piker/brokers/_daemon.py

@@ -23,7 +23,6 @@ from __future__ import annotations
 from contextlib import (
     asynccontextmanager as acm,
 )
-from functools import partial
 from types import ModuleType
 from typing import (
     TYPE_CHECKING,
@@ -191,17 +190,14 @@ def broker_init(
 
 
 async def spawn_brokerd(
+
     brokername: str,
     loglevel: str | None = None,
 
     **tractor_kwargs,
 
 ) -> bool:
-    '''
-    Spawn a `brokerd.<backendname>` subactor service daemon
-    using `pikerd`'s service mngr.
 
-    '''
     from piker.service._util import log  # use service mngr log
     log.info(f'Spawning {brokername} broker daemon')
 
@@ -221,35 +217,27 @@ async def spawn_brokerd(
 
     # ask `pikerd` to spawn a new sub-actor and manage it under its
     # actor nursery
-    from piker.service import (
+    from piker.service import Services
-        get_service_mngr,
-        ServiceMngr,
-    )
-    dname: str = tractor_kwargs.pop('name')  # f'brokerd.{brokername}'
-    mngr: ServiceMngr = get_service_mngr()
-    ctx: tractor.Context = await mngr.start_service(
-        daemon_name=dname,
-        ctx_ep=partial(
-            # signature of target root-task endpoint
-            daemon_fixture_ep,
 
-            # passed to daemon_fixture_ep(**kwargs)
+    dname: str = tractor_kwargs.pop('name')  # f'brokerd.{brokername}'
-            brokername=brokername,
+    portal = await Services.actor_n.start_actor(
-            loglevel=loglevel,
+        dname,
-        ),
+        enable_modules=_data_mods + tractor_kwargs.pop('enable_modules'),
-        debug_mode=mngr.debug_mode,
+        debug_mode=Services.debug_mode,
-        loglevel=loglevel,
-        enable_modules=(
-            _data_mods
-            +
-            tractor_kwargs.pop('enable_modules')
-        ),
         **tractor_kwargs
     )
-    assert (
+
-        not ctx.cancel_called
+    # NOTE: the service mngr expects an already spawned actor + its
-        and ctx.portal  # parent side
+    # portal ref in order to do non-blocking setup of brokerd
-        and dname in ctx.chan.uid  # subactor is named as desired
+    # service nursery.
+    await Services.start_service_task(
+        dname,
+        portal,
+
+        # signature of target root-task endpoint
+        daemon_fixture_ep,
+        brokername=brokername,
+        loglevel=loglevel,
     )
     return True
 
@@ -274,7 +262,8 @@ async def maybe_spawn_brokerd(
     from piker.service import maybe_spawn_daemon
 
     async with maybe_spawn_daemon(
-        service_name=f'brokerd.{brokername}',
+
+        f'brokerd.{brokername}',
         service_task_target=spawn_brokerd,
         spawn_args={
             'brokername': brokername,

piker/data/_sampling.py

@@ -25,7 +25,6 @@ from collections import (
     defaultdict,
 )
 from contextlib import asynccontextmanager as acm
-from functools import partial
 import time
 from typing import (
     Any,
@@ -43,7 +42,7 @@ from tractor.trionics import (
     maybe_open_nursery,
 )
 import trio
-from trio import TaskStatus
+from trio_typing import TaskStatus
 
 from .ticktools import (
     frame_ticks,
@@ -71,7 +70,6 @@ if TYPE_CHECKING:
 _default_delay_s: float = 1.0
 
 
-# TODO: use new `tractor.singleton_acm` API for this!
 class Sampler:
     '''
     Global sampling engine registry.
@@ -81,9 +79,9 @@ class Sampler:
 
     This non-instantiated type is meant to be a singleton within
     a `samplerd` actor-service spawned once by the user wishing to
-    time-step-sample a (real-time) quote feeds, see
+    time-step-sample (real-time) quote feeds, see
-    `.service.maybe_open_samplerd()` and the below
+    ``.service.maybe_open_samplerd()`` and the below
-    `register_with_sampler()`.
+    ``register_with_sampler()``.
 
