Chameth.com - posts like migrating-from-github-to-forgejo, why-you-should-be-using-https but not docker-automatic-nginx-proxy, monthly-meanderings-2026-01

Migrating from GitHub to Forgejo

2026-04-30T00:00:00Z

When Microsoft bought GitHub in 2018 my kneejerk reaction — like so many others — was to start looking for alternatives. For a while I self hosted a Gitea instance but I never totally bought into it: some repositories I still pushed to GitHub, some I pushed to Gitea and they got mirrored, and I ended up causing myself problems when I got the two confused. Part of the problem was that the GitHub UI was faster and cleaner than Gitea’s at the time; using Gitea felt like a chore compared to GitHub. I ended up not maintaining it and eventually binning it and just going back to GitHub.

An all-too familiar unicorn

Fast forward eight years, and GitHub is about what we all imagined when Microsoft bought it. If you take the most pessimistic way of counting, they have zero nines of reliability¹. If you take the most generous, they have a single nine. That’s around 30 minutes of downtime every day. It feels like it must be more than that, given how many times you see the damned unicorn.

Uptime aside, they’ve crowbarred LLMs in all over the place; they don’t have the time to maintain official GitHub actions; the ones they do maintain have Copilot running roughshod all over them²; actions themselves are slow to run³, often have weird transient failures, and there are so many footguns that I’m pretty sure GitHub actions should be an entire category in the CWE top 10.

Speaking of security, while I was drafting this post a remote code execution was reported and the details are… impressive. The actual security issue was a pretty stupid oversight. Those happen. But they end up being able to execute code as a globally shared git user with access to all the other repositories on the node. What? I can’t quite get my head around it. No sandboxing, no containers, it just runs as a git user?

So, yeah, I’m not a fan of GitHub in its current state. A few months back I took the plunge and set up Forgejo, a fork of Gitea where they did radical things like add tests and ensure that it’s community operated not twisted for commercial use. Forgejo also potentially has some fun security problems⁴, but the way I host it mitigates more-or-less all problems. It’s also slightly less shocking when an open source project has lapses in basic security versus a $2 trillion corporation.

It’s taken a bit of doing, but I’m very happy with the setup I have.

The basic setup

I run all my server software using Docker, and Forgejo is no exception. They have decent documentation on how to get it running, and publish rootless images which is nice (and diminishes my urge to make an artisanal version myself). You can set configuration options using environment variables, which is perfect for containers, although the names can end up a bit unwieldy. Like this thing: FORGEJO__repository.signing__SIGNING_NAME=Chris Smith. It gets the job done, but the environment-to-ini mapping is pretty ugly.

I didn’t want to expose Forgejo publicly, as I wanted to avoid having to try and secure it⁵, or dealing with bots scraping it, or users signing up, and so on. I wanted somewhere to store my git repositories, handle CI for me, and mirror them somewhere public for other people to see and interact with. If you’ve read some of my other posts you’ll probably guess where this is heading: Tailscale. Alongside the Forgejo container, I run a Tailscale instance with a serve.json that covers both the web frontend and the SSH listener used for git operations:

{
    "TCP": {
        "22": {
            "TCPForward": "forgejo:2222"
        },
        "443": {
            "HTTPS": true
        }
    },
    "Web": {
        "${TS_CERT_DOMAIN}:443": {
            "Handlers": {
                "/": {
                    "Proxy": "http://forgejo:3000"
                }
            }
        }
    },
    "AllowFunnel": {
        "${TS_CERT_DOMAIN}:443": false
    }
}

This allows me to interact normally with Forgejo from any of my devices or servers (which all run Tailscale), while not exposing it to the Internet at all. It also handles the TLS certificates automatically, which saves me setting up something else to do that.

For CI, I run the Forgejo runner image on the same server, and gave it a dind container to use to actually run the workloads. dind is the cutesy name for Docker-in-Docker, basically a Docker daemon running inside a Docker container. That keeps the CI workload separated nicely from the “production” workload running on the server, which is nice from both a security and a monitoring point of view.

The uncanny valley of actions

Forgejo actions are basically like GitHub actions: they run a series of steps using one or more container images. You define those steps in the exact same clunky YAML format as with GitHub. The big difference between them is that GitHub defaults to using an absolutely massive base image filled with out-of-date preinstalled software, and Forgejo leaves that for the administrator to configure. You could, of course, just use the same image as GitHub, but lugging around a multi-gigabyte image that doesn’t even have recent versions of the software I want isn’t really my style. Instead, I set about using a plain debian image as the base, and then did a face-palm when I tried to run a “normal” action and remembered they’re all written in JavaScript, so expect node to exist.

Accommodating JavaScript isn’t really my style, either, so I did the very sensible thing of writing my own suite of actions in Go. Being written in Go means they can be compiled statically, published as a container, and manage their own very limited dependencies. For example, the checkout action is built into an alpine container with git added, while the dockerbuild action uses the buildah image as a base. Each image has the tools it needs, pinned to a recent version, and nothing more. This is very much not a sensible approach to take for most people, but it made me happy. With six basic actions, I could replace almost all the ad-hoc workflows I had in GitHub⁶.

Other than the base images and my self-inflicted JavaScript machinations, everything works the same as GitHub. But faster. So much faster. Most of my CI workflows finish on Forgejo before GitHub would even have allocated a runner to the job⁷. And I can actually view the logs without them glitching out.

Step aside Dependabot, here comes Renovate

One of the boons and/or banes of hosting code on GitHub is access to Dependabot⁸. It’s a tool that monitors your dependencies, and automatically submits PRs when new versions are available. It also does security alerts, but they’re comically bad for Go at least⁹. I do like having dependencies automatically handled, especially with a cooldown, which is how I had Dependabot configured before moving.

To replace it, I’ve configured Renovate, an open source alternative. I’d seen it used a bunch before: both by projects on GitHub who prefer it over Dependabot, and by people using GitLab and other platforms where Dependabot isn’t. It mostly does the same things, but Renovate has a few very nice extras.

Firstly, it supports transcluding config from another repo. So in each of my many, many projects, I just have this stub of a renovate config:

{
  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
  "extends": [
    "local>meta/renovate"
  ]
}

Then the actual config lives in a default.json in the meta/renovate repository. I mirror that repository to GitHub, if you want to have a look. This is an amazing feature. When I enabled cooldowns in my Dependabot config it was a slog to go through all my active repositories and make the same change over and over again. With Renovate I can configure that centrally. As far as I know Dependabot can’t do anything like that, even for enterprises.

Within that central config I use some of the other nice features. It has the ability to auto merge changes. I use this to automatically accept changes from trusted projects, or my own libraries:

    {
      "matchManagers": ["gomod"],
      "matchPackagePatterns": [
        "^github\\.com\\/csmith\\/",
        "^chameth\\.com\\/"
      ],
      "matchUpdateTypes": ["minor", "patch"],
      "automerge": true,
      "minimumReleaseAge": "0 days"
    },
    {
      "matchManagers": ["gomod"],
      "matchPackagePatterns": [
        "^github\\.com\\/csmith\\/",
        "^chameth\\.com\\/"
      ],
      "matchUpdateTypes": ["major"],
      "minimumReleaseAge": "0 days"
    },

This takes any minor or patch release of my libraries, and automerges it with no cooldown. For major version changes it overrides the cooldown but doesn’t automerge. To automerge Dependabot PRs you have to write an action, implement that logic yourself, and hope you’ve successfully avoided all the footguns inherent in that.

