Prep service mngr for move to `tractor.hilevel`

Given it's a fairly simple yet useful abstraction, it makes sense to
offer this sub-sys alongside the core `tractor` runtime lib.

Without going into extreme detail on the impl changes (it'll come in
the commit that moves to the other repo) here is the high level summary:
------ - ------
- rename `Services` -> `ServiceMngr` and use an factory `@acm`
  to guarantee a single-instance-per-actor using a niche approach for a
  singleton object using a default keyword-arg B)
  - the mod level `open_service_mngr()` and `get_service_mngr()` are the
    new allocation/access API.
- add a `ServiceMngr.start_service()` method which does the work of both
  spawning a new subactor (for the daemon) and uses its portal to start
  the mngr side supervision task.
- open actor/task nurseries inside the `@acm` allocator.

Adjust other dependent subsystems to match:
------ - ------
- use `open_service_mngr()` when first allocated in `open_pikerd()`.
- use `get_service_mngr()` instead of importing the class ref inside
  `.service.maybe_spawn_daemon()`, `.brokers._daemon.spawn_brokerd()`
  and `.data._sampling.spawn_samplerd()` using a `partial` to pack in
  the endpoint ctx kwargs (unpacked inside `.start_service()` XD).

piker/brokers/_daemon.py

@@ -23,6 +23,7 @@ from __future__ import annotations
 from contextlib import (
     asynccontextmanager as acm,
 )
+from functools import partial
 from types import ModuleType
 from typing import (
     TYPE_CHECKING,
@@ -190,14 +191,17 @@ 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')
 
@@ -217,27 +221,35 @@ async def spawn_brokerd(
 
     # ask `pikerd` to spawn a new sub-actor and manage it under its
     # actor nursery
-    from piker.service import Services
+    from piker.service import (
-
+        get_service_mngr,
+        ServiceMngr,
+    )
     dname: str = tractor_kwargs.pop('name')  # f'brokerd.{brokername}'
-    portal = await Services.actor_n.start_actor(
+    mngr: ServiceMngr = get_service_mngr()
-        dname,
+    ctx: tractor.Context = await mngr.start_service(
-        enable_modules=_data_mods + tractor_kwargs.pop('enable_modules'),
+        daemon_name=dname,
-        debug_mode=Services.debug_mode,
+        ctx_ep=partial(
+            # signature of target root-task endpoint
+            daemon_fixture_ep,
+
+            # passed to daemon_fixture_ep(**kwargs)
+            brokername=brokername,
+            loglevel=loglevel,
+        ),
+        debug_mode=mngr.debug_mode,
+        loglevel=loglevel,
+        enable_modules=(
+            _data_mods
+            +
+            tractor_kwargs.pop('enable_modules')
+        ),
         **tractor_kwargs
     )
-
+    assert (
-    # NOTE: the service mngr expects an already spawned actor + its
+        not ctx.cancel_called
-    # portal ref in order to do non-blocking setup of brokerd
+        and ctx.portal  # parent side
-    # service nursery.
+        and dname in ctx.chan.uid  # subactor is named as desired
-    await Services.start_service_task(
-        dname,
-        portal,
-
-        # signature of target root-task endpoint
-        daemon_fixture_ep,
-        brokername=brokername,
-        loglevel=loglevel,
     )
     return True
 
@@ -262,8 +274,7 @@ 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/brokers/ib/_util.py

@@ -100,7 +100,7 @@ async def data_reset_hack(
         log.warning(
             no_setup_msg
             +
-            f'REQUIRES A `vnc_addrs: array` ENTRY'
+            'REQUIRES A `vnc_addrs: array` ENTRY'
         )
 
     vnc_host, vnc_port = vnc_sockaddr.get(
@@ -259,7 +259,7 @@ def i3ipc_xdotool_manual_click_hack() -> None:
                         timeout=timeout,
                     )
 
-    # re-activate and focus original window
+        # re-activate and focus original window
         subprocess.call([
             'xdotool',
             'windowactivate', '--sync', str(orig_win_id),

piker/brokers/ib/api.py

@@ -287,9 +287,31 @@ class Client:
         self.conf = config
 
         # NOTE: the ib.client here is "throttled" to 45 rps by default
-        self.ib = ib
+        self.ib: IB = ib
         self.ib.RaiseRequestErrors: bool = True
 
