llama.cpp's start-up output is read as a shard becomes ready: the devices it
used, its backend, and the layers it offloaded. That goes up with READY in a
new ShardStatus.compute, is kept on the shard, and is shown by the admin
API, ctl replicas (ON) and the console (COMPUTE). A shard given GPUs whose
engine says it found no usable GPU or offloaded no layer is stopped and
failed, even where nvidia-smi cannot be asked.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A reconcile pass that does something is a trace, with placement (where it
went, or every candidate turned down), scale-up/down, drain, stop, eviction,
preemption, reaping and restarts beneath it. A replica's start is a span open
from placement until it serves; the start command carries its context in a
new ControlMessage.trace field, and the agent continues the trace through
the weights fetch, engine launch, rendezvous and readiness wait. Stops,
drains, adoption and engine installs are traced on the node, model jobs are
a trace with a span per step linked to the replica's start, and agent.yaml
takes the same tracing block as server.yaml. Off, every span is the no-op one
and commands carry nothing.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A model's class (critical, standard, opportunistic; unset follows its
scaling) decides what may be stopped to make room for it: a lower class
for a higher, and within a class only what another grew into under load,
for a model below its minimum. Victims are tried on a copy of the
inventory and stopped only if they make the room. Preempted replicas are
drained with a short grace and their model is held back until the room is
used. ctl model resources and class move under ctl model.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
There was no way to restart a running replica. A running engine picks up an
engine key, an edited profile or a new engine version only when it starts,
so after v0.10.3 the nine replicas already running stayed without a key —
reachable from any node — with nothing to do about it short of draining
nodes, which on a small CPU fleet has nowhere to move a model to.
`llmgw ctl restart REPLICA... | --model M | --all` queues replicas to be
replaced. A replica being replaced keeps serving but stops counting toward
its model, so the reconciler places a replacement beside it; once that is
ready the old one is drained and stopped as a node drain would. Replicas of
one model go one at a time, so a model never needs the memory of every
replica twice. Where no second copy fits anywhere, the old replica is
stopped after the drain grace period and the new one starts in its place,
and the log says so, since that is the one case with an outage.
`ctl replicas` shows "(restart queued)" and "(restart replacing)" while it
happens.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Two defects, both of the same kind: something the CLI knew and the rest of
the system did not.
A profile can be edited while a replica is running against the old one. The
reconciler deliberately leaves it alone — churning a replica that is serving
costs more than the imperfection — but there was no way to see it, so the
cluster could disagree with its own configuration indefinitely and read as
healthy. Profile now carries a fingerprint, a replica records the one it was
placed with, and both the API and `ctl replicas` say "stale profile" when
they differ. An empty fingerprint is not stale: it means a replica adopted
from an older agent, which is unknown rather than wrong.
Adding a model from the admin page skipped the source check `ctl model add`
has done all along, so a typo or a mirror that is down became a replica
failing on a node minutes later, with an error naming the node. The check
moves out of the CLI into a package both use.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The agent has always logged a percentage as it fetches weights, with a comment
saying a replica pulling a hundred gigabytes and one that is wedged look
identical from the control plane. They still did: the log is on the node, and
the node is not where anyone is looking when a replica has been starting for
ten minutes.
Progress now rides on the shard status and appears under the replica in `ctl
replicas` — a line rather than a column, because most replicas are not
downloading anything and a column would be empty for all of them.
It is deliberately not a state transition. Treating each chunk as one would
re-mark the shard as starting on every report and reset the timer that decides
when a slow start has become a failed one, so an hour-long download would keep
a doomed replica alive indefinitely. It arrives on its own method for that
reason, and a real transition clears it — otherwise a finished download sits in
the listing at ninety-nine percent under a shard that has been serving for an
hour.
Watchers are keyed by source rather than by shard, because a fetch is
single-flight: eight shards starting together produce one download and all
eight are waiting on it.
No percentage is invented when the server sent no length. One that stops moving
is worse than a byte count that keeps rising, so the field is absent and the
listing says "so far".
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
On-demand loading worked right up to the moment the cluster was full and
then stopped meaning anything: the model somebody had just asked for could
not be placed, and the cards were held by a model nobody had asked for in an
hour. That is the only situation in which any of it matters.
Deliberately narrow. Only idle replicas of other on-demand models — a model
at min 1 is a promise that it stays up, and breaking it to serve a different
request would make every guarantee in the catalog conditional on load. Only
single-node replicas, since evicting a multi-node one frees several machines
and costs tens of minutes to rebuild. One at a time, because freeing
everything that qualifies would empty a cluster for a request that needed
one node. And never a replica with no reported usage: after a router restart
that is all of them, and unknown is not idle.