Speaking of major version updates, Renovate also has an option to automatically update the imports in Go packages when it’s offering a major update. In the config I have:

"postUpdateOptions": ["gomodTidy", "gomodUpdateImportPaths"],

Which means that every time it does an update it’ll run go mod tidy, and it’ll update the import paths. In Go, v2 of a module has a different import path to v1 (so they can coexist if transient dependencies need different versions), so usually you have to go through and find and replace those paths. Renovate handles that for me now! I still have to address whatever breaking changes are in the new version, but there’s a lot less grunt work.

It can also run custom commands¹⁰, so for example in my legotapas project I have this extra snippet in the renovate.json:

  "postUpgradeTasks": {
    "commands": [
      "sh -c 'rm plate_*.go'",
      "go run ./cmd/generate"
    ],
    "executionMode": "branch",
    "fileFilters": ["*.go"]
  }

I won’t go into the gory details, but this handles automatically regenerating a bunch of files that change every time a certain dependency is updated. Previously I had a separate action to do that on GitHub; just being able to drop commands in the config file is much nicer.

To actually run Renovate, I simply have a workflow in Forgejo on a schedule that uses their official Docker image. It also triggers if I update the config, which is nice when I add a new rule, as it’ll immediately update the open PRs to comply. Overall, Renovate has felt like a pretty big quality-of-life upgrade.

Odd problems

Not everything has been smooth sailing. Sometimes when Renovate automerged a change, it would just… disappear. The PR was closed as merged, but the commit never landed on master. It wasn’t a huge issue as the next Renovate run would just recreate it, but it would then disable the automerge and I’d get confused as to why. It turns out there was a major problem with how I had everything set up. Renovate was telling Forgejo to automerge when the required checks pass, but I had no branch protection rules set up in Forgejo, so as soon as the PR was created it was eligible to merge. As the CI was so fast I hadn’t noticed that the automerges were happening before the CI results were posted.

The disappearing commits were because the repository was getting into a bad state when Renovate tried to automerge multiple changes instantly in the same repo. Forgejo has a bunch of maintenance commands that helped to fix that problem, and I then wrote a little script to enable branch protection rules so the CI would actually run. The automerging has been smooth since.

Another issue I had early on was that merging would fail because the GPG keyring was locked. I had Forgejo configured to sign all the automatic commits, so you can verify what commits came from my infrastructure. Forgejo is the only process using the keyring, so I wasn’t sure why it was becoming locked. It turns out that GnuPG uses the hostname as part of the lockfile, and because Forgejo was running in Docker it was getting random hostnames based on the container ID. Explicitly setting a hostname made GnuPG and by extension Forgejo much happier.

Webhooks and updating

Forgejo has this amazing feature: you can add a webhook that’s called for all your repos. GitHub, for some reason, supports this for organisations but not people. Even though the two are treated the same in a lot of places. It doesn’t seem like it would be hard, and it’s such an obvious thing to want, but… no. I wrote a whole tool to add webhooks for me to get around this. Now I don’t need it, Forgejo does the right thing!

One particularly interesting use of these webhooks has been making my Docker containers auto-update when a new image is pushed. I previously had a webhook receiver for a few projects that would update them automatically, but GitHub package notifications were extremely laggy. Every other webhook fired within a minute or so of the event happening, but package webhooks would sometimes take 30-60+ minutes to fire. I opened a support case with GitHub and it got escalated to engineering and fixed about 10 weeks later¹¹. It was better for a while, and then got worse again. Trying to do continuous deployment with a 30 minute random lag was frustrating.

So now I had reliable webhooks, but the update process was a bit gross. I have a hangup about internet-facing services not having access to the Docker socket. It just feels like too big a security risk. So I had a process that received hooks, and then another that figured out if containers needed to be updated and restarted them. Adding a new container to the system meant recompiling the second process, which was a massive faff.

Fortunately, I was saved from this mess by my friend Greg. He wrote adze, a tool that receives webhooks and uses Docker Compose to update matching containers. He wrote a blog post about it. It’s all one process, but that’s no longer a blocker for me because the webhooks can be delivered privately from my Forgejo instance without exposing adze to the internet. It finds matching containers automatically based on the images they’re using¹², and combined with Forgejo not forcing me to add a webhook to every single repository makes my life so much easier. I write some code, push it to Forgejo, and within a minute or so it’s running on my dev instance.

I have IRC notifications set up for when adze does updates, and I still have some old ones that announce GitHub package webhooks. I keep seeing things like this and chuckling:

15:44:42 <@ircjag> [ADZE] chameth.com: pending updating git.yak-wall.ts.net/public/chameth.com
15:44:45 <@ircjag> [ADZE] chameth.com: success updating git.yak-wall.ts.net/public/chameth.com
17:11:54 <@ircjag> [GHCR] Container pushed to csmith/chameth.com:dev.

I pushed a change at 15:43, Forgejo built it and pushed the image (to both its own registry and to GitHub), then at 15:44 adze updated the container to the new version. An hour and a half later GitHub gets around to delivering its own webhook.

Mirroring and PRs

The final piece I had to figure out was how to actually interact with people. Most of my projects are small and don’t get a massive amount of public contributions, but the option should still be there. And ideally not involve anyone having to figure out how to e-mail patches¹³.

Mirroring outwards is simple: Forgejo supports it natively. Whenever I push to Forgejo, it pushes out to the corresponding repo on GitHub. I’ve also started mirroring some projects to Codeberg, to avoid having GitHub as my single “public” presence. But what happens when I get a pull request? If I merge it in the GitHub web UI, Forgejo will push its own branch over the top and get rid of it¹⁴. I could pull the changes, merge them, and push the result to Forgejo but then I don’t get the benefit of any CI.

I ended up writing a small private tool that deals with this for me. I give it a GitHub PR, and it effectively imports it into Forgejo for me. I created a prs organisation, and it’ll create a fork of the project in that org if it doesn’t exist. Then it pushes the PR contents to a branch, and creates a PR from the prs repo into the main one. It runs as a user which can write to the PRs org, but only submit pull requests to public repositories outside of it.

When the PR is imported, I can review it in the Forgejo UI, and then I can approve the CI workflows for that particular PR. This gives me some extra defence-in-depth in case anyone is trying to abuse one of those action footguns. Once the CI passes, I can merge it as normal in the Forgejo UI, it gets mirrored out to GitHub, and GitHub marks the PR as merged automatically. It’s not the most elegant solution, but the actual workflow is pretty smooth, especially for the low volumes of PRs I get.

With that, I have Forgejo set up to do everything I need from a git host, and I’m no longer hamstrung every time GitHub goes down.

