mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-08 14:02:55 +00:00
b6ec11ad78
## Problem To test sharding, we need something to control it. We could write python code for doing this from the test runner, but this wouldn't be usable with neon_local run directly, and when we want to write tests with large number of shards/tenants, Rust is a better fit efficiently handling all the required state. This service enables automated tests to easily get a system with sharding/HA without the test itself having to set this all up by hand: existing tests can be run against sharded tenants just by setting a shard count when creating the tenant. ## Summary of changes Attachment service was previously a map of TenantId->TenantState, where the principal state stored for each tenant was the generation and the last attached pageserver. This enabled it to serve the re-attach and validate requests that the pageserver requires. In this PR, the scope of the service is extended substantially to do overall management of tenants in the pageserver, including tenant/timeline creation, live migration, evacuation of offline pageservers etc. This is done using synchronous code to make declarative changes to the tenant's intended state (`TenantState.policy` and `TenantState.intent`), which are then translated into calls into the pageserver by the `Reconciler`. Top level summary of modules within `control_plane/attachment_service/src`: - `tenant_state`: structure that represents one tenant shard. - `service`: implements the main high level such as tenant/timeline creation, marking a node offline, etc. - `scheduler`: for operations that need to pick a pageserver for a tenant, construct a scheduler and call into it. - `compute_hook`: receive notifications when a tenant shard is attached somewhere new. Once we have locations for all the shards in a tenant, emit an update to postgres configuration via the neon_local `LocalEnv`. - `http`: HTTP stubs. These mostly map to methods on `Service`, but are separated for readability and so that it'll be easier to adapt if/when we switch to another RPC layer. - `node`: structure that describes a pageserver node. The most important attribute of a node is its availability: marking a node offline causes tenant shards to reschedule away from it. This PR is a precursor to implementing the full sharding service for prod (#6342). What's the difference between this and a production-ready controller for pageservers? - JSON file persistence to be replaced with a database - Limited observability. - No concurrency limits. Marking a pageserver offline will try and migrate every tenant to a new pageserver concurrently, even if there are thousands. - Very simple scheduler that only knows to pick the pageserver with fewest tenants, and place secondary locations on a different pageserver than attached locations: it does not try to place shards for the same tenant on different pageservers. This matters little in tests, because picking the least-used pageserver usually results in round-robin placement. - Scheduler state is rebuilt exhaustively for each operation that requires a scheduler. - Relies on neon_local mechanisms for updating postgres: in production this would be something that flows through the real control plane. --------- Co-authored-by: Arpad Müller <arpad-m@users.noreply.github.com>
288 lines
9.0 KiB
TOML
288 lines
9.0 KiB
TOML
[workspace]
|
|
resolver = "2"
|
|
members = [
|
|
"compute_tools",
|
|
"control_plane",
|
|
"control_plane/attachment_service",
|
|
"pageserver",
|
|
"pageserver/ctl",
|
|
"pageserver/client",
|
|
"pageserver/pagebench",
|
|
"proxy",
|
|
"safekeeper",
|
|
"storage_broker",
|
|
"s3_scrubber",
|
|
"workspace_hack",
|
|
"trace",
|
|
"libs/compute_api",
|
|
"libs/pageserver_api",
|
|
"libs/postgres_ffi",
|
|
"libs/safekeeper_api",
|
|
"libs/utils",
|
|
"libs/consumption_metrics",
|
|
"libs/postgres_backend",
|
|
"libs/pq_proto",
|
|
"libs/tenant_size_model",
|
|
"libs/metrics",
|
|
"libs/postgres_connection",
|
|
"libs/remote_storage",
|
|
"libs/tracing-utils",
|
|
"libs/postgres_ffi/wal_craft",
|
|
"libs/vm_monitor",
|
|
"libs/walproposer",
|
|
]
|
|
|
|
[workspace.package]
|
|
edition = "2021"
|
|
license = "Apache-2.0"
|
|
|
|
## All dependency versions, used in the project
|
|
[workspace.dependencies]
|
|
anyhow = { version = "1.0", features = ["backtrace"] }
|
|
arc-swap = "1.6"
|
|
async-compression = { version = "0.4.0", features = ["tokio", "gzip", "zstd"] }
