Fluksio/app
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Schedule a node across every machine, not just this one

Browse Source 
The engine answered "where does this node run" twice, in two ways that could
not see each other: a device sent it to a worker carrying that label, and
resources were counted against the engine's own cores. Declaring both meant the
second answer won and nothing was counted at all — which the data-science
getting-started page and the worked example both do.

One question now, in flow/placement.py: of every machine attached, which could
grant what this node asked for, and which of those has it free. The books move
onto each machine — one accountant per worker, built from the inventory it
reported — and the waiting moves above them, where one condition variable can
be woken by a release anywhere or by a worker attaching. Locks go one way:
placer, then a machine's books, never back.

So a node asking for a card now finds the box that has one, rather than being
clamped down to none and run here. When nothing can grant the ask at all it is
still cut down and run — a flow written on a cluster has to work on a laptop —
but the ceiling is one real machine now, since taking the largest of each
dimension separately can describe a machine nobody has.

Two things fixed on the way. A device on a connector node held every batch run
of its flow forever, waiting for a worker that could never run an entry point.
And `prefer` falling back to the engine skipped the books, so the fallback held
nothing.

The bench flow's node has taken a `params` argument that with_settings has not
forwarded for some time, so the benchmark could not run at all: 62 ms median
submit-to-result with this, against the 61 ms on record.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A6HeySA27EkGANZN95QySW
This commit is contained in:
stroblme
2026-08-27 08:49:36 +02:00
co-authored by Claude Opus 5
parent 1a9753fa9d
commit 6ff56533f5
14 changed files with 1214 additions and 326 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/fluksio/alembic/versions/b3f1a7c50d92_run_needs.py
+31
View File
@@ -0,0 +1,31 @@
"""run.needs
A run recorded the worker *labels* its nodes asked for, which answered whether
anything was attached to run them but nothing about whether that machine was
big enough. The size goes beside the labels, so a queued run can tell waiting
for a machine from having nowhere to run at all.
Revision ID: b3f1a7c50d92
Revises: e5b8c2f4a913
Create Date: 2026-08-27
"""
import sqlalchemy as sa
from alembic import op
# revision identifiers, used by Alembic.
revision = "b3f1a7c50d92"
down_revision = "e5b8c2f4a913"
branch_labels = None
depends_on = None
def upgrade():
# Nullable: a run submitted before this declared nothing, and null is that
# rather than a run that needs nothing in particular.
op.add_column("run", sa.Column("needs", sa.JSON(), nullable=True))
def downgrade():
op.drop_column("run", "needs")
backend/fluksio/api/routes/workers.py
+41 -5
View File
@@ -90,18 +90,54 @@ def read_workers(request: Request) -> Any:
]
@router.get("/resources", dependencies=[Depends(get_current_user)])
class ResourceLevel(BaseModel):
total: int
free: int
class WaitingNode(BaseModel):
node: str
reason: str
seconds: float
class TargetResources(BaseModel):
"""One machine: this engine, or a worker attached to it."""
target: str
cpus: ResourceLevel
gpus: ResourceLevel
#: Absent where the machine did not say how much memory it has.
ram_mb: ResourceLevel | None = None
labels: list[str] = Field(default_factory=list)
in_flight: int = 0
class ResourcesSnapshot(BaseModel):
#: This engine's own figures, kept where they have always been.
cpus: ResourceLevel
gpus: ResourceLevel
waiting: list[WaitingNode] = Field(default_factory=list)
targets: list[TargetResources] = Field(default_factory=list)
provisioners: list[dict[str, Any]] = Field(default_factory=list)
@router.get(
"/resources",
response_model=ResourcesSnapshot,
dependencies=[Depends(get_current_user)],
)
def read_resources(request: Request) -> Any:
"""What this machine has free, and which nodes are queued for it.
"""Every machine, what is free of it, and which nodes are queued.
A node waiting its turn looks exactly like a node that has hung — the run
sits at `running` and says nothing — so what is waiting, and for what, has
to be readable somewhere.
"""
accountant = getattr(request.app.state, "resources", None)
if accountant is None:
placer = getattr(request.app.state, "placer", None)
if placer is None:
raise HTTPException(status_code=503, detail="Resources are not accounted here")
return accountant.snapshot()
return placer.snapshot()
@router.post(
backend/fluksio/flow/controller.py
+80 -37
View File
@@ -62,6 +62,7 @@ from fluksio.flow.pipeline import (
ValidationIssue,
ValueSource,
)
from fluksio.flow.placement import Placer
from fluksio.flow.remote import RemoteWorkerHub
from fluksio.flow.resources import ResourceAccountant, derive_env
from fluksio.flow.schemas import (
@@ -413,6 +414,7 @@ class FlowController:
workers: PythonWorkerPool | None = None,
remote: RemoteWorkerHub | None = None,
resources: ResourceAccountant | None = None,
placer: Placer | None = None,
) -> None:
self.store = store
# Without a pool, python nodes are compiled and run in this process —
@@ -420,9 +422,11 @@ class FlowController:
self.workers = workers
# Workers on other hosts. A node without a device never touches it.
self.remote = remote
# What the machine has, for the nodes that say what they need. Without
# one, a declaration is recorded and nothing is held against it.
# This machine's own books. The pool sizes its fair share off them.
self.resources = resources
# Every machine there is, for the nodes that say what they need.
# Without one, a declaration is recorded and nothing is held against it.
self.placer = placer
self.state = state if state is not None else MemoryState()
self.events = events
self.max_workers = max_workers
@@ -865,9 +869,18 @@ class FlowController:
# Building
# -------------------------------------------------------------------------
def _allocated(
def _runs_elsewhere(self, node_def: NodeDef) -> bool:
"""Whether this node asks for more than this machine could ever give."""
if node_def.resources is None or self.placer is None:
return False
wanted = node_def.resources
return not self.placer.local.fits(wanted.cpus, wanted.gpus, wanted.ram or 0)
def _placed(
self,
wanted: Resources,
device: str | None,
policy: str,
owner: str,
local: str,
code: str,
@@ -877,32 +890,40 @@ class FlowController:
run_id: str,
on_event: Callable[[dict[str, Any]], None],
) -> Callable[..., Any]:
"""A call that holds its share of the machine while it runs.
"""A call that picks a machine and holds its share while it runs.
Which machine is decided per call rather than when the flow was built,
so a worker that attaches later is used without anything being rebuilt.
The order is load-bearing: the resources are claimed first, and only
then is a worker slot taken. The other way round, a node holding a slot
could sit waiting for cores that a node holding the cores cannot get a
slot to release.
The worker comes from the pool whose environment this allocation
derives, so what the node is told about its share is what the library
inside it reads at import — the only moment those variables are read.
What the allocation implies is handed to the process the node runs in,
here or on the worker, because a library reads those variables when it
is imported and never again.