This way of counting isn’t particularly fair, but it’s somewhat realistic. GitHub break out their uptime for things like git operations, pull requests, actions, webhooks and packages. Realistically if any of those independent things are down then my overall workflow doesn’t, well, work. ↩︎
To be clear, I’m not objecting to the use of Copilot here. It’s a tool. But if you use a tool to do something fairly simple and it spews out 35 commits, including at least 5 reverts, then either it’s a terrible tool or you’re using it very wrong. I didn’t hunt down this example, I came across it while trying to debug something and wasted a bunch of time trying to figure out what on earth was going on. ↩︎
You could self-host runners, which may help, except they’ve already threatened to charge you for the privilege of bringing your own runners. ↩︎
If people could stop finding RCEs in git services for a few days so I can stop redrafting this intro, that’d be great. ↩︎
I’m feeling pretty smug about this decision after reading about the security issues. ↩︎
There’s one holdout: my dockerfiles repo which is a very special snowflake with a very complex workflow and I’m still deciding how to handle it. ↩︎
Which is to be expected, given I’ve got a server dedicated to one person, and they’re trying to serve however-many million users at once. That doesn’t make it any less nice, though! ↩︎
I’d link to it but there’s nowhere really good to link to. It’s just been subsumed into the ‘security’ functions of GitHub, along with a bunch of copilot nonsense. ↩︎
The go project maintain a vulnerability database that includes details about which exact symbols are affected, and the govulncheck tool uses this to only report security issues in code that’s actually used. Dependabot doesn’t do that: it constantly alerts about code that’s not imported, so won’t ever be shipped. ↩︎
In the default config it doesn’t allow anything of the sort, of course. You can whitelist individual commands, but because this is a private server I can merrily whitelist .* and do whatever I like. ↩︎
The turnaround time isn’t particularly impressive, but the fact that they kept the support case open, and the (human!) support agent updated me several times is. I don’t have a lot of good things to say about GitHub, but I don’t think I’ve ever had a support experience that good from a company of a similar size. Especially as I wasn’t a paying customer at the time. ↩︎
Why didn’t I do that in the first place? It seems so obvious now… ↩︎
I really like the idea of an e-mail based workflow, but I absolutely hate actually doing it. ↩︎
This is what happened to me a lot when I was half using Gitea. ↩︎

Finding an awkward bug with Claude Code

2025-06-30T00:00:00Z

The many times Claude thought it was right…

I recently encountered a bug in one of my projects that I couldn’t immediately figure out. It was an issue in Centauri, my reverse proxy. After its config was updated, I noticed¹ it stopped serving responses. Looking at the logs, I could see it was obtaining new certificates from Let’s Encrypt for a couple of domains, but I’d designed it so that wouldn’t block requests (or so I thought). After a few minutes of confusion, everything went back to working.

It felt like an issue with locking, but a quick glance didn’t show me anything obvious. I decided to throw the problem at Claude Code and see how it did. With some guidance² it managed to identify the cause, but it was a bit of a journey to get there. I’m going to share the prompts and responses, as it was an interesting process.

The initial prompt

I thought the issue might be quite obvious, and I’d just overlooked it. Centauri isn’t that complex a project, after all. So I gave Claude a fairly minimal prompt to set it off:

> Hello! Please examine this codebase. I have noticed an issue that when a
  certificate is being renewed, the application seems to not serve any other
  requests. I suspect there is a misplaced lock somewhere.
 
  Can you see what's happening? Think very hard.

Claude Code has special hardcoded triggers to engage “thinking” mode, which makes it take more time to think about alternatives. The keywords are: “think”, “think hard”, “think harder”, and “ultrathink”. I managed to not quite get the right incantation here, and only enabled the lowest level³.

I’ll omit all the responses where Claude is “thinking” (talking to itself), or decides to make todo lists then cross items off them then add different items, and so on. Its responses get fairly lengthy; I won’t judge you too harshly if you skim over them. Its first response was blessedly brief:

● I found the issue! Looking at the certificate manager code, I can see the
  problem:

… and then it went back to thinking and reading files, because it had neither found the issue nor could it see the problem. Ho-hum. Some time later it came back with:

● I found the issue! The problem is in certificate/manager.go:53-54:
  
  m.store.LockCertificate(subject, altNames)
  defer m.store.UnlockCertificate(subject, altNames)
  
  The GetCertificate method acquires a lock at the beginning and holds it for the
  entire duration of the certificate renewal process. This includes:
  
  1. Contacting the ACME server
  2. Solving DNS-01 challenges (can take minutes for DNS propagation)
  3. Obtaining the certificate
  4. Getting OCSP staple
  5. Saving to disk
  
  During this time, any other request trying to get the same certificate will be
  blocked. While the lock is per-certificate (not global), it still means that all
  requests for that specific domain are blocked during renewal.
  
  Let me check if there are other places where this might cause blocking:

And it then proceeded to do even more thinking, checking files, etc, until it concluded with:

● I found the root cause! The issue is actually worse than just a
  per-certificate lock. Here's what's happening:
  
  The main blocking issue is in proxy/manager.go:133-144:
   
  func (m *Manager) CheckCertificates() {
      m.lock.RLock()  // ← Acquires read lock on the entire manager
      for i := range m.routes {
          route := m.routes[i]
          // ...
          m.updateCert(route)  // ← This can take MINUTES for ACME renewal!
      }
      m.lock.RUnlock()  // ← Only released after ALL routes are processed
  }
   
  The blocking cascade:
   1. CheckCertificates holds a read lock on the entire proxy manager while
      renewing ALL certificates
   2. Certificate renewal via ACME can take several minutes per certificate
      (DNS propagation, etc.)
   3. Every incoming request calls routeFor (proxy/manager.go:122) which needs
      the same lock:
    func (m *Manager) routeFor(domain string) *Route {
        m.lock.RLock()  // ← BLOCKED until CheckCertificates completes!
        match := m.domains[strings.ToLower(domain)]
        m.lock.RUnlock()
        // ...
    }
  
  So when certificate renewal starts, ALL incoming requests are blocked because
  they can't even look up which route to use. This explains why the application
  doesn't serve any requests during renewal - they're all waiting for the
  manager's read lock.
  
  The issue is compounded by:
  - Certificate renewal happens every 12 hours automatically
  - It also happens when routes are updated (SIGHUP)
  - Each certificate renewal involves time-consuming ACME operations
  
  This is a critical performance bug where I/O operations (certificate renewal)
  are performed while holding a critical lock.

This doesn’t actually follow on from the earlier response, it’s completely flipped onto a different lock being the issue. Amusingly, it’s nearly right here, but it’s highlighting this code for completely the wrong reason.

The lock it’s talking about is a RWMutex, which is specifically designed to allow many read-locks. Everything it’s pointing out are read locks, so they cannot block one another as it described. The response Claude has given sounds very confident, seems appropriately technical, but is in fact complete rubbish. This is one of the big issue with all LLMs at the minute, and it makes me despair at the idea of people “vibe coding” things when they don’t know enough to push back against nonsense like this.

Course correction

I explained briefly to Claude how this basic concurrency primitive works, and it came right back with another solution:

> But that's a RW Mutex. You can hold many read locks concurrently.

● You're absolutely right! I apologize for the confusion. With a RWMutex,
  multiple readers can hold the lock concurrently. Let me trace through this
  more carefully.
  
● Task(Analyze updateCert method)
  ⎿ Done (8 tool uses · 20.0k tokens · 1m 11.9s)
  
● Excellent analysis! You're right about RWMutex allowing concurrent readers.
  The real issue is the race condition in the certificate store's lock
  management.

  Looking at certificate/store.go:82-91:

  func (j *JsonStore) lockFor(subjectName string, altNames []string) *sync.Mutex {
      key := strings.Join(append([]string{subjectName}, altNames...), ";")

      if mu, ok := j.locks[key]; ok {
          return mu
      } else {
          mu = &sync.Mutex{}
          j.locks[key] = mu  // ← Concurrent map write!
          return mu
      }
  }

  This is a classic concurrent map access bug. When multiple requests hit the
  same domain during certificate operations:

  1. Multiple goroutines call lockFor() simultaneously
  2. They read/write to j.locks map without synchronization
  3. Go runtime can:
    - Panic with "concurrent map writes"
    - Corrupt the map structure
    - Block indefinitely if map internals get corrupted

  This explains the blocking behavior - it's not the RWMutex, but rather a race
  condition causing either panics or deadlocks when the map gets corrupted
  during concurrent certificate operations.

