Zachery Aaron Shores-Chmielewski
ae9ca3bcf3
Promote pipeline-parallel-inference to a first-class app and consolidate observability on the datastream wire, decoupling the dashboard crate from `distribution`. - apps/pipeline-parallel-inference: move the example out of `examples/` into `apps/` as its own workspace, rename binaries to `pp-worker`/`pp-orchestrator`, and strip release binaries - cluster: add `ClusterNode`, a synchronous facade over the actorized distribution protocol (IrohDriver + per-node Runtime hosting Swim/Registry/Metadata/Directory actors with a `MembershipFanout`), replacing ad-hoc `driver.node()`/`tick()` call sites - fleet: add per-node fleet telemetry that ships identity/resource records as `DatastreamFrame`s over the cluster transport to the orchestrator's `DatastreamSink`, folded into a `FleetView` on a 3s tick - provision: add best-effort, opt-in SSH boot-phase telemetry (`PP_DEPLOY_KEY`) that streams rented-node boot logs onto the orchestrator's datastream as `proc.boot.<stage>.*` - dashboard: rewire the crate dependency from `distribution` to `datastream`, drop the standalone `swactor-datastream-dashboard` binary, and rewrite `datastream_source.rs` to demux per-node frames into Overview/Distribution/Fleet views with live-node TTL filtering - distribution: refresh dist/netmap plugin copy and README from "Kademlia routing" to gossip-directory terminology Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
53 lines
2 KiB
TOML
53 lines
2 KiB
TOML
[package]
|
|
name = "distribution"
|
|
version = "0.1.0"
|
|
edition = "2024"
|
|
|
|
[features]
|
|
default = []
|
|
# `dep:iroh-relay` is pulled in here (with only the empty `test-utils` feature)
|
|
# so the client side can name `CaRootsConfig::insecure_skip_verify()` for a
|
|
# custom relay's self-signed QAD cert. iroh already depends on iroh-relay
|
|
# transitively, so this adds no real weight — it only flips the cfg gate.
|
|
iroh = ["dep:iroh", "dep:tokio", "dep:iroh-metrics", "dep:iroh-relay", "tokio/time"]
|
|
relay = [
|
|
"iroh",
|
|
# The standalone relay binary additionally needs the (heavy) server side.
|
|
"iroh-relay/server",
|
|
"tokio/macros",
|
|
"tokio/signal",
|
|
"tokio/time",
|
|
]
|
|
|
|
[dependencies]
|
|
swactor = { path = "../..", features = ["serde", "transport"] }
|
|
swactor-transport = { path = "../transport" }
|
|
datastream = { path = "../datastream" }
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
uuid = { version = "1", features = ["v4", "serde"] }
|
|
iroh = { version = "0.98", optional = true }
|
|
# `test-utils` (an empty feature) exposes two cfg-gated APIs we rely on:
|
|
# - client: `CaRootsConfig::insecure_skip_verify()` (trust a custom relay's
|
|
# self-signed QAD cert) — needs only `test-utils`.
|
|
# - relay binary: `server::testing::self_signed_tls_certs_and_config()` for
|
|
# the QAD cert — needs `test-utils` + `server` (the latter via the `relay`
|
|
# feature). Using the helper keeps the `rustls::ServerConfig` version in
|
|
# lockstep with what `QuicConfig` expects.
|
|
iroh-relay = { version = "0.98", features = ["test-utils"], optional = true }
|
|
iroh-metrics = { version = "0.38", optional = true }
|
|
tokio = { version = "1", features = ["rt-multi-thread"], optional = true }
|
|
|
|
[target.'cfg(target_os = "linux")'.dependencies]
|
|
libc = "0.2"
|
|
|
|
[dev-dependencies]
|
|
serde_json = "1"
|
|
proptest = "1"
|
|
iroh-relay = { version = "0.98", features = ["server", "test-utils"] }
|
|
tokio = { version = "1", features = ["rt-multi-thread", "macros", "net", "io-util", "time"] }
|
|
|
|
[[bin]]
|
|
name = "swactor-iroh-relay"
|
|
path = "src/bin/swactor-iroh-relay.rs"
|
|
required-features = ["relay"]
|