"""
if self.workers is None or self.resources is None:
return self.workers.proxy( # type: ignore[union-attr]
owner,
local,
code,
node_id=node_id,
timeout=timeout,
run_id=run_id,
on_event=on_event,
)
accountant, pool = self.resources, self.workers
placer, pool = self.placer, self.workers
def call(**kwargs: Any) -> Any:
with accountant.claim(wanted, node=node_id, run=run_id) as allocation:
return pool.for_env(derive_env(wanted, allocation)).run(
with placer.claim(
wanted, device=device, policy=policy, node=node_id, run=run_id
) as (target, allocation):
env = derive_env(wanted, allocation)
if target.worker is None:
return pool.for_env(env).run(
owner,
local,
code,
kwargs,
node_id,
timeout,
run_id=run_id,
on_event=on_event,
)
return self.remote.run_on( # type: ignore[union-attr]
target.worker,
owner,
local,
code,
@@ -911,6 +932,7 @@ class FlowController:
timeout,
run_id=run_id,
on_event=on_event,
env=env,
)
return call
@@ -1003,6 +1025,11 @@ class FlowController:
problem = self.remote.compile(
node_def.device or "", owner, local, code
)
elif self._runs_elsewhere(node_def):
# Asks for more than this machine has, so it will run on
# one that has it. Same reason as a device: checking the
# import here would fail a node that is fine there.
problem = None
else:
problem = self.workers.compile(owner, local, code)
if problem:
@@ -1016,18 +1043,15 @@ class FlowController:
if node_def.timeout is not None
else settings.FLOW_NODE_TIMEOUT
)
function = self.workers.proxy(
owner,
local,
code,
node_id=node_id,
timeout=timeout,
run_id=run.run_id if run else "",
on_event=emissions.handle,
)
if node_def.resources is not None and not node_def.device:
function = self._allocated(
if node_def.resources is not None and self.placer is not None:
# Says how much of a machine it takes, so which machine
# and how much of it are one decision — including when
# it also names a device, which used to mean the two
# answers disagreed and nothing was accounted at all.
function = self._placed(
node_def.resources,
node_def.device,
node_def.device_policy,
owner,
local,
code,
@@ -1036,11 +1060,9 @@ class FlowController:
run_id=run.run_id if run else "",
on_event=emissions.handle,
)
if node_def.device and self.remote is not None:
# A node with a device runs on a worker carrying that
# label. Which worker is decided per call, so one that
# attaches after this flow was built is used without
# anything being rebuilt.
elif node_def.device and self.remote is not None:
# A device and nothing about size: the label alone
# decides, least busy first, as it always has.
function = self.remote.proxy(
node_def.device,
owner,
@@ -1051,9 +1073,30 @@ class FlowController:
run_id=run.run_id if run else "",
on_event=emissions.handle,
fallback=(
function if node_def.device_policy == "prefer" else None
self.workers.proxy(
owner,
local,
code,
node_id=node_id,
timeout=timeout,
run_id=run.run_id if run else "",
on_event=emissions.handle,
)
if node_def.device_policy == "prefer"
else None
),
)
else:
# Declares nothing: the shared pool, at no extra cost.
function = self.workers.proxy(
owner,
local,
code,
node_id=node_id,
timeout=timeout,
run_id=run.run_id if run else "",
on_event=emissions.handle,
)
# Outermost, so it sees the result whichever of the three
# above answered the call.
function = emissions.wrap(function)
backend/fluksio/flow/placement.py
+390
View File
@@ -0,0 +1,390 @@
"""Which machine a node runs on, and the waiting when none of them has room.
The engine used to answer this twice, in two ways that could not see each
other. A node with a ``device`` went to a worker carrying that label, chosen by
which of them had least in flight — a machine's *name*, never its size. A node
with ``resources`` was accounted against the engine's own cores, and only the
engine's: declaring both meant the second answer silently won and nothing was
counted at all.
One question, then, asked once here: of every machine attached — this one and
each worker — which could grant what this node asked for, and which of those
has it free right now. A worker reports its inventory when it attaches, so the
answer covers the whole installation rather than the host the engine happens to
be on.
Two properties are worth stating because they are what make the waiting safe:
*Waiting is central.* One condition variable, woken by a release on any machine
and by a worker attaching. A node waiting inside one machine's books could not
be woken by a second machine appearing, which is exactly the case a cluster is
for.
*Locks go one way.* This condition, then a machine's books, never the reverse —
:meth:`ResourceAccountant.try_take` does not block and
:meth:`ResourceAccountant.give_back` calls back out after dropping its own
lock. The other invariant the engine already had still holds too: the claim is
taken before a worker slot, so a node holding a slot can never be waiting on
resources that a node holding those resources cannot get a slot to release.
"""
from __future__ import annotations
import logging
import threading
import time
from collections.abc import Iterator
from contextlib import contextmanager
from dataclasses import dataclass
from typing import TYPE_CHECKING, Any
from fluksio.flow.events import EventBus
from fluksio.flow.resources import Allocation, ResourceAccountant
from fluksio.flow.schemas import Resources
if TYPE_CHECKING: # pragma: no cover - imported for types only
from fluksio.flow.provision import Provisioner
from fluksio.flow.remote import RemoteWorker, RemoteWorkerHub
logger = logging.getLogger(__name__)
#: How long a waiting node sleeps before looking again without being woken.
#: Everything that frees a machine wakes it, so this only catches a wakeup lost
#: to a race and gives a provisioned machine's timeout somewhere to be noticed.
WAKE_S = 5.0
@dataclass(frozen=True)
class Target:
"""One machine a node could run on: this engine, or an attached worker."""
name: str
accountant: ResourceAccountant
#: None is the engine itself, which runs nodes in its own worker pool.
worker: RemoteWorker | None = None
def carries(self, device: str) -> bool:
"""Whether a node asking for this device may run here.
The engine carries no label: a label names a machine somebody attached
for the purpose, and the engine is where the node would have run anyway.
"""
if self.worker is None:
return False
return device == self.name or device in self.worker.labels
@dataclass
class _Waiting:
node: str
since: float
reason: str
class Placer:
"""Every machine the engine can reach, and who is queued for one."""
def __init__(
self,
local: ResourceAccountant,
hub: RemoteWorkerHub | None = None,
events: EventBus | None = None,
) -> None:
self.local = local
self.hub = hub
self.events = events
self.provisioners: list[Provisioner] = []
self._condition = threading.Condition()
self._waiting: dict[int, _Waiting] = {}
self._ticket = 0
local.on_release = self.wake
# -- the machines ----------------------------------------------------------
def wake(self) -> None:
"""Something changed: a machine freed up, or one attached or left."""
for provisioner in self.provisioners:
provisioner.reconcile(self._attached_names())
with self._condition:
self._condition.notify_all()
def _attached_names(self) -> set[str]:
if self.hub is None:
return set()
return {worker.name for worker in self.hub.workers() if not worker.gone}
def targets(self) -> list[Target]:
"""This engine, and every worker attached right now."""
found = [Target(name="engine", accountant=self.local)]
if self.hub is not None:
for worker in self.hub.workers():
if worker.gone:
continue
# Assigned here rather than at attach so a worker that
# reconnects — a new object, with fresh books — is wired up
# without the hub having to know about placement at all.
worker.accountant.on_release = self.wake
found.append(
Target(
name=worker.name,
accountant=worker.accountant,
worker=worker,
)
)
return found
def _candidates(
self,
cpus: int,
gpus: int,
ram_mb: int,
device: str | None,
policy: str,
) -> list[Target]:
"""The machines that could run this node, best first."""
targets = self.targets()
remote = [target for target in targets if target.worker is not None]
engine = [target for target in targets if target.worker is None]
if device:
labelled = [target for target in remote if target.carries(device)]
fitting = self._fitting(labelled, cpus, gpus, ram_mb)
if fitting or policy != "prefer":
# `require` waits for the labelled machine even when the engine
# could take the node: the label is a statement about where
# this node is correct, not a preference.
return fitting
# `prefer` is what makes a flow work before the GPU box exists. It
# falls back only when nothing labelled could ever take the node —
# one that is merely busy is worth queueing for.
return self._fitting(engine, cpus, gpus, ram_mb)
# No label: the engine first when it fits, because a node that runs
# here costs no network and reuses a warm worker.
ordered = engine + sorted(
remote, key=lambda target: target.worker.in_flight if target.worker else 0
)
return self._fitting(ordered, cpus, gpus, ram_mb)
@staticmethod
def _fitting(
targets: list[Target], cpus: int, gpus: int, ram_mb: int
) -> list[Target]:
return [t for t in targets if t.accountant.fits(cpus, gpus, ram_mb)]
# -- what can actually be granted ------------------------------------------
def _shapes(self, device: str | None, policy: str) -> list[tuple[int, int, int]]:
"""Every machine's size, as something to measure a request against.
A provisioner's job shapes count: a machine it can start on demand is
one this installation has, even when nothing is attached yet.
