pikers
/
piker
3
0
Fork 0
Code Issues 4 Pull Requests 6 Packages Projects Releases Wiki Activity

Add basic tsdb history loading 

If `marketstore` is detected try to only load most recent missing data
from the data provider (broker) and the rest from the tsdb and push it
all to shm for display in the UI. If the provider/broker doesn't have
the history client endpoint, just use the old one for now so we can
start to incrementally add support. Don't start the ohlc step
incrementer task until the backend signals that the feed is live.
mkts_backup
Tyler Goodlet 2022-03-29 14:06:28 -04:00
parent b5d566fed5
commit 97439e882c
1 changed files with 108 additions and 79 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

155
piker/data/feed.py
View File

@ -22,7 +22,6 @@ This module is enabled for ``brokerd`` daemons.
""" """
from __future__ import annotations from __future__ import annotations
from dataclasses import dataclass, field from dataclasses import dataclass, field
from datetime import datetime
from contextlib import asynccontextmanager from contextlib import asynccontextmanager
from functools import partial from functools import partial
from types import ModuleType from types import ModuleType
@ -32,6 +31,8 @@ from typing import (
Awaitable, Awaitable,
) )
import pendulum
import trio import trio
from trio.abc import ReceiveChannel from trio.abc import ReceiveChannel
from trio_typing import TaskStatus from trio_typing import TaskStatus
@ -49,7 +50,6 @@ from ._sharedmem import (
maybe_open_shm_array, maybe_open_shm_array,
attach_shm_array, attach_shm_array,
ShmArray, ShmArray,
_secs_in_day,
) )
from .ingest import get_ingestormod from .ingest import get_ingestormod
from ._source import ( from ._source import (
@ -236,51 +236,97 @@ async def manage_history(
# we expect the sub-actor to write # we expect the sub-actor to write
readonly=False, readonly=False,
) )
# TODO: history validation
if not opened:
raise RuntimeError(
"Persistent shm for sym was already open?!"
)
log.info('Scanning for existing `marketstored`') log.info('Scanning for existing `marketstored`')
is_up = await check_for_service('marketstored') is_up = await check_for_service('marketstored')
# for now only do backfilling if no tsdb can be found # for now only do backfilling if no tsdb can be found
do_backfill = not is_up and opened do_legacy_backfill = not is_up and opened
open_history_client = getattr(mod, 'open_history_client', None)
if is_up and opened and open_history_client:
if is_up and opened:
log.info('Found existing `marketstored`') log.info('Found existing `marketstored`')
from . import marketstore from . import marketstore
async with marketstore.open_storage_client( async with marketstore.open_storage_client(
fqsn, fqsn,
) as (storage, tsdb_arrays): ) as storage:
# TODO: get this shit workin tsdb_arrays = await storage.read_ohlcv(fqsn)
from tractor.trionics import ipython_embed
await ipython_embed()
# await ipython_embed(ns=locals())
# TODO: history validation if not tsdb_arrays:
# assert opened, f'Persistent shm for {symbol} was already open?!' do_legacy_backfill = True
# if not opened:
# raise RuntimeError(
# "Persistent shm for sym was already open?!"
# )
else:
if tsdb_arrays:
log.info(f'Loaded tsdb history {tsdb_arrays}') log.info(f'Loaded tsdb history {tsdb_arrays}')
fastest = list(tsdb_arrays[fqsn].values())[0]
last_s = fastest['Epoch'][-1] fastest = list(tsdb_arrays.values())[0]
times = fastest['Epoch']
first, last = times[0], times[-1]
first_tsdb_dt, last_tsdb_dt = map(
pendulum.from_timestamp, [first, last]
)
# TODO: this should be used verbatim for the pure
# shm backfiller approach below.
# start history anal and load missing new data via backend.
async with open_history_client(fqsn) as hist:
# get latest query's worth of history all the way
# back to what is recorded in the tsdb
array, start_dt, end_dt = await hist(end_dt='')
shm.push(array)
# let caller unblock and deliver latest history frame
task_status.started(shm)
some_data_ready.set()
# pull new history frames until we hit latest
# already in the tsdb
while start_dt > last_tsdb_dt:
array, start_dt, end_dt = await hist(end_dt=start_dt)
s_diff = (last_tsdb_dt - start_dt).seconds
# if we detect a partial frame's worth of data
# that is new, slice out only that history and
# write to shm.
if s_diff > 0:
assert last_tsdb_dt > start_dt
selected = array['time'] > last_tsdb_dt.timestamp()