  The fix would be to either:
  1. Add a mutex to protect j.locks map access
  2. Use sync.Map instead of a regular map
  3. Pre-initialize all locks at startup

I do appreciate when me stating a basic fact is called out as “excellent analysis”. Definitely doesn’t make me feel like I’m having smoke blown up my ass.

I think the issue it’s describing here is actually a problem⁴, albeit one that’s unlikely to be hit. But it’s definitely not the one we’re looking for. Claude even describes the possible consequences of the bug, and they don’t match what happened at all.

Maybe logs will help?

While Claude was chugging away, I’d been looking into the issue as well. I had logs from when it happened, and figured Claude may be able to glean something from them too. The first thing I’d noticed is that I wasn’t logging when a process finished, so I’d already added that to the code base, hence the note so Claude doesn’t get itself confused:

> That may be an issue, but it's not the one I was looking for. I've found logs
  from the time it happened. Note that a few logs have been added to the
  codebase since (so we can't tell from the logs when ACME or OCSP processes
  *finished*, just when they started). Here are the logs:
  
  {"time":"22:40:53.187887976Z","level":"INFO","msg":"Received signal, updating routes...","signal":1}
  {"time":"22:40:53.19947532Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:40:53.199507942Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:09.048465968Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:09.048482309Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:17.419299795Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:17.419325744Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:23.238027386Z","level":"INFO","msg":"Received signal, updating routes...","signal":1}
  {"time":"22:41:29.994330646Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:29.994353329Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:43.658794811Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:43.658819548Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:57.635325513Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:57.635347515Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:42:10.52439779Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:42:10.524417107Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:42:23.159430249Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:42:23.159452171Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:42:36.347407326Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:42:36.347433295Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:42:52.544628775Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:42:52.544653993Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:43:25.409579107Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:43:25.409602842Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:43:43.819479448Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:43:43.819502041Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:43:54.358957563Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:43:54.358979355Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:44:06.180278128Z","level":"INFO","msg":"Renewing certificate", <big list of alt names>}
  {"time":"22:44:06.180302585Z","level":"INFO","msg":"Starting ACME process to obtain certificate", <big list of alt names>}
  {"time":"22:45:03.830331922Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:45:03.830528134Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:45:03.832388931Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:46:10.225854865Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:46:10.488432434Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:46:10.488439397Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:46:30.617614536Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}

I’ve cut down the logs a bit to remove the specific domains, simplify the timestamps, and remove a bunch of other cruft. The key points are there were two SIGHUPs received, and the last certificate before everything started breaking covered 6 different hostnames.

Claude then went through a phase of periodically shouting “Eureka!” then deciding it hadn’t actually found anything yet:

● Now I see it! The key insight is in the timing and the "context canceled"
  errors. Let me trace through what's happening:
  
● Ah, now I see what's happening! Looking at the logs more carefully:

  1. 22:40:53 - First SIGHUP received, routes updated
  2. 22:40:53 to 22:44:06 - Multiple certificates start renewing (14 certificates!)
  3. 22:41:23 - Another SIGHUP received while renewals are still in progress
  4. 22:45:03 onwards - "context canceled" errors start appearing

  The issue is that SetRoutes is being called AGAIN (at 22:41:23) while the
  previous CheckCertificates() goroutine is still running and renewing
  certificates. Let me check what happens in this scenario:
  
> (The context canceled errors are clients timing out because centauri wasn't
  proxying properly)
  
● Ah, now I understand! The "context canceled" errors are from clients timing
  out because Centauri wasn't proxying their requests. This confirms the
  blocking issue.

  Let me check how incoming requests actually get their certificates:
  
● Now I found the real issue! Looking at the timeline and the code:

  1. 22:40:53 - SIGHUP triggers SetRoutes() which:
    - Calls loadCertificate() for each route
    - Sets route.certificate to the existing certificate
    - Starts go m.CheckCertificates() in background
  2. 22:41:23 - Another SIGHUP while certificates are still renewing
    - SetRoutes() is called AGAIN
    - Creates NEW Route objects with route.certificate = nil initially
    - Replaces the old routes in m.routes
    - The old Route objects (with valid certificates) are replaced!

  The critical issue is in proxy/manager.go:42-65:

  func (m *Manager) SetRoutes(newRoutes []*Route, fallback *Route) error {
      // ... validation ...

      for i := range newRoutes {
          route := newRoutes[i]  // These are NEW Route objects!
          // ...
          m.loadCertificate(route)  // Try to load certificate
      }

      m.lock.Lock()
      m.routes = newRoutes  // REPLACES all routes!
      m.lock.Unlock()
  }

  When the second SIGHUP arrives:
  1. New Route objects are created
  2. For domains currently being renewed, GetExistingCertificate might fail or
     return expired certs
  3. These routes get route.certificate = nil and CertificateMissing status
  4. CertificateForClient returns nil for these domains
  5. TLS handshake fails → clients can't connect → "context canceled" errors

  The fix would be to either:
  1. Prevent concurrent CheckCertificates runs
  2. Copy certificates from existing routes before replacing them
  3. Make certificate renewal truly independent of route management

Midway through it had started searching for “context canceled” errors in the codebase, which doesn’t make much sense. That’s what happens when a client gives up waiting, so the corresponding backend request is terminated. You won’t actually find “context canceled” anywhere in Centauri, because it’s a feature of the Go standard library. I gave it a little nudge to try to stop it rabbit holing.

As far as I can tell, what it’s talking about in this response isn’t an issue. I guess it’s possible that there’s a race condition whereby a route would be replaced and end up with an old version of a certificate that was just being renewed, but it wouldn’t cause an issue in practice; it’d just get updated next time the certificates were refreshed.

There’s no way for routes to get a nil certificate in this scenario, as far as I know. But I don’t have the unfounded confidence of an LLM, so I simply said:

> I don't follow why the certificate would be nil?

Attempt the third

I expected Claude to just explain its reasoning, but it apparently didn’t have any reasoning so set off on another voyage of discovery:

● You're right to question that. Let me trace through this more carefully.

● Good point! Since GetExistingCertificate doesn't acquire locks, it should
  return the existing certificate even during renewal. Let me dig deeper:
  
● Now I see a potential race condition! Here's what could happen:

● I found it! There's a critical race condition that explains the blocking:

  The Race Condition

  1. Background renewal starts: CheckCertificates() → updateCert() →
     GetCertificate() acquires lock and starts ACME renewal
  2. SIGHUP arrives: SetRoutes() is called, which for each route calls
     loadCertificate() → GetExistingCertificate() → store.GetCertificate()
  3. The race:
    - store.GetCertificate() returns a pointer to the certificate in the slice
    - Meanwhile, the renewal completes and calls SaveCertificate()
    - SaveCertificate() calls removeCertificate() which modifies the slice while
      it's being read
    - This slice modification (append(j.certificates[:i], j.certificates[i+1:]...))
      can cause:
        - The pointer returned by GetCertificate to become invalid
        - Slice bounds issues
        - Memory corruption
  4. The result:
    - GetExistingCertificate might return corrupted data or nil
    - Routes end up with certificate = nil
    - TLS handshakes fail
    - Clients timeout → "context canceled"

  The Timeline Confirms This

  - 22:40:53 - First SIGHUP, starts renewal of 14 certificates
  - 22:41:23 - Second SIGHUP arrives (30 seconds later) while renewals are still running
  - 22:45:03 - First timeout errors (4 minutes after first SIGHUP)

  The 4-minute delay matches ACME renewal time. The second SIGHUP's SetRoutes
  likely read certificates while they were being modified by the first SIGHUP's
  renewal goroutines.