"""
shapes = []
for target in self.targets():
if device and not target.carries(device):
# A `prefer` node may end up here, so the engine still counts.
if policy == "require" or target.worker is not None:
continue
books = target.accountant
shapes.append((books.cpus, books.gpus, books.ram_mb or 0))
for provisioner in self.provisioners:
shapes.extend(provisioner.shapes(device))
return shapes or [(self.local.cpus, self.local.gpus, self.local.ram_mb or 0)]
def _clamp(
self, wanted: Resources, node: str, device: str | None, policy: str
) -> tuple[int, int, int]:
"""What can be granted somewhere, which may be less than was asked.
A flow written against a sixty-four core box should still run on a
laptop — waiting forever for cores that do not exist is not a smaller
machine, it is a hung run. What it must not become is an ask no single
machine can grant: taking the largest of each dimension separately can
describe a machine that is not there, and waiting on *that* is the hung
run this exists to avoid. So the GPUs are settled first, and the rest is
measured only against machines that carry that many.
"""
ram = wanted.ram or 0
shapes = self._shapes(device, policy)
gpus = min(wanted.gpus, max(shape[1] for shape in shapes))
capable = [shape for shape in shapes if shape[1] >= gpus]
cpus = min(wanted.cpus, max(shape[0] for shape in capable))
# A machine that reported no memory is not a memory limit; only those
# that did have anything to say about it.
said = [shape[2] for shape in capable if shape[2]]
ram = min(ram, max(said)) if said and ram else ram
if (cpus, gpus, ram) != (wanted.cpus, wanted.gpus, wanted.ram or 0):
logger.warning(
"%s asked for %d cpu(s), %d gpu(s) and %s MB; "
"the largest machine here can give %d, %d and %s",
node or "a node",
wanted.cpus,
wanted.gpus,
wanted.ram or "no stated",
cpus,
gpus,
ram or "no stated",
)
return cpus, gpus, ram
# -- holding a machine for the length of a call ----------------------------
@contextmanager
def claim(
self,
wanted: Resources,
*,
device: str | None = None,
policy: str = "require",
node: str = "",
run: str = "",
) -> Iterator[tuple[Target, Allocation]]:
"""Hold a machine's share of itself for as long as this node runs."""
waited_from = time.monotonic()
ticket = 0
chosen: Target | None = None
allocation: Allocation | None = None
with self._condition:
while chosen is None:
cpus, gpus, ram = self._clamp(wanted, node, device, policy)
for target in self._candidates(cpus, gpus, ram, device, policy):
got = target.accountant.try_take(cpus, gpus, ram)
if got is not None:
chosen, allocation = target, got
break
if chosen is not None:
break
if not ticket:
ticket = self._announce(
node, run, waited_from, self._reason(cpus, gpus, device)
)
self._provision(cpus, gpus, ram, device)
self._condition.wait(timeout=WAKE_S)
if ticket:
self._waiting.pop(ticket, None)
if ticket:
logger.info(
"%s waited %.1fs and runs on '%s'",
node or "a node",
time.monotonic() - waited_from,
chosen.name,
)
assert allocation is not None
try:
yield chosen, allocation
finally:
# Every way a call can end comes through here: an answer, a
# timeout, a cancellation, or the worker going away mid-call.
chosen.accountant.give_back(allocation)
def _reason(self, cpus: int, gpus: int, device: str | None) -> str:
parts = []
if gpus:
parts.append(f"{gpus} gpu(s)")
parts.append(f"{cpus} cpu(s)")
wants = " and ".join(parts)
if device:
return f"waiting for a worker labelled '{device}' with {wants} free"
return f"waiting for {wants}"
def _provision(self, cpus: int, gpus: int, ram_mb: int, device: str | None) -> None:
"""Ask for a machine, if something here can start one."""
for provisioner in self.provisioners:
if provisioner.covers(cpus, gpus, ram_mb, device):
provisioner.provision(cpus, gpus, ram_mb, device)
return
def _announce(self, node: str, run: str, since: float, reason: str) -> int:
"""Say a node is queued, not stuck.
The failure this exists for looked identical to a hang: a run sitting
at `running` for twenty minutes with no error and no output. A node
waiting its turn has to say so somewhere a person will look.
"""
self._ticket += 1
ticket = self._ticket
self._waiting[ticket] = _Waiting(node=node, since=since, reason=reason)
logger.info("%s is %s", node or "a node", reason)
if self.events is not None:
self.events.publish(
{
"type": "node_queued",
"flow": node.split(".", 1)[0] if node else "",
"node": node,
"run": run,
"detail": reason,
"ts": time.time(),
}
)
return ticket
# -- what it looks like from outside ---------------------------------------
def satisfiable(self, needs: dict[str, Any] | None) -> str | None:
"""What a run would have to wait for, or None if it would not wait.
Only a genuine wait is worth holding a run for. A request nothing can
grant is cut down to what is here and runs anyway, so answering "no
machine has 64 cores" would hold a run that was about to work.
"""
if not needs:
return None
cpus = int(needs.get("cpus") or 1)
gpus = int(needs.get("gpus") or 0)
ram = int(needs.get("ram_mb") or 0)
device = needs.get("device") or None
for target in self.targets():
if device and not target.carries(device):
continue
if target.accountant.fits(cpus, gpus, ram):
# Something here could take it. Busy is queueing, not waiting.
return None
if not any(
provisioner.covers(cpus, gpus, ram, device)
for provisioner in self.provisioners
):
# Nothing attached fits and nothing can be started, so the node
# will be clamped onto what is here and run. Holding the run would
# be holding it for something that is not going to happen — and
# where the wait is a missing *label*, `required_labels` says so
# already.
return None
return f"{gpus} gpu(s) and {cpus} cpu(s)" if gpus else f"{cpus} cpu(s)"
def snapshot(self) -> dict[str, Any]:
"""Every machine, what is free of it, and who is queued.
A node waiting its turn looks exactly like a node that has hung — the
run sits at `running` and says nothing — so what is waiting, and for
what, has to be readable somewhere.
"""
targets = []
for target in self.targets():
entry: dict[str, Any] = {"target": target.name}
entry.update(target.accountant.snapshot())
if target.worker is not None:
entry["labels"] = sorted(target.worker.labels)
entry["in_flight"] = target.worker.in_flight
targets.append(entry)
with self._condition:
waiting = list(self._waiting.values())
local = self.local.snapshot()
return {
# The engine's own figures stay where they were, so a reader that
# only ever knew about one machine still finds them.
"cpus": local["cpus"],
"gpus": local["gpus"],
"waiting": [
{
"node": entry.node,
"reason": entry.reason,
"seconds": round(time.monotonic() - entry.since, 1),
}
for entry in waiting
],
"targets": targets,
"provisioners": [p.status() for p in self.provisioners],
}
backend/fluksio/flow/remote.py
+52 -1
View File
@@ -32,6 +32,7 @@ from dataclasses import dataclass
from typing import Any
from fluksio.flow.nodes.base import NodeOutputError
from fluksio.flow.resources import ResourceAccountant
from fluksio.flow.workers import NodeTimeout, RemoteError, _remote_class
logger = logging.getLogger(__name__)
@@ -106,6 +107,14 @@ class RemoteWorker:
self.labels = set(labels)
self.info = info or {}
self.inventory = inventory or WorkerInventory()
# This machine's books, held here so that a worker reconnecting — which
# is a new object — starts from a clean set rather than from counters
# the engine kept for a socket that is gone.
self.accountant = ResourceAccountant(
cpus=self.inventory.cpus,
gpus=self.inventory.gpus,
ram_mb=self.inventory.ram_mb,
)
self.attached_at = time.time()
self.last_seen = time.time()
self._send = send
@@ -251,9 +260,13 @@ class RemoteWorker:
class RemoteWorkerHub:
"""Every attached worker, and which of them a node may run on."""
def __init__(self) -> None:
def __init__(self, on_change: Callable[[], None] | None = None) -> None:
self._workers: dict[str, RemoteWorker] = {}
self._lock = threading.Lock()
#: Told when the set of attached workers changes, so whoever is waiting
#: for a machine can look again. Called outside the lock: it takes one
#: of its own, and the two are only ever taken in that order.