+        # self._acnt_names: set[str] = {}
+        self._acnt_names: list[str] = []
+
+    @property
+    def acnts(self) -> list[str]:
+        # return list(self._acnt_names)
+        return self._acnt_names
+
+    def __repr__(self) -> str:
+        return (
+            f'<{type(self).__name__}('
+            f'ib={self.ib} '
+            f'acnts={self.acnts}'
+
+            # TODO: we need to mask out acnt-#s and other private
+            # infos if we're going to console this!
+            # f' |_.conf:\n'
+            # f'    {pformat(self.conf)}\n'
+
+            ')>'
+        )
+
     async def get_fills(self) -> list[Fill]:
         '''
         Return list of rents `Fills` from trading session.
@@ -376,55 +398,63 @@ class Client:
             # whatToShow='MIDPOINT',
             # whatToShow='TRADES',
         )
-        log.info(
-            f'REQUESTING {ib_duration_str} worth {bar_size} BARS\n'
-            f'fqme: {fqme}\n'
-            f'global _enters: {_enters}\n'
-            f'kwargs: {pformat(kwargs)}\n'
-        )
-
         bars = await self.ib.reqHistoricalDataAsync(
             **kwargs,
         )
 
+        query_info: str = (
+            f'REQUESTING IB history BARS\n'
+            f'    ------ - ------\n'
+            f'dt_duration: {dt_duration}\n'
+            f'ib_duration_str: {ib_duration_str}\n'
+            f'bar_size: {bar_size}\n'
+            f'fqme: {fqme}\n'
+            f'actor-global _enters: {_enters}\n'
+            f'kwargs: {pformat(kwargs)}\n'
+        )
         # tail case if no history for range or none prior.
+        # NOTE: there's actually 3 cases here to handle (and
+        # this should be read alongside the implementation of
+        # `.reqHistoricalDataAsync()`):
+        # - a timeout occurred in which case insync internals return
+        #   an empty list thing with bars.clear()...
+        # - no data exists for the period likely due to
+        #   a weekend, holiday or other non-trading period prior to
+        #   ``end_dt`` which exceeds the ``duration``,
+        # - LITERALLY this is the start of the mkt's history!
         if not bars:
-            # NOTE: there's actually 3 cases here to handle (and
+            # TODO: figure out wut's going on here.
-            # this should be read alongside the implementation of
-            # `.reqHistoricalDataAsync()`):
-            # - a timeout occurred in which case insync internals return
-            #   an empty list thing with bars.clear()...
-            # - no data exists for the period likely due to
-            #   a weekend, holiday or other non-trading period prior to
-            #   ``end_dt`` which exceeds the ``duration``,
-            # - LITERALLY this is the start of the mkt's history!
 
+            # TODO: is this handy, a sync requester for tinkering
+            # with empty frame cases?
+            # def get_hist():
+            #     return self.ib.reqHistoricalData(**kwargs)
+            # import pdbp
+            # pdbp.set_trace()
 
-            # sync requester for debugging empty frame cases
+            log.critical(
-            def get_hist():
+                'STUPID IB SAYS NO HISTORY\n\n'
-                return self.ib.reqHistoricalData(**kwargs)
+                + query_info
+            )
 
-            assert get_hist
-            import pdbp
-            pdbp.set_trace()
-
-            return [], np.empty(0), dt_duration
             # TODO: we could maybe raise ``NoData`` instead if we
-            # rewrite the method in the first case? right now there's no
+            # rewrite the method in the first case?
-            # way to detect a timeout.
+            # right now there's no way to detect a timeout..
+            return [], np.empty(0), dt_duration
 
