Files
neon/pageserver/Cargo.toml
John Spray c4e0ef507f pageserver: heatmap uploads (#6050)
Dependency (commits inline):
https://github.com/neondatabase/neon/pull/5842

## Problem

Secondary mode tenants need a manifest of what to download. Ultimately
this will be some kind of heat-scored set of layers, but as a robust
first step we will simply use the set of resident layers: secondary
tenant locations will aim to match the on-disk content of the attached
location.

## Summary of changes

- Add heatmap types representing the remote structure
- Add hooks to Tenant/Timeline for generating these heatmaps
- Create a new `HeatmapUploader` type that is external to `Tenant`, and
responsible for walking the list of attached tenants and scheduling
heatmap uploads.

Notes to reviewers:
- Putting the logic for uploads (and later, secondary mode downloads)
outside of `Tenant` is an opinionated choice, motivated by:
- Enable future smarter scheduling of operations, e.g. uploading the
stalest tenant first, rather than having all tenants compete for a fair
semaphore on a first-come-first-served basis. Similarly for downloads,
we may wish to schedule the tenants with the hottest un-downloaded
layers first.
- Enable accessing upload-related state without synchronization (it
belongs to HeatmapUploader, rather than being some Mutex<>'d part of
Tenant)
- Avoid further expanding the scope of Tenant/Timeline types, which are
already among the largest in the codebase
- You might reasonably wonder how much of the uploader code could be a
generic job manager thing. Probably some of it: but let's defer pulling
that out until we have at least two users (perhaps secondary downloads
will be the second one) to highlight which bits are really generic.

Compromises:
- Later, instead of using digests of heatmaps to decide whether anything
changed, I would prefer to avoid walking the layers in tenants that
don't have changes: tracking that will be a bit invasive, as it needs
input from both remote_timeline_client and Layer.
2023-12-14 13:09:24 +00:00

100 lines
2.8 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-compression.workspace = true
async-stream.workspace = true
async-trait.workspace = true
byteorder.workspace = true
bytes.workspace = true
camino.workspace = true
camino-tempfile.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
flate2.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
md5.workspace = true
nix.workspace = true
# hack to get the number of worker threads tokio uses
num_cpus = { version = "1.15" }
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_path_to_error.workspace = true
serde_with.workspace = true
signal-hook.workspace = true
smallvec = { workspace = true, features = ["write"] }
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-io-timeout.workspace = true
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
tokio = { workspace = true, features = ["process", "sync", "fs", "rt", "io-util", "time", "test-util"] }
[[bench]]
name = "bench_layer_map"
harness = false
[[bench]]
name = "bench_walredo"
harness = false