self.on_change = on_change
# -------------------------------------------------------------------------
# Attachment
@@ -270,6 +283,7 @@ class RemoteWorkerHub:
logger.info(
"Worker '%s' attached with labels %s", worker.name, sorted(worker.labels)
)
self._changed()
def detach(self, name: str) -> None:
with self._lock:
@@ -277,6 +291,11 @@ class RemoteWorkerHub:
if worker is not None:
worker.detach()
logger.info("Worker '%s' detached", name)
self._changed()
def _changed(self) -> None:
if self.on_change is not None:
self.on_change()
def workers(self) -> list[RemoteWorker]:
with self._lock:
@@ -326,6 +345,38 @@ class RemoteWorkerHub:
worker = self.pick(label)
if worker is None:
raise NoWorker(f"no worker labelled '{label}' is attached")
return self.run_on(
worker,
flow,
node,
source,
kwargs,
node_id,
timeout,
run_id=run_id,
on_event=on_event,
env=env,
)
def run_on(
self,
worker: RemoteWorker,
flow: str,
node: str,
source: str,
kwargs: dict[str, Any],
node_id: str,
timeout: float,
run_id: str = "",
on_event: Callable[[dict[str, Any]], None] | None = None,
env: dict[str, str] | None = None,
) -> Any:
"""Run this node on the worker the caller has already settled on.
The placer holds that machine's cores for the length of the call, so
resolving the label a second time here could send the work somewhere
else and leave the claim on a machine doing nothing.
"""
payload = {
"op": "run",
"call_id": f"{run_id}:{node_id}" if run_id else node_id,
backend/fluksio/flow/resources.py
+69 -124
View File
@@ -8,16 +8,18 @@ seconds. On a GPU the same shape is worse: three processes each preallocating
most of the card deadlock at zero utilisation, with nothing failing and nothing
to read.
:class:`ResourceAccountant` is the first half: a node that declares what it
needs waits until that much is free, the way it already waits for a worker
slot. :func:`derive_env` is the second: what it got is handed to the library as
the environment it reads at import, because that is the only moment those knobs
are read.
:class:`ResourceAccountant` is the first half: the books for one machine, which
hand out what is free and take it back. :func:`derive_env` is the second: what
a node got is handed to the library as the environment it reads at import,
because that is the only moment those knobs are read.
One accountant is one machine. Which machine a node goes to, and the waiting
when none of them has room, is :mod:`fluksio.flow.placement` — the books here
never block, so a caller holding several of them can ask each in turn.
Deliberately cooperative — nothing here is enforced with cgroups or rlimits, so
a node that ignores its share is only accounted for, not stopped. That is the
same trust the worker pool already extends to node code, and the enforcement
half belongs with the scheduler work this is the first step of.
same trust the worker pool already extends to node code.
"""
from __future__ import annotations
@@ -25,12 +27,9 @@ from __future__ import annotations
import logging
import os
import threading
import time
from collections.abc import Iterator
from contextlib import contextmanager
from collections.abc import Callable
from dataclasses import dataclass
from fluksio.flow.events import EventBus
from fluksio.flow.schemas import Resources
logger = logging.getLogger(__name__)
@@ -63,146 +62,92 @@ class Allocation:
cpus: int = 1
gpus: tuple[int, ...] = ()
@dataclass
class _Waiting:
node: str
since: float
reason: str
ram_mb: int = 0
class ResourceAccountant:
"""What is free on this machine, and who is waiting for it.
"""The books for one machine: what it holds, and what is free of it.
A plain condition variable over two counters. Blocking is the whole
mechanism: the caller is a node thread that would otherwise be executing,
and making it wait is the same backpressure that the worker pool's slot
queue already applies — one reason the two must always be taken in the same
order, resources first, so neither can be held while waiting for the other.
Nothing here blocks. A node that has to wait waits in the placer, which
holds one of these per machine and tries each in turn — a lock per machine
could not answer "is there room anywhere", and a node waiting inside one
machine's books could not be woken by another machine attaching.
``on_release`` is how it tells the placer something came free. It is called
outside this object's lock, deliberately: the placer takes its own lock
there, and the two are only ever taken in that one order.
"""
def __init__(
self, cpus: int = 0, gpus: int = 0, events: EventBus | None = None
self,
cpus: int = 0,
gpus: int = 0,
ram_mb: int | None = None,
on_release: Callable[[], None] | None = None,
) -> None:
self.cpus = cpus or machine_cpus()
self.gpus = max(0, gpus)
self.events = events
#: None is memory this machine did not report, which is allowed: it is
#: then not accounted rather than accounted as zero, since zero would
#: refuse every node that asks for any.
self.ram_mb = ram_mb
self.on_release = on_release
self._free_cpus = self.cpus
self._free_gpus = list(range(self.gpus))
self._waiting: dict[int, _Waiting] = {}
self._ticket = 0
self._condition = threading.Condition()
self._free_ram = ram_mb or 0
self._lock = threading.Lock()
# -- what a caller asks for ------------------------------------------------
def fits(self, cpus: int, gpus: int, ram_mb: int = 0) -> bool:
"""Whether this machine could ever grant that much, busy or not.
def _clamp(self, wanted: Resources, node: str) -> tuple[int, int]:
"""What can be granted here, which may be less than what was asked.
A flow written against a sixty-four core box should still run on a
laptop. Waiting forever for cores that do not exist is not a smaller
machine, it is a hung run.
The question a placer asks before it decides to wait: waiting for a
card that is merely busy is queueing, and waiting for one the machine
does not have is a hung run.
"""
cpus = min(wanted.cpus, self.cpus)
gpus = min(wanted.gpus, self.gpus)
if cpus != wanted.cpus or gpus != wanted.gpus:
logger.warning(
"%s asked for %d cpu(s) and %d gpu(s); this engine has %d and %d",
node or "a node",
wanted.cpus,
wanted.gpus,
self.cpus,
self.gpus,
)
return cpus, gpus
if cpus > self.cpus or gpus > self.gpus:
return False
return self.ram_mb is None or ram_mb <= self.ram_mb
@contextmanager
def claim(
self, wanted: Resources, node: str = "", run: str = ""
) -> Iterator[Allocation]:
"""Hold this node's share for as long as it runs."""
cpus, gpus = self._clamp(wanted, node)
allocation = self._take(cpus, gpus, node, run)
try:
yield allocation
finally:
self._give_back(allocation)
def _take(self, cpus: int, gpus: int, node: str, run: str) -> Allocation:
waited_from = time.monotonic()
ticket = 0
with self._condition:
while self._free_cpus < cpus or len(self._free_gpus) < gpus:
if not ticket:
reason = (
f"waiting for {cpus} cpu(s) ({self._free_cpus} free)"
if self._free_cpus < cpus
else f"waiting for {gpus} gpu(s) ({len(self._free_gpus)} free)"
)
ticket = self._announce(node, run, waited_from, reason)
self._condition.wait()
def try_take(self, cpus: int, gpus: int, ram_mb: int = 0) -> Allocation | None:
"""Take this much if it is free right now, or answer that it is not."""
with self._lock:
if self._free_cpus < cpus or len(self._free_gpus) < gpus:
return None
if self.ram_mb is not None and self._free_ram < ram_mb:
return None
self._free_cpus -= cpus
taken = tuple(self._free_gpus.pop(0) for _ in range(gpus))
if ticket:
self._waiting.pop(ticket, None)
if ticket:
logger.info(
"%s waited %.1fs for %d cpu(s) and %d gpu(s)",
node or "a node",
time.monotonic() - waited_from,
cpus,
gpus,
)
return Allocation(cpus=cpus, gpus=taken)
if self.ram_mb is not None:
self._free_ram -= ram_mb
return Allocation(cpus=cpus, gpus=taken, ram_mb=ram_mb)
def _give_back(self, allocation: Allocation) -> None:
with self._condition:
def give_back(self, allocation: Allocation) -> None:
"""Return what an execution held, however it ended."""
with self._lock:
self._free_cpus += allocation.cpus
self._free_gpus.extend(allocation.gpus)
self._free_gpus.sort()
self._condition.notify_all()
# -- what it looks like from outside ---------------------------------------
def _announce(self, node: str, run: str, since: float, reason: str) -> int:
"""Say a node is queued, not stuck.