-        # NOTE XXX: ensure minimum duration in bars B)
+        log.info(query_info)
-        # => we recursively call this method until we get at least
+        # NOTE XXX: ensure minimum duration in bars?
-        # as many bars such that they sum in aggregate to the the
+        # => recursively call this method until we get at least as
-        # desired total time (duration) at most.
+        #   many bars such that they sum in aggregate to the the
-        # XXX XXX XXX
+        #   desired total time (duration) at most.
-        # WHY DID WE EVEN NEED THIS ORIGINALLY!?
+        #  - if you query over a gap and get no data
-        # XXX XXX XXX
+        #    that may short circuit the history
-        # - if you query over a gap and get no data
-        #   that may short circuit the history 
         if (
-            end_dt
+            # XXX XXX XXX
-            and False
+            # => WHY DID WE EVEN NEED THIS ORIGINALLY!? <=
+            # XXX XXX XXX
+            False
+            and end_dt
         ):
             nparr: np.ndarray = bars_to_np(bars)
             times: np.ndarray = nparr['time']
@@ -927,7 +957,10 @@ class Client:
                         warnset = True
 
             else:
-                log.info(f'Got first quote for {contract}')
+                log.info(
+                    'Got first quote for contract\n'
+                    f'{contract}\n'
+                )
                 break
         else:
             if timeouterr and raise_on_timeout:
@@ -991,8 +1024,12 @@ class Client:
                     outsideRth=True,
 
                     optOutSmartRouting=True,
+                    # TODO: need to understand this setting better as
+                    # it pertains to shit ass mms..
                     routeMarketableToBbo=True,
+
                     designatedLocation='SMART',
+
                     # TODO: make all orders GTC?
                     # https://interactivebrokers.github.io/tws-api/classIBApi_1_1Order.html#a95539081751afb9980f4c6bd1655a6ba
                     # goodTillDate=f"yyyyMMdd-HH:mm:ss",
@@ -1120,8 +1157,8 @@ def get_config() -> dict[str, Any]:
     names = list(accounts.keys())
     accts = section['accounts'] = bidict(accounts)
     log.info(
-        f'brokers.toml defines {len(accts)} accounts: '
+        f'{path} defines {len(accts)} account aliases:\n'
-        f'{pformat(names)}'
+        f'{pformat(names)}\n'
     )
 
     if section is None:
@@ -1188,7 +1225,7 @@ async def load_aio_clients(
         try_ports = list(try_ports.values())
 
     _err = None
-    accounts_def = config.load_accounts(['ib'])
+    accounts_def: dict[str, str] = config.load_accounts(['ib'])
     ports = try_ports if port is None else [port]
     combos = list(itertools.product(hosts, ports))
     accounts_found: dict[str, Client] = {}
@@ -1227,7 +1264,9 @@ async def load_aio_clients(
                 client = Client(ib=ib, config=conf)
 
                 # update all actor-global caches
-                log.info(f"Caching client for {sockaddr}")
+                log.runtime(
+                    f'Connected and caching `Client` @ {sockaddr!r}'
+                )
                 _client_cache[sockaddr] = client
                 break
 
@@ -1242,37 +1281,59 @@ async def load_aio_clients(
                 OSError,
             ) as ce:
                 _err = ce
-                log.warning(
+                message: str = (
-                    f'Failed to connect on {host}:{port} for {i} time with,\n'
+                    f'Failed to connect on {host}:{port} after {i} tries with\n'
-                    f'{ib.client.apiError.value()}\n'
+                    f'{ib.client.apiError.value()!r}\n\n'
-                    'retrying with a new client id..')
+                    'Retrying with a new client id..\n'
+                )
+                log.runtime(message)
+        else:
+            # XXX report loudly if we never established after all
+            # re-tries
+            log.warning(message)
 
         # Pre-collect all accounts available for this
         # connection and map account names to this client
         # instance.
         for value in ib.accountValues():
-            acct_number = value.account
+            acct_number: str = value.account
 