  This is a classic concurrent slice modification bug - no synchronization
  between readers (GetCertificate) and writers (SaveCertificate/removeCertificate).

Once again we have a very confident and technical answer that does not explain the symptoms we’re looking for. It’s also mostly rubbish again. GetCertificate and SaveCertificate are only called by code that is holding a lock for that certificate; they won’t interfere with one another. There may, again, be a small concurrency issue if different certificates are handled in parallel, but it’s definitely not the cause of our current problems.⁵

Working through these explanations and debunking them was annoying me at this point. I decided to give it once last chance, and used the “ultrathink” shibboleth:

> So there may be a concurrent modification issue, but that doesn't explain the
  symptoms. If a TLS handshake failed it wouldn't result in the clients timing
  out. Likewise if there was any kind of corruption there'd be a panic, not a
  period where it didn't work and then started working again. Engage ultrathink.

Fourth time lucky

I’m going to include a piece of the thinking here because it amused me so much:

✻ Thinking…

  Oh! I need to think about this differently. Let me trace through what happens
  when a request comes in:

Apparently it takes “ultrathink” to actually work through the problem logically? Amusingly it did actually get there:

● You're absolutely right. Let me think more carefully about this...

● EXACTLY! That's the issue. Looking at the timeline:

  1. 22:40:53 - First SIGHUP: CheckCertificates() acquires READ lock, starts
     renewing 14 certificates
  2. 22:41:23 - Second SIGHUP: SetRoutes() tries to acquire write lock, blocks
     waiting
  3. Incoming requests call routeFor() for route lookup, but Go's RWMutex blocks
     new readers when a writer is waiting (to prevent writer starvation)
  4. 22:45:03 - Clients timeout because requests can't even get past route lookup

  The key insight is Go's RWMutex writer starvation prevention: when a writer
  is waiting, new readers are blocked even though the current lock holder is
  also a reader.

  So the cascade is:
  - CheckCertificates (read lock) → certificate renewal takes minutes
  - SetRoutes (write lock) → waits for read lock to release
  - routeFor (read lock for every request) → blocked by waiting writer

  Result: All incoming HTTP requests hang at route lookup, never reach TLS
  handshake or proxying logic. Clients timeout waiting for any response
  → "context canceled".

  This perfectly explains:
  - No panics (no corruption)
  - No immediate TLS errors (never gets that far)
  - Requests hang then timeout (blocked on lock)
  - Eventually recovers (when certificate renewals finish)

  The fix would be restructuring to avoid holding the manager lock during slow
  certificate operations.

We’re back to the RWMutex again, but this time it’s dropping knowledge on me not the other way around: if there’s a writer waiting, then new readers are blocked. This does indeed perfectly explain the symptoms, and was something I’d overlooked. The write lock is only held briefly to update some struct members to prevent it from blocking the readers, but this behaviour coupled with the long-running read lock ends up doing that anyway.

The fix

After all this work it’s very tempting just to ask Claude to fix it, but I had almost no confidence it’d be able to maintain any of the concurrency requirements given how much it flailed around with bad explanations. But in the interests of science, I asked it to try. Here’s what it came up with:

   // CheckCertificates checks and updates the certificates required for registered routes.
   // It should be called periodically to renew certificates and obtain new OCSP staples.
   func (m *Manager) CheckCertificates() {
+    // Create a snapshot of routes to avoid holding the lock during slow certificate operations
     m.lock.RLock()
+    routes := make([]*Route, len(m.routes))
+    copy(routes, m.routes)
+    provider := m.provider
+    m.lock.RUnlock()

+    // Process certificate renewals without holding the manager lock
-    for i := range m.routes {
+    for i := range routes {
-      route := m.routes[i]
+      route := routes[i]
 
       if provider == nil {
         route.certificateStatus = CertificateNotRequired
       } else {
         m.updateCert(route)
       }
     }
-    m.lock.RUnlock()
   }

   // updateCert updates the certificate for the given route.

That’s about what I expect. It definitely fixes the exact issue described, but it’s a bit… sloppy. Routes are now being updated when the lock isn’t being held, which is a change in semantics. It also doesn’t address the underlying issue that requests can be blocked if there’s a pending writer, and pending writes can be blocked by readers. A better approach would be to allow these operations to happen without blocking, maybe by using an atomic pointer to an immutable slice. I guess I’ve got some coding to do!

As for Claude: while the journey was frustrating, I think trying to figure this out by myself would have been even more so. It’s one of those things where everything looks right to me, and I’d have to go down a fairly long chain of checking my assumptions to find where I’d gone wrong.

There’s definitely a lot of room for improvement in coding LLMs: being able to estimate their own confidence level instead of stating everything as absolute truth would go a long way. I imagine there’s also a lot of benefit of having one LLM vet the responses of another; that’s sort-of how thinking mode works, but it doesn’t seem to go far enough to stop it outputting rubbish. It’ll be interesting to see how they develop in the future, anyway.

read as “I got spammed by a bunch of monitoring notifications” ↩︎
read as “Me repeatedly telling it that it was talking rubbish” ↩︎
If only we had some kind of language model technology that could understand this kind of thing. ↩︎
I sense some fun times with Go’s race detector in my near future ↩︎
The most likely outcome from these concurrency issues is Centauri panicking, which isn’t great but would only interrupt ongoing connections before it restarts and starts serving traffic again. Much less problematic than the “block for five minutes” behaviour I’m trying to fix. ↩︎

How I use Tailscale

2025-06-25T00:00:00Z

The Tailscale logo

I’ve been using Tailscale for around four years to connect my disparate devices, servers and apps together. I wanted to talk a bit about how I use it, some cool features you might not know about, and some stumbling blocks I encountered.

I’m not sure Tailscale needs an introduction for the likely audience of this blog, but I’ll give one anyway. Tailscale is basically a WireGuard¹ orchestration service, with lots of nice features sprinkled on top. It’s a subscription product, but it has an insanely generous free tier that covers basically anything you’d ever want to do as an individual. They also open source all their client software, and there’s a third party control server implementation called Headscale if you want to avoid the hosted system entirely.

Basic connectivity

At its core, Tailscale lets you easily connect from one device to another, even if they’re not directly exposed to the Internet. You install the Tailscale client wherever you like (on your phone, computer, servers, Raspberry Pi, etc), authenticate the machine with the control server, and it can then talk to all the other machines on the tailnet using their private Tailscale IP addresses.

That isn’t anything revolutionary: it’s the basic premise behind VPNs. But Tailscale makes it so easy. You don’t have to bother with any networking configuration. You don’t have to distribute keys. You just install the client², and login.

For example, my home automation service runs on a Raspberry Pi that sits behind two different routers. I installed Tailscale on it³, logged in, and immediately I could SSH into it from my computer or my phone even when they’re on different networks.

Speaking of SSH, Tailscale has special support for it whereby it handles any incoming connection to port 22 from the Tailscale network, and deals with authentication itself. No public keys or passwords: if you’re logged into Tailscale you can be logged into the machine. This is particularly handy when you SSH from a phone, as proper credential management is a bit of a nightmare there.

Exposing entire machines is just the start, though. If you run multiple services on the machine you need to remember which port they’re all on. Yuck. Instead, you can expose individual services as their own node on a tailnet. There are lots of options for doing so: there’s an official Docker image, a Go library, and many third-party tools (such as my own Centauri and tsp).

Not just a VPN

Exposing individual services wouldn’t be much use if you still had to remember their IP addresses. For a long time I manually added DNS entries for Tailscale nodes, allowing me to connect to http://grafana/ instead of http://100.73.190.100. Recently I switched to Tailscale’s MagicDNS, though, which takes care of that for you. Every machine on the tailnet gets an automatic DNS entry based on its name.