     '''
     service_nursery: None | trio.Nursery = None
@@ -377,10 +375,7 @@ async def register_with_sampler(
                 assert Sampler.ohlcv_shms
 
             # unblock caller
-            await ctx.started(
+            await ctx.started(set(Sampler.ohlcv_shms.keys()))
-                # XXX bc msgpack only allows one array type!
-                list(Sampler.ohlcv_shms.keys())
-            )
 
             if open_index_stream:
                 try:
@@ -424,6 +419,7 @@ async def register_with_sampler(
 
 
 async def spawn_samplerd(
+
     loglevel: str | None = None,
     **extra_tractor_kwargs
 
@@ -433,10 +429,7 @@ async def spawn_samplerd(
     update and increment count write and stream broadcasting.
 
     '''
-    from piker.service import (
+    from piker.service import Services
-        get_service_mngr,
-        ServiceMngr,
-    )
 
     dname = 'samplerd'
     log.info(f'Spawning `{dname}`')
@@ -444,33 +437,26 @@ async def spawn_samplerd(
     # singleton lock creation of ``samplerd`` since we only ever want
     # one daemon per ``pikerd`` proc tree.
     # TODO: make this built-into the service api?
-    mngr: ServiceMngr = get_service_mngr()
+    async with Services.locks[dname + '_singleton']:
-    already_started: bool = dname in mngr.service_tasks
 
-    async with mngr._locks[dname + '_singleton']:
+        if dname not in Services.service_tasks:
-        ctx: Context = await mngr.start_service(
+
-            daemon_name=dname,
+            portal = await Services.actor_n.start_actor(
-            ctx_ep=partial(
+                dname,
+                enable_modules=[
+                    'piker.data._sampling',
+                ],
+                loglevel=loglevel,
+                debug_mode=Services.debug_mode,  # set by pikerd flag
+                **extra_tractor_kwargs
+            )
+
+            await Services.start_service_task(
+                dname,
+                portal,
                 register_with_sampler,
                 period_s=1,
                 sub_for_broadcasts=False,
-            ),
-            debug_mode=mngr.debug_mode,  # set by pikerd flag
-
-            # proxy-through to tractor
-            enable_modules=[
-                'piker.data._sampling',
-            ],
-            loglevel=loglevel,
-            **extra_tractor_kwargs
-        )
-        if not already_started:
-            assert (
-                ctx
-                and
-                ctx.portal
-                and
-                not ctx.cancel_called
             )
             return True
 
@@ -903,7 +889,6 @@ async def uniform_rate_send(
             # to consumers which crash or lose network connection.
             # I.e. we **DO NOT** want to crash and propagate up to
             # ``pikerd`` these kinds of errors!
-            trio.EndOfChannel,
             trio.ClosedResourceError,
             trio.BrokenResourceError,
             ConnectionResetError,

piker/service/__init__.py

@@ -30,11 +30,7 @@ Actor runtime primtives and (distributed) service APIs for,
   => TODO: maybe to (re)move elsewhere?
 
 '''
-from ._mngr import (
+from ._mngr import Services as Services
-    get_service_mngr as get_service_mngr,
-    open_service_mngr as open_service_mngr,
-    ServiceMngr as ServiceMngr,
-)
 from ._registry import (
     _tractor_kwargs as _tractor_kwargs,
     _default_reg_addr as _default_reg_addr,

piker/service/_actor_runtime.py

@@ -21,6 +21,7 @@
 from __future__ import annotations
 import os
 from typing import (
+    Optional,
     Any,
     ClassVar,
 )
@@ -29,13 +30,13 @@ from contextlib import (
 )
 
 import tractor
+import trio
 
 from ._util import (
     get_console_log,
 )
 from ._mngr import (
-    open_service_mngr,
+    Services,
-    ServiceMngr,
 )
 from ._registry import (  # noqa
     _tractor_kwargs,
@@ -58,7 +59,7 @@ async def open_piker_runtime(
     registry_addrs: list[tuple[str, int]] = [],
 
     enable_modules: list[str] = [],
-    loglevel: str|None = None,
+    loglevel: Optional[str] = None,
 