-            entry = accounts_def.inverse.get(acct_number)
+            acnt_alias: str = accounts_def.inverse.get(acct_number)
-            if not entry:
+            if not acnt_alias:
+
+                # TODO: should we constuct the below reco-ex from
+                # the existing config content?
+                _, path = config.load(
+                    conf_name='brokers',
+                )
                 raise ValueError(
-                    'No section in brokers.toml for account:'
+                    'No alias in account section for account!\n'
-                    f' {acct_number}\n'
+                    f'Please add an acnt alias entry to your {path}\n'
-                    f'Please add entry to continue using this API client'
+                    'For example,\n\n'
+
+                    '[ib.accounts]\n'
+                    'margin = {accnt_number!r}\n'
+                    '^^^^^^ <- you need this part!\n\n'
+
+                    'This ensures `piker` will not leak private acnt info '
+                    'to console output by default!\n'
                 )
 
             # surjection of account names to operating clients.
-            if acct_number not in accounts_found:
+            if acnt_alias not in accounts_found:
-                accounts_found[entry] = client
+                accounts_found[acnt_alias] = client
+                # client._acnt_names.add(acnt_alias)
+                client._acnt_names.append(acnt_alias)
 
-        log.info(
+        if accounts_found:
-            f'Loaded accounts for client @ {host}:{port}\n'
+            log.info(
-            f'{pformat(accounts_found)}'
+                f'Loaded accounts for api client\n\n'
-        )
+                f'{pformat(accounts_found)}\n'
+            )
 
-        # XXX: why aren't we just updating this directy above
+            # XXX: why aren't we just updating this directy above
-        # instead of using the intermediary `accounts_found`?
+            # instead of using the intermediary `accounts_found`?
-        _accounts2clients.update(accounts_found)
+            _accounts2clients.update(accounts_found)
 
     # if we have no clients after the scan loop then error out.
     if not _client_cache:
@@ -1472,7 +1533,7 @@ async def open_aio_client_method_relay(
         msg: tuple[str, dict] | dict | None = await from_trio.get()
         match msg:
             case None:  # termination sentinel
-                print('asyncio PROXY-RELAY SHUTDOWN')
+                log.info('asyncio `Client` method-proxy SHUTDOWN!')
                 break
 
             case (meth_name, kwargs):

piker/brokers/ib/broker.py

@@ -1183,7 +1183,14 @@ async def deliver_trade_events(
                         pos
                         and fill
                     ):
-                        assert fill.commissionReport == cr
+                        now_cr: CommissionReport = fill.commissionReport
+                        if (now_cr != cr):
+                            log.warning(
+                                'UhhHh ib updated the commission report mid-fill..?\n'
+                                f'was: {pformat(cr)}\n'
+                                f'now: {pformat(now_cr)}\n'
+                            )
+
                         await emit_pp_update(
                             ems_stream,
                             accounts_def,

piker/brokers/ib/feed.py

@@ -671,8 +671,8 @@ async def _setup_quote_stream(
         # making them mostly useless and explains why the scanner
         # is always slow XD
         # '293',  # Trade count for day
-        '294',  # Trade rate / minute
+        # '294',  # Trade rate / minute
-        '295',  # Vlm rate / minute
+        # '295',  # Vlm rate / minute
     ),
     contract: Contract | None = None,
 
@@ -915,9 +915,13 @@ async def stream_quotes(
 
         if first_ticker:
             first_quote: dict = normalize(first_ticker)
-            log.info(
+
-                'Rxed init quote:\n'
+            # TODO: we need a stack-oriented log levels filters for
-                f'{pformat(first_quote)}'
+            # this!
+            # log.info(message, filter={'stack': 'live_feed'}) ?
+            log.runtime(
+                'Rxed init quote:\n\n'
+                f'{pformat(first_quote)}\n'
             )
 
         # NOTE: it might be outside regular trading hours for
@@ -969,7 +973,11 @@ async def stream_quotes(
             raise_on_timeout=True,
         )
         first_quote: dict = normalize(first_ticker)
-        log.info(
+
+        # TODO: we need a stack-oriented log levels filters for
+        # this!
+        # log.info(message, filter={'stack': 'live_feed'}) ?
+        log.runtime(
             'Rxed init quote:\n'
             f'{pformat(first_quote)}'
         )

piker/brokers/ib/ledger.py

@@ -31,7 +31,11 @@ from typing import (
 )
 
 from bidict import bidict
-import pendulum
+from pendulum import (
+    DateTime,
+    parse,
+    from_timestamp,
+)
 from ib_insync import (
     Contract,
     Commodity,
@@ -66,10 +70,11 @@ tx_sort: Callable = partial(
     iter_by_dt,
     parsers={
         'dateTime': parse_flex_dt,
-        'datetime': pendulum.parse,
+        'datetime': parse,
-        # for some some fucking 2022 and
+
-        # back options records...fuck me.
+        # XXX: for some some fucking 2022 and
-        'date': pendulum.parse,
+        # back options records.. f@#$ me..
+        'date': parse,
     }
 )
 