to_push = array[selected]
log.info(
f'Pushing partial frame {to_push.size} to shm'
)
shm.push(to_push, prepend=True)
break
else:
# write to shm
log.info(f'Pushing {array.size} datums to shm')
shm.push(array, prepend=True)
# TODO: see if there's faster multi-field reads: # TODO: see if there's faster multi-field reads:
# https://numpy.org/doc/stable/user/basics.rec.html#accessing-multiple-fields # https://numpy.org/doc/stable/user/basics.rec.html#accessing-multiple-fields
# re-index with a `time` and index field # re-index with a `time` and index field
# await tractor.breakpoint()
shm.push( shm.push(
fastest[-3 * _secs_in_day:], fastest[-shm._first.value:],
# insert the history pre a "days worth" of samples # insert the history pre a "days worth" of samples
# to leave some real-time buffer space at the end. # to leave some real-time buffer space at the end.
prepend=True, prepend=True,
start=shm._len - _secs_in_day, # start=shm._len - _secs_in_day,
field_map={ field_map={
'Epoch': 'time', 'Epoch': 'time',
'Open': 'open', 'Open': 'open',
@ -291,37 +337,24 @@ async def manage_history(
}, },
) )
# start history anal and load missing new data via backend. # TODO: write new data to tsdb to be ready to for next
async with mod.open_history_client(fqsn) as hist: # read.
# get latest query's worth of history if do_legacy_backfill:
array, next_dt = await hist(end_dt='') # do a legacy incremental backfill from the provider.
last_dt = datetime.fromtimestamp(last_s)
array, next_dt = await hist(end_dt=last_dt)
else:
do_backfill = True
# await tractor.breakpoint()
some_data_ready.set()
if do_backfill:
log.info('No existing `marketstored` found..') log.info('No existing `marketstored` found..')
bfqsn = fqsn.replace('.' + mod.name, '')
# start history backfill task ``backfill_bars()`` is # start history backfill task ``backfill_bars()`` is
# a required backend func this must block until shm is # a required backend func this must block until shm is
# filled with first set of ohlc bars # filled with first set of ohlc bars
await bus.nursery.start( await bus.nursery.start(
start_backfill, start_backfill,
mod, mod,
fqsn, bfqsn,
shm, shm,
) )
# _ = await bus.nursery.start(mod.backfill_bars, fqsn, shm)
# yield back after client connect with filled shm # yield back after client connect with filled shm
task_status.started(shm) task_status.started(shm)
@ -330,27 +363,10 @@ async def manage_history(
# data that can be used. # data that can be used.
some_data_ready.set() some_data_ready.set()
# detect sample step size for sampled historical data # history retreival loop depending on user interaction and thus
times = shm.array['time'] # a small RPC-prot for remotely controllinlg what data is loaded
delay_s = times[-1] - times[times != times[-1]][-1] # for viewing.
# begin real-time updates of shm and tsb once the feed
# goes live.
await feed_is_live.wait()
if opened:
sampler.ohlcv_shms.setdefault(delay_s, []).append(shm)
# start shm incrementing for OHLC sampling at the current
# detected sampling period if one dne.
if sampler.incrementers.get(delay_s) is None:
await bus.start_task(
increment_ohlc_buffer,
delay_s,
)
await trio.sleep_forever() await trio.sleep_forever()
# cs.cancel()
async def allocate_persistent_feed( async def allocate_persistent_feed(
@ -418,7 +434,7 @@ async def allocate_persistent_feed(
manage_history, manage_history,
mod, mod,
bus, bus,
bfqsn, '.'.join((bfqsn, brokername)),
some_data_ready, some_data_ready,
feed_is_live, feed_is_live,
) )
@ -465,9 +481,22 @@ async def allocate_persistent_feed(
if not start_stream: if not start_stream:
await trio.sleep_forever() await trio.sleep_forever()
# backend will indicate when real-time quotes have begun. # begin real-time updates of shm and tsb once the feed goes live and
# the backend will indicate when real-time quotes have begun.
await feed_is_live.wait() await feed_is_live.wait()
# start shm incrementer task for OHLC style sampling
# at the current detected step period.
times = shm.array['time']
delay_s = times[-1] - times[times != times[-1]][-1]
sampler.ohlcv_shms.setdefault(delay_s, []).append(shm)
if sampler.incrementers.get(delay_s) is None:
await bus.start_task(
increment_ohlc_buffer,
delay_s,
)
sum_tick_vlm: bool = init_msg.get( sum_tick_vlm: bool = init_msg.get(
'shm_write_opts', {} 'shm_write_opts', {}
).get('sum_tick_vlm', True) ).get('sum_tick_vlm', True)