     # XXX NOTE XXX: you should pretty much never want debug mode
     # for data daemons when running in production.
@@ -68,7 +69,7 @@ async def open_piker_runtime(
     # and spawn the service tree distributed per that.
     start_method: str = 'trio',
 
-    tractor_runtime_overrides: dict|None = None,
+    tractor_runtime_overrides: dict | None = None,
     **tractor_kwargs,
 
 ) -> tuple[
@@ -118,10 +119,6 @@ async def open_piker_runtime(
                 # spawn other specialized daemons I think?
                 enable_modules=enable_modules,
 
-                # TODO: how to configure this?
-                # keep it on by default if debug mode is set?
-                # maybe_enable_greenback=debug_mode,
-
                 **tractor_kwargs,
             ) as actor,
 
@@ -170,13 +167,12 @@ async def open_pikerd(
 
     **kwargs,
 
-) -> ServiceMngr:
+) -> Services:
     '''
-    Start a root piker daemon actor (aka `pikerd`) with an indefinite
+    Start a root piker daemon with an indefinite lifetime.
-    lifetime.
 
-    A root actor-nursery is created which can be used to spawn and
+    A root actor nursery is created which can be used to create and keep
-    supervise underling service sub-actors (see below).
+    alive underling services (see below).
 
     '''
     # NOTE: for the root daemon we always enable the root
@@ -203,6 +199,8 @@ async def open_pikerd(
             root_actor,
             reg_addrs,
         ),
+        tractor.open_nursery() as actor_nursery,
+        trio.open_nursery() as service_nursery,
     ):
         for addr in reg_addrs:
             if addr not in root_actor.accept_addrs:
@@ -211,17 +209,25 @@ async def open_pikerd(
                     'Maybe you have another daemon already running?'
                 )
 
-        mngr: ServiceMngr
+        # assign globally for future daemon/task creation
-        async with open_service_mngr(
+        Services.actor_n = actor_nursery
-            debug_mode=debug_mode,
+        Services.service_n = service_nursery
-        ) as mngr:
+        Services.debug_mode = debug_mode
-            yield mngr
+
+        try:
+            yield Services
+
+        finally:
+            # TODO: is this more clever/efficient?
+            # if 'samplerd' in Services.service_tasks:
+            #     await Services.cancel_service('samplerd')
+            service_nursery.cancel_scope.cancel()
 
 
 # TODO: do we even need this?
 # @acm
 # async def maybe_open_runtime(
-#     loglevel: str|None = None,
+#     loglevel: Optional[str] = None,
 #     **kwargs,
 
 # ) -> None:
@@ -250,7 +256,7 @@ async def maybe_open_pikerd(
     loglevel: str | None = None,
     **kwargs,
 
-) -> tractor._portal.Portal | ClassVar[ServiceMngr]:
+) -> tractor._portal.Portal | ClassVar[Services]:
     '''
     If no ``pikerd`` daemon-root-actor can be found start it and
     yield up (we should probably figure out returning a portal to self

piker/service/_ahab.py

@@ -49,7 +49,7 @@ from requests.exceptions import (
     ReadTimeout,
 )
 
-from ._mngr import ServiceMngr
+from ._mngr import Services
 from ._util import (
     log,  # sub-sys logger
     get_console_log,
@@ -453,7 +453,7 @@ async def open_ahabd(
 
 @acm
 async def start_ahab_service(
-    services: ServiceMngr,
+    services: Services,
     service_name: str,
 
     # endpoint config passed as **kwargs
@@ -549,8 +549,7 @@ async def start_ahab_service(
         log.warning('Failed to cancel root permsed container')
 
     except (
-        # trio.MultiError,
+        trio.MultiError,
-        ExceptionGroup,
     ) as err:
         for subexc in err.exceptions:
             if isinstance(subexc, PermissionError):

piker/service/_daemon.py

@@ -26,17 +26,14 @@ from typing import (
 from contextlib import (
     asynccontextmanager as acm,
 )
-from collections import defaultdict
 
 import tractor
-import trio
 
 from ._util import (
     log,  # sub-sys logger
 )
 from ._mngr import (
-    get_service_mngr,
+    Services,
-    ServiceMngr,
 )
 from ._actor_runtime import maybe_open_pikerd
 from ._registry import find_service
@@ -44,14 +41,15 @@ from ._registry import find_service
 