The failure this exists for looked identical to a hang: a run sitting
at `running` for twenty minutes with no error and no output. A node
waiting its turn has to say so somewhere a person will look.
"""
self._ticket += 1
ticket = self._ticket
self._waiting[ticket] = _Waiting(node=node, since=since, reason=reason)
logger.info("%s is %s", node or "a node", reason)
if self.events is not None:
self.events.publish(
{
"type": "node_queued",
"flow": node.split(".", 1)[0] if node else "",
"node": node,
"run": run,
"detail": reason,
"ts": time.time(),
}
)
return ticket
if self.ram_mb is not None:
self._free_ram += allocation.ram_mb
if self.on_release is not None:
self.on_release()
def snapshot(self) -> dict[str, object]:
"""What is free and who is waiting, for the workers screen."""
with self._condition:
free_cpus, free_gpus = self._free_cpus, len(self._free_gpus)
"""What this machine holds and what is free of it."""
with self._lock:
free_cpus, free_gpus, free_ram = (
self._free_cpus,
len(self._free_gpus),
self._free_ram,
)
return {
"cpus": {"total": self.cpus, "free": free_cpus},
"gpus": {"total": self.gpus, "free": free_gpus},
"waiting": [
{
"node": entry.node,
"reason": entry.reason,
"seconds": round(time.monotonic() - entry.since, 1),
}
for entry in list(self._waiting.values())
],
"ram_mb": (
None
if self.ram_mb is None
else {"total": self.ram_mb, "free": free_ram}
),
}
backend/fluksio/flow/runs.py
+56 -8
View File
@@ -160,6 +160,17 @@ def _has_no_body(
return not store.has_node_source(flow, node.id, draft=draft)
def _runs_on_a_worker(node: NodeDef) -> bool:
"""Whether this node's body could go to a worker at all.
Only a node whose source travels can: a connector is an entry point loaded
in this process, so a device on one is a field nothing reads. Holding a run
for a worker that could never take that node is a run that never starts.
"""
node_type = NODE_TYPES.get(node.type)
return node_type is not None and node_type.has_source
def required_labels(flow: FlowDef) -> list[str]:
"""Worker labels this flow cannot run without.
@@ -171,11 +182,38 @@ def required_labels(flow: FlowDef) -> list[str]:
{
node.device
for node in flow.nodes
if node.device and node.device.strip() and node.device_policy == "require"
if node.device
and node.device.strip()
and node.device_policy == "require"
and _runs_on_a_worker(node)
}
)
def required_resources(flow: FlowDef) -> dict[str, Any] | None:
"""The largest single thing this flow needs a machine to have.
Dimension by dimension rather than per node, which is deliberately blunt:
it answers "could this run start at all", not "in what order". A node that
only *prefers* its device is left out — it runs here when nothing carries
the label, so it is never what a run is waiting for.
"""
cpus, gpus, ram = 0, 0, 0
device = ""
for node in flow.nodes:
wanted = node.resources
if wanted is None or not _runs_on_a_worker(node):
continue
cpus = max(cpus, wanted.cpus)
gpus = max(gpus, wanted.gpus)
ram = max(ram, wanted.ram or 0)
if node.device and node.device_policy == "require":
device = node.device
if not (cpus or gpus or ram):
return None
return {"cpus": cpus, "gpus": gpus, "ram_mb": ram, "device": device}
#: What a run's output is called from outside it: ``@run:<id>.<output>``.
RUN_REF_PREFIX = "@run:"
@@ -759,6 +797,7 @@ class RunService:
no_cache=no_cache,
status="queued",
labels=required_labels(flow),
needs=required_resources(flow),
created_at=datetime.now(UTC),
actor=actor,
idempotency_key=idempotency_key,
@@ -854,7 +893,7 @@ class RunService:
if not item.run_id:
self.queue.ack(item)
continue
missing = self._missing_labels(item.run_id)
missing = self._missing_requirements(item.run_id)
if missing:
# Left in the queue rather than failed: submitting a run
# before turning the GPU box on is a normal way to work, and
@@ -870,21 +909,30 @@ class RunService:
except RuntimeError:
logger.warning("Run %s not started: shutting down", item.run_id)
def _missing_labels(self, run_id: str) -> list[str]:
"""Worker labels this run needs that nothing attached carries."""
def _missing_requirements(self, run_id: str) -> list[str]:
"""What this run needs that nothing attached can give it yet."""
with Session(db_engine) as session:
run = session.get(Run, run_id)
needed = list(run.labels) if run else []
if not needed:
return []
needs = dict(run.needs) if run and run.needs else None
hub = self.controller.remote
available = hub.labels() | {w.name for w in hub.workers()} if hub else set()
# A node that only prefers its label runs locally instead, so it is not
# a reason to hold the run back; that is decided per node at call time.
return sorted(set(needed) - available)
missing = [f"labelled {label}" for label in sorted(set(needed) - available)]
placer = self.controller.placer
if placer is not None:
# Only a wait something is going to end — a machine that could take
# this is being started for it. An ask nothing can grant is cut down
# to what is here and runs, so holding the run would be holding it
# for something that is not coming.
short = placer.satisfiable(needs)
if short:
missing.append(f"with {short}")
return missing
def _waiting(self, run_id: str, missing: list[str]) -> None:
reason = f"Waiting for a worker labelled {', '.join(missing)}"
reason = f"Waiting for a worker {' and '.join(missing)}"
try:
with Session(db_engine) as session:
session.exec(
backend/fluksio/flow/schemas.py
+10
View File
@@ -60,6 +60,16 @@ class Resources(BaseModel):
"runs, which is what keeps two preallocating processes apart."
),
)
ram: int | None = Field(
default=None,
ge=1,
description=(
"Megabytes held for the whole execution. Counted against machines "
"that said how much they have, and ignored by those that did not — "
"which is a machine with nothing to say about memory, not one with "
"none."
),
)
env: dict[str, str] = Field(
default_factory=dict,
description=(
backend/fluksio/main.py
+10 -4
View File
@@ -29,6 +29,7 @@ from fluksio.flow.executor import ExecutionService
from fluksio.flow.metrics import MetricsCollector
from fluksio.flow.nodes.http import close_shared_client
from fluksio.flow.pipeline import ValueSource
from fluksio.flow.placement import Placer
from fluksio.flow.plugins import load_plugins
from fluksio.flow.queue import MemoryWorkQueue, RedisWorkQueue, WorkQueue
from fluksio.flow.remote import RemoteWorkerHub
@@ -142,10 +143,11 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
# not something anyone wrote, so it has no business in the git repository.
artifacts = ArtifactStore(settings.FLOWS_DIR.parent / "artifacts")
app.state.artifact_store = artifacts
accountant = ResourceAccountant(
cpus=settings.FLOW_CPUS, gpus=settings.FLOW_GPUS, events=event_bus
)
accountant = ResourceAccountant(cpus=settings.FLOW_CPUS, gpus=settings.FLOW_GPUS)
app.state.resources = accountant
# Every machine a node could run on: this one, and whatever attaches.
placer = Placer(local=accountant, events=event_bus)
app.state.placer = placer
pool = PythonWorkerPool(
python=modules.venv_python(),
size=settings.FLOW_MAX_WORKERS,
@@ -163,7 +165,10 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
)
pool.start()
app.state.worker_pool = pool
worker_hub = RemoteWorkerHub()
# Assigned rather than passed both ways: the hub tells the placer when a
# machine comes or goes, and the placer needs the hub to know what is there.
worker_hub = RemoteWorkerHub(on_change=placer.wake)
placer.hub = worker_hub
app.state.worker_hub = worker_hub
controller = FlowController(
store=store,
@@ -176,6 +181,7 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
workers=pool,
remote=worker_hub,
resources=accountant,
placer=placer,
)
app.state.flow_controller = controller
# A "dashboard" alert channel puts its alert into the graph. Bound here
backend/fluksio/models.py
+4
View File
@@ -362,6 +362,10 @@ class Run(SQLModel, table=True):
status_reason: str = Field(default="", max_length=1024)
#: Worker labels its nodes need, so a run with nowhere to go can say so.
labels: list[str] = Field(sa_column=Column(JSON), default_factory=list)
#: The largest machine its nodes ask for, as cpus, gpus, ram_mb and device.
