Merge branch 'main' into customizable-audit-broadcast

This commit is contained in:
David Heinemeier Hansson
2023-05-02 10:25:25 +02:00
committed by GitHub
35 changed files with 486 additions and 130 deletions

View File

@@ -6,8 +6,6 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
using_version(version_or_latest) do |version|
say "Start container with version #{version} using a #{MRSK.config.readiness_delay}s readiness delay (or reboot if already running)...", :magenta
cli = self
on(MRSK.hosts) do
execute *MRSK.auditor.record("Tagging #{MRSK.config.absolute_image} as the latest image"), verbosity: :debug
execute *MRSK.app.tag_current_as_latest
@@ -17,19 +15,24 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
roles = MRSK.roles_on(host)
roles.each do |role|
execute *MRSK.auditor(role: role).record("Booted app version #{version}"), verbosity: :debug
app = MRSK.app(role: role)
auditor = MRSK.auditor(role: role)
if capture_with_info(*MRSK.app(role: role).container_id_for_version(version), raise_on_non_zero_exit: false).present?
execute *auditor.record("Booted app version #{version}"), verbosity: :debug
if capture_with_info(*app.container_id_for_version(version), raise_on_non_zero_exit: false).present?
tmp_version = "#{version}_#{SecureRandom.hex(8)}"
info "Renaming container #{version} to #{tmp_version} as already deployed on #{host}"
execute *MRSK.auditor(role: role).record("Renaming container #{version} to #{tmp_version}"), verbosity: :debug
execute *MRSK.app(role: role).rename_container(version: version, new_version: tmp_version)
execute *auditor.record("Renaming container #{version} to #{tmp_version}"), verbosity: :debug
execute *app.rename_container(version: version, new_version: tmp_version)
end
old_version = capture_with_info(*MRSK.app(role: role).current_running_version, raise_on_non_zero_exit: false).strip
execute *MRSK.app(role: role).run
sleep MRSK.config.readiness_delay
execute *MRSK.app(role: role).stop(version: old_version), raise_on_non_zero_exit: false if old_version.present?
old_version = capture_with_info(*app.current_running_version, raise_on_non_zero_exit: false).strip
execute *app.run
Mrsk::Utils::HealthcheckPoller.wait_for_healthy(pause_after_ready: true) { capture_with_info(*app.status(version: version)) }
execute *app.stop(version: old_version), raise_on_non_zero_exit: false if old_version.present?
end
end
end

View File

@@ -107,7 +107,7 @@ module Mrsk::Cli
MRSK.holding_lock = true
rescue SSHKit::Runner::ExecuteError => e
if e.message =~ /cannot create directory/
invoke "mrsk:cli:lock:status", []
on(MRSK.primary_host) { execute *MRSK.lock.status }
raise LockError, "Deploy lock found"
else
raise e

View File

@@ -1,7 +1,4 @@
class Mrsk::Cli::Healthcheck < Mrsk::Cli::Base
class HealthcheckError < StandardError; end
default_command :perform
desc "perform", "Health check current app version"
@@ -9,38 +6,10 @@ class Mrsk::Cli::Healthcheck < Mrsk::Cli::Base
on(MRSK.primary_host) do
begin
execute *MRSK.healthcheck.run
target = "Health check against #{MRSK.config.healthcheck["path"]}"
attempt = 1
max_attempts = MRSK.config.healthcheck["max_attempts"]
begin
status = capture_with_info(*MRSK.healthcheck.curl)
if status == "200"
info "#{target} succeeded with 200 OK!"
else
raise HealthcheckError, "#{target} failed with status #{status}"
end
rescue SSHKit::Command::Failed
if attempt <= max_attempts
info "#{target} failed to respond, retrying in #{attempt}s (attempt #{attempt}/#{max_attempts})..."
sleep attempt
attempt += 1
retry
else
raise
end
end
rescue SSHKit::Command::Failed, HealthcheckError => e
Mrsk::Utils::HealthcheckPoller.wait_for_healthy { capture_with_info(*MRSK.healthcheck.status) }
rescue Mrsk::Utils::HealthcheckPoller::HealthcheckError => e
error capture_with_info(*MRSK.healthcheck.logs)
if e.message =~ /curl/
raise SSHKit::Command::Failed, "#{target} failed to return 200 OK!"
else
raise
end
raise
ensure
execute *MRSK.healthcheck.stop, raise_on_non_zero_exit: false
execute *MRSK.healthcheck.remove, raise_on_non_zero_exit: false