 @acm
 async def maybe_spawn_daemon(
+
     service_name: str,
     service_task_target: Callable,
+
     spawn_args: dict[str, Any],
 
     loglevel: str | None = None,
     singleton: bool = False,
 
-    _locks = defaultdict(trio.Lock),
     **pikerd_kwargs,
 
 ) -> tractor.Portal:
@@ -69,7 +67,7 @@ async def maybe_spawn_daemon(
     '''
     # serialize access to this section to avoid
     # 2 or more tasks racing to create a daemon
-    lock = _locks[service_name]
+    lock = Services.locks[service_name]
     await lock.acquire()
 
     async with find_service(
@@ -134,65 +132,7 @@ async def maybe_spawn_daemon(
         async with tractor.wait_for_actor(service_name) as portal:
             lock.release()
             yield portal
-            # --- ---- ---
+            await portal.cancel_actor()
-            # XXX NOTE XXX
-            # --- ---- ---
-            # DO NOT PUT A `portal.cancel_actor()` here (as was prior)!
-            #
-            # Doing so will cause an "out-of-band" ctxc
-            # (`tractor.ContextCancelled`) to be raised inside the
-            # `ServiceMngr.open_context_in_task()`'s call to
-            # `ctx.wait_for_result()` AND the internal self-ctxc
-            # "graceful capture" WILL NOT CATCH IT!
-            #
-            # This can cause certain types of operations to raise
-            # that ctxc BEFORE THEY `return`, resulting in
-            # a "false-negative" ctxc being raised when really
-            # nothing actually failed, other then our semantic
-            # "failure" to suppress an expected, graceful,
-            # self-cancel scenario..
-            #
-            # bUt wHy duZ It WorK lIKe dis..
-            # ------------------------------
-            # from the perspective of the `tractor.Context` this
-            # cancel request was conducted "out of band" since
-            # `Context.cancel()` was never called and thus the
-            # `._cancel_called: bool` was never set. Despite the
-            # remote `.canceller` being set to `pikerd` (i.e. the
-            # same `Actor.uid` of the raising service-mngr task) the
-            # service-task's ctx itself was never marked as having
-            # requested cancellation and thus still raises the ctxc
-            # bc it was unaware of any such request.
-            #
-            # How to make grokin these cases easier tho?
-            # ------------------------------------------
-            # Because `Portal.cancel_actor()` was called it requests
-            # "full-`Actor`-runtime-cancellation" of it's peer
-            # process which IS NOT THE SAME as a single inter-actor
-            # RPC task cancelling its local context with a remote
-            # peer `Task` in that same peer process.
-            #
-            # ?TODO? It might be better if we do one (or all) of the
-            # following:
-            #
-            # -[ ] at least set a special message for the
-            #    `ContextCancelled` when raised locally by the
-            #    unaware ctx task such that we check for the
-            #    `.canceller` being *our `Actor`* and in the case
-            #    where `Context._cancel_called == False` we specially
-            #    note that this is likely an "out-of-band"
-            #    runtime-cancel request triggered by some call to
-            #    `Portal.cancel_actor()`, possibly even reporting the
-            #    exact LOC of that caller by tracking it inside our
-            #    portal-type?
-            # -[ ] possibly add another field `ContextCancelled` like
-            #    maybe a,
-            #    `.request_type: Literal['os', 'proc', 'actor',
-            #    'ctx']` type thing which would allow immediately
-            #    being able to tell what kind of cancellation caused
-            #    the unexpected ctxc?
-            # -[ ] REMOVE THIS COMMENT, once we've settled on how to
-            #     better augment `tractor` to be more explicit on this!
 
 
 async def spawn_emsd(
@@ -207,22 +147,21 @@ async def spawn_emsd(
     """
     log.info('Spawning emsd')
 
-    smngr: ServiceMngr = get_service_mngr()
+    portal = await Services.actor_n.start_actor(
-    portal = await smngr.actor_n.start_actor(
         'emsd',
         enable_modules=[
             'piker.clearing._ems',
             'piker.clearing._client',
         ],
         loglevel=loglevel,
-        debug_mode=smngr.debug_mode,  # set by pikerd flag
+        debug_mode=Services.debug_mode,  # set by pikerd flag
         **extra_tractor_kwargs
     )
 
     # non-blocking setup of clearing service
     from ..clearing._ems import _setup_persistent_emsd
 
-    await smngr.start_service_task(
+    await Services.start_service_task(
         'emsd',
         portal,
 

piker/service/_mngr.py

@@ -18,29 +18,16 @@
 daemon-service management API.
 
