Files
neon/Cargo.toml
Erik Grinaker 65addfc524 storcon: add per-tenant rate limiting for API requests (#10924)
## Problem

Incoming requests often take the service lock, and sometimes even do
database transactions. That creates a risk that a rogue client can
starve the controller of the ability to do its primary job of
reconciling tenants to an available state.

## Summary of changes

* Use the `governor` crate to rate limit tenant requests at 10 requests
per second. This is ~10-100x lower than the worst "attack" we've seen
from a client bug. Admin APIs are not rate limited.
* Add a `storage_controller_http_request_rate_limited` histogram for
rate limited requests.
* Log a warning every 10 seconds for rate limited tenants.

The rate limiter is parametrized on TenantId, because the kinds of
client bug we're protecting against generally happen within tenant
scope, and the rates should be somewhat stable: we expect the global
rate of requests to increase as we do more work, but we do not expect
the rate of requests to one tenant to increase.

---------

Co-authored-by: John Spray <john@neon.tech>
2025-03-03 22:04:59 +00:00

343 lines
12 KiB
TOML

[workspace]
resolver = "2"
members = [
"compute_tools",
"control_plane",
"control_plane/storcon_cli",
"pageserver",
"pageserver/compaction",
"pageserver/ctl",
"pageserver/client",
"pageserver/pagebench",
"proxy",
"safekeeper",
"safekeeper/client",
"storage_broker",
"storage_controller",
"storage_controller/client",
"storage_scrubber",
"workspace_hack",
"libs/compute_api",
"libs/http-utils",
"libs/pageserver_api",
"libs/postgres_ffi",
"libs/safekeeper_api",
"libs/desim",
"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",
"libs/wal_decoder",
"libs/postgres_initdb",
"libs/proxy/postgres-protocol2",
"libs/proxy/postgres-types2",
"libs/proxy/tokio-postgres2",
]
[workspace.package]
edition = "2024"
license = "Apache-2.0"
## All dependency versions, used in the project
[workspace.dependencies]
ahash = "0.8"
anyhow = { version = "1.0", features = ["backtrace"] }
arc-swap = "1.6"
async-compression = { version = "0.4.0", features = ["tokio", "gzip", "zstd"] }
atomic-take = "1.1.0"
backtrace = "0.3.74"
flate2 = "1.0.26"
assert-json-diff = "2"
async-stream = "0.3"
async-trait = "0.1"
aws-config = { version = "1.5", default-features = false, features=["rustls", "sso"] }
aws-sdk-s3 = "1.52"
aws-sdk-iam = "1.46.0"
aws-sdk-kms = "1.47.0"
aws-smithy-async = { version = "1.2.1", default-features = false, features=["rt-tokio"] }
aws-smithy-types = "1.2"
aws-credential-types = "1.2.0"
aws-sigv4 = { version = "1.2", features = ["sign-http"] }
aws-types = "1.3"
axum = { version = "0.8.1", features = ["ws"] }
base64 = "0.13.0"
bincode = "1.3"
bindgen = "0.71"
bit_field = "0.10.2"
bstr = "1.0"
byteorder = "1.4"
bytes = "1.9"
camino = "1.1.6"
cfg-if = "1.0.0"
cron = "0.15"
chrono = { version = "0.4", default-features = false, features = ["clock"] }
clap = { version = "4.0", features = ["derive", "env"] }
clashmap = { version = "1.0", features = ["raw-api"] }
comfy-table = "7.1"
const_format = "0.2"
crc32c = "0.6"
diatomic-waker = { version = "0.2.3" }
either = "1.8"
enum-map = "2.4.2"
enumset = "1.0.12"
fail = "0.5.0"
fallible-iterator = "0.2"
framed-websockets = { version = "0.1.0", git = "https://github.com/neondatabase/framed-websockets" }
futures = "0.3"
futures-core = "0.3"
futures-util = "0.3"
git-version = "0.3"
governor = "0.8"
hashbrown = "0.14"
hashlink = "0.9.1"
hdrhistogram = "7.5.2"
hex = "0.4"
hex-literal = "0.4"
hmac = "0.12.1"
hostname = "0.4"
http = {version = "1.1.0", features = ["std"]}
http-types = { version = "2", default-features = false }
http-body-util = "0.1.2"
humantime = "2.1"
humantime-serde = "1.1.1"
hyper0 = { package = "hyper", version = "0.14" }
hyper = "1.4"
hyper-util = "0.1"
tokio-tungstenite = "0.21.0"
indexmap = "2"
indoc = "2"
inferno = "0.12.0"
ipnet = "2.10.0"
itertools = "0.10"
itoa = "1.0.11"
jemalloc_pprof = "0.6"
jsonwebtoken = "9"
lasso = "0.7"
libc = "0.2"
md5 = "0.7.0"
measured = { version = "0.0.22", features=["lasso"] }
measured-process = { version = "0.0.22" }
memoffset = "0.9"
nix = { version = "0.27", features = ["dir", "fs", "process", "socket", "signal", "poll"] }
notify = "8.0.0"
num_cpus = "1.15"
num-traits = "0.2.15"
once_cell = "1.13"
opentelemetry = "0.27"
opentelemetry_sdk = "0.27"
opentelemetry-otlp = { version = "0.27", default-features = false, features = ["http-proto", "trace", "http", "reqwest-client"] }
opentelemetry-semantic-conventions = "0.27"
parking_lot = "0.12"
parquet = { version = "53", default-features = false, features = ["zstd"] }
parquet_derive = "53"
pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