#: Read while the run is queued, to tell waiting for a machine from having
#: nowhere to run at all.
needs: dict[str, Any] | None = Field(sa_column=Column(JSON), default=None)
created_at: datetime = Field(
index=True,
sa_type=UTCDateTime,
backend/scripts/bench_startup.py
+1 -1
View File
@@ -37,7 +37,7 @@ log = logging.getLogger("bench")
#: A flow that computes nothing, so what is timed is the getting-started.
BENCH_FLOW = "bench_startup"
NODE_SOURCE = '"""Does nothing, on purpose."""\n\n\ndef process(n, params):\n return {"out": n}\n'
NODE_SOURCE = '"""Does nothing, on purpose."""\n\n\ndef process(n):\n return {"out": n}\n'
class Api:
backend/tests/flow/test_placement.py
+394
View File
@@ -0,0 +1,394 @@
"""Which machine a node runs on, and what happens when none of them is free.
The two questions the engine used to answer separately — where does a node run,
and how much of that machine does it get — are one question here. What is
checked is that the answer covers every machine attached rather than only the
host the engine is on, that a claim is given back however the call ends, and
that a node with nowhere to go waits and says so instead of failing.
"""
import asyncio
import threading
import time
from collections.abc import Iterator
import pytest
from fluksio.flow.placement import Placer
from fluksio.flow.remote import RemoteWorker, RemoteWorkerHub, WorkerInventory
from fluksio.flow.resources import ResourceAccountant
from fluksio.flow.schemas import NodeDef, Resources
@pytest.fixture
def loop() -> Iterator[asyncio.AbstractEventLoop]:
"""An event loop running in a thread, as the server's does."""
running = asyncio.new_event_loop()
thread = threading.Thread(target=running.run_forever, daemon=True)
thread.start()
yield running
running.call_soon_threadsafe(running.stop)
thread.join(timeout=5)
running.close()
class FakeSocket:
def __init__(self) -> None:
self.sent: list[dict] = []
self.arrived = threading.Event()
async def send_json(self, payload: dict) -> None:
self.sent.append(payload)
self.arrived.set()
def attach(
hub: RemoteWorkerHub,
loop: asyncio.AbstractEventLoop,
name: str = "gpu1",
labels: tuple[str, ...] = ("gpu",),
cpus: int = 8,
gpus: int = 1,
ram_mb: int | None = None,
):
socket = FakeSocket()
worker = RemoteWorker(
name=name,
labels=list(labels),
send=socket.send_json,
loop=loop,
max_parallel=4,
inventory=WorkerInventory(cpus=cpus, gpus=gpus, ram_mb=ram_mb),
)
hub.attach(worker)
return worker, socket
def placer_over(hub: RemoteWorkerHub | None = None, cpus: int = 4, gpus: int = 0):
return Placer(local=ResourceAccountant(cpus=cpus, gpus=gpus), hub=hub)
# -----------------------------------------------------------------------------
# Where a node goes
# -----------------------------------------------------------------------------
def test_a_node_asking_for_a_card_finds_the_machine_that_has_one(loop):
"""No label anywhere — the size of the ask is what places it.
This is the whole point of a worker reporting its inventory: the engine has
no GPU, so a node that needs one used to be clamped down to none and run
here anyway.
"""
hub = RemoteWorkerHub()
placer = placer_over(hub)
worker, _ = attach(hub, loop, labels=())
with placer.claim(Resources(cpus=2, gpus=1)) as (target, allocation):
assert target.worker is worker
assert allocation.gpus == (0,)
assert worker.accountant.snapshot()["gpus"]["free"] == 0
assert worker.accountant.snapshot()["gpus"]["free"] == 1
def test_a_node_that_fits_here_stays_here(loop):
"""No network, and a worker pool that is already warm."""
hub = RemoteWorkerHub()
placer = placer_over(hub)
attach(hub, loop)
with placer.claim(Resources(cpus=2)) as (target, _):
assert target.worker is None
assert target.name == "engine"
def test_a_required_label_waits_for_its_machine_rather_than_running_here(loop):
hub = RemoteWorkerHub()
placer = placer_over(hub)
worker, _ = attach(hub, loop, labels=("gpu",))
with placer.claim(Resources(cpus=2), device="gpu", policy="require") as (
target,
_,
):
assert target.worker is worker
def test_a_preferred_label_falls_back_here_and_is_still_accounted(loop):
"""The fallback used to skip the books entirely, so it held nothing."""
hub = RemoteWorkerHub()
placer = placer_over(hub)
with placer.claim(Resources(cpus=3), device="gpu", policy="prefer") as (
target,
allocation,
):
assert target.worker is None
assert allocation.cpus == 3
assert placer.local.snapshot()["cpus"]["free"] == 1
def test_asking_for_more_than_anything_has_gets_what_there_is(loop):
"""A flow written on a cluster still has to run on a laptop."""
placer = placer_over(cpus=2)
with placer.claim(Resources(cpus=64, gpus=4)) as (target, allocation):
assert target.name == "engine"
assert allocation.cpus == 2
assert allocation.gpus == ()
def test_what_is_clamped_to_is_a_machine_that_exists(loop):
"""Each dimension taken separately can describe a machine nobody has.
A big CPU box and a small GPU box are not one machine with both. Clamping
to the largest of each would ask for something that never comes free, which
is the hung run the clamping is there to avoid.
"""
hub = RemoteWorkerHub()
placer = placer_over(hub, cpus=2)
attach(hub, loop, name="big", labels=(), cpus=64, gpus=0)
attach(hub, loop, name="small-gpu", labels=(), cpus=4, gpus=1)
with placer.claim(Resources(cpus=64, gpus=1)) as (target, allocation):
assert target.name == "small-gpu"
assert (allocation.cpus, allocation.gpus) == (4, (0,))
# -----------------------------------------------------------------------------
# Waiting
# -----------------------------------------------------------------------------
def test_a_node_waits_for_a_busy_machine_and_says_so(loop):
hub = RemoteWorkerHub()
events: list[dict] = []
placer = Placer(
local=ResourceAccountant(cpus=2),
hub=hub,
events=type("Bus", (), {"publish": lambda self, e: events.append(e)})(),
)
started = threading.Event()
def second() -> None:
with placer.claim(Resources(cpus=2), node="study.b"):
started.set()
with placer.claim(Resources(cpus=2), node="study.a"):
thread = threading.Thread(target=second, daemon=True)
thread.start()
# Long enough to have run if nothing was holding it back.
assert not started.wait(0.3)
assert placer.snapshot()["waiting"][0]["node"] == "study.b"
assert events[0]["type"] == "node_queued"
assert "2 cpu(s)" in events[0]["detail"]
thread.join(timeout=5)
assert started.is_set()
assert placer.snapshot()["waiting"] == []
def test_a_worker_attaching_wakes_what_was_waiting_for_one(loop):
"""A node waiting inside one machine's books could not hear this."""