 """
-from __future__ import annotations
-from contextlib import (
-    asynccontextmanager as acm,
-    # contextmanager as cm,
-)
 from collections import defaultdict
-from dataclasses import (
-    dataclass,
-    field,
-)
-import functools
-import inspect
 from typing import (
     Callable,
     Any,
 )
 
-import msgspec
-import tractor
 import trio
-from trio import TaskStatus
+from trio_typing import TaskStatus
+import tractor
 from tractor import (
-    ActorNursery,
     current_actor,
     ContextCancelled,
     Context,
@@ -52,130 +39,6 @@ from ._util import (
 )
 
 
-# TODO: implement a singleton deco-API for wrapping the below
-# factory's impl for general actor-singleton use?
-#
-# @singleton
-# async def open_service_mngr(
-#     **init_kwargs,
-# ) -> ServiceMngr:
-#     '''
-#     Note this function body is invoke IFF no existing singleton instance already
-#     exists in this proc's memory.
-
-#     '''
-#     # setup
-#     yield ServiceMngr(**init_kwargs)
-#     # teardown
-
-
-
-# TODO: singleton factory API instead of a class API
-@acm
-async def open_service_mngr(
-    *,
-    debug_mode: bool = False,
-
-    # impl deat which ensures a single global instance
-    _singleton: list[ServiceMngr|None] = [None],
-    **init_kwargs,
-
-) -> ServiceMngr:
-    '''
-    Open a multi-subactor-as-service-daemon tree supervisor.
-
-    The delivered `ServiceMngr` is a singleton instance for each
-    actor-process and is allocated on first open and never
-    de-allocated unless explicitly deleted by al call to
-    `del_service_mngr()`.
-
-    '''
-    # TODO: factor this an allocation into
-    # a `._mngr.open_service_mngr()` and put in the
-    # once-n-only-once setup/`.__aenter__()` part!
-    # -[ ] how to make this only happen on the `mngr == None` case?
-    #  |_ use `.trionics.maybe_open_context()` (for generic
-    #     async-with-style-only-once of the factory impl, though
-    #     what do we do for the allocation case?
-    #    / `.maybe_open_nursery()` (since for this specific case
-    #    it's simpler?) to activate
-    async with (
-        tractor.open_nursery() as an,
-        trio.open_nursery() as tn,
-    ):
-        # impl specific obvi..
-        init_kwargs.update({
-            'actor_n': an,
-            'service_n': tn,
-        })
-
-        mngr: ServiceMngr|None
-        if (mngr := _singleton[0]) is None:
-
-            log.info('Allocating a new service mngr!')
-            mngr = _singleton[0] = ServiceMngr(**init_kwargs)
-
-            # TODO: put into `.__aenter__()` section of
-            # eventual `@singleton_acm` API wrapper.
-            #
-            # assign globally for future daemon/task creation
-            mngr.actor_n = an
-            mngr.service_n = tn
-
-        else:
-            assert (
-                mngr.actor_n
-                and
-                mngr.service_tn
-            )
-            log.info(
-                'Using extant service mngr!\n\n'
-                f'{mngr!r}\n'  # it has a nice `.__repr__()` of services state
-            )
-
-        try:
-            # NOTE: this is a singleton factory impl specific detail
-            # which should be supported in the condensed
-            # `@singleton_acm` API?
-            mngr.debug_mode = debug_mode
-
-            yield mngr
-        finally:
-            # TODO: is this more clever/efficient?
-            # if 'samplerd' in mngr.service_tasks:
-            #     await mngr.cancel_service('samplerd')
-            tn.cancel_scope.cancel()
-
-
-
-def get_service_mngr() -> ServiceMngr:
-    '''
-    Try to get the singleton service-mngr for this actor presuming it
-    has already been allocated using,
-
-    .. code:: python
-
-        async with open_<@singleton_acm(func)>() as mngr`
-            ... this block kept open ...
-
-    If not yet allocated raise a `ServiceError`.
-
-    '''
-    # https://stackoverflow.com/a/12627202
-    # https://docs.python.org/3/library/inspect.html#inspect.Signature
-    maybe_mngr: ServiceMngr|None = inspect.signature(
-        open_service_mngr
-    ).parameters['_singleton'].default[0]
-
-    if maybe_mngr is None:
-        raise RuntimeError(
-            'Someone must allocate a `ServiceMngr` using\n\n'
-            '`async with open_service_mngr()` beforehand!!\n'
-        )
-
-    return maybe_mngr
-
-
 # TODO: we need remote wrapping and a general soln:
 # - factor this into a ``tractor.highlevel`` extension # pack for the
 #   library.
@@ -183,46 +46,31 @@ def get_service_mngr() -> ServiceMngr:
 #   to the pikerd actor for starting services remotely!
 # - prolly rename this to ActorServicesNursery since it spawns
 #   new actors and supervises them to completion?
-@dataclass
+class Services:
-class ServiceMngr:
-# class ServiceMngr(msgspec.Struct):
-    '''
-    A multi-subactor-as-service manager.
 
