tvl-depot/tvix/store/src/import.rs

200 lines
7 KiB
Rust
Raw Normal View History

use crate::blobservice::BlobService;
use crate::directoryservice::DirectoryService;
use crate::{directoryservice::DirectoryPutter, proto};
use std::os::unix::ffi::OsStrExt;
use std::sync::Arc;
use std::{
collections::HashMap,
fmt::Debug,
os::unix::prelude::PermissionsExt,
path::{Path, PathBuf},
};
use tracing::instrument;
use walkdir::WalkDir;
#[derive(Debug, thiserror::Error)]
pub enum Error {
#[error("failed to upload directory at {0}: {1}")]
UploadDirectoryError(PathBuf, crate::Error),
#[error("invalid encoding encountered for entry {0:?}")]
InvalidEncoding(PathBuf),
#[error("unable to stat {0}: {1}")]
UnableToStat(PathBuf, std::io::Error),
#[error("unable to open {0}: {1}")]
UnableToOpen(PathBuf, std::io::Error),
#[error("unable to read {0}: {1}")]
UnableToRead(PathBuf, std::io::Error),
}
impl From<super::Error> for Error {
fn from(value: super::Error) -> Self {
match value {
crate::Error::InvalidRequest(_) => panic!("tvix bug"),
crate::Error::StorageError(_) => panic!("error"),
}
}
}
// This processes a given [walkdir::DirEntry] and returns a
// proto::node::Node, depending on the type of the entry.
//
// If the entry is a file, its contents are uploaded.
// If the entry is a directory, the Directory is uploaded as well.
// For this to work, it relies on the caller to provide the directory object
// with the previously returned (child) nodes.
//
// It assumes entries to be returned in "contents first" order, means this
// will only be called with a directory if all children of it have been
// visited. If the entry is indeed a directory, it'll also upload that
// directory to the store. For this, the so-far-assembled Directory object for
// this path needs to be passed in.
//
// It assumes the caller adds returned nodes to the directories it assembles.
#[instrument(skip_all, fields(entry.file_type=?&entry.file_type(),entry.path=?entry.path()))]
refactor(tvix/store/blobsvc): make BlobStore async We previously kept the trait of a BlobService sync. This however had some annoying consequences: - It became more and more complicated to track when we're in a context with an async runtime in the context or not, producing bugs like https://b.tvl.fyi/issues/304 - The sync trait shielded away async clients from async worloads, requiring manual block_on code inside the gRPC client code, and spawn_blocking calls in consumers of the trait, even if they were async (like the gRPC server) - We had to write our own custom glue code (SyncReadIntoAsyncRead) to convert a sync io::Read into a tokio::io::AsyncRead, which already existed in tokio internally, but upstream ia hesitant to expose. This now makes the BlobService trait async (via the async_trait macro, like we already do in various gRPC parts), and replaces the sync readers and writers with their async counterparts. Tests interacting with a BlobService now need to have an async runtime available, the easiest way for this is to mark the test functions with the tokio::test macro, allowing us to directly .await in the test function. In places where we don't have an async runtime available from context (like tvix-cli), we can pass one down explicitly. Now that we don't provide a sync interface anymore, the (sync) FUSE library now holds a pointer to a tokio runtime handle, and needs to at least have 2 threads available when talking to a blob service (which is why some of the tests now use the multi_thread flavor). The FUSE tests got a bit more verbose, as we couldn't use the setup_and_mount function accepting a callback anymore. We can hopefully move some of the test fixture setup to rstest in the future to make this less repetitive. Co-Authored-By: Connor Brewster <cbrewster@hey.com> Change-Id: Ia0501b606e32c852d0108de9c9016b21c94a3c05 Reviewed-on: https://cl.tvl.fyi/c/depot/+/9329 Reviewed-by: Connor Brewster <cbrewster@hey.com> Tested-by: BuildkiteCI Reviewed-by: raitobezarius <tvl@lahfa.xyz>
2023-09-13 14:20:21 +02:00
async fn process_entry(
blob_service: Arc<dyn BlobService>,
directory_putter: &mut Box<dyn DirectoryPutter>,
entry: &walkdir::DirEntry,
maybe_directory: Option<proto::Directory>,
) -> Result<proto::node::Node, Error> {
let file_type = entry.file_type();
if file_type.is_dir() {
let directory = maybe_directory
.expect("tvix bug: must be called with some directory in the case of directory");
let directory_digest = directory.digest();
let directory_size = directory.size();
// upload this directory
directory_putter
.put(directory)
.await
.map_err(|e| Error::UploadDirectoryError(entry.path().to_path_buf(), e))?;
return Ok(proto::node::Node::Directory(proto::DirectoryNode {
name: entry.file_name().as_bytes().to_owned().into(),
digest: directory_digest.into(),
size: directory_size,
}));
}
if file_type.is_symlink() {
let target: bytes::Bytes = std::fs::read_link(entry.path())
.map_err(|e| Error::UnableToStat(entry.path().to_path_buf(), e))?