pin-project-lite = "0.2"
pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "protobuf", "protobuf-codec"] }
procfs = "0.16"
prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
prost = "0.13"
rand = "0.8"
redis = { version = "0.25.2", features = ["tokio-rustls-comp", "keep-alive"] }
regex = "1.10.2"
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls"] }
reqwest-tracing = { version = "0.5", features = ["opentelemetry_0_27"] }
reqwest-middleware = "0.4"
reqwest-retry = "0.7"
routerify = "3"
rpds = "0.13"
rustc-hash = "1.1.0"
rustls = { version = "0.23.16", default-features = false }
rustls-pemfile = "2"
scopeguard = "1.1"
sysinfo = "0.29.2"
sd-notify = "0.4.1"
send-future = "0.1.0"
sentry = { version = "0.32", 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 = { version = "2.0", features = [ "base64" ] }
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 = "0.26"
strum_macros = "0.26"
"subtle" = "2.5.0"
svg_fmt = "0.4.3"
sync_wrapper = "0.1.2"
tar = "0.4"
test-context = "0.3"
thiserror = "1.0"
tikv-jemallocator = { version = "0.6", features = ["profiling", "stats", "unprefixed_malloc_on_supported_platforms"] }
tikv-jemalloc-ctl = { version = "0.6", features = ["stats"] }
tokio = { version = "1.41", features = ["macros"] }
tokio-epoll-uring = { git = "https://github.com/neondatabase/tokio-epoll-uring.git" , branch = "main" }
tokio-io-timeout = "1.2.0"
tokio-postgres-rustls = "0.12.0"
tokio-rustls = { version = "0.26.0", default-features = false, features = ["tls12", "ring"]}
tokio-stream = "0.1"
tokio-tar = "0.3"
tokio-util = { version = "0.7.10", features = ["io", "rt"] }
toml = "0.8"
toml_edit = "0.22"
tonic = {version = "0.12.3", default-features = false, features = ["channel", "tls", "tls-roots"]}
tower = { version = "0.5.2", default-features = false }
tower-http = { version = "0.6.2", features = ["request-id", "trace"] }
# This revision uses opentelemetry 0.27. There's no tag for it.
tower-otel = { git = "https://github.com/mattiapenati/tower-otel", rev = "56a7321053bcb72443888257b622ba0d43a11fcd" }
tower-service = "0.3.3"
tracing = "0.1"
tracing-error = "0.2"
tracing-log = "0.2"
tracing-opentelemetry = "0.28"
tracing-serde = "0.2.0"
tracing-subscriber = { version = "0.3", default-features = false, features = ["smallvec", "fmt", "tracing-log", "std", "env-filter", "json"] }
try-lock = "0.2.5"
twox-hash = { version = "1.6.3", default-features = false }
typed-json = "0.1"
url = "2.2"
urlencoding = "2.1"
uuid = { version = "1.6.1", features = ["v4", "v7", "serde"] }
walkdir = "2.3.2"
rustls-native-certs = "0.8"
x509-parser = "0.16"
whoami = "1.5.1"
zerocopy = { version = "0.7", features = ["derive"] }
json-structural-diff = { version = "0.2.0" }
## 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-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" }
## Azure SDK crates
azure_core = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
azure_identity = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage_blobs = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
## Local libraries
compute_api = { version = "0.1", path = "./libs/compute_api/" }
consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
http-utils = { version = "0.1", path = "./libs/http-utils/" }
metrics = { version = "0.1", path = "./libs/metrics/" }
pageserver = { path = "./pageserver" }
pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
pageserver_client = { path = "./pageserver/client" }
pageserver_compaction = { version = "0.1", path = "./pageserver/compaction/" }
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/" }
postgres_initdb = { path = "./libs/postgres_initdb" }
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" }
safekeeper_client = { path = "./safekeeper/client" }
desim = { version = "0.1", path = "./libs/desim" }
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.
storage_controller_client = { path = "./storage_controller/client" }
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/" }
wal_decoder = { version = "0.1", path = "./libs/wal_decoder" }
## Common library dependency
workspace_hack = { version = "0.1", path = "./workspace_hack/" }
## Build dependencies
criterion = "0.5.1"
rcgen = "0.13"
rstest = "0.18"
camino-tempfile = "1.0.2"
tonic-build = "0.12"
[patch.crates-io]
# Needed to get `tokio-postgres-rustls` to depend on our fork.
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
################# Binary contents sections
[profile.release]
# This is useful for profiling and, to some extent, debug.
# Besides, debug info should not affect the performance.
#
# NB: we also enable frame pointers for improved profiling, see .cargo/config.toml.
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