Files
LocalAI/core/config/distributed_config_test.go
T
Ettore Di Giacinto 7a205fbbba fix(cluster): pin the derived retention to the sweep that applies it
The retention a worker's departure is kept for is now derived from the
reconnect grace, so a purge can never outrun the window Presence measures
against. Nothing pinned that. The sweep could be reverted to pass the constant,
or the setter emptied out, and the suite stayed green either way: the specs
covered the arithmetic helper, and the fix is the wiring.

The loop now has a spec of its own. It departs two workers either side of the
difference between the floor and the derived retention, and the row that must
go is what witnesses the sweep running at all, so the row that must stay cannot
survive by nothing happening.

The default grace goes from 60s to 90s. Two of the worker's ceiling backoffs is
60s, but the failed dial between them costs its handshake timeout too, which
puts the worst case at 70s, and the backoff resets only after a session long
enough that a replica accepting a dial and then dying denies it. So the ceiling
is reachable exactly during the rolling restart this window exists for, and 60s
sat on the edge of it. Too short reports a live worker as gone and costs a
model reload; too long reaps a dead one later. The cheaper mistake is the long
one.

A held row whose owner is dead and whose stamp is stale is the state a rolling
upgrade actually produces, and it was the one state no spec built. It has an
answer now, and the two ways to get this wrong land either side of it: reading
the stamp first says gone, reading held-ness without the liveness join says
connected.

Two comments claimed more than the code did. There IS a grace at which a live
worker is reported as gone, which is the point of it being a duration; and the
switch that reads held-ness first is only a partial second gate, since with the
SQL gate gone and a dead owner it answers gone rather than reconnecting.

Assisted-by: Claude Opus 5 [claude-code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-09-20 03:05:34 +00:00