-    Spawn, supervise and monitor service/daemon subactors in a SC
+    actor_n: tractor._supervise.ActorNursery
-    process tree.
-
-    '''
-    actor_n: ActorNursery
     service_n: trio.Nursery
-    debug_mode: bool = False # tractor sub-actor debug mode flag
+    debug_mode: bool  # tractor sub-actor debug mode flag
-
     service_tasks: dict[
         str,
         tuple[
             trio.CancelScope,
-            Context,
             Portal,
             trio.Event,
         ]
-    ] = field(default_factory=dict)
+    ] = {}
-
+    locks = defaultdict(trio.Lock)
-    # internal per-service task mutexs
-    _locks = defaultdict(trio.Lock)
 
+    @classmethod
     async def start_service_task(
         self,
         name: str,
         portal: Portal,
-
-        # TODO: typevar for the return type of the target and then
-        # use it below for `ctx_res`?
         target: Callable,
-
         allow_overruns: bool = False,
         **ctx_kwargs,
 
-    ) -> (trio.CancelScope, Context, Any):
+    ) -> (trio.CancelScope, Context):
         '''
         Open a context in a service sub-actor, add to a stack
         that gets unwound at ``pikerd`` teardown.
@@ -235,7 +83,6 @@ class ServiceMngr:
             task_status: TaskStatus[
                 tuple[
                     trio.CancelScope,
-                    Context,
                     trio.Event,
                     Any,
                 ]
@@ -243,87 +90,64 @@ class ServiceMngr:
 
         ) -> Any:
 
-            # TODO: use the ctx._scope directly here instead?
-            # -[ ] actually what semantics do we expect for this
-            #   usage!?
             with trio.CancelScope() as cs:
-                try:
-                    async with portal.open_context(
-                        target,
-                        allow_overruns=allow_overruns,
-                        **ctx_kwargs,
 
-                    ) as (ctx, started):
+                async with portal.open_context(
+                    target,
+                    allow_overruns=allow_overruns,
+                    **ctx_kwargs,
 
-                        # unblock once the remote context has started
+                ) as (ctx, first):
-                        complete = trio.Event()
+
-                        task_status.started((
+                    # unblock once the remote context has started
-                            cs,
+                    complete = trio.Event()
-                            ctx,
+                    task_status.started((cs, complete, first))
-                            complete,
+                    log.info(
-                            started,
+                        f'`pikerd` service {name} started with value {first}'
-                        ))
+                    )
-                        log.info(
+                    try:
-                            f'`pikerd` service {name} started with value {started}'
-                        )
                         # wait on any context's return value
                         # and any final portal result from the
                         # sub-actor.
-                        ctx_res: Any = await ctx.wait_for_result()
+                        ctx_res: Any = await ctx.result()
 