@@ -89,15 +94,38 @@ def norm_trade(
 
     conid: int = str(record.get('conId') or record['conid'])
     bs_mktid: str = str(conid)
-    comms = record.get('commission')
-    if comms is None:
-        comms = -1*record['ibCommission']
 
-    price = record.get('price') or record['tradePrice']
+    # NOTE: sometimes weird records (like BTTX?)
+    # have no field for this?
+    comms: float = -1 * (
+        record.get('commission')
+        or record.get('ibCommission')
+        or 0
+    )
+    if not comms:
+        log.warning(
+            'No commissions found for record?\n'
+            f'{pformat(record)}\n'
+        )
+
+    price: float = (
+        record.get('price')
+        or record.get('tradePrice')
+    )
+    if price is None:
+        log.warning(
+            'No `price` field found in record?\n'
+            'Skipping normalization..\n'
+            f'{pformat(record)}\n'
+        )
+        return None
 
     # the api doesn't do the -/+ on the quantity for you but flex
     # records do.. are you fucking serious ib...!?
-    size = record.get('quantity') or record['shares'] * {
+    size: float|int = (
+        record.get('quantity')
+        or record['shares']
+    ) * {
         'BOT': 1,
         'SLD': -1,
     }[record['side']]
@@ -128,26 +156,31 @@ def norm_trade(
         # otype = tail[6]
         # strike = tail[7:]
 
-        print(f'skipping opts contract {symbol}')
+        log.warning(
+            f'Skipping option contract -> NO SUPPORT YET!\n'
+            f'{symbol}\n'
+        )
         return None
 
     # timestamping is way different in API records
-    dtstr = record.get('datetime')
+    dtstr: str = record.get('datetime')
-    date = record.get('date')
+    date: str = record.get('date')
-    flex_dtstr = record.get('dateTime')
+    flex_dtstr: str = record.get('dateTime')
 
     if dtstr or date:
-        dt = pendulum.parse(dtstr or date)
+        dt: DateTime = parse(dtstr or date)
 
     elif flex_dtstr:
         # probably a flex record with a wonky non-std timestamp..
-        dt = parse_flex_dt(record['dateTime'])
+        dt: DateTime = parse_flex_dt(record['dateTime'])
 
     # special handling of symbol extraction from
     # flex records using some ad-hoc schema parsing.
-    asset_type: str = record.get(
+    asset_type: str = (
-        'assetCategory'
+        record.get('assetCategory')
-    ) or record.get('secType', 'STK')
+        or record.get('secType')
+        or 'STK'
+    )
 
     if (expiry := (
             record.get('lastTradeDateOrContractMonth')
@@ -357,6 +390,7 @@ def norm_trade_records(
         if txn is None:
             continue
 
+        # inject txns sorted by datetime
         insort(
             records,
             txn,
@@ -405,7 +439,7 @@ def api_trades_to_ledger_entries(
                     txn_dict[attr_name] = val
 
         tid = str(txn_dict['execId'])
-        dt = pendulum.from_timestamp(txn_dict['time'])
+        dt = from_timestamp(txn_dict['time'])
         txn_dict['datetime'] = str(dt)
         acctid = accounts[txn_dict['acctNumber']]
 

piker/brokers/ib/symbols.py

@@ -209,7 +209,10 @@ async def open_symbol_search(ctx: tractor.Context) -> None:
                 break
 
             ib_client = proxy._aio_ns.ib
-            log.info(f'Using {ib_client} for symbol search')
+            log.info(
+                f'Using API client for symbol-search\n'
+                f'{ib_client}\n'
+            )
 
             last = time.time()
             async for pattern in stream:
@@ -294,7 +297,7 @@ async def open_symbol_search(ctx: tractor.Context) -> None:
                     elif stock_results:
                         break
                     # else:
-                    await tractor.pause()
+                    # await tractor.pause()
 