|
|
azure_core = "0.18"
|
|
azure_identity = "0.18"
|
|
azure_storage = "0.18"
|
|
azure_storage_blobs = "0.18"
|
|
flate2 = "1.0.26"
|
|
async-stream = "0.3"
|
|
async-trait = "0.1"
|
|
aws-config = { version = "1.0", default-features = false, features=["rustls"] }
|
|
aws-sdk-s3 = "1.0"
|
|
aws-smithy-async = { version = "1.0", default-features = false, features=["rt-tokio"] }
|
|
aws-smithy-types = "1.0"
|
|
aws-credential-types = "1.0"
|
|
axum = { version = "0.6.20", features = ["ws"] }
|
|
base64 = "0.13.0"
|
|
bincode = "1.3"
|
|
bindgen = "0.65"
|
|
bstr = "1.0"
|
|
byteorder = "1.4"
|
|
bytes = "1.0"
|
|
camino = "1.1.6"
|
|
cfg-if = "1.0.0"
|
|
chrono = { version = "0.4", default-features = false, features = ["clock"] }
|
|
clap = { version = "4.0", features = ["derive"] }
|
|
close_fds = "0.3.2"
|
|
comfy-table = "6.1"
|
|
const_format = "0.2"
|
|
crc32c = "0.6"
|
|
crossbeam-utils = "0.8.5"
|
|
dashmap = { version = "5.5.0", features = ["raw-api"] }
|
|
either = "1.8"
|
|
enum-map = "2.4.2"
|
|
enumset = "1.0.12"
|
|
fail = "0.5.0"
|
|
fs2 = "0.4.3"
|
|
futures = "0.3"
|
|
futures-core = "0.3"
|
|
futures-util = "0.3"
|
|
git-version = "0.3"
|
|
hashbrown = "0.13"
|
|
hashlink = "0.8.1"
|
|
hdrhistogram = "7.5.2"
|
|
hex = "0.4"
|
|
hex-literal = "0.4"
|
|
hmac = "0.12.1"
|
|
hostname = "0.3.1"
|
|
http-types = { version = "2", default-features = false }
|
|
humantime = "2.1"
|
|
humantime-serde = "1.1.1"
|
|
hyper = "0.14"
|
|
hyper-tungstenite = "0.11"
|
|
inotify = "0.10.2"
|
|
ipnet = "2.9.0"
|
|
itertools = "0.10"
|
|
jsonwebtoken = "9"
|
|
libc = "0.2"
|
|
md5 = "0.7.0"
|
|
memoffset = "0.8"
|
|
native-tls = "0.2"
|
|
nix = "0.26"
|
|
notify = "5.0.0"
|
|
num_cpus = "1.15"
|
|
num-traits = "0.2.15"
|
|
once_cell = "1.13"
|
|
opentelemetry = "0.19.0"
|
|
opentelemetry-otlp = { version = "0.12.0", default_features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
|
|
opentelemetry-semantic-conventions = "0.11.0"
|
|
parking_lot = "0.12"
|
|
parquet = { version = "49.0.0", default-features = false, features = ["zstd"] }
|
|
parquet_derive = "49.0.0"
|
|
pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
|
|
pin-project-lite = "0.2"
|
|
prometheus = {version = "0.13", default_features=false, features = ["process"]} # removes protobuf dependency
|
|
prost = "0.11"
|
|
rand = "0.8"
|
|
redis = { version = "0.24.0", features = ["tokio-rustls-comp", "keep-alive"] }
|
|
regex = "1.10.2"
|
|
reqwest = { version = "0.11", default-features = false, features = ["rustls-tls"] }
|
|
reqwest-tracing = { version = "0.4.0", features = ["opentelemetry_0_19"] }
|
|
reqwest-middleware = "0.2.0"
|
|
reqwest-retry = "0.2.2"
|
|
routerify = "3"
|
|
rpds = "0.13"
|
|
rustc-hash = "1.1.0"
|
|
rustls = "0.21"
|
|
rustls-pemfile = "1"
|
|
rustls-split = "0.3"
|
|
scopeguard = "1.1"
|
|
sysinfo = "0.29.2"
|
|
sd-notify = "0.4.1"
|
|
sentry = { version = "0.31", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
|
|
serde = { version = "1.0", features = ["derive"] }
|
|
serde_json = "1"
|
|
serde_path_to_error = "0.1"
|
|
serde_with = "2.0"
|
|
serde_assert = "0.5.0"
|
|
sha2 = "0.10.2"
|
|
signal-hook = "0.3"
|
|
smallvec = "1.11"
|
|
smol_str = { version = "0.2.0", features = ["serde"] }
|
|
socket2 = "0.5"
|
|
strum = "0.24"
|
|
strum_macros = "0.24"
|
|
svg_fmt = "0.4.1"
|
|
sync_wrapper = "0.1.2"
|
|
tar = "0.4"
|
|
task-local-extensions = "0.1.4"
|
|
test-context = "0.1"
|
|
thiserror = "1.0"
|
|
tls-listener = { version = "0.7", features = ["rustls", "hyper-h1"] }
|
|
tokio = { version = "1.17", features = ["macros"] }
|
|
tokio-io-timeout = "1.2.0"
|
|
tokio-postgres-rustls = "0.10.0"
|
|
tokio-rustls = "0.24"
|
|
tokio-stream = "0.1"
|
|
tokio-tar = "0.3"
|
|
tokio-util = { version = "0.7.10", features = ["io", "rt"] }
|
|
toml = "0.7"
|
|
toml_edit = "0.19"
|
|
tonic = {version = "0.9", features = ["tls", "tls-roots"]}
|
|
tracing = "0.1"
|
|
tracing-error = "0.2.0"
|
|
tracing-opentelemetry = "0.19.0"
|
|
tracing-subscriber = { version = "0.3", default_features = false, features = ["smallvec", "fmt", "tracing-log", "std", "env-filter", "json"] }
|
|
url = "2.2"
|
|
uuid = { version = "1.6.1", features = ["v4", "v7", "serde"] }
|
|
walkdir = "2.3.2"
|
|
webpki-roots = "0.25"
|
|
x509-parser = "0.15"
|
|
|
|
## TODO replace this with tracing
|
|
env_logger = "0.10"
|
|
log = "0.4"
|
|
|
|