250 lines
9.9 KiB
Go

package config_test
import (
"time"
. "github.com/onsi/ginkgo/v2"
. "github.com/onsi/gomega"
"github.com/mudler/LocalAI/core/config"
)
var _ = Describe("DistributedConfig backend NATS timeouts", func() {
Context("BackendInstallTimeoutOrDefault", func() {
It("returns 15 minutes when unset", func() {
c := config.DistributedConfig{}
Expect(c.BackendInstallTimeoutOrDefault()).To(Equal(15 * time.Minute))
})
It("returns the configured value when set", func() {
c := config.DistributedConfig{BackendInstallTimeout: 42 * time.Minute}
Expect(c.BackendInstallTimeoutOrDefault()).To(Equal(42 * time.Minute))
})
})
Context("BackendUpgradeTimeoutOrDefault", func() {
It("returns 15 minutes when unset", func() {
c := config.DistributedConfig{}
Expect(c.BackendUpgradeTimeoutOrDefault()).To(Equal(15 * time.Minute))
})
It("returns the configured value when set", func() {
c := config.DistributedConfig{BackendUpgradeTimeout: 30 * time.Minute}
Expect(c.BackendUpgradeTimeoutOrDefault()).To(Equal(30 * time.Minute))
})
})
Context("ModelLoadTimeoutOrDefault", func() {
It("returns 5 minutes when unset so existing clusters keep today's behaviour", func() {
c := config.DistributedConfig{}
Expect(c.ModelLoadTimeoutOrDefault()).To(Equal(5 * time.Minute))
})
It("returns the configured value when set", func() {
c := config.DistributedConfig{ModelLoadTimeout: 45 * time.Minute}
Expect(c.ModelLoadTimeoutOrDefault()).To(Equal(45 * time.Minute))
})
})
})
// Heartbeat checkpointing makes last_heartbeat up to one checkpoint interval
// stale by design, which is why the threshold defaults to 5 minutes. An
// operator who widens the checkpoint has to widen this to match, so it has to
// be reachable from the CLI rather than being a compile-time constant.
var _ = Describe("DistributedConfig stale node threshold", func() {
It("defaults to 5 minutes, wide enough to cover a suppressed beat", func() {
Expect(config.DistributedConfig{}.StaleNodeThresholdOrDefault()).
To(Equal(5 * time.Minute))
Expect(config.DefaultStaleNodeThreshold).
To(BeNumerically(">", config.DefaultNodeHeartbeatCheckpoint),
"a threshold at or below the checkpoint interval marks healthy, "+
"beating nodes offline every cycle")
})
It("is configurable, so a widened checkpoint can be matched", func() {
o := config.NewApplicationConfig(config.WithStaleNodeThreshold(20 * time.Minute))
Expect(o.Distributed.StaleNodeThreshold).To(Equal(20 * time.Minute))
Expect(o.Distributed.StaleNodeThresholdOrDefault()).To(Equal(20 * time.Minute))
})
})
var _ = Describe("DistributedConfig flag-name constants", func() {
// Pin the kebab-case strings so a rename of the Go field name (or a
// CLI flag naming convention change) forces the constant to update,
// keeping the Validate error messages and any future operator-facing
// surface in sync with the actual CLI flag.
DescribeTable("flag name constants",
func(actual, expected string) {
Expect(actual).To(Equal(expected))
},
Entry("MCP tool timeout", config.FlagMCPToolTimeout, "mcp-tool-timeout"),
Entry("MCP discovery timeout", config.FlagMCPDiscoveryTimeout, "mcp-discovery-timeout"),
Entry("worker wait timeout", config.FlagWorkerWaitTimeout, "worker-wait-timeout"),
Entry("drain timeout", config.FlagDrainTimeout, "drain-timeout"),
Entry("health check interval", config.FlagHealthCheckInterval, "health-check-interval"),
Entry("stale node threshold", config.FlagStaleNodeThreshold, "stale-node-threshold"),
Entry("node heartbeat checkpoint", config.FlagNodeHeartbeatCheckpoint, "node-heartbeat-checkpoint"),
Entry("MCP CI job timeout", config.FlagMCPCIJobTimeout, "mcp-ci-job-timeout"),
Entry("backend install timeout", config.FlagBackendInstallTimeout, "backend-install-timeout"),
Entry("backend upgrade timeout", config.FlagBackendUpgradeTimeout, "backend-upgrade-timeout"),
Entry("model load timeout", config.FlagModelLoadTimeout, "model-load-timeout"),
)
})
var _ = Describe("DistributedConfig.Validate negative-duration errors", func() {
It("rejects a negative BackendInstallTimeout with the flag name in the error", func() {
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
BackendInstallTimeout: -1 * time.Second,
}
err := c.Validate()
Expect(err).To(HaveOccurred())
Expect(err.Error()).To(ContainSubstring(config.FlagBackendInstallTimeout))
Expect(err.Error()).To(ContainSubstring("must not be negative"))
})
It("rejects a negative BackendUpgradeTimeout with the flag name in the error", func() {
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
BackendUpgradeTimeout: -1 * time.Second,
}
err := c.Validate()
Expect(err).To(HaveOccurred())
Expect(err.Error()).To(ContainSubstring(config.FlagBackendUpgradeTimeout))