.as_os_str()
.as_bytes()
.to_owned()
.into();
return Ok(proto::node::Node::Symlink(proto::SymlinkNode {
name: entry.file_name().as_bytes().to_owned().into(),
target,
}));
}
if file_type.is_file() {
let metadata = entry
.metadata()
.map_err(|e| Error::UnableToStat(entry.path().to_path_buf(), e.into()))?;
refactor(tvix/store/blobsvc): make BlobStore async We previously kept the trait of a BlobService sync. This however had some annoying consequences: - It became more and more complicated to track when we're in a context with an async runtime in the context or not, producing bugs like https://b.tvl.fyi/issues/304 - The sync trait shielded away async clients from async worloads, requiring manual block_on code inside the gRPC client code, and spawn_blocking calls in consumers of the trait, even if they were async (like the gRPC server) - We had to write our own custom glue code (SyncReadIntoAsyncRead) to convert a sync io::Read into a tokio::io::AsyncRead, which already existed in tokio internally, but upstream ia hesitant to expose. This now makes the BlobService trait async (via the async_trait macro, like we already do in various gRPC parts), and replaces the sync readers and writers with their async counterparts. Tests interacting with a BlobService now need to have an async runtime available, the easiest way for this is to mark the test functions with the tokio::test macro, allowing us to directly .await in the test function. In places where we don't have an async runtime available from context (like tvix-cli), we can pass one down explicitly. Now that we don't provide a sync interface anymore, the (sync) FUSE library now holds a pointer to a tokio runtime handle, and needs to at least have 2 threads available when talking to a blob service (which is why some of the tests now use the multi_thread flavor). The FUSE tests got a bit more verbose, as we couldn't use the setup_and_mount function accepting a callback anymore. We can hopefully move some of the test fixture setup to rstest in the future to make this less repetitive. Co-Authored-By: Connor Brewster <cbrewster@hey.com> Change-Id: Ia0501b606e32c852d0108de9c9016b21c94a3c05 Reviewed-on: https://cl.tvl.fyi/c/depot/+/9329 Reviewed-by: Connor Brewster <cbrewster@hey.com> Tested-by: BuildkiteCI Reviewed-by: raitobezarius <tvl@lahfa.xyz>
2023-09-13 14:20:21 +02:00
let mut file = tokio::fs::File::open(entry.path())
.await
.map_err(|e| Error::UnableToOpen(entry.path().to_path_buf(), e))?;
refactor(tvix/store/blobsvc): make BlobStore async We previously kept the trait of a BlobService sync. This however had some annoying consequences: - It became more and more complicated to track when we're in a context with an async runtime in the context or not, producing bugs like https://b.tvl.fyi/issues/304 - The sync trait shielded away async clients from async worloads, requiring manual block_on code inside the gRPC client code, and spawn_blocking calls in consumers of the trait, even if they were async (like the gRPC server) - We had to write our own custom glue code (SyncReadIntoAsyncRead) to convert a sync io::Read into a tokio::io::AsyncRead, which already existed in tokio internally, but upstream ia hesitant to expose. This now makes the BlobService trait async (via the async_trait macro, like we already do in various gRPC parts), and replaces the sync readers and writers with their async counterparts. Tests interacting with a BlobService now need to have an async runtime available, the easiest way for this is to mark the test functions with the tokio::test macro, allowing us to directly .await in the test function. In places where we don't have an async runtime available from context (like tvix-cli), we can pass one down explicitly. Now that we don't provide a sync interface anymore, the (sync) FUSE library now holds a pointer to a tokio runtime handle, and needs to at least have 2 threads available when talking to a blob service (which is why some of the tests now use the multi_thread flavor). The FUSE tests got a bit more verbose, as we couldn't use the setup_and_mount function accepting a callback anymore. We can hopefully move some of the test fixture setup to rstest in the future to make this less repetitive. Co-Authored-By: Connor Brewster <cbrewster@hey.com> Change-Id: Ia0501b606e32c852d0108de9c9016b21c94a3c05 Reviewed-on: https://cl.tvl.fyi/c/depot/+/9329 Reviewed-by: Connor Brewster <cbrewster@hey.com> Tested-by: BuildkiteCI Reviewed-by: raitobezarius <tvl@lahfa.xyz>