                     # # match against our ad-hoc set immediately
                     # adhoc_matches = fuzzy.extract(
@@ -522,7 +525,21 @@ async def get_mkt_info(
         venue = con.primaryExchange or con.exchange
 
     price_tick: Decimal = Decimal(str(details.minTick))
-    # price_tick: Decimal = Decimal('0.01')
+    ib_min_tick_gt_2: Decimal = Decimal('0.01')
+    if (
+        price_tick < ib_min_tick_gt_2
+    ):
+        # TODO: we need to add some kinda dynamic rounding sys
+        # to our MktPair i guess?
+        # not sure where the logic should sit, but likely inside
+        # the `.clearing._ems` i suppose...
+        log.warning(
+            'IB seems to disallow a min price tick < 0.01 '
+            'when the price is > 2.0..?\n'
+            f'Decreasing min tick precision for {fqme} to 0.01'
+        )
+        # price_tick = ib_min_tick
+        # await tractor.pause()
 
     if atype == 'stock':
         # XXX: GRRRR they don't support fractional share sizes for

piker/data/_sampling.py

@@ -25,6 +25,7 @@ from collections import (
     defaultdict,
 )
 from contextlib import asynccontextmanager as acm
+from functools import partial
 import time
 from typing import (
     Any,
@@ -42,7 +43,7 @@ from tractor.trionics import (
     maybe_open_nursery,
 )
 import trio
-from trio_typing import TaskStatus
+from trio import TaskStatus
 
 from .ticktools import (
     frame_ticks,
@@ -70,6 +71,7 @@ if TYPE_CHECKING:
 _default_delay_s: float = 1.0
 
 
+# TODO: use new `tractor.singleton_acm` API for this!
 class Sampler:
     '''
     Global sampling engine registry.
@@ -79,9 +81,9 @@ 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 (real-time) quote feeds, see
+    time-step-sample a (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
@@ -375,7 +377,10 @@ async def register_with_sampler(
                 assert Sampler.ohlcv_shms
 
             # unblock caller
-            await ctx.started(set(Sampler.ohlcv_shms.keys()))
+            await ctx.started(
+                # XXX bc msgpack only allows one array type!
+                list(Sampler.ohlcv_shms.keys())
+            )
 
             if open_index_stream:
                 try:
@@ -419,7 +424,6 @@ async def register_with_sampler(
 
 
 async def spawn_samplerd(
-
     loglevel: str | None = None,
     **extra_tractor_kwargs
 
@@ -429,7 +433,10 @@ async def spawn_samplerd(
     update and increment count write and stream broadcasting.
 
     '''
-    from piker.service import Services
+    from piker.service import (
+        get_service_mngr,
+        ServiceMngr,
+    )
 
     dname = 'samplerd'
     log.info(f'Spawning `{dname}`')
@@ -437,26 +444,33 @@ 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?
-    async with Services.locks[dname + '_singleton']:
+    mngr: ServiceMngr = get_service_mngr()
+    already_started: bool = dname in mngr.service_tasks
 
-        if dname not in Services.service_tasks:
+    async with mngr._locks[dname + '_singleton']:
-
+        ctx: Context = await mngr.start_service(
-            portal = await Services.actor_n.start_actor(
+            daemon_name=dname,
-                dname,
+            ctx_ep=partial(
-                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
 
@@ -889,6 +903,7 @@ 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

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

@@ -21,7 +21,6 @@
 from __future__ import annotations
 import os
 from typing import (
-    Optional,
     Any,
     ClassVar,
 )
@@ -30,13 +29,13 @@ from contextlib import (
 )
 
 import tractor
-import trio
 
 from ._util import (
     get_console_log,
 )
 from ._mngr import (
-    Services,
+    open_service_mngr,
+    ServiceMngr,
 )
 from ._registry import (  # noqa
     _tractor_kwargs,
@@ -59,7 +58,7 @@ async def open_piker_runtime(
     registry_addrs: list[tuple[str, int]] = [],
 
     enable_modules: list[str] = [],
-    loglevel: Optional[str] = None,
+    loglevel: str|None = None,
 