})
It("rejects a negative ModelLoadTimeout with the flag name in the error", func() {
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
ModelLoadTimeout: -1 * time.Second,
}
err := c.Validate()
Expect(err).To(HaveOccurred())
Expect(err.Error()).To(ContainSubstring(config.FlagModelLoadTimeout))
Expect(err.Error()).To(ContainSubstring("must not be negative"))
})
It("accepts all-zero durations as valid (defaults apply)", func() {
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
}
Expect(c.Validate()).To(Succeed())
})
})
var _ = Describe("DistributedConfig.Validate registration auth", func() {
It("rejects an empty registration token when RequireAuth is set", func() {
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
RegistrationRequireAuth: true,
}
err := c.Validate()
Expect(err).To(HaveOccurred())
Expect(err.Error()).To(ContainSubstring("LOCALAI_REGISTRATION_REQUIRE_AUTH"))
Expect(err.Error()).To(ContainSubstring("LOCALAI_REGISTRATION_TOKEN"))
})
It("accepts a set registration token when RequireAuth is set", func() {
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
RegistrationToken: "s3cret",
RegistrationRequireAuth: true,
}
Expect(c.Validate()).To(Succeed())
})
It("warns but succeeds with an empty token when RequireAuth is unset", func() {
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
}
Expect(c.Validate()).To(Succeed())
})
It("rejects an empty token when the umbrella RequireAuth is set", func() {
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
RequireAuth: true,
// Provide NATS creds so only the registration-token gap remains.
NatsServiceJWT: "jwt",
NatsServiceSeed: "seed",
NatsAccountSeed: "acct",
}
err := c.Validate()
Expect(err).To(HaveOccurred())
Expect(err.Error()).To(ContainSubstring("LOCALAI_DISTRIBUTED_REQUIRE_AUTH"))
Expect(err.Error()).To(ContainSubstring("LOCALAI_REGISTRATION_TOKEN"))
})
It("the umbrella implies NATS auth is required", func() {
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
RegistrationToken: "tok", // registration layer satisfied
RequireAuth: true, // umbrella → NATS creds now required
}
Expect(c.NatsAuthRequired()).To(BeTrue())
Expect(c.RegistrationAuthRequired()).To(BeTrue())
// Missing NATS service JWT/seed must now be fatal.
err := c.Validate()
Expect(err).To(HaveOccurred())
Expect(err.Error()).To(ContainSubstring("LOCALAI_NATS_REQUIRE_AUTH"))
})
})
var _ = Describe("DistributedConfig worker reconnect grace", func() {
It("defaults clear of two ceiling backoffs plus the dial between them", func() {
// The worker's own numbers (core/services/worker/tunnel.go): a 30s
// backoff ceiling and a 10s dial budget, so two ceiling waits with a
// hung dial between them puts the worker back at 70s. 60s would sit
// under that and condemn a worker reconnecting exactly as designed;
// 90s clears it with margin.
Expect(config.DistributedConfig{}.ReconnectGraceOrDefault()).To(Equal(90 * time.Second))
Expect(config.DefaultWorkerReconnectGrace).To(BeNumerically(">", 70*time.Second),
"the default must clear two ceiling backoffs plus one handshake timeout")
})
It("takes a configured worker reconnect grace verbatim", func() {
cfg := config.DistributedConfig{WorkerReconnectGrace: 5 * time.Minute}
Expect(cfg.ReconnectGraceOrDefault()).To(Equal(5 * time.Minute))
})
It("falls back to the default rather than condemning every worker on a negative value", func() {
// A negative grace makes every departure older than the window the
// instant it is stamped, which reports a worker that has been gone for
// two seconds as GONE, and gone is the one value a caller may reap on.
cfg := config.DistributedConfig{WorkerReconnectGrace: -1 * time.Second}
Expect(cfg.ReconnectGraceOrDefault()).To(Equal(config.DefaultWorkerReconnectGrace))
})
It("refuses to start on a negative grace rather than reaping on it", func() {
// The flag is in Validate's negative-duration table, and this is what
// says so. A negative grace makes every departure older than the window
// the instant it is stamped, so the deployment would answer GONE for
// every worker that has ever lost a tunnel, and gone is the one answer
// a caller may reap and evict on.
c := config.DistributedConfig{
Enabled: true,
NatsURL: "nats://localhost:4222",
RegistrationToken: "tok",
WorkerReconnectGrace: -1 * time.Second,
}
err := c.Validate()
Expect(err).To(HaveOccurred())
Expect(err.Error()).To(ContainSubstring(config.FlagWorkerReconnectGrace))
})
It("is settable through the application option", func() {
o := &config.ApplicationConfig{}
config.WithWorkerReconnectGrace(90 * time.Second)(o)
Expect(o.Distributed.ReconnectGraceOrDefault()).To(Equal(90 * time.Second))
})
})