2023-09-13 14:20:21 +02:00
let mut writer = blob_service.open_write().await;
refactor(tvix/store/blobsvc): make BlobStore async We previously kept the trait of a BlobService sync. This however had some annoying consequences: - It became more and more complicated to track when we're in a context with an async runtime in the context or not, producing bugs like https://b.tvl.fyi/issues/304 - The sync trait shielded away async clients from async worloads, requiring manual block_on code inside the gRPC client code, and spawn_blocking calls in consumers of the trait, even if they were async (like the gRPC server) - We had to write our own custom glue code (SyncReadIntoAsyncRead) to convert a sync io::Read into a tokio::io::AsyncRead, which already existed in tokio internally, but upstream ia hesitant to expose. This now makes the BlobService trait async (via the async_trait macro, like we already do in various gRPC parts), and replaces the sync readers and writers with their async counterparts. Tests interacting with a BlobService now need to have an async runtime available, the easiest way for this is to mark the test functions with the tokio::test macro, allowing us to directly .await in the test function. In places where we don't have an async runtime available from context (like tvix-cli), we can pass one down explicitly. Now that we don't provide a sync interface anymore, the (sync) FUSE library now holds a pointer to a tokio runtime handle, and needs to at least have 2 threads available when talking to a blob service (which is why some of the tests now use the multi_thread flavor). The FUSE tests got a bit more verbose, as we couldn't use the setup_and_mount function accepting a callback anymore. We can hopefully move some of the test fixture setup to rstest in the future to make this less repetitive. Co-Authored-By: Connor Brewster <cbrewster@hey.com> Change-Id: Ia0501b606e32c852d0108de9c9016b21c94a3c05 Reviewed-on: https://cl.tvl.fyi/c/depot/+/9329 Reviewed-by: Connor Brewster <cbrewster@hey.com> Tested-by: BuildkiteCI Reviewed-by: raitobezarius <tvl@lahfa.xyz>
2023-09-13 14:20:21 +02:00
if let Err(e) = tokio::io::copy(&mut file, &mut writer).await {
return Err(Error::UnableToRead(entry.path().to_path_buf(), e));
};
refactor(tvix/store/blobsvc): make BlobStore async We previously kept the trait of a BlobService sync. This however had some annoying consequences: - It became more and more complicated to track when we're in a context with an async runtime in the context or not, producing bugs like https://b.tvl.fyi/issues/304 - The sync trait shielded away async clients from async worloads, requiring manual block_on code inside the gRPC client code, and spawn_blocking calls in consumers of the trait, even if they were async (like the gRPC server) - We had to write our own custom glue code (SyncReadIntoAsyncRead) to convert a sync io::Read into a tokio::io::AsyncRead, which already existed in tokio internally, but upstream ia hesitant to expose. This now makes the BlobService trait async (via the async_trait macro, like we already do in various gRPC parts), and replaces the sync readers and writers with their async counterparts. Tests interacting with a BlobService now need to have an async runtime available, the easiest way for this is to mark the test functions with the tokio::test macro, allowing us to directly .await in the test function. In places where we don't have an async runtime available from context (like tvix-cli), we can pass one down explicitly. Now that we don't provide a sync