     # XXX NOTE XXX: you should pretty much never want debug mode
     # for data daemons when running in production.
@@ -69,7 +68,7 @@ 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[
@@ -119,6 +118,10 @@ 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,
 
@@ -167,12 +170,13 @@ async def open_pikerd(
 
     **kwargs,
 
-) -> Services:
+) -> ServiceMngr:
     '''
-    Start a root piker daemon with an indefinite lifetime.
+    Start a root piker daemon actor (aka `pikerd`) with an indefinite
+    lifetime.
 
-    A root actor nursery is created which can be used to create and keep
+    A root actor-nursery is created which can be used to spawn and
-    alive underling services (see below).
+    supervise underling service sub-actors (see below).
 
     '''
     # NOTE: for the root daemon we always enable the root
@@ -199,8 +203,6 @@ 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:
@@ -209,25 +211,17 @@ async def open_pikerd(
                     'Maybe you have another daemon already running?'
                 )
 
-        # assign globally for future daemon/task creation
+        mngr: ServiceMngr
-        Services.actor_n = actor_nursery
+        async with open_service_mngr(
-        Services.service_n = service_nursery
+            debug_mode=debug_mode,
-        Services.debug_mode = debug_mode
+        ) as mngr:
-
+            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: Optional[str] = None,
+#     loglevel: str|None = None,
 #     **kwargs,
 
 # ) -> None:
@@ -256,7 +250,7 @@ async def maybe_open_pikerd(
     loglevel: str | None = None,
     **kwargs,
 
-) -> tractor._portal.Portal | ClassVar[Services]:
+) -> tractor._portal.Portal | ClassVar[ServiceMngr]:
     '''
     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 Services
+from ._mngr import ServiceMngr
 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: Services,
+    services: ServiceMngr,
     service_name: str,
 
     # endpoint config passed as **kwargs
@@ -549,7 +549,8 @@ 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

@@ -26,14 +26,17 @@ 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 (
-    Services,
+    get_service_mngr,
+    ServiceMngr,
 )
 from ._actor_runtime import maybe_open_pikerd
 from ._registry import find_service
@@ -41,15 +44,14 @@ 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:
@@ -67,7 +69,7 @@ async def maybe_spawn_daemon(
     '''
     # serialize access to this section to avoid
     # 2 or more tasks racing to create a daemon
-    lock = Services.locks[service_name]
+    lock = _locks[service_name]
     await lock.acquire()
 
     async with find_service(
@@ -147,21 +149,22 @@ async def spawn_emsd(
     """
     log.info('Spawning emsd')
 
-    portal = await Services.actor_n.start_actor(
+    smngr: ServiceMngr = get_service_mngr()
+    portal = await smngr.actor_n.start_actor(
         'emsd',
         enable_modules=[
             'piker.clearing._ems',
             'piker.clearing._client',
         ],
         loglevel=loglevel,
-        debug_mode=Services.debug_mode,  # set by pikerd flag
+        debug_mode=smngr.debug_mode,  # set by pikerd flag
         **extra_tractor_kwargs
     )
 
     # non-blocking setup of clearing service
     from ..clearing._ems import _setup_persistent_emsd
 
-    await Services.start_service_task(
+    await smngr.start_service_task(
         'emsd',
         portal,
 

piker/service/_mngr.py

@@ -18,16 +18,29 @@
 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 trio
+import msgspec
-from trio_typing import TaskStatus
 import tractor
+import trio
+from trio import TaskStatus
 from tractor import (
+    ActorNursery,
     current_actor,
     ContextCancelled,
     Context,
@@ -39,6 +52,130 @@ 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.
@@ -46,31 +183,46 @@ from ._util import (
 #   to the pikerd actor for starting services remotely!
 # - prolly rename this to ActorServicesNursery since it spawns
 #   new actors and supervises them to completion?
-class Services:
+@dataclass
+class ServiceMngr:
+# class ServiceMngr(msgspec.Struct):
+    '''
+    A multi-subactor-as-service manager.
 