I initially shied off of this because it changes the DNS resolver on every machine it’s installed on, and it all seemed a bit too “magic” for me⁴. I got fed up with manually adding DNS entries though, so I spent a bit of time learning about it and got over my knee-jerk “what on earth is going on?!” reaction. The DNS controls also let you force a specific upstream DNS server. I use NextDNS everywhere, so having Tailscale automatically configure this for me on all my devices was a bonus⁵.

As well as the short names, you can resolve nodes on the tailnet using a slightly longer form: machine.your-tailnet.ts.net. The “your-tailnet” bit is randomly generated, and you can reroll it in the control panel to find a fun one. But why waste time say lot word, when few word do trick? Because Tailscale can make these addresses globally routable, and issue TLS certs for them too.

Say you’re developing something on your local machine, and want to get feedback from someone. You can use Tailscale’s “funnel” feature to expose it publicly:

tailscale funnel 127.0.0.1:8080

With no other options, this will expose the service over HTTPS on port 443. You can then invite people to visit https://machine.your-tailnet.ts.net and they’ll connect through to port 8080 on your machine. They don’t even need Tailscale installed. I don’t use this terribly often, but it’s a great quality-of-life improvement on the occasions I do want to share something.

Tailscale also has a “serve” command, which does much the same but only exposes it over your tailnet. This is how you’d use the Tailscale Docker image to expose a normal service onto your tailnet, but it’s also useful for similar development scenarios. Occasionally I’ll want to test something on my phone, and rather than make sure it’s connected to the right Wi-Fi network, recompiling the app to not bind to localhost, figuring out my machine’s IP, and so on, and so forth, I just run tailscale serve and access it over Tailscale.

Authentication, two ways

One of my minor frustrations with Tailscale was how cumbersome the authentication process was. I logged in using GitHub, and every time I tried to login to Tailscale, I had to bounce through the GitHub OAuth flow and then select which organisation I wanted to use. Even if I was logged in to GitHub, it still shows the permission page every time. It’s not a dealbreaker, but it’s definitely not smooth. This is what it looks like:

Logging in to Tailscale with a GitHub account

Tailscale have since added the ability to sign in with a custom OIDC provider, so I set up a KeyCloak instance, and my login flow now looks like this:

Logging in to Tailscale with KeyCloak as an OIDC provider

It’s a significantly shorter flow, and because KeyCloak is entirely under my control I can configure how long I stay logged in for. It also reduces my reliance on third parties: if GitHub goes down, or decides to ban my account⁶ or something, I can still access Tailscale.

That’s how you log in to Tailscale, but Tailscale can also assist with logging in to other services. If you connect to a HTTP service over Tailscale, it will add in the following headers:

Tailscale-User-Login: alice@example.com
Tailscale-User-Name: Alice Smith
Tailscale-User-Profile-Pic: https://example.com/photo.jpg

A lot of software has support for accepting login credentials provided by a reverse proxy, which is basically what’s happening here. For example, I run a Grafana instance that’s only exposed over Tailscale. Its config (set in environment variables) is:

GF_USERS_AUTO_ASSIGN_ORG: "true"
GF_USERS_AUTO_ASSIGN_ORG_ROLE: "Admin"
GF_AUTH_PROXY_ENABLED: "true"
GF_AUTH_PROXY_HEADER_NAME: "Tailscale-User-Login"
GF_AUTH_PROXY_HEADER_PROPERTY: "email"
GF_AUTH_PROXY_AUTO_SIGN_UP: "true"

So anyone who presents a Tailscale-User-Login header gets an admin account created with that as their e-mail address. It’s super convenient, but obviously make sure it’s only exposed via Tailscale if you do that!

Other services I run that support this include Miniflux (an RSS reader), Jelu (a book tracker), Linkding (a bookmark manager), and Seafile (a file storage system). If you’re hosting something yourself, look out for “proxy auth” or “remote users” in the documentation or configuration. It’s amazingly convenient to be able to access things without entering credentials.

ACLs, tags and mistakes

For a long time I didn’t bother with any kind of ACLs within my Tailscale network. Every machine could access every other machine. Then one day a thought hit me. The default Tailscale SSH config re-prompts you for user authentication, but I’d disabled that by tweaking the config… That means anyone with access to any of my machines (or who managed to get Tailscale credentials out of one of my apps) would be able to SSH into anywhere else on my network. Even as root! Compromising a small bit of my network would immediately lead to a complete take-over. What’s the point in defence-in-depth if you roll out a red carpet over the drawbridge for any attackers?

The first and most obvious fix for this was to restrict root access over SSH. I changed my Tailscale ACL to prompt for reauthentication for root access, but still allow regular SSH unprompted:

{
  "ssh": [
    {
      "action": "accept",
      "src":    ["autogroup:member"],
      "dst":    ["autogroup:self"],
      "users":  ["autogroup:nonroot"],
    },
    {
      "action": "check",
      "src":    ["autogroup:member"],
      "dst":    ["autogroup:self"],
      "users":  ["root"],
    },
  ],
}

This still didn’t sit right with me, though. Why should a random webserver be able to (theoretically) SSH into my desktop computer unchallenged? Tailscale allows you to do more advanced ACLs by applying tags to devices. I dutifully created a bunch of tags, and went through and tagged every device: user, server, app, container, and so on. This, it turns out, was a mistake. I could no longer SSH to anywhere. If I’d read the docs properly, I might have noticed how they describe tags:

Tailscale tags are how you authenticate and identify non-user devices, such as servers and ephemeral nodes. They serve two primary purposes: to provide an identity to non-user devices and to let you manage access control policies based on purpose.

By applying a nice user tag to all of my devices (computer, phone, tablet and so on), I’d effectively removed my own identity from them. They no longer counted for the autogroup:member source in the SSH config. Whoops. And it’s not easy to fix either:

You cannot remove all tags from a device. A device with a tag-based identity must have at least one tag.

So I’d have to remove all the affected devices, then re-add them. At the time I wanted to roll back all the tags, which would mean reconnecting dozens of nodes to the Tailnet. I did end up doing that, but I also took it as an opportunity to switch to KeyCloak as I mentioned earlier. Setting everything up again was a bit less painful when it wasn’t just correcting a dumb mistake.

I now have a much more sensible tag setup: servers are tagged server, apps are tagged app, and a few special apps are tagged integration. I then use Tailscale’s grants to limit access within the tailnet:

{
  "grants": [
    {
      // Users can access everything
      "src": ["autogroup:member"],
      "dst": ["*"],
      "ip":  ["*"],
    },
    {
      // Servers and integrations can access integrations and apps
      "src": ["tag:server", "tag:integration"],
      "dst": ["tag:integration", "tag:app"],
      "ip":  ["*"],
    },
  ],
}

This stops anyone but a user device from accessing servers, and stops plain apps from accessing anything at all. So for example my Grafana instance is tagged as an app; it doesn’t connect out over Tailscale for anything, it only exposes its interface over Tailscale. My home automation software is tagged as an integration, as it reaches out to other services over Tailscale (e.g., to push metrics it receives from devices).

You could go even further and limit which specific machines talk to which others, but I think this tier system sets reasonable boundaries for my use without getting too much in the way.

