Arvados

h1. Dispatching containers to cloud VMs

(Draft)

{{>toc}}

h2. Component name / purpose

crunch-dispatch-cloud runs Arvados user containers on generic public cloud infrastructure by automatically creating and destroying VMs of various sizes according to demand, preparing the VMs' runtime environments, and running containers on them.

h2. Deployment

The crunch-dispatch-cloud process can run anywhere, as long as it has network access to the Arvados controller, the cloud provider's API, and the worker VMs. Each Arvados cluster should run only one crunch-dispatch-cloud process (future versions will support multiple dispatchers).

h2. Overview of operation

The dispatcher waits for containers to appear in the queue, and runs them on appropriately sized cloud VMs. When there are no idle cloud VMs with the desired size, the dispatcher brings up more VMs using the cloud provider's API. The dispatcher also shuts down idle VMs that exceed the configured idle timer -- and sooner if the provider starts refusing to create new VMs.

h2. Interaction with other components

Controller (backed by RailsAPI and PostgreSQL) supplies the container queue: which containers the system should be trying to execute (or cancel) at any given time.

The cloud provider's API supplies a list of VMs that exist (or are being created) at a given time and their network addresses, accepts orders to create new VMs, updates instance tags, and (optionally, depending on the driver) obtains the VMs' SSH server public keys.

The SSH server on each cloud VM allows the dispatcher to authenticate with a private key and execute shell commands as root.

h2. Configuration

Arvados configuration (currently a file in /etc) supplies cloud provider credentials, allowed node types, spending limits/policies, etc.

<pre><code class="yaml">

    CloudVMs:

      BootProbeCommand: "docker ps -q"

      SyncInterval: 1m    # get list of 

      TimeoutIdle: 1m     # shutdown if idle longer than this

      TimeoutBooting: 10m # shutdown if exists longer than this without running BootProbeCommand successfully

      TimeoutProbe: 2m    # shutdown if (after booting) communication fails longer than this, even if ctrs are running

      TimeoutShutdown: 1m # shutdown again if node still exists this long after shutdown

      Driver: Amazon

      DriverParameters:   # following configs are driver dependent

        Region: us-east-1

        APITimeout: 20s

        EC2Key: abcdef

        EC2Secret: abcdefghijklmnopqrstuvwxyz

        StorageKey: abcdef

        StorageSecret: abcdefghijklmnopqrstuvwxyz

        ImageID: ami-0123456789abcdef0

        SubnetID: subnet-01234567

        SecurityGroups: sg-01234567

    Dispatch:

      StaleLockTimeout: 1m     # after restart, time to wait for workers to come up before abandoning locks from previous run

      PollInterval: 1m         # how often to get latest queue from arvados controller

      ProbeInterval: 10s       # how often to probe each instance for current status/vital signs

      MaxProbesPerSecond: 1000 # limit total probe rate for dispatch process (across all instances)