hub = RemoteWorkerHub()
placer = placer_over(hub)
hub.on_change = placer.wake
ran = threading.Event()
def needs_a_card() -> None:
with placer.claim(Resources(cpus=1, gpus=1), node="study.fit") as (target, _):
if target.worker is not None:
ran.set()
thread = threading.Thread(target=needs_a_card, daemon=True)
thread.start()
# Nothing has a GPU yet, so it is clamped to none and runs here — the wait
# only happens while a machine that *could* take it is busy.
thread.join(timeout=5)
assert not thread.is_alive()
worker, _ = attach(hub, loop, labels=())
held = worker.accountant.try_take(cpus=1, gpus=1)
thread = threading.Thread(target=needs_a_card, daemon=True)
thread.start()
assert not ran.wait(0.3)
worker.accountant.give_back(held)
thread.join(timeout=5)
assert ran.is_set()
def test_everything_comes_back_when_a_node_fails(loop):
placer = placer_over(cpus=4, gpus=1)
with pytest.raises(ValueError):
with placer.claim(Resources(cpus=4, gpus=1)):
raise ValueError("the node raised")
assert placer.local.snapshot()["cpus"]["free"] == 4
assert placer.local.snapshot()["gpus"]["free"] == 1
def test_a_worker_going_away_mid_call_gives_its_share_back(loop):
hub = RemoteWorkerHub()
placer = placer_over(hub)
worker, _ = attach(hub, loop, labels=())
with pytest.raises(RuntimeError):
with placer.claim(Resources(cpus=2, gpus=1)) as (target, _):
assert target.worker is worker
hub.detach(worker.name)
raise RuntimeError("worker went away mid-call")
# The books are the worker's own, so they go with it — what matters is that
# nothing is left holding them and the next claim is not blocked.
assert worker.accountant.snapshot()["gpus"]["free"] == 1
def test_many_nodes_at_once_all_finish(loop):
"""The placer must not deadlock under contention; it is on every call."""
placer = placer_over(cpus=4)
done = []
def work() -> None:
with placer.claim(Resources(cpus=2), node="study.n"):
time.sleep(0.01)
done.append(1)
threads = [threading.Thread(target=work) for _ in range(8)]
for thread in threads:
thread.start()
for thread in threads:
thread.join(timeout=10)
assert len(done) == 8
assert placer.local.snapshot()["cpus"]["free"] == 4
# -----------------------------------------------------------------------------
# What a run is told before it starts
# -----------------------------------------------------------------------------
def test_a_run_is_only_held_for_a_wait_that_will_end(loop):
"""An ask nothing can grant is cut down and runs; holding it would hang."""
placer = placer_over(cpus=4)
assert placer.satisfiable(None) is None
assert placer.satisfiable({"cpus": 2}) is None
# No machine here has a GPU and nothing can be started with one.
assert placer.satisfiable({"cpus": 1, "gpus": 1}) is None
def test_a_run_waits_for_a_machine_something_can_start(loop):
class Cluster:
def covers(self, cpus, gpus, ram_mb, label=None):
return gpus <= 2
def provision(self, cpus, gpus, ram_mb, label=None):
pass
def reconcile(self, attached):
pass
def shapes(self, label=None):
return [(16, 2, 65536)]
def status(self):
return {"name": "hpc"}
placer = placer_over(cpus=4)
placer.provisioners = [Cluster()]
assert placer.satisfiable({"cpus": 1, "gpus": 1}) == "1 gpu(s) and 1 cpu(s)"
assert placer.satisfiable({"cpus": 1, "gpus": 0}) is None
# -----------------------------------------------------------------------------
# The whole path, through a real worker
# -----------------------------------------------------------------------------
def test_a_declared_node_is_held_to_its_share(tmp_path):
"""Four nodes wanting two cores each, on a machine with four.
What is checked is the pair: never more than the machine has in flight at
once, and every one of them told what it was given — the two halves that
together are the oversubscription this is for. Also that it does not
deadlock, since the claim is taken before a worker slot and both block.
"""
import sys
from fluksio.flow.controller import FlowController, RunContext
from fluksio.flow.messages import DType, MessageSpec
from fluksio.flow.schemas import FlowDef
from fluksio.flow.state import MemoryState
from fluksio.flow.store import FlowStore
from fluksio.flow.workers import PythonWorkerPool
store = FlowStore(tmp_path / "flows")
store.write_flow(
FlowDef(
name="study",
mode="batch",
nodes=[
NodeDef(
id="fit",
provides=[MessageSpec(name="threads", dtype=DType.INT)],
resources=Resources(cpus=2, env={"XLA_FLAGS": "--x=false"}),
)
],
)
)
store.write_node_source(
"study",
"fit",
"import os, time\n\n\ndef process():\n"
" time.sleep(0.2)\n"
" return {'threads': int(os.environ['OMP_NUM_THREADS'])}\n",
)
pool = PythonWorkerPool(python=sys.executable, size=4)
pool.start()
accountant = ResourceAccountant(cpus=4)
placer = Placer(local=accountant)
controller = FlowController(
store, workers=pool, resources=accountant, placer=placer
)
answers: list[object] = []
in_flight: list[int] = []
def once(index: int) -> None:
pipeline = controller.build_run_pipeline(
store.read_flow("study"),
state=MemoryState(),
run=RunContext(run_id=f"r{index}"),
)
pipeline.run({})
answers.append(pipeline.state.get("study.threads"))
def watch(until: threading.Event) -> None:
while not until.is_set():
in_flight.append(4 - int(accountant.snapshot()["cpus"]["free"]))
time.sleep(0.01)
finished = threading.Event()
watcher = threading.Thread(target=watch, args=(finished,))
watcher.start()
threads = [threading.Thread(target=once, args=(i,)) for i in range(4)]
try:
for thread in threads:
thread.start()
for thread in threads:
thread.join(timeout=60)
assert not thread.is_alive(), "a claim and a worker slot deadlocked"
finally:
finished.set()
watcher.join(timeout=5)
pool.stop()
assert answers == [2, 2, 2, 2]
assert max(in_flight) <= 4
assert accountant.snapshot()["cpus"]["free"] == 4
# One environment, so one extra pool however many nodes derived it.
assert len(pool._children) == 1
backend/tests/flow/test_resources.py
+48 -145
View File
@@ -1,15 +1,14 @@
"""Who gets the machine: accounting, exclusivity, and what the worker is told.
"""One machine's books: what it holds, and what is free of it.
The failure this exists for is not subtle — five concurrent nodes each sizing a
thread pool to every core starved the engine's own event loop, and three GPU
processes each preallocating most of the card deadlocked at zero utilisation.
Both come down to arithmetic nobody was doing, so the arithmetic is what is
checked here.
checked here. Which machine a node goes to, and the waiting, is
``test_placement.py``.
"""
import os
import threading
import time
import pytest
@@ -25,79 +24,70 @@ from fluksio.flow.schemas import NodeDef, Resources
def test_what_is_free_is_what_was_handed_out():
accountant = ResourceAccountant(cpus=4, gpus=0)
with accountant.claim(Resources(cpus=3)):
assert accountant.snapshot()["cpus"] == {"total": 4, "free": 1}
held = accountant.try_take(cpus=3, gpus=0)
assert accountant.snapshot()["cpus"] == {"total": 4, "free": 1}
accountant.give_back(held)
assert accountant.snapshot()["cpus"] == {"total": 4, "free": 4}
def test_a_node_waits_until_there_is_room():
"""Blocking is the mechanism — the same backpressure a worker slot applies."""
def test_asking_for_more_than_is_free_is_answered_not_waited_on():
"""The books never block: the placer has other machines to try first."""
accountant = ResourceAccountant(cpus=2)
running = threading.Event()
started = threading.Event()
def second() -> None:
with accountant.claim(Resources(cpus=2), node="study.b"):
started.set()
with accountant.claim(Resources(cpus=2), node="study.a"):
thread = threading.Thread(target=second)
thread.start()
# Long enough to have run if nothing was holding it back.
assert not started.wait(0.2)
assert accountant.snapshot()["waiting"][0]["node"] == "study.b"
running.set()
thread.join(timeout=5)
assert started.is_set()
assert accountant.try_take(cpus=2, gpus=0) is not None
assert accountant.try_take(cpus=2, gpus=0) is None
def test_a_gpu_is_held_by_one_node_at_a_time():
"""The deadlock was three processes each preallocating most of one card."""