Even more

There are lots of other cool features offered by Tailscale that I’ve not covered: exit nodes (allowing you to route normal Internet traffic over Tailscale; very handy when you’re behind a router you don’t trust, or if you want to appear as being in another country for totally legitimate reasons); Tailscale lock (a system where existing nodes have to verify any new ones, guarding against both unauthorised access and Tailscale themselves inserting nodes into your network); file sharing, and more I’ve probably forgotten.

As I mentioned before, an awful lot is available on the free personal plan. It’s definitely worth checking out if you manage servers, or self-host anything. I can’t imagine going back to managing servers and private apps without Tailscale, and I’m excited to see what else they do going forward.

If you’re not familiar with it, WireGuard is a modern VPN included in the Linux kernel. It’s basically the only VPN that isn’t terrible. ↩︎
They have installation instructions and packaged versions of the client for just about every device you can imagine: Windows, Mac, every major Linux distribution, iOS, Android, etc, etc ↩︎
They even have an apt repository specifically for raspbian builds, so it’s super easy. ↩︎
Lots of people seem to treat “magic” as a good thing in software. I think it’s the absolutely opposite. I want to know how something works, not for it to be inscrutable! ↩︎
This is entirely optional, of course, you can just let each device do their own thing as well. ↩︎
I don’t think this is likely, but it’s one of my biggest concerns about using “social” logins. More-or-less all of these services can arbitrarily ban you with no recourse; why would you trust them as keyholders to other things? ↩︎

Simple backups with Restic and Hetzner Cloud

2024-12-06T00:00:00Z

Restic’s mascot, who’s dual-wielding umbrellas to save you from a rainy day.

I have a confession: for the past few years I’ve not been backing up any of my computers. Everyone knows that you should do backups, but actually getting around to doing it is another story.

Don’t get me wrong: most of my important things are “backed up” by virtue of being committed to remote git repositories, or attached to e-mails, or re-obtainable from the original source, and so on. I don’t think any machine failing completely would be a disaster for me, but it would certainly be a pain.

This week I finally got around to doing something, and it ended up being a lot more straight forward than my previous forays into backup-land.

Restic

After soliciting a few opinions, the choice of backup software came down to either Borg or Restic. I’m pretty sure either would have done what I want, but I leaned towards Restic for a few reasons: it has a more informative website, it’s written in Go rather than Python¹, and Borg seems to be transitioning between major releases at the moment².

The way Restic works is pretty simple: you initialise a ‘repository’, and can then call restic backup /some/path and it’ll get backed up to the repository. Restic handles keeping different backups separate, and only sending data that’s changed, and deduplicating, and so on. You basically point it at a thing you don’t want to lose, and it sorts it out for you. Perfect.

There are equally straight-forward commands for removing old snapshots (restic forget) and verifying backups (restic check). One of the nice things about modern backup solutions is they support a whole range of backends. I was originally going to spin up a small VPS to host my backups, but noticed that Restic supported S3-compatible stores…

Hetzner Cloud Object Storage

I host my servers with Hetzner, and was going to use them to spin up a VPS as well. Despite the “Cloud” branding on a bunch of products, they offer reasonable prices and good service. A couple of months ago, they started offering S3-compatible object storage.

The pricing isn’t totally straight forward, but for continuous use the “free quota” amounts to 1TB of storage and 1TB of egress a month. Ingress is free, as is traffic within the eu-central region (where all my servers are). That quota is only awarded when you pay the “base price”, though, which is €4.99 a month. So basically it’s €5 a month for 1TB of storage and enough egress to fully restore every single byte. That’s better value than any VPS I can find, much cheaper than Amazon S3, and about the same as Backblaze B2.

Getting them to work together

Now you’d think making the tool that supports S3-compatible object storage work with your S3-compatible object storage would be easy, right? Well not quite. The library Restic uses to deal with S3 backends has some strange logic for figuring out the bucket name given a URL. It doesn’t quite seem to work right, though…

Hetzner buckets have URLs like s3://bucketname.hel1.your-objectstorage.com³, but just passing that to Restic gives an error that the bucket is not specified. The docs mention there’s an advanced option to make it use the virtual host for the bucket name: -o s3.bucket-lookup=dns. But that… also doesn’t work. What I ended up doing was specifying the URL as s3://hel1.your-objectstorage.com/bucketname, and also passing in the dns option. The library then seems to muddle its way back to a real, working URL. I’m not sure why it works like this: maybe it’s just a weird aspect of S3 that I’m oblivious to?

The next fun part is that you can configure Restic entirely by using environment variables, except for that -o s3.bucket-lookup=dns argument. That has to go on the command line. I ended up making a little wrapper script to invoke Restic correctly:

#!/bin/sh

# The password restic will use to encrypt your data. You should generate
# something nice and secure.
export RESTIC_PASSWORD=repo-password

# The path to the repository where restic will save the backup. In our case
# this takes the form `s3:<endpoint>/<bucket>`. Your endpoint might be different
# to mine depending on the region your bucket is in.
export RESTIC_REPOSITORY=s3:hel1.your-objectstorage.com/bucket-name

# The access and secret key generated in the 'S3 credentials' section of the
# Hetzner Cloud Console
export AWS_ACCESS_KEY_ID=hetzner-access-key-id
export AWS_SECRET_ACCESS_KEY=hetzner-access-key

# Pass any arguments on to the restic command, along with the magic
# `s3.bucket-lookup` option we need to resolve the S3 URL properly.
exec restic -o s3.bucket-lookup=dns "$@"

Then in the backup script I just alias restic to use the script:

#!/bin/bash

set -eu

# This means any time we use `restic` below, we'll actually execute our special
# script which supplies all the env vars and arguments needed to find the
# repository. Make sure the path matches where you saved the script!
alias restic='~/.bin/restic'

# Actually do the backup. Each directory in the list below will be backed up
# separately.
dirs=(
	"/some/path/to/backup/"
	"/some/other/path/"
)
for i in "${dirs[@]}" 
do
	echo $i
	(cd $i && restic --verbose backup .)
done

# Prune our snapshots. You can tweak the numbers here. Run with `--dry-run` to
# see what effect any changes would have before actually committing to them. 
restic forget --keep-daily 7 --keep-weekly 10 --keep-monthly 24 --keep-yearly 10

The only other notable thing here is that the script changes into the directory to be backed up. If you give Restic an absolute path, it will create a new snapshot if the metadata of any folder in the path changes, which is not what I want.

If it wasn’t for the S3 URL issues, the whole thing would’ve probably taken me about half an hour. That’s including setting up the object storage, installing Restic, and so on. It’s painfully easy. Why didn’t I do this three years ago?!

Addendum: a step-by-step guide

If you want to do this yourself, here’s a quick step-by-step guide:

Log in to the Hetzner Cloud Console, and create a project.
On the “Object Storage” tab, create a new bucket. Note the name and the endpoint.
On the “Security” tab, go to “S3 Credentials” and generate new credentials. Note down the access key and the secret key.
Copy the first shell script above, fill in the password (you can pick!), endpoint, bucket name, access key and secret key.
Run the script with the init argument (e.g. ~/.bin/restic init). This will create a new repository, and only needs to be done once even if you backup multiple machines.
Copy the second shell script above, making sure the restic alias points at the script you saved in step 4. Change the list of directories to whatever you want to backup.
Schedule the script to be run automatically, using crontab or systemd timers or however you prefer.

To check everything is working, you can use the snapshots subcommand to see a list of saved snapshots. You might also want to try to restore a snapshot using the restore subcommand.