View File

@@ -94,7 +94,7 @@ class Mrsk::Cli::Traefik < Mrsk::Cli::Base
end
end
desc "remove_container", "Remove Traefik image from servers", hide: true
desc "remove_image", "Remove Traefik image from servers", hide: true
def remove_image
with_lock do
on(MRSK.traefik_hosts) do

View File

@@ -15,6 +15,7 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
"--name", container_name,
"-e", "MRSK_CONTAINER_NAME=\"#{container_name}\"",
*role.env_args,
*role.health_check_args,
*config.logging_args,
*config.volume_args,
*role.label_args,
@@ -27,6 +28,10 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
docker :start, container_name
end
def status(version:)
pipe container_id_for_version(version), xargs(docker(:inspect, "--format", DOCKER_HEALTH_STATUS_FORMAT))
end
def stop(version: nil)
pipe \
version ? container_id_for_version(version) : current_running_container_id,

View File

@@ -2,6 +2,8 @@ module Mrsk::Commands
class Base
delegate :sensitive, :argumentize, to: Mrsk::Utils
DOCKER_HEALTH_STATUS_FORMAT = "'{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'"
attr_accessor :config
def initialize(config)

View File

@@ -11,14 +11,15 @@ class Mrsk::Commands::Healthcheck < Mrsk::Commands::Base
"--label", "service=#{container_name}",
"-e", "MRSK_CONTAINER_NAME=\"#{container_name}\"",
*web.env_args,
*web.health_check_args,
*config.volume_args,
*web.option_args,
config.absolute_image,
web.cmd
end
def curl
[ :curl, "--silent", "--output", "/dev/null", "--write-out", "'%{http_code}'", "--max-time", "2", health_url ]
def status
pipe container_id, xargs(docker(:inspect, "--format", DOCKER_HEALTH_STATUS_FORMAT))
end
def logs

View File

@@ -35,6 +35,21 @@ class Mrsk::Configuration::Role
argumentize_env_with_secrets env
end
def health_check_args
if health_check_cmd.present?
optionize({ "health-cmd" => health_check_cmd, "health-interval" => "1s" })
else
[]
end
end
def health_check_cmd
options = specializations["healthcheck"] || {}
options = config.healthcheck.merge(options) if running_traefik?
options["cmd"] || http_health_check(port: options["port"], path: options["path"])
end
def cmd
specializations["cmd"]
end
@@ -75,8 +90,6 @@ class Mrsk::Configuration::Role
if running_traefik?
{
"traefik.http.routers.#{traefik_service}.rule" => "PathPrefix(`/`)",
"traefik.http.services.#{traefik_service}.loadbalancer.healthcheck.path" => config.healthcheck["path"],
"traefik.http.services.#{traefik_service}.loadbalancer.healthcheck.interval" => "1s",
"traefik.http.middlewares.#{traefik_service}-retry.retry.attempts" => "5",
"traefik.http.middlewares.#{traefik_service}-retry.retry.initialinterval" => "500ms",
"traefik.http.routers.#{traefik_service}.middlewares" => "#{traefik_service}-retry@docker"
@@ -125,4 +138,8 @@ class Mrsk::Configuration::Role
new_env["clear"] = (clear_app_env + clear_role_env).uniq
end
end
def http_health_check(port:, path:)
"curl -f #{URI.join("http://localhost:#{port}", path)} || exit 1" if path.present? || port.present?
end
end

View File

@@ -0,0 +1,39 @@
class Mrsk::Utils::HealthcheckPoller
TRAEFIK_HEALTHY_DELAY = 1
class HealthcheckError < StandardError; end
class << self
def wait_for_healthy(pause_after_ready: false, &block)
attempt = 1
max_attempts = MRSK.config.healthcheck["max_attempts"]
begin
case status = block.call
when "healthy"
sleep TRAEFIK_HEALTHY_DELAY if pause_after_ready
when "running" # No health check configured
sleep MRSK.config.readiness_delay if pause_after_ready
else
raise HealthcheckError, "container not ready (#{status})"
end
rescue HealthcheckError => e
if attempt <= max_attempts
info "#{e.message}, retrying in #{attempt}s (attempt #{attempt}/#{max_attempts})..."
sleep attempt
attempt += 1
retry
else
raise
end
end
info "Container is healthy!"
end
private
def info(message)
SSHKit.config.output.info(message)
end
end
end