mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-08 14:02:55 +00:00
a64dd3ecb5
This patch adds a pageserver-global background loop that evicts layers in response to a shortage of available bytes in the $repo/tenants directory's filesystem. The loop runs periodically at a configurable `period`. Each loop iteration uses `statvfs` to determine filesystem-level space usage. It compares the returned usage data against two different types of thresholds. The iteration tries to evict layers until app-internal accounting says we should be below the thresholds. We cross-check this internal accounting with the real world by making another `statvfs` at the end of the iteration. We're good if that second statvfs shows that we're _actually_ below the configured thresholds. If we're still above one or more thresholds, we emit a warning log message, leaving it to the operator to investigate further. There are two thresholds: - `max_usage_pct` is the relative available space, expressed in percent of the total filesystem space. If the actual usage is higher, the threshold is exceeded. - `min_avail_bytes` is the absolute available space in bytes. If the actual usage is lower, the threshold is exceeded. The iteration evicts layers in LRU fashion with a reservation of up to `tenant_min_resident_size` bytes of the most recent layers per tenant. The layers not part of the per-tenant reservation are evicted least-recently-used first until we're below all thresholds. The `tenant_min_resident_size` can be overridden per tenant as `min_resident_size_override` (bytes). In addition to the loop, there is also an HTTP endpoint to perform one loop iteration synchronous to the request. The endpoint takes an absolute number of bytes that the iteration needs to evict before pressure is relieved. The tests use this endpoint, which is a great simplification over setting up loopback-mounts in the tests, which would be required to test the statvfs part of the implementation. We will rely on manual testing in staging to test the statvfs parts. The HTTP endpoint is also handy in emergencies where an operator wants the pageserver to evict a given amount of space _now. Hence, it's arguments documented in openapi_spec.yml. The response type isn't documented though because we don't consider it stable. The endpoint should _not_ be used by Console but it could be used by on-call. Co-authored-by: Joonas Koivunen <joonas@neon.tech> Co-authored-by: Dmitry Rodionov <dmitry@neon.tech> Co-authored-by: Heikki Linnakangas <heikki@neon.tech>
90 lines
2.4 KiB
TOML
90 lines
2.4 KiB
TOML
[package]
|
|
name = "pageserver"
|
|
version = "0.1.0"
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
|
|
[features]
|
|
default = []
|
|
# Enables test-only APIs, incuding failpoints. In particular, enables the `fail_point!` macro,
|
|
# which adds some runtime cost to run tests on outage conditions
|
|
testing = ["fail/failpoints"]
|
|
|
|
[dependencies]
|
|
anyhow.workspace = true
|
|
async-stream.workspace = true
|
|
async-trait.workspace = true
|
|
byteorder.workspace = true
|
|
bytes.workspace = true
|
|
chrono = { workspace = true, features = ["serde"] }
|
|
clap = { workspace = true, features = ["string"] }
|
|
close_fds.workspace = true
|
|
const_format.workspace = true
|
|
consumption_metrics.workspace = true
|
|
crc32c.workspace = true
|
|
crossbeam-utils.workspace = true
|
|
either.workspace = true
|
|
fail.workspace = true
|
|
futures.workspace = true
|
|
git-version.workspace = true
|
|
hex.workspace = true
|
|
humantime.workspace = true
|
|
humantime-serde.workspace = true
|
|
hyper.workspace = true
|
|
itertools.workspace = true
|
|
nix.workspace = true
|
|
num-traits.workspace = true
|
|
once_cell.workspace = true
|
|
pin-project-lite.workspace = true
|
|
postgres.workspace = true
|
|
postgres_backend.workspace = true
|
|
postgres-protocol.workspace = true
|
|
postgres-types.workspace = true
|
|
rand.workspace = true
|
|
regex.workspace = true
|
|
scopeguard.workspace = true
|
|
serde.workspace = true
|
|
serde_json = { workspace = true, features = ["raw_value"] }
|
|
serde_with.workspace = true
|
|
signal-hook.workspace = true
|
|
svg_fmt.workspace = true
|
|
sync_wrapper.workspace = true
|
|
tokio-tar.workspace = true
|
|
thiserror.workspace = true
|
|
tokio = { workspace = true, features = ["process", "sync", "fs", "rt", "io-util", "time"] }
|
|
tokio-postgres.workspace = true
|
|
tokio-util.workspace = true
|
|
toml_edit = { workspace = true, features = [ "serde" ] }
|
|
tracing.workspace = true
|
|
url.workspace = true
|
|
walkdir.workspace = true
|
|
metrics.workspace = true
|
|
pageserver_api.workspace = true
|
|
postgres_connection.workspace = true
|
|
postgres_ffi.workspace = true
|
|
pq_proto.workspace = true
|
|
remote_storage.workspace = true
|
|
storage_broker.workspace = true
|
|
tenant_size_model.workspace = true
|
|
utils.workspace = true
|
|
workspace_hack.workspace = true
|
|
reqwest.workspace = true
|
|
rpds.workspace = true
|
|
enum-map.workspace = true
|
|
enumset.workspace = true
|
|
strum.workspace = true
|
|
strum_macros.workspace = true
|
|
|
|
[dev-dependencies]
|
|
criterion.workspace = true
|
|
hex-literal.workspace = true
|
|
tempfile.workspace = true
|
|
|
|
[[bench]]
|
|
name = "bench_layer_map"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "bench_walredo"
|
|
harness = false
|