update the running limit time to 9 hours

Author: jdkent

README.md

@@ -44,7 +44,7 @@ The deployed architecture works like this:
    Pass `-c resultsBucketName=<bucket>` to use an existing S3 bucket, or omit it
    to let the stack create and retain a dedicated bucket. Additional knobs:
 
-   - `-c stateMachineTimeoutSeconds=7200` to control the max wall clock per run
+  - `-c stateMachineTimeoutSeconds=32400` to control the max wall clock per run
    - `-c submitTimeoutSeconds` / `-c statusTimeoutSeconds` / `-c pollTimeoutSeconds`
      to tune Lambda timeouts
    - `-c taskEphemeralStorageGiB` if the default 21 GiB scratch volume is insufficient

infra/cdk/stacks/compose_runner_stack.py

@@ -41,8 +41,8 @@ def __init__(self, scope: Construct, construct_id: str, **kwargs: object) -> Non
         task_memory_mib = int(self.node.try_get_context("taskMemoryMiB") or 30720)
         task_ephemeral_storage_gib = int(self.node.try_get_context("taskEphemeralStorageGiB") or 21)
         task_cpu_large = int(self.node.try_get_context("taskCpuLarge") or 16384)
-        task_memory_large_mib = int(self.node.try_get_context("taskMemoryLargeMiB") or 32768)
-        state_machine_timeout_seconds = int(self.node.try_get_context("stateMachineTimeoutSeconds") or 7200)
+        task_memory_large_mib = int(self.node.try_get_context("taskMemoryLargeMiB") or 65536)
+        state_machine_timeout_seconds = int(self.node.try_get_context("stateMachineTimeoutSeconds") or 32400)
 
         if task_cpu_large >= 16384 and task_memory_large_mib < 32768:
             raise ValueError("taskMemoryLargeMiB must be at least 32768 MiB for 16 vCPU tasks.")