accountant = ResourceAccountant(cpus=8, gpus=2)
with accountant.claim(Resources(cpus=1, gpus=1)) as first:
with accountant.claim(Resources(cpus=1, gpus=1)) as second:
assert set(first.gpus) & set(second.gpus) == set()
assert accountant.snapshot()["gpus"] == {"total": 2, "free": 0}
first = accountant.try_take(cpus=1, gpus=1)
second = accountant.try_take(cpus=1, gpus=1)
assert set(first.gpus) & set(second.gpus) == set()
assert accountant.snapshot()["gpus"] == {"total": 2, "free": 0}
assert accountant.try_take(cpus=1, gpus=1) is None
accountant.give_back(first)
accountant.give_back(second)
assert accountant.snapshot()["gpus"] == {"total": 2, "free": 2}
def test_asking_for_more_than_there_is_gets_what_there_is():
"""A flow written on a big box still has to run on a laptop."""
accountant = ResourceAccountant(cpus=2, gpus=0)
with accountant.claim(Resources(cpus=64, gpus=4)) as allocation:
assert allocation.cpus == 2
assert allocation.gpus == ()
def test_everything_comes_back_when_a_node_fails():
def test_what_a_machine_could_ever_grant_is_a_different_question():
"""Busy is worth queueing for; too small is not, and reads the same."""
accountant = ResourceAccountant(cpus=4, gpus=1)
with pytest.raises(ValueError):
with accountant.claim(Resources(cpus=4, gpus=1)):
raise ValueError("the node raised")
assert accountant.fits(cpus=4, gpus=1)
assert not accountant.fits(cpus=8, gpus=0)
assert not accountant.fits(cpus=1, gpus=2)
assert accountant.snapshot()["cpus"]["free"] == 4
assert accountant.snapshot()["gpus"]["free"] == 1
accountant.try_take(cpus=4, gpus=1)
# Still true with nothing free: it is about the machine, not the moment.
assert accountant.fits(cpus=4, gpus=1)
def test_many_nodes_at_once_all_finish():
"""The accountant must not deadlock under contention; it is on every call."""
accountant = ResourceAccountant(cpus=4)
done = []
def test_a_machine_that_said_nothing_about_memory_is_not_a_machine_with_none():
said = ResourceAccountant(cpus=4, ram_mb=2048)
assert said.fits(cpus=1, gpus=0, ram_mb=2048)
assert not said.fits(cpus=1, gpus=0, ram_mb=4096)
held = said.try_take(cpus=1, gpus=0, ram_mb=1536)
assert said.try_take(cpus=1, gpus=0, ram_mb=1024) is None
said.give_back(held)
assert said.snapshot()["ram_mb"] == {"total": 2048, "free": 2048}
def work() -> None:
with accountant.claim(Resources(cpus=2), node="study.n"):
time.sleep(0.01)
done.append(1)
quiet = ResourceAccountant(cpus=4)
assert quiet.fits(cpus=1, gpus=0, ram_mb=999_999)
assert quiet.try_take(cpus=1, gpus=0, ram_mb=999_999) is not None
assert quiet.snapshot()["ram_mb"] is None
threads = [threading.Thread(target=work) for _ in range(8)]
for thread in threads:
thread.start()
for thread in threads:
thread.join(timeout=10)
assert len(done) == 8
assert accountant.snapshot()["cpus"]["free"] == 4
def test_a_release_says_so_once_it_has_let_go():
"""The placer is told outside the lock, which is what keeps the order one-way."""
seen: list[dict] = []
accountant = ResourceAccountant(cpus=2)
accountant.on_release = lambda: seen.append(accountant.snapshot()["cpus"])
accountant.give_back(accountant.try_take(cpus=2, gpus=0))
assert seen == [{"total": 2, "free": 2}]
# -----------------------------------------------------------------------------
@@ -160,90 +150,3 @@ def test_declaring_nothing_stays_exactly_as_it_was():
def test_a_misspelled_resource_is_refused():
with pytest.raises(ValueError):
Resources(cpu=4)
# -----------------------------------------------------------------------------
# The whole path, through a real worker
# -----------------------------------------------------------------------------
def test_a_declared_node_is_held_to_its_share(tmp_path):
"""Four nodes wanting two cores each, on a machine with four.
What is checked is the pair: never more than the machine has in flight at
once, and every one of them told what it was given — the two halves that
together are the oversubscription this is for. Also that it does not
deadlock, since the claim is taken before a worker slot and both block.
"""
import sys
from fluksio.flow.controller import FlowController, RunContext
from fluksio.flow.messages import DType, MessageSpec
from fluksio.flow.schemas import FlowDef
from fluksio.flow.state import MemoryState
from fluksio.flow.store import FlowStore
from fluksio.flow.workers import PythonWorkerPool
store = FlowStore(tmp_path / "flows")
store.write_flow(
FlowDef(
name="study",
mode="batch",
nodes=[
NodeDef(
id="fit",
provides=[MessageSpec(name="threads", dtype=DType.INT)],
resources=Resources(cpus=2, env={"XLA_FLAGS": "--x=false"}),
)
],
)
)
store.write_node_source(
"study",
"fit",
"import os, time\n\n\ndef process():\n"
" time.sleep(0.2)\n"
" return {'threads': int(os.environ['OMP_NUM_THREADS'])}\n",
)
pool = PythonWorkerPool(python=sys.executable, size=4)
pool.start()
accountant = ResourceAccountant(cpus=4)
controller = FlowController(store, workers=pool, resources=accountant)
answers: list[object] = []
in_flight: list[int] = []
def once(index: int) -> None:
pipeline = controller.build_run_pipeline(
store.read_flow("study"),
state=MemoryState(),
run=RunContext(run_id=f"r{index}"),
)
pipeline.run({})
answers.append(pipeline.state.get("study.threads"))
def watch(until: threading.Event) -> None:
while not until.is_set():
in_flight.append(4 - int(accountant.snapshot()["cpus"]["free"]))
time.sleep(0.01)
finished = threading.Event()
watcher = threading.Thread(target=watch, args=(finished,))
watcher.start()
threads = [threading.Thread(target=once, args=(i,)) for i in range(4)]
try:
for thread in threads:
thread.start()
for thread in threads:
thread.join(timeout=60)
assert not thread.is_alive(), "a claim and a worker slot deadlocked"
finally:
finished.set()
watcher.join(timeout=5)
pool.stop()
assert answers == [2, 2, 2, 2]
assert max(in_flight) <= 4
assert accountant.snapshot()["cpus"]["free"] == 4
# One environment, so one extra pool however many nodes derived it.
assert len(pool._children) == 1
backend/tests/flow/test_runs.py
+28 -1
View File
@@ -19,9 +19,10 @@ from fluksio.flow.runs import (
collect_result,
digest_of,
required_labels,
required_resources,
seed_values,
)
from fluksio.flow.schemas import FlowDef, FlowInput, NodeDef
from fluksio.flow.schemas import FlowDef, FlowInput, NodeDef, Resources
from fluksio.flow.state import MemoryState
@@ -365,6 +366,32 @@ def test_a_preferred_device_does_not_hold_a_run_back():
assert required_labels(flow) == []
def test_a_device_on_a_node_no_worker_could_run_is_not_waited_for():
"""A connector is an entry point loaded here, so a worker cannot take it.
Holding the run for one is a run that never starts — and it looked exactly
like a GPU box somebody had forgotten to turn on.
"""
flow = double_flow()
flow.nodes[0].type = "mqtt"
flow.nodes[0].device = "gpu"
assert required_labels(flow) == []
def test_what_a_run_needs_is_the_largest_single_machine_it_asks_for():
flow = double_flow()
assert required_resources(flow) is None
flow.nodes[0].resources = Resources(cpus=2, gpus=1)
flow.nodes.append(NodeDef(id="fit", resources=Resources(cpus=8)))
assert required_resources(flow) == {
"cpus": 8,
"gpus": 1,
"ram_mb": 0,
"device": "",
}
def test_a_runs_seed_fills_an_input_of_that_name():
flow = double_flow()
flow.inputs.append(FlowInput(spec=spec("seed", DType.INT), initial=0))