CommandsPruneTest < ActiveSupport::TestCase
test "images" do
assert_equal \
"docker image prune --all --force --filter label=service=app --filter until=168h",
"docker image prune --all --force --filter label=service=app --filter dangling=true",
new_command.images.join(" ")
end
test "containers" do
assert_equal \
"docker container prune --force --filter label=service=app --filter until=72h",
"docker ps -q -a --filter label=service=app --filter status=created --filter status=exited --filter status=dead | tail -n +6 | while read container_id; do docker rm $container_id; done",
new_command.containers.join(" ")
end

View File

@@ -42,7 +42,7 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
end
test "special label args for web" do
assert_equal [ "--label", "service=\"app\"", "--label", "role=\"web\"", "--label", "traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\"", "--label", "traefik.http.middlewares.app-web-retry.retry.attempts=\"5\"", "--label", "traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\"", "--label", "traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\"" ], @config.role(:web).label_args
assert_equal [ "--label", "service=\"app\"", "--label", "role=\"web\"", "--label", "traefik.http.services.app-web.loadbalancer.server.scheme=\"http\"", "--label", "traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\"", "--label", "traefik.http.middlewares.app-web-retry.retry.attempts=\"5\"", "--label", "traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\"", "--label", "traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\"" ], @config.role(:web).label_args
end
test "custom labels" do
@@ -66,7 +66,7 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
c[:servers]["beta"] = { "traefik" => "true", "hosts" => [ "1.1.1.5" ] }
})
assert_equal [ "--label", "service=\"app\"", "--label", "role=\"beta\"", "--label", "traefik.http.routers.app-beta.rule=\"PathPrefix(\\`/\\`)\"", "--label", "traefik.http.middlewares.app-beta-retry.retry.attempts=\"5\"", "--label", "traefik.http.middlewares.app-beta-retry.retry.initialinterval=\"500ms\"", "--label", "traefik.http.routers.app-beta.middlewares=\"app-beta-retry@docker\"" ], config.role(:beta).label_args
assert_equal [ "--label", "service=\"app\"", "--label", "role=\"beta\"", "--label", "traefik.http.services.app-beta.loadbalancer.server.scheme=\"http\"", "--label", "traefik.http.routers.app-beta.rule=\"PathPrefix(\\`/\\`)\"", "--label", "traefik.http.middlewares.app-beta-retry.retry.attempts=\"5\"", "--label", "traefik.http.middlewares.app-beta-retry.retry.initialinterval=\"500ms\"", "--label", "traefik.http.routers.app-beta.middlewares=\"app-beta-retry@docker\"" ], config.role(:beta).label_args
end
test "env overwritten by role" do

View File

@@ -0,0 +1,17 @@
service: app
image: dhh/app
servers:
web:
- "1.1.1.1"
- "1.1.1.2"
workers:
- "1.1.1.3"
- "1.1.1.4"
registry:
username: user
password: pw
boot:
limit: 3
wait: 2

View File

@@ -0,0 +1,17 @@
service: app
image: dhh/app
servers:
web:
- "1.1.1.1"
- "1.1.1.2"
workers:
- "1.1.1.3"
- "1.1.1.4"
registry:
username: user
password: pw
boot:
limit: 25%
wait: 2

View File

@@ -51,7 +51,15 @@ class DeployTest < ActiveSupport::TestCase
end
def assert_app_is_up
assert_equal "200", app_response.code
code = app_response.code
if code != "200"
puts "Got response code #{code}, here are the traefik logs:"
mrsk :traefik, :logs
puts "And here are the load balancer logs"
docker_compose :logs, :load_balancer
puts "Tried to get the response code again and got #{app_response.code}"
end
assert_equal "200", code
end
def app_response
@@ -61,7 +69,10 @@ class DeployTest < ActiveSupport::TestCase
def wait_for_healthy(timeout: 20)
timeout_at = Time.now + timeout
while docker_compose("ps -a | tail -n +2 | grep -v '(healthy)' | wc -l", capture: true) != "0"
if timeout_at < Time.now
docker_compose("ps -a | tail -n +2 | grep -v '(healthy)'")
raise "Container not healthy after #{timeout} seconds" if timeout_at < Time.now
end
sleep 0.1
end
end

View File

@@ -2,7 +2,7 @@ FROM ruby:3.2
WORKDIR /app
RUN apt-get update && apt-get install -y ca-certificates openssh-client curl gnupg docker.io
RUN apt-get update --fix-missing && apt-get install -y ca-certificates openssh-client curl gnupg docker.io
RUN install -m 0755 -d /etc/apt/keyrings
RUN curl -fsSL https://download.docker.com/linux/debian/gpg | gpg --dearmor -o /etc/apt/keyrings/docker.gpg
@@ -12,7 +12,7 @@ RUN echo \
"$(. /etc/os-release && echo "$VERSION_CODENAME")" stable" | \
tee /etc/apt/sources.list.d/docker.list > /dev/null
RUN apt-get update && apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
RUN apt-get update --fix-missing && apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
COPY boot.sh .
COPY app/ .

View File

@@ -10,5 +10,8 @@ registry:
builder:
multiarch: false
healthcheck:
path: /
port: 80
cmd: wget -qO- http://localhost > /dev/null
traefik:
args:
accesslog: true
accesslog.format: json

View File

@@ -2,7 +2,7 @@ FROM ubuntu:22.10
WORKDIR /work
RUN apt-get update && apt-get -y install openssh-client openssl
RUN apt-get update --fix-missing && apt-get -y install openssh-client openssl
RUN mkdir ssh && \
ssh-keygen -t rsa -f ssh/id_rsa -N ""

View File

@@ -2,7 +2,7 @@ FROM ubuntu:22.10
WORKDIR /work
RUN apt-get update && apt-get -y install openssh-client openssh-server docker.io
RUN apt-get update --fix-missing && apt-get -y install openssh-client openssh-server docker.io
RUN mkdir /root/.ssh && ln -s /shared/ssh/id_rsa.pub /root/.ssh/authorized_keys
RUN mkdir -p /etc/docker/certs.d/registry:4443 && ln -s /shared/certs/domain.crt /etc/docker/certs.d/registry:4443/ca.crt