interface anymore, the (sync) FUSE library now holds a pointer to a tokio runtime handle, and needs to at least have 2 threads available when talking to a blob service (which is why some of the tests now use the multi_thread flavor). The FUSE tests got a bit more verbose, as we couldn't use the setup_and_mount function accepting a callback anymore. We can hopefully move some of the test fixture setup to rstest in the future to make this less repetitive. Co-Authored-By: Connor Brewster <cbrewster@hey.com> Change-Id: Ia0501b606e32c852d0108de9c9016b21c94a3c05 Reviewed-on: https://cl.tvl.fyi/c/depot/+/9329 Reviewed-by: Connor Brewster <cbrewster@hey.com> Tested-by: BuildkiteCI Reviewed-by: raitobezarius <tvl@lahfa.xyz>
2023-09-13 14:20:21 +02:00
let digest = writer.close().await?;
return Ok(proto::node::Node::File(proto::FileNode {
name: entry.file_name().as_bytes().to_vec().into(),
digest: digest.into(),
size: metadata.len() as u32,
// If it's executable by the user, it'll become executable.
// This matches nix's dump() function behaviour.
executable: metadata.permissions().mode() & 64 != 0,
}));
}
todo!("handle other types")
}
/// Ingests the contents at the given path into the tvix store,
/// interacting with a [BlobService] and [DirectoryService].
/// It returns the root node or an error.
///
/// It does not follow symlinks at the root, they will be ingested as actual
/// symlinks.
///
/// It's not interacting with a
/// [PathInfoService](crate::pathinfoservice::PathInfoService), it's up to the
/// caller to possibly register it somewhere (and potentially rename it based on
/// some naming scheme.
#[instrument(skip(blob_service, directory_service), fields(path=?p))]
refactor(tvix/store/blobsvc): make BlobStore async We previously kept the trait of a BlobService sync. This however had some annoying consequences: - It became more and more complicated to track when we're in a context with an async runtime in the context or not, producing bugs like https://b.tvl.fyi/issues/304 - The sync trait shielded away async clients from async worloads, requiring manual block_on code inside the gRPC client code, and spawn_blocking calls in consumers of the trait, even if they were async (like the gRPC server) - We had to write our own custom glue code (SyncReadIntoAsyncRead) to convert a sync io::Read into a tokio::io::AsyncRead, which already existed in tokio internally, but upstream ia hesitant to expose. This now makes the BlobService trait async (via the async_trait macro, like we already do in various gRPC parts), and replaces the sync readers and writers with their async counterparts. Tests interacting with a BlobService now need to have an async runtime available, the easiest way for this is to mark the test functions with the tokio::test macro, allowing us to directly .await in the test function. In places where we don't have an async runtime available from context (like tvix-cli), we can pass one down explicitly. Now that we don't provide a sync interface anymore, the (sync) FUSE library now holds a pointer to a tokio runtime handle, and needs to at least have 2 threads available when talking to a blob service (which is why some of the tests now use the multi_thread flavor). The FUSE tests got a bit more verbose, as we couldn't use the setup_and_mount function accepting a callback anymore. We can hopefully move some of the test fixture setup to rstest in the future to make this less repetitive. Co-Authored-By: Connor Brewster <cbrewster@hey.com> Change-Id: Ia0501b606e32c852d0108de9c9016b21c94a3c05 Reviewed-on: https://cl.tvl.fyi/c/depot/+/9329 Reviewed-by: Connor Brewster <cbrewster@hey.com> Tested-by: BuildkiteCI Reviewed-by: raitobezarius <tvl@lahfa.xyz>
2023-09-13 14:20:21 +02:00
pub async fn ingest_path<P: AsRef<Path> + Debug>(
blob_service: Arc<dyn BlobService>,
directory_service: Arc<dyn DirectoryService>,
p: P,
) -> Result<proto::node::Node, Error> {
let mut directories: HashMap<PathBuf, proto::Directory> = HashMap::default();
// TODO: pass this one instead?