Writing the test found a gap the feature had rather than a bug in the test.
Two on-demand models on a cluster with room for one would take turns
evicting each other, at a model load per cycle — worse for both than one of
them waiting. A replica is now safe from eviction for a few minutes after it
starts serving, which bounds that.
Which in turn found a latent bug: deriveState stamped ReadyAt with
time.Now() inside a package that has an injectable clock, so the new
lifetime rule could not be tested at all — the fake clock said three minutes
and the wall clock said eight months. Invisible while nothing compared
ReadyAt to anything.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Two things a cluster with many nodes and many GPUs needs that were missing,
and they are the same thing seen from two distances.
Idle tracking. The control plane knew what was placed and whether it was
healthy, never whether anyone wanted it — so on a fleet with more models
than cards there was no way to answer the first question anyone asks, which
is what can I stop. The router is the only thing that knows, so it now
reports it: a timestamp written in Acquire, where a request already meets an
endpoint under a lock already held, and collected once a tick as a map. That
shape is the point. Per-request notification would be a firehose carrying
one bit — the newest timestamp wins — and this costs the same on four
replicas as on four hundred.
It travels through an interface in the direction opposite EndpointSink, for
the same reason that one exists: the control plane decides what should run,
the router knows whether anyone wants it, and neither should need to be in
the other's process to say so.
Unknown is kept distinct from idle throughout. A router that has just
restarted knows nothing, and a zero timestamp would be the oldest idle
replica in every comparison — so one restart would nominate an entire fleet
for eviction. Absent from the map, "-" in the table, negative in the JSON,
and IdleFor returns a second value rather than a duration anything could
act on by mistake.
ctl status. A per-node listing is right for four nodes and wrong for two
hundred: how full am I, what is broken, what is holding cards nobody is
using are aggregates, and reading them off a long table is a chore, which
means it gets skipped. Capacity per GPU class with usage bars, free whole
nodes per fabric — the number that decides whether a multi-node replica can
land, since free cards on the wrong fabric are not capacity for a model that
spans nodes — replica and model counts, models that cannot be placed, and
what has gone unasked-for. Derived from the same state the tables show, so
it cannot disagree with them.
Unhealthy GPUs count as neither used nor free, because counting them free is
how a cluster looks like it has room it does not.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
A replica spanning two nodes is reported by two agents, registering
separately about a second apart. Adoption assumed one call carried a whole
replica, so the first half was adopted with WantShards=2 and immediately
failed for "replica has 1 of 2 shards" — and when the second node
registered, its half was condemned as unclaimed because the replica was
already written off.
big-model therefore could not survive a control plane restart. Seen after
today's deploy: adopted, failed, both halves stopped, rebuilt from
scratch, backing off 9s, 20s, 38s, and never becoming ready. The first
reconcile tick also runs before any agent has reconnected, which is the
harmless-looking "no node reports a fabric" that precedes it.
Two changes. Adopt merges a group into a replica it is still assembling
instead of treating it as a competing claim, and takes the endpoint from
whichever group carries rank 0 — the leader's agent is not necessarily the
first to register. deriveState leaves a replica that is short of shards
while still assembling in Starting rather than Failed, which puts it under
the startup timeout that already exists: a sibling that never arrives
still fails, one second later than it used to rather than one second
before its sibling reports in. AdoptedAt is cleared once the replica is
whole, so losing a shard after that is a failure again.
The existing multi-node adoption test passed throughout, because it hands
both shards to a single Adopt call — which no caller makes. Same shape as
the agentsvc bug in c97b671: a test that calls the function under test
directly cannot tell you how the caller calls it. The new test registers
one node at a time, and fails without this change.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Restarting the control plane over a running two-node replica adopted half of
it. Every shard it still had was healthy, so it was reported Ready — with one
shard of two and no endpoint at all, because the missing one was rank 0. The
router was handed a replica nothing could route to.
The cause is that a replica had no idea how many shards it should have. It
could tell "every shard I have is ready" and nothing else, which is the same
sentence whether or not half of it is gone. It now carries the count from its
profile, set at placement and again at adoption, and a replica short of shards
fails rather than pretending.
Onboarding also wrote no engine paths, so a node onboarded by the script could
not find llama-server and failed every shard placed on it with "executable
file not found". The script now takes them, and says so when none are given —
a node with no engine paths can run the sim engine and nothing else.