## Libraries from neondatabase/ git forks, ideally with changes to be upstreamed
|
|
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch="neon" }
|
|
postgres-native-tls = { git = "https://github.com/neondatabase/rust-postgres.git", branch="neon" }
|
|
postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", branch="neon" }
|
|
postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", branch="neon" }
|
|
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch="neon" }
|
|
|
|
## Other git libraries
|
|
heapless = { default-features=false, features=[], git = "https://github.com/japaric/heapless.git", rev = "644653bf3b831c6bb4963be2de24804acf5e5001" } # upstream release pending
|
|
|
|
## Local libraries
|
|
compute_api = { version = "0.1", path = "./libs/compute_api/" }
|
|
consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
|
|
metrics = { version = "0.1", path = "./libs/metrics/" }
|
|
pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
|
|
pageserver_client = { path = "./pageserver/client" }
|
|
postgres_backend = { version = "0.1", path = "./libs/postgres_backend/" }
|
|
postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
|
|
postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
|
|
pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
|
|
remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
|
|
safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
|
|
storage_broker = { version = "0.1", path = "./storage_broker/" } # Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
|
|
tenant_size_model = { version = "0.1", path = "./libs/tenant_size_model/" }
|
|
tracing-utils = { version = "0.1", path = "./libs/tracing-utils/" }
|
|
utils = { version = "0.1", path = "./libs/utils/" }
|
|
vm_monitor = { version = "0.1", path = "./libs/vm_monitor/" }
|
|
walproposer = { version = "0.1", path = "./libs/walproposer/" }
|
|
|
|
## Common library dependency
|
|
workspace_hack = { version = "0.1", path = "./workspace_hack/" }
|
|
|
|
## Build dependencies
|
|
criterion = "0.5.1"
|
|
rcgen = "0.11"
|
|
rstest = "0.18"
|
|
camino-tempfile = "1.0.2"
|
|
tonic-build = "0.9"
|
|
|
|
[patch.crates-io]
|
|
|
|
# This is only needed for proxy's tests.
|
|
# TODO: we should probably fork `tokio-postgres-rustls` instead.
|
|
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch="neon" }
|
|
|
|
# bug fixes for UUID
|
|
parquet = { git = "https://github.com/neondatabase/arrow-rs", branch = "neon-fix-bugs" }
|
|
parquet_derive = { git = "https://github.com/neondatabase/arrow-rs", branch = "neon-fix-bugs" }
|
|
|
|
################# Binary contents sections
|
|
|
|
[profile.release]
|
|
# This is useful for profiling and, to some extent, debug.
|
|
# Besides, debug info should not affect the performance.
|
|
debug = true
|
|
|
|
# disable debug symbols for all packages except this one to decrease binaries size
|
|
[profile.release.package."*"]
|
|
debug = false
|
|
|
|
[profile.release-line-debug]
|
|
inherits = "release"
|
|
debug = 1 # true = 2 = all symbols, 1 = line only
|
|
[profile.release-line-debug-lto]
|
|
inherits = "release"
|
|
debug = 1 # true = 2 = all symbols, 1 = line only
|
|
lto = true
|
|
|
|
[profile.release-line-debug-size]
|
|
inherits = "release"
|
|
debug = 1 # true = 2 = all symbols, 1 = line only
|
|
opt-level = "s"
|
|
[profile.release-line-debug-zize]
|
|
inherits = "release"
|
|
debug = 1 # true = 2 = all symbols, 1 = line only
|
|
opt-level = "z"
|
|
[profile.release-line-debug-size-lto]
|
|
inherits = "release"
|
|
debug = 1 # true = 2 = all symbols, 1 = line only
|
|
opt-level = "s"
|
|
lto = true
|
|
[profile.release-line-debug-zize-lto]
|
|
inherits = "release"
|
|
debug = 1 # true = 2 = all symbols, 1 = line only
|
|
opt-level = "z"
|
|
lto = true
|
|
|
|
[profile.release-no-debug]
|
|
inherits = "release"
|
|
debug = false # true = 2 = all symbols, 1 = line only
|
|
|
|
[profile.release-no-debug-size]
|
|
inherits = "release"
|
|
debug = false # true = 2 = all symbols, 1 = line only
|
|
opt-level = "s"
|
|
[profile.release-no-debug-zize]
|
|
inherits = "release"
|
|
debug = false # true = 2 = all symbols, 1 = line only
|
|
opt-level = "z"
|
|
|
|
[profile.release-no-debug-size-lto]
|
|
inherits = "release"
|
|
debug = false # true = 2 = all symbols, 1 = line only
|
|
opt-level = "s"
|
|
lto = true
|
|
|
|
[profile.release-no-debug-zize-lto]
|
|
inherits = "release"
|
|
debug = false # true = 2 = all symbols, 1 = line only
|
|
opt-level = "z"
|
|
lto = true
|