      PrivateKey: |            # SSH key able to log in as root@ worker VMs

        -----BEGIN RSA PRIVATE KEY-----

        MIIEowIBAAKCAQEAqYm4XsQHm8sBSZFwUX5VeW1OkGsfoNzcGPG2nzzYRhNhClYZ

        0ABHhUk82HkaC/8l6d/jpYTf42HrK42nNQ0r0Yzs7qw8yZMQioK4Yk+kFyVLF78E

        GRG4pGAWXFs6pUchs/lm8fo9zcda4R3XeqgI+NO+nEERXmdRJa1FhI+Za3/S/+CV

        mg+6O00wZz2+vKmDPptGN4MCKmQOCKsMJts7wSZGyVcTtdNv7jjfr6yPAIOIL8X7

        LtarBCFaK/pD7uWll/Uj7h7D8K48nIZUrvBJJjXL8Sm4LxCNoz3Z83k8J5ZzuDRD

        gRiQe/C085mhO6VL+2fypDLwcKt1tOL8fI81MwIDAQABAoIBACR3tEnmHsDbNOav

        Oxq8cwRQh9K2yDHg8BMJgz/TZa4FIx2HEbxVIw0/iLADtJ+Z/XzGJQCIiWQuvtg6

        exoFQESt7JUWRWkSkj9JCQJUoTY9Vl7APtBpqG7rIEQzd3TvzQcagZNRQZQO6rR7

        p8sBdBSZ72lK8cJ9tM3G7Kor/VNK7KgRZFNhEWnmvEa3qMd4hzDcQ4faOn7C9NZK

        dwJAuJVVfwOLlOORYcyEkvksLaDOK2DsB/p0AaCpfSmThRbBKN5fPXYaKgUdfp3w

        70Hpp27WWymb1cgjyqSH3DY+V/kvid+5QxgxCBRq865jPLn3FFT9bWEVS/0wvJRj

        iMIRrjECgYEA4Ffv9rBJXqVXonNQbbstd2PaprJDXMUy9/UmfHL6pkq1xdBeuM7v

        yf2ocXheA8AahHtIOhtgKqwv/aRhVK0ErYtiSvIk+tXG+dAtj/1ZAKbKiFyxjkZV

        X72BH7cTlR6As5SRRfWM/HaBGEgED391gKsI5PyMdqWWdczT5KfxAksCgYEAwXYE

        ewPmV1GaR5fbh2RupoPnUJPMj36gJCnwls7sGaXDQIpdlq56zfKgrLocGXGgj+8f

        QH7FHTJQO15YCYebtsXWwB3++iG43gVlJlecPAydsap2CCshqNWC5JU5pan0QzsP

        exzNzWqfUPSbTkR2SRaN+MenZo2Y/WqScOAth7kCgYBgVoLujW9EXH5QfXJpXLq+

        jTvE38I7oVcs0bJwOLPYGzcJtlwmwn6IYAwohgbhV2pLv+EZSs42JPEK278MLKxY

        lgVkp60npgunFTWroqDIvdc1TZDVxvA8h9VeODEJlSqxczgbMcIUXBM9yRctTI+5

        7DiKlMUA4kTFW2sWwuOlFwKBgGXvrYS0FVbFJKm8lmvMu5D5x5RpjEu/yNnFT4Pn

        G/iXoz4Kqi2PWh3STl804UF24cd1k94D7hDoReZCW9kJnz67F+C67XMW+bXi2d1O

        JIBvlVfcHb1IHMA9YG7ZQjrMRmx2Xj3ce4RVPgUGHh8ra7gvLjd72/Tpf0doNClN

        ti/hAoGBAMW5D3LhU05LXWmOqpeT4VDgqk4MrTBcstVe7KdVjwzHrVHCAmI927vI

        pjpphWzpC9m3x4OsTNf8m+g6H7f3IiQS0aiFNtduXYlcuT5FHS2fSATTzg5PBon9

        1E6BudOve+WyFyBs7hFWAqWFBdWujAl4Qk5Ek09U2ilFEPE7RTgJ

        -----END RSA PRIVATE KEY-----

    InstanceTypes:

    - Name: m4.large

      VCPUs: 2

      RAM: 7782000000

      Scratch: 32000000000

      Price: 0.1

    - Name: m4.large.spot

      Preemptible: true

      VCPUs: 2

      RAM: 7782000000

      Scratch: 32000000000

      Price: 0.1

    - Name: m4.xlarge

      VCPUs: 4

      RAM: 15564000000

      Scratch: 80000000000

      Price: 0.2

    - Name: m4.xlarge.spot

      Preemptible: true

      VCPUs: 4

      RAM: 15564000000

      Scratch: 80000000000

      Price: 0.2

    - Name: m4.2xlarge

      VCPUs: 8

      RAM: 31129000000

      Scratch: 160000000000

      Price: 0.4

    - Name: m4.2xlarge.spot

      Preemptible: true

      VCPUs: 8

      RAM: 31129000000

      Scratch: 160000000000

      Price: 0.4

</code></pre>

h2. Management API

APIs for monitoring/diagnostics/control are available via HTTP on a configurable address/port. Request headers must include "Authorization: Bearer {management token}".

Responses are JSON-encoded and resemble other Arvados APIs:

<pre><code class="json">

{

  "Items": [

    {

      "Name": "...",

      ...

    },

    ...