let mut directory_putter = directory_service.put_multiple_start();
for entry in WalkDir::new(p)
.follow_links(false)
.follow_root_links(false)
.contents_first(true)
.sort_by_file_name()
{
let entry = entry.unwrap();
// process_entry wants an Option<Directory> in case the entry points to a directory.
// make sure to provide it.
let maybe_directory: Option<proto::Directory> = {
if entry.file_type().is_dir() {
Some(
directories
.entry(entry.path().to_path_buf())
.or_default()
.clone(),
)
} else {
None
}
};
let node = process_entry(
blob_service.clone(),
&mut directory_putter,
&entry,
maybe_directory,
refactor(tvix/store/blobsvc): make BlobStore async We previously kept the trait of a BlobService sync. This however had some annoying consequences: - It became more and more complicated to track when we're in a context with an async runtime in the context or not, producing bugs like https://b.tvl.fyi/issues/304 - The sync trait shielded away async clients from async worloads, requiring manual block_on code inside the gRPC client code, and spawn_blocking calls in consumers of the trait, even if they were async (like the gRPC server) - We had to write our own custom glue code (SyncReadIntoAsyncRead) to convert a sync io::Read into a tokio::io::AsyncRead, which already existed in tokio internally, but upstream ia hesitant to expose. This now makes the BlobService trait async (via the async_trait macro, like we already do in various gRPC parts), and replaces the sync readers and writers with their async counterparts. Tests interacting with a BlobService now need to have an async runtime available, the easiest way for this is to mark the test functions with the tokio::test macro, allowing us to directly .await in the test function. In places where we don't have an async runtime available from context (like tvix-cli), we can pass one down explicitly. Now that we don't provide a sync interface anymore, the (sync) FUSE library now holds a pointer to a tokio runtime handle, and needs to at least have 2 threads available when talking to a blob service (which is why some of the tests now use the multi_thread flavor). The FUSE tests got a bit more verbose, as we couldn't use the setup_and_mount function accepting a callback anymore. We can hopefully move some of the test fixture setup to rstest in the future to make this less repetitive. Co-Authored-By: Connor Brewster <cbrewster@hey.com> Change-Id: Ia0501b606e32c852d0108de9c9016b21c94a3c05 Reviewed-on: https://cl.tvl.fyi/c/depot/+/9329 Reviewed-by: Connor Brewster <cbrewster@hey.com> Tested-by: BuildkiteCI Reviewed-by: raitobezarius <tvl@lahfa.xyz>
2023-09-13 14:20:21 +02:00
)
.await?;
if entry.depth() == 0 {
return Ok(node);
} else {
// calculate the parent path, and make sure we register the node there.
// NOTE: entry.depth() > 0
let parent_path = entry.path().parent().unwrap().to_path_buf();
// record node in parent directory, creating a new [proto:Directory] if not there yet.
let parent_directory = directories.entry(parent_path).or_default();
match node {
proto::node::Node::Directory(e) => parent_directory.directories.push(e),
proto::node::Node::File(e) => parent_directory.files.push(e),
proto::node::Node::Symlink(e) => parent_directory.symlinks.push(e),
}
}
}
// unreachable, we already bailed out before if root doesn't exist.
panic!("tvix bug")
}