The cluster now runs both at once: two-node simulated replicas on each fabric,
and real llama.cpp inference on the CPU, which is a better test bed than
either alone.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
`ctl bench` measures what a replica can actually serve, so weight,
target_waiting and kv_ceiling stop being numbers somebody typed. Concurrency
climbs until the SLO breaks and the last level that met it is the capacity:
peak throughput arrives long after latency has become unusable, so throughput
alone overstates what the hardware can serve. Queue depth and KV usage are
read from the engine while it is still meeting the target, which is exactly
what admission should treat as healthy.
Prompts are unique per request by default. With one repeated prompt the
engine's cache answers most of the prefill and the measurement describes the
cache rather than the hardware; --shared-prefix asks that question
deliberately, and it now produces byte-identical prompts, which the first
version did not — it dropped the random header and still picked words at
random, so the cache missed and the flag quietly measured the thing it exists
to avoid.
Running it against the cluster turned up two real defects:
A replica stuck in Starting never timed out. Every other way out of that state
needs the agent to report something, and when it never does the replica sits
there holding GPUs and counting towards the model's replica count while
serving nothing. Two of them had been like that for eight minutes past a
two-minute startup timeout, and nothing would ever have moved them.
They were stuck because adoption lost to a replica we had only placed. Replica
ids come from the model name and a counter, so a control plane that restarts
and places before its agents reconnect builds a different replica under the
same id on a freshly allocated port; the agent's report of the engine that was
actually serving was then discarded as already-known. The cluster pointed at
port 20004 while the engine answered on 20000. The fleet is authoritative
about what is running, so what we merely placed now loses to what an agent
reports — unless our copy has a shard that has actually come up, in which case
two things really are running and the stray is the one we did not ask for.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
ctl talks to a management API on the admin listener, not the client-facing one.
The two have different audiences: one serves inference to whoever holds an API
key, the other lets a caller cordon nodes and read the cluster's shape.
- nodes surfaces unhealthy GPUs and why they are excluded. That is usually the
answer when a node looks idle but nothing will schedule onto it, and it was
invisible before.
- explain-placement prints every candidate considered and why it was rejected.
- replicas shows the shards a replica is made of, with per-shard errors.
- cordon, uncordon and drain are one endpoint with different targets, because
the difference between cordon and drain is exactly what an operator needs to
be sure of before running either.
Draining had to be fixed first to make ctl drain worth having. A drained replica
was stopped on the next pass, which cuts in-flight requests — the thing draining
exists to avoid. Now a node marked Draining has its replicas drained, the model
falls below its desired count, a replacement is placed elsewhere, and the
original is stopped only once the replacement is serving. A grace period bounds
it, because draining the only node that can host a model would otherwise never
finish and the node could never be taken out of service.
Verified against a two-node cluster of real binaries: draining moved a replica
to the surviving node and traffic kept returning 200 throughout.
ctl logs is deliberately absent. It needs a request/response pair the agent
protocol does not have, and the failure path already ships an engine log tail
with every status report — so the case that matters most is covered, and
reading a healthy shard's output on demand is not worth a protocol change yet.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The desired-versus-actual loop, with a Dispatcher interface where the agent
stream will go. The loop's logic is where the interesting failures live, not the
transport, so it is tested against a fake dispatcher and a synthetic clock.
- catalog: models, profiles, aliases, fallbacks, scaling bounds. Aliases and
fallbacks resolve at load rather than at request time, because a typo in a
fallback should stop a deployment instead of surfacing during the outage when
the fallback is finally needed. The node/GPU/TP arithmetic is checked here
too, so a bad profile fails at config load rather than minutes into loading.
- reconciler: one replica placed per pass, since placement depends on what is
already allocated and several from one snapshot would be handed the same GPUs.
Workers start before rank 0: SGLang's ranks rendezvous and vLLM under Ray
needs its workers attached before the head serves.
- a failed shard fails the whole replica. The others are waiting on collectives
that will never complete while holding GPUs, so every shard is stopped and the
replica rebuilt, with a jittered exponential backoff carried on the model
rather than on the replica that was just destroyed.
- node expiry has two stages, Unreachable then Lost, deliberately far apart: a
network blip must not tear down replicas that are still serving, and
rebuilding a multi-node replica costs tens of minutes of model loading.
- scale-down drains before stopping, so in-flight requests finish.
The phase 3 exit criterion is half met. TestLostNodeMovesReplicas covers the
reconciliation half end to end. The router continuing to serve throughout needs
the EndpointSource wiring and the agent stream.
Writing the tests caught a real property of the design worth recording: advancing
the clock makes every node look silent, so placement correctly stops. The test
harness now heartbeats nodes as it advances time, except where a node going
silent is the point.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>