  ]

}

</code></pre>

@GET /arvados/v1/dispatch/instances@ lists cloud VMs. Each returned item includes:

* provider's instance ID

* hourly price (from configuration file)

* instance type (from configuration file)

* instance type (from provider's menu)

* UUID of the current / most recent container attempted (if known)

* time last container finished (or boot time, if nothing run yet)

@GET /arvados/v1/dispatch/containers@ lists queued/locked/running containers. Each returned item includes:

* container UUID

* container state (Queued/Locked/Running/Complete/Cancelled)

* desired instance type

* time appeared in queue

* time started (if started)

@POST /arvados/v1/dispatch/instances/:instance_id/drain@ puts an instance in "drain" state.

* if the instance is currently running a container, it is allowed to continue

* no further containers will be scheduled on the instance

* (TBD) the instance will not be shut down automatically

@POST /arvados/v1/dispatch/instances/:instance_id/shutdown@ puts an instance in "shutdown" state.

* if the instance is currently running a container, the instance is shut down when the container finishes

* otherwise, the instance is shut down immediately

h2. Metrics

Metrics are available via HTTP on a configurable address/port (conventionally :9005). Request headers must include "Authorization: Bearer {management token}".

Metrics include:

* [future] (summary) time elapsed between VM creation and first successful SSH connection to that VM

* [future] (summary) time elapsed between first successful SSH connection on a VM and ready to run a container on that VM

* (gauge) total hourly price of all existing VMs

* (gauge) total VCPUs and memory allocated to containers

* (gauge) number of containers running

* (gauge) number of containers allocated to VMs but not started yet (because VMs are pending/booting)

* (gauge) number of containers not allocated to VMs (because provider quota is reached)

h2. Internal details

h3. Scheduling policy

The container priority field determines the order in which resources are allocated.

* If container C1 has priority P1,

* ...and C2 has higher priority P2,

* ...and there is no pending/booting/idle VM suitable for running C2,

* ...then C1 will not be started.

However, containers that run on different VM types don't necessarily start in priority order.

* If container C1 has priority P1,

* ...and C2 has higher priority P2,

* ...and there is no idle VM suitable for running C2,

* ...and there is a pending/booting VM that will be suitable for running C2 when it comes up,

* ...and there is an idle VM suitable for running C1,

* ...then C1 will start before C2.

h3. Special cases / synchronizing state

When first starting up, dispatcher inspects API server’s container queue and the cloud provider’s list of dispatcher-tagged cloud nodes, and restores internal state accordingly.

Some containers might have state=Locked at startup. The dispatcher can't be sure these have no corresponding crunch-run process anywhere until it establishes communication with all running instances. To avoid breaking priority order by guessing wrong, the dispatcher avoids scheduling any new containers until all such "stale-locked" containers are matched up with crunch-run processes on existing VMs (typically preparing a docker image) or all of the existing VMs have been probed successfully (meaning the locked containers aren't running anywhere and need to be rescheduled).

When a user cancels a container request with state=Locked or Running, the container priority changes to 0. On its next poll, the dispatcher notices this and kills any corresponding crunch-run processes (or, if there is no such process, just unlocks the container).

When a crunch-run process ends without finalizing its container's state, the dispatcher notices this and sets state to Cancelled.

h3. SSH keys

The operator must install a public key in /root/.ssh/authorized_keys on each worker node. Dispatcher has the corresponding private key.

(Future) Dispatcher generates its own keys and installs its public key on new VMs using cloud provider bootstrapping/metadata features.

h3. Probes

Sometimes (on the happy path) the dispatcher knows the state of each worker, whether it's idle, and which container it's running. In general, it's necessary to probe the worker node itself.

Probe:

* Check whether the SSH connection is alive; reopen if needed.

* Run the configured "ready?" command (e.g., "grep /encrypted-tmp /etc/mtab"); if this fails, conclude the node is still booting.

* Run "crunch-run --list" to get a list of crunch-run supervisors (pid + container UUID)

h3. Detecting dead/lame nodes

If a node has been up for N seconds without a successful probe, despite at least M attempts, it is shut down, even if it was running a container last time it was contacted successfully.

h3. Multiple dispatchers

Not supported in initial version.