Files
neon/s3_scrubber/Cargo.toml
John Spray 306c4f9967 s3_scrubber: prepare for scrubbing buckets with generation-aware content (#5700)
## Problem

The scrubber didn't know how to find the latest index_part when
generations were in use.

## Summary of changes

- Teach the scrubber to do the same dance that pageserver does when
finding the latest index_part.json
- Teach the scrubber how to understand layer files with generation
suffixes.
- General improvement to testability: scan_metadata has a machine
readable output that the testing `S3Scrubber` wrapper can read.
- Existing test coverage of scrubber was false-passing because it just
didn't see any data due to prefixing of data in the bucket. Fix that.

This is incremental improvement: the more confidence we can have in the
scrubber, the more we can use it in integration tests to validate the
state of remote storage.

---------

Co-authored-by: Arpad Müller <arpad-m@users.noreply.github.com>
2023-11-03 17:36:02 +00:00

43 lines
1.2 KiB
TOML

[package]
name = "s3_scrubber"
version = "0.1.0"
edition.workspace = true
license.workspace = true
[dependencies]
aws-sdk-s3.workspace = true
aws-smithy-http.workspace = true
aws-types.workspace = true
either.workspace = true
tokio-rustls.workspace = true
anyhow.workspace = true
hex.workspace = true
thiserror.workspace = true
rand.workspace = true
bytes.workspace = true
bincode.workspace = true
crc32c.workspace = true
serde.workspace = true
serde_json.workspace = true
serde_with.workspace = true
workspace_hack.workspace = true
utils.workspace = true
async-stream.workspace = true
tokio-stream.workspace = true
futures-util.workspace = true
itertools.workspace = true
tokio = { workspace = true, features = ["macros", "rt-multi-thread"] }
chrono = { workspace = true, default-features = false, features = ["clock", "serde"] }
reqwest = { workspace = true, default-features = false, features = ["rustls-tls", "json"] }
aws-config = { workspace = true, default-features = false, features = ["rustls", "credentials-sso"] }
pageserver = { path = "../pageserver" }
remote_storage = { path = "../libs/remote_storage" }
tracing.workspace = true
tracing-subscriber.workspace = true
clap.workspace = true
tracing-appender = "0.2"
histogram = "0.7"