refactor(tvix): move castore into tvix-castore crate r/6629

This splits the pure content-addressed layers from tvix-store into a
`castore` crate, and only leaves PathInfo related things, as well as the
CLI entrypoint in the tvix-store crate.

Notable changes:
 - `fixtures` and `utils` had to be moved out of the `test` cfg, so they
   can be imported from tvix-store.
 - Some ad-hoc fixtures in the test were moved to proper fixtures in the
   same step.
 - The protos are now created by a (more static) recipe in the protos/
   directory.

The (now two) golang targets are commented out, as it's not possible to
update them properly in the same CL. This will be done by a followup CL
once this is merged (and whitby deployed)

Bug: https://b.tvl.fyi/issues/301

Change-Id: I8d675d4bf1fb697eb7d479747c1b1e3635718107
Reviewed-on: https://cl.tvl.fyi/c/depot/+/9370
Reviewed-by: tazjin <tazjin@tvl.su>
Reviewed-by: flokli <flokli@flokli.de>
Autosubmit: flokli <flokli@flokli.de>
Tested-by: BuildkiteCI
Reviewed-by: Connor Brewster <cbrewster@hey.com>

1 files changed, 177 insertions, 0 deletions

diff --git a/tvix/castore/src/proto/grpc_blobservice_wrapper.rs b/tvix/castore/src/proto/grpc_blobservice_wrapper.rs
new file mode 100644
index 000000000000..93db1deef69a
--- /dev/null
+++ b/tvix/castore/src/proto/grpc_blobservice_wrapper.rs
@@ -0,0 +1,177 @@
+use crate::blobservice::BlobService;
+use core::pin::pin;
+use futures::TryFutureExt;
+use std::{
+    collections::VecDeque,
+    io,
+    ops::{Deref, DerefMut},
+    pin::Pin,
+    sync::Arc,
+};
+use tokio_stream::StreamExt;
+use tokio_util::io::ReaderStream;
+use tonic::{async_trait, Request, Response, Status, Streaming};
+use tracing::{instrument, warn};
+
+pub struct GRPCBlobServiceWrapper {
+    blob_service: Arc<dyn BlobService>,
+}
+
+impl From<Arc<dyn BlobService>> for GRPCBlobServiceWrapper {
+    fn from(value: Arc<dyn BlobService>) -> Self {
+        Self {
+            blob_service: value,
+        }
+    }
+}
+
+// This is necessary because bytes::BytesMut comes up with
+// a default 64 bytes capacity that cannot be changed
+// easily if you assume a bytes::BufMut trait implementation
+// Therefore, we override the Default implementation here
+// TODO(raitobezarius?): upstream me properly
+struct BytesMutWithDefaultCapacity<const N: usize> {
+    inner: bytes::BytesMut,
+}
+
+impl<const N: usize> Deref for BytesMutWithDefaultCapacity<N> {
+    type Target = bytes::BytesMut;
+    fn deref(&self) -> &Self::Target {
+        &self.inner
+    }
+}
+
+impl<const N: usize> DerefMut for BytesMutWithDefaultCapacity<N> {
+    fn deref_mut(&mut self) -> &mut Self::Target {
+        &mut self.inner
+    }
+}
+
+impl<const N: usize> Default for BytesMutWithDefaultCapacity<N> {
+    fn default() -> Self {
+        BytesMutWithDefaultCapacity {
+            inner: bytes::BytesMut::with_capacity(N),
+        }
+    }
+}
+
+impl<const N: usize> bytes::Buf for BytesMutWithDefaultCapacity<N> {
+    fn remaining(&self) -> usize {
+        self.inner.remaining()
+    }
+
+    fn chunk(&self) -> &[u8] {
+        self.inner.chunk()
+    }
+
+    fn advance(&mut self, cnt: usize) {
+        self.inner.advance(cnt);
+    }
+}
+
+unsafe impl<const N: usize> bytes::BufMut for BytesMutWithDefaultCapacity<N> {
+    fn remaining_mut(&self) -> usize {
+        self.inner.remaining_mut()
+    }
+
+    unsafe fn advance_mut(&mut self, cnt: usize) {
+        self.inner.advance_mut(cnt);
+    }
+
+    fn chunk_mut(&mut self) -> &mut bytes::buf::UninitSlice {
+        self.inner.chunk_mut()
+    }
+}
+
+#[async_trait]
+impl super::blob_service_server::BlobService for GRPCBlobServiceWrapper {
+    // https://github.com/tokio-rs/tokio/issues/2723#issuecomment-1534723933
+    type ReadStream =
+        Pin<Box<dyn futures::Stream<Item = Result<super::BlobChunk, Status>> + Send + 'static>>;
+
+    #[instrument(skip(self))]
+    async fn stat(
+        &self,
+        request: Request<super::StatBlobRequest>,
+    ) -> Result<Response<super::BlobMeta>, Status> {
+        let rq = request.into_inner();
+        let req_digest = rq
+            .digest
+            .try_into()
+            .map_err(|_e| Status::invalid_argument("invalid digest length"))?;
+
+        match self.blob_service.has(&req_digest).await {
+            Ok(true) => Ok(Response::new(super::BlobMeta::default())),
+            Ok(false) => Err(Status::not_found(format!("blob {} not found", &req_digest))),
+            Err(e) => Err(e.into()),
+        }
+    }
+
+    #[instrument(skip(self))]
+    async fn read(
+        &self,
+        request: Request<super::ReadBlobRequest>,
+    ) -> Result<Response<Self::ReadStream>, Status> {
+        let rq = request.into_inner();
+
+        let req_digest = rq
+            .digest
+            .try_into()
+            .map_err(|_e| Status::invalid_argument("invalid digest length"))?;
+
+        match self.blob_service.open_read(&req_digest).await {
+            Ok(Some(reader)) => {
+                fn stream_mapper(
+                    x: Result<bytes::Bytes, io::Error>,
+                ) -> Result<super::BlobChunk, Status> {
+                    match x {
+                        Ok(bytes) => Ok(super::BlobChunk { data: bytes }),
+                        Err(e) => Err(Status::from(e)),
+                    }
+                }
+
+                let chunks_stream = ReaderStream::new(reader).map(stream_mapper);
+                Ok(Response::new(Box::pin(chunks_stream)))
+            }
+            Ok(None) => Err(Status::not_found(format!("blob {} not found", &req_digest))),
+            Err(e) => Err(e.into()),
+        }
+    }
+
+    #[instrument(skip(self))]
+    async fn put(
+        &self,
+        request: Request<Streaming<super::BlobChunk>>,
+    ) -> Result<Response<super::PutBlobResponse>, Status> {
+        let req_inner = request.into_inner();
+
+        let data_stream = req_inner.map(|x| {
+            x.map(|x| VecDeque::from(x.data.to_vec()))
+                .map_err(|e| std::io::Error::new(std::io::ErrorKind::InvalidInput, e))
+        });
+
+        let mut data_reader = tokio_util::io::StreamReader::new(data_stream);
+
+        let mut blob_writer = pin!(self.blob_service.open_write().await);
+
+        tokio::io::copy(&mut data_reader, &mut blob_writer)
+            .await
+            .map_err(|e| {
+                warn!("error copying: {}", e);
+                Status::internal("error copying")
+            })?;
+
+        let digest = blob_writer
+            .close()
+            .map_err(|e| {
+                warn!("error closing stream: {}", e);
+                Status::internal("error closing stream")
+            })
+            .await?
+            .to_vec();
+
+        Ok(Response::new(super::PutBlobResponse {
+            digest: digest.into(),
+        }))
+    }
+}