This repository has been archived on 2026-08-30. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
varde/varde-daemon/src/store.rs
T
bl 20bdf56668 Milestone 4: LAN discovery, trust gate, auto-sync, rate limits, events
mDNS-style LAN discovery (iroh MdnsDiscovery, discovery flag, default
on) feeds a presence tracker; trusted peers that appear trigger fetches
of every incomplete pin, and Pin itself now fetches from present
trusted peers. Serving is our own ProtocolHandler: trusted NodeIds get
the full store, everyone else a filtered view limited to open_lan pins
and ticket-exported hashes (