I’m not trying to be a language snob, but given the choice between two otherwise equal projects one in Go and one in Python, I’ll take the Go one. I know I’m not going to have weird library issues down the line, and I’m much more comfortable rummaging around the source. ↩︎
With a “Don’t use this in production!” notice on the shiny new version. ↩︎
Aside: I really hate URLs like that. What is with the trend for completely generic domains divorced from the service they’re a part of? ↩︎

Artisanal Docker images

2022-02-05T00:00:00Z

Artisanal containers…

I run a fair number of services as docker containers. Recently, I’ve been moving away from pre-built images pulled from Docker Hub in favour of those I’ve hand-crafted myself. If you’re thinking “that sounds like a lot of effort”, you’re right. It also comes with a number of advantages, though, and has been a fairly fun journey.

The problems with Docker Hub and its images

Rate limits

For the last few years, I’ve been getting increasingly unhappy with Docker Hub itself. Docker-the-technology is wonderful, but Docker-the-company has been making some rather large missteps. The biggest and most impactful of these has been introducing “pull rate” limits. At the time of writing, if you want to just pull a public image without logging in then you are limited to 100 pulls every 6 hours. If you log in then you’re limited to 200 pulls per 6 hours, but it’s account wide. This might seem like a big enough number, but I repeatedly hit it and there is no way to actually audit what is causing it. I have various containers that may all pull images at arbitrary times (e.g. continuous integration build agents), and the only information you get back from Docker Hub is the number of pulls remaining.

Obviously, I could start paying Docker Hub for a “Pro” plan. That gets you 5,000 pulls per day for $7/month. The downside is that every docker client would have to be authenticated, which presents a fair annoyance in terms of credential management. I also don’t really like how they positioned the service as a public utility with special treatment in the docker software, and then start tightening the ratchet to make money.

“Bad” images

I’m fairly opinionated about what a container image should look like: most importantly it should run just a single process, and only include the bare minimum dependencies required for that. Other people think differently, and it’s very hard to tell at a glance whether an image on Docker Hub contains just the application you want, or whether it also bundles MySQL, Redis, Elasticsearch, and a partridge in a pear tree. Some people want that kind of thing, but I really don’t. It’s also very hard to tell whether an image is officially endorsed by the upstream project, and where the source Dockerfile is. This used to be better because most projects used Docker Hub’s automatic builds, but they’re now a “pro” feature.

I quite often found that I’d be looking for an image for X, and there would be 5-10 images from different users. None of them looked official, some of them were out-of-date, some bundled the kitchen sink. Even when one looked good, it’s a bit of a gamble whether the author is going to keep it updated or not.

Doijanky

The rate limits and other problems were annoying, but they weren’t really annoying enough to force me to do anything about it. The straw that broke the camel’s back came later: I was looking at the official golang images, and noticed that all the tags were pushed by a random user account called “doijanky”:

An ‘official’ Docker Hub image pushed by user ‘doijanky’

I, perhaps naively, assumed that official images were built on Docker Hub’s own infrastructure. Why would all the Golang images be attributed to this user? Checking out their profile, they’re simply identified as a “Community User” like everyone else, with no repositories of their own. The only thing in the profile is their homepage, which is a link to a Jenkins dashboard: https://doi-janky.infosiftr.net/. It appears legitimate: “Infosiftr” are a container consultancy and the dashboard is linked to from the README in the official images git repository, but I find it baffling that they’re using third-party infrastructure and a normal user account (with a dubious name) to push these images. There doesn’t seem to be a good way to verify what you pull corresponds to the Dockerfile it came from; if infosiftr wanted to inject something into the build they could happily do so, and who knows how good their infosec posture is? If someone got access to the “doijanky” account, how long could they upload malicious images before someone noticed?

This little roller-coaster ride from “are all the official images compromised?!” to “oh, no, they’re not, it’s all just awful” finally convinced me to look at building my own images from scratch.

The implementation: templating with contempt

One of the big issues I needed to tackle was how to deal with updates. I didn’t want to have to go and edit a file every time some minor release was made of some software, or every time there was a security vulnerability in a common library. The official images use a shell-scripting based system to check for updates and generate Dockerfiles, I decided to do something similar but with Go templates. The result is a tool called contempt. It takes a template like:

FROM {{image "golang"}} AS build

ARG TAG="{{github_tag "example/project"}}"

RUN apk add --no-cache \
        {{range $key, $value := alpine_packages "git" -}}
        {{$key}}={{$value}}\
        {{end}}; \
# ...

Contempt has support for getting information from a variety of sources. In this case, it’s getting the latest digest of another Docker image, the latest tag from a Git repository, and the latest version of an alpine package and all its dependencies. The resulting Dockerfile looks something like this:

# Generated from https://github.com/csmith/dockerfiles/blob/master/miniflux/Dockerfile.gotpl
# BOM: {"apk:brotli-libs":"1.0.9-r5","apk:busybox":"1.34.1-r4", <snip> }

FROM reg.c5h.io/golang@sha256:ac8fa5f4078b0a697796b5d741... AS build

ARG TAG="2.0.35"

RUN apk add --no-cache \
        brotli-libs=1.0.9-r5\
        busybox=1.34.1-r4\
        # <snip>
        pcre2=10.39-r0\
        zlib=1.2.11-r3\
        ; \
# ...

I’ve cut out the longer parts for readability. You can see that it pins all versions of the alpine packages in use, as well as the base image. This ensures that if you build from the same Dockerfile at a later time it will build the same image (or will fail entirely, as Alpine doesn’t keep their old packages around indefinitely). It also produces a “bill of materials” as a really long JSON-encoded comment. If you let contempt commit the Dockerfile it uses the BOM to generate useful commit messages like: [project] apk:busybox: 1.34.1-r3->1.34.1-r4, so you can see exactly what changed.

Contempt also has support for building and pushing images whenever it changes the Dockerfile. I use it in a GitHub action that runs daily to check all my images are up-to-date and push those that aren’t. It understands the dependencies between images (by pre-analysing the templates) so it will always check and build base images before ones that require them. This means an update to, say, the “alpine” base image will cause anything that depends on it to get updated at the same time, ensuring security updates are rolled out promptly.

The result

You can see my collection of lovingly hand-crafted Dockerfiles in my dockerfiles repository.

There are a number of advantages to handwriting all the images I use. The obvious one is that they’re all built how I want: there are no extraneous dependencies, they’re all based on the same small set of base images (rather than pulling around 10 different versions of debian), nothing tries to also run a DBMS in its container, etc.

This level of customisation goes further, though. Because I’m packaging the software myself, I can tweak how it’s built to fit my needs. A couple of things I run need their own TLS certificates separate from my normal HTTPS setup, so I bake my certwrapper tool in to manage those; I can even set the build flags on certwrapper to only enable the particular DNS provider I personally need (thus avoiding dragging in clients for AWS, GCP, etc). Some software like Hashicorp Vault has an optional web interface that I don’t need, so I simply don’t enable it in the build. These changes save build time, reduce image sizes, in some cases improve runtime performance, and generally reduce the attack surface of what’s running in the container.

It’s also been a great way to learn more about how software is distributed. Writing a Dockerfile is not that distant from writing a PKGBUILD file for an Arch Linux package, or the equivalent for other distributions. In a couple of instances I’ve googled how to solve a particular issue, and found an Arch or Void linux maintainer asking the upstream project about the exact same issue.

Finally, all the images I build I push to my own registry so there are obviously no rate limiting issues. Standing up a service (assuming the Dockerfile has been written!) is amazingly quick because the base layers are all shared and cached, and the registry is a lot physically closer than Docker Hub. Bootstrapping this whole thing becomes an interesting problem because the image for the registry is stored on the registry, but I’ll leave that discussion for another post…