-    actor_n: tractor._supervise.ActorNursery
+    Spawn, supervise and monitor service/daemon subactors in a SC
+    process tree.
+
+    '''
+    actor_n: ActorNursery
     service_n: trio.Nursery
-    debug_mode: bool  # tractor sub-actor debug mode flag
+    debug_mode: bool = False # 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):
+    ) -> (trio.CancelScope, Context, Any):
         '''
         Open a context in a service sub-actor, add to a stack
         that gets unwound at ``pikerd`` teardown.
@@ -83,6 +235,7 @@ class Services:
             task_status: TaskStatus[
                 tuple[
                     trio.CancelScope,
+                    Context,
                     trio.Event,
                     Any,
                 ]
@@ -90,64 +243,87 @@ class Services:
 
         ) -> 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,
 
-                async with portal.open_context(
+                    ) as (ctx, started):
-                    target,
-                    allow_overruns=allow_overruns,
-                    **ctx_kwargs,
 
-                ) as (ctx, first):
+                        # unblock once the remote context has started
-
+                        complete = trio.Event()
-                    # unblock once the remote context has started
+                        task_status.started((
-                    complete = trio.Event()
+                            cs,
-                    task_status.started((cs, complete, first))
+                            ctx,
-                    log.info(
+                            complete,
-                        f'`pikerd` service {name} started with value {first}'
+                            started,
-                    )
+                        ))
-                    try:
+                        log.info(
+                            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.result()
+                        ctx_res: Any = await ctx.wait_for_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 (await portal.result(), ctx_res)
+                        return (
-                    except ContextCancelled as ctxe:
+                            await portal.wait_for_result(),
-                        canceller: tuple[str, str] = ctxe.canceller
+                            ctx_res,
-                        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'
 
-                    finally:
+                            f'cancellee: {portal.chan.uid}\n'
-                        await portal.cancel_actor()
+                            f'canceller: {canceller}\n'
-                        complete.set()
+                        )
-                        self.service_tasks.pop(name)
+                    else:
+                        raise
 
-        cs, complete, first = await self.service_n.start(open_context_in_task)
+                finally:
+                    # 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, portal, complete)
+        self.service_tasks[name] = (cs, sub_ctx, portal, complete)
+        return cs, sub_ctx, started
 
-        return cs, first
-
-    @classmethod
     async def cancel_service(
         self,
         name: str,
@@ -158,8 +334,80 @@ class Services:
 
         '''
         log.info(f'Cancelling `pikerd` service {name}')
-        cs, portal, complete = self.service_tasks[name]
+        cs, sub_ctx, portal, complete = self.service_tasks[name]
-        cs.cancel()
+
+        # cs.cancel()
+        await sub_ctx.cancel()
         await complete.wait()
-        assert name not in self.service_tasks, \
+
-            f'Serice task for {name} not terminated?'
+        if name in self.service_tasks:
+            # 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

@@ -21,11 +21,13 @@ 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 (
@@ -127,7 +129,7 @@ def start_elasticsearch(
 
 @acm
 async def start_ahab_daemon(
-    service_mngr: Services,
+    service_mngr: ServiceMngr,
     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 Services
+from . import ServiceMngr
 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: Services,
+    service_mngr: ServiceMngr,
     user_config: dict | None = None,
     loglevel: str | None = None,
 

tests/conftest.py

@@ -10,7 +10,7 @@ from piker import (
     config,
 )
 from piker.service import (
-    Services,
+    get_service_mngr,
 )
 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 Services
+        assert service_manager is get_service_mngr()
 
         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 Services
+from piker.service import ServiceMngr
 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: Services,
+    open_test_pikerd: ServiceMngr,
     loglevel: str,
 ):
     async def load_bad_fqme():

tests/test_services.py

@@ -15,7 +15,7 @@ import tractor
 
 from piker.service import (
     find_service,
-    Services,
+    ServiceMngr,
 )
 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: Services
+        services: ServiceMngr
 
         async with (
             open_test_pikerd(