missions/tests/Azaion.Missions.E2E.Tests/Tests/ResourceLimits/ColdStartRssTests.cs

using System.Diagnostics;
using System.Globalization;
using System.Net;
using Azaion.Missions.E2E.Helpers;
using Xunit;

namespace Azaion.Missions.E2E.Tests.ResourceLimits;

/// <summary>
/// NFT-RES-LIM-04 — cold-start RSS. Driven independently from the
/// steady-state window because it requires a fresh container start; lives
/// in the <c>MigratorRestart</c> collection so it serialises with the
/// other docker-compose-restarting tests rather than racing them.
/// </summary>
/// <remarks>
/// The 30-second wait between health-OK and the measurement is the spec's
/// way of letting the JIT and the JWKS prefetch settle without doing any
/// real work — measuring at health-OK alone would conflate the genuine cold
/// baseline with bootstrap noise.
/// </remarks>
[Collection("MigratorRestart")]
[Trait("Category", "ResLim")]
public sealed class ColdStartRssTests
{
    private static readonly MetricCsvRecorder Csv = new("RESLIM_RESULTS_FILE");
    private const long ProvisionalColdRssCapMiB = 200;
    private const string ComposeFile = "/workspace/docker-compose.test.yml";

    [SkippableFact]
    [Trait("Traces", "H1|H3")]
    [Trait("max_ms", "120000")]
    public async Task NFT_RES_LIM_04_cold_start_rss_within_provisional_200_MiB()
    {
        Skip.IfNot(Environment.GetEnvironmentVariable("COMPOSE_RESTART_ENABLED") == "1",
            "COMPOSE_RESTART_ENABLED!=1 — docker compose restart unavailable in this consumer image");
        Skip.IfNot(MissionsContainerHelper.Enabled,
            "MissionsContainerHelper disabled — docker CLI unavailable");

        // Arrange — bring missions down hard and start it fresh. The
        // surrounding "MigratorRestart" collection serialises us against
        // any other test that touches the SUT.
        DockerCompose("stop missions");
        DockerCompose("rm -f missions");
        DockerCompose("up -d missions");

        await WaitForHealthOkAsync(TimeSpan.FromSeconds(60));

        // Act — wait 30s after health-OK so JIT/JWKS settle, then measure.
        await Task.Delay(TimeSpan.FromSeconds(30));
        var rssBytes = ReadRssBytes("missions-sut");
        var rssMiB = rssBytes / (double)(1024 * 1024);

        var pass = rssMiB <= ProvisionalColdRssCapMiB;
        Csv.Record(
            category: "ResLim",
            scenario: "NFT-RES-LIM-04",
            result: pass ? "pass" : "fail",
            traces: $"H1|H3; COLD_RSS_MiB={rssMiB.ToString("F1", CultureInfo.InvariantCulture)}");

        // Assert — provisional gate.
        Assert.True(pass,
            $"cold-start RSS {rssMiB:F1} MiB exceeds provisional {ProvisionalColdRssCapMiB} MiB gate");
    }

    private static async Task WaitForHealthOkAsync(TimeSpan timeout)
    {
        using var http = new HttpClient { Timeout = TimeSpan.FromSeconds(2) };
        var deadline = DateTime.UtcNow + timeout;
        var healthUrl = new Uri(TestEnvironment.MissionsBaseUrl + "/health");
        while (DateTime.UtcNow < deadline)
        {
            try
            {
                using var resp = await http.GetAsync(healthUrl);
                if (resp.StatusCode == HttpStatusCode.OK) return;
            }
            catch (HttpRequestException) { /* not yet listening */ }
            catch (TaskCanceledException) { /* slow first response */ }
            await Task.Delay(500);
        }
        throw new TimeoutException(
            $"missions did not become healthy within {timeout.TotalSeconds:F0}s of cold start");
    }

    private static long ReadRssBytes(string containerName)
    {
        var raw = Run("docker",
            $"stats --no-stream --format '{{{{.MemUsage}}}}' {containerName}");
        var lhs = raw.Split('/')[0].Trim().Trim('\'');
        return ParseHumanBytes(lhs);
    }

    private static long ParseHumanBytes(string text)
    {
        var unitIx = text.IndexOfAny(new[] { 'K', 'M', 'G', 'T', 'B' });
        if (unitIx < 0) return long.Parse(text, CultureInfo.InvariantCulture);
        var num = double.Parse(text.Substring(0, unitIx), CultureInfo.InvariantCulture);
        var unit = text.Substring(unitIx);
        return unit switch
        {
            "B"   => (long)num,
            "KiB" or "KB" or "K" => (long)(num * 1024),
            "MiB" or "MB" or "M" => (long)(num * 1024 * 1024),
            "GiB" or "GB" or "G" => (long)(num * 1024 * 1024 * 1024),
            "TiB" or "TB" or "T" => (long)(num * 1024L * 1024 * 1024 * 1024),
            _ => throw new FormatException($"unknown human-bytes unit in '{text}'")
        };
    }

    private static void DockerCompose(string subcommand) =>
        Run("docker", $"compose -f {ComposeFile} {subcommand}");

    private static string Run(string file, string args)
    {
        var psi = new ProcessStartInfo(file, args)
        {
            RedirectStandardOutput = true,
            RedirectStandardError = true,
            UseShellExecute = false
        };
        using var p = Process.Start(psi)
            ?? throw new InvalidOperationException($"failed to launch `{file} {args}`");
        var stdout = p.StandardOutput.ReadToEnd();
        var stderr = p.StandardError.ReadToEnd();
        p.WaitForExit();
        if (p.ExitCode != 0)
            throw new InvalidOperationException(
                $"`{file} {args}` exited {p.ExitCode}: {stderr}");
        return stdout;
    }
}