                         # NOTE: blocks indefinitely until cancelled
                         # either by error from the target context
                         # function or by being cancelled here by the
                         # surrounding cancel scope.
-                        return (
+                        return (await portal.result(), ctx_res)
-                            await portal.wait_for_result(),
+                    except ContextCancelled as ctxe:
-                            ctx_res,
+                        canceller: tuple[str, str] = ctxe.canceller
-                        )
+                        our_uid: tuple[str, str] = current_actor().uid
+                        if (
+                            canceller != portal.channel.uid
+                            and
+                            canceller != our_uid
+                        ):
+                            log.cancel(
+                                f'Actor-service {name} was remotely cancelled?\n'
+                                f'remote canceller: {canceller}\n'
+                                f'Keeping {our_uid} alive, ignoring sub-actor cancel..\n'
+                            )
+                        else:
+                            raise
 
-                except ContextCancelled as ctxe:
-                    canceller: tuple[str, str] = ctxe.canceller
-                    our_uid: tuple[str, str] = current_actor().uid
-                    if (
-                        canceller != portal.chan.uid
-                        and
-                        canceller != our_uid
-                    ):
-                        log.cancel(
-                            f'Actor-service `{name}` was remotely cancelled by a peer?\n'
 
-                            # TODO: this would be a good spot to use
-                            # a respawn feature Bo
-                            f'-> Keeping `pikerd` service manager alive despite this inter-peer cancel\n\n'
 
-                            f'cancellee: {portal.chan.uid}\n'
+                    finally:
-                            f'canceller: {canceller}\n'
+                        await portal.cancel_actor()
-                        )
+                        complete.set()
-                    else:
+                        self.service_tasks.pop(name)
-                        raise
 
-                finally:
+        cs, complete, first = await self.service_n.start(open_context_in_task)
-                    # NOTE: the ctx MUST be cancelled first if we
-                    # don't want the above `ctx.wait_for_result()` to
-                    # raise a self-ctxc. WHY, well since from the ctx's
-                    # perspective the cancel request will have
-                    # arrived out-out-of-band at the `Actor.cancel()`
-                    # level, thus `Context.cancel_called == False`,
-                    # meaning `ctx._is_self_cancelled() == False`.
-                    # with trio.CancelScope(shield=True):
-                    # await ctx.cancel()
-                    await portal.cancel_actor()
-                    complete.set()
-                    self.service_tasks.pop(name)
-
-        cs, sub_ctx, complete, started = await self.service_n.start(
-            open_context_in_task
-        )
 
         # store the cancel scope and portal for later cancellation or
         # retstart if needed.
-        self.service_tasks[name] = (cs, sub_ctx, portal, complete)
+        self.service_tasks[name] = (cs, portal, complete)
-        return cs, sub_ctx, started
 
+        return cs, first
+
+    @classmethod
     async def cancel_service(
         self,
         name: str,
@@ -334,80 +158,8 @@ class ServiceMngr:
 
         '''
         log.info(f'Cancelling `pikerd` service {name}')
-        cs, sub_ctx, portal, complete = self.service_tasks[name]
+        cs, portal, complete = self.service_tasks[name]
-
+        cs.cancel()
-        # cs.cancel()
-        await sub_ctx.cancel()
         await complete.wait()
-
+        assert name not in self.service_tasks, \
-        if name in self.service_tasks:
+            f'Serice task for {name} not terminated?'
-            # TODO: custom err?
-            # raise ServiceError(
-            raise RuntimeError(
-                f'Serice task for {name} not terminated?'
-            )
-
-        # assert name not in self.service_tasks, \
-        #     f'Serice task for {name} not terminated?'
-
-    async def start_service(
-        self,
-        daemon_name: str,
-        ctx_ep: Callable,  # kwargs must `partial`-ed in!
-
-        debug_mode: bool = False,
-        **tractor_actor_kwargs,
-
-    ) -> Context:
-        '''
-        Start a "service" task in a new sub-actor (daemon) and manage it's lifetime
-        indefinitely.
-
-        Services can be cancelled/shutdown using `.cancel_service()`.
-
-        '''
-        entry: tuple|None = self.service_tasks.get(daemon_name)
-        if entry:
-            (cs, sub_ctx, portal, complete) = entry
-            return sub_ctx
-
-        if daemon_name not in self.service_tasks:
-            portal = await self.actor_n.start_actor(
-                daemon_name,
-                debug_mode=(  # maybe set globally during allocate
-                    debug_mode
-                    or
-                    self.debug_mode
-                ),
-                **tractor_actor_kwargs,
-            )
-            ctx_kwargs: dict[str, Any] = {}
-            if isinstance(ctx_ep, functools.partial):
-                ctx_kwargs: dict[str, Any] = ctx_ep.keywords
-                ctx_ep: Callable = ctx_ep.func
-
-            (cs, sub_ctx, started) = await self.start_service_task(
-                daemon_name,
-                portal,
-                ctx_ep,
-                **ctx_kwargs,
-            )
-
-            return sub_ctx
-
-
-# TODO:
-# -[ ] factor all the common shit from `.data._sampling`
-#   and `.brokers._daemon` into here / `ServiceMngr`
-#   in terms of allocating the `Portal` as part of the
-#   "service-in-subactor" starting!
-# -[ ] move to `tractor.hilevel._service`, import and use here!
-# NOTE: purposely leaks the ref to the mod-scope Bo
-# import tractor
-# from tractor.hilevel import (
-#     open_service_mngr,
-#     ServiceMngr,
-# )
-# mngr: ServiceMngr|None = None
-# with tractor.hilevel.open_service_mngr() as mngr:
-#     Services = proxy(mngr)

piker/service/elastic.py

@@ -21,13 +21,11 @@ from typing import (
     TYPE_CHECKING,
 )
 
-# TODO: oof, needs to be changed to `httpx`!
 import asks
 
 if TYPE_CHECKING:
     import docker
     from ._ahab import DockerContainer
-    from . import ServiceMngr
 
 from ._util import log  # sub-sys logger
 from ._util import (
@@ -129,7 +127,7 @@ def start_elasticsearch(
 
 @acm
 async def start_ahab_daemon(
-    service_mngr: ServiceMngr,
+    service_mngr: Services,
     user_config: dict | None = None,
     loglevel: str | None = None,
 

piker/service/marketstore.py

@@ -53,7 +53,7 @@ import pendulum
 # import purerpc
 
 from ..data.feed import maybe_open_feed
-from . import ServiceMngr
+from . import Services
 from ._util import (
     log,  # sub-sys logger
     get_console_log,
@@ -233,7 +233,7 @@ def start_marketstore(
 
 @acm
 async def start_ahab_daemon(
-    service_mngr: ServiceMngr,
+    service_mngr: Services,
     user_config: dict | None = None,
     loglevel: str | None = None,
 

tests/conftest.py

@@ -10,7 +10,7 @@ from piker import (
     config,
 )
 from piker.service import (
-    get_service_mngr,
+    Services,
 )
 from piker.log import get_console_log
 
@@ -129,7 +129,7 @@ async def _open_test_pikerd(
         ) as service_manager,
     ):
         # this proc/actor is the pikerd
-        assert service_manager is get_service_mngr()
+        assert service_manager is Services
 
         async with tractor.wait_for_actor(
             'pikerd',

tests/test_ems.py

@@ -26,7 +26,7 @@ import pytest
 import tractor
 from uuid import uuid4
 
-from piker.service import ServiceMngr
+from piker.service import Services
 from piker.log import get_logger
 from piker.clearing._messages import (
     Order,
@@ -158,7 +158,7 @@ def load_and_check_pos(
 
 
 def test_ems_err_on_bad_broker(
-    open_test_pikerd: ServiceMngr,
+    open_test_pikerd: Services,
     loglevel: str,
 ):
     async def load_bad_fqme():

tests/test_services.py

@@ -15,7 +15,7 @@ import tractor
 
 from piker.service import (
     find_service,
-    ServiceMngr,
+    Services,
 )
 from piker.data import (
     open_feed,
@@ -44,7 +44,7 @@ def test_runtime_boot(
     async def main():
         port = 6666
         daemon_addr = ('127.0.0.1', port)
-        services: ServiceMngr
+        services: Services
 
         async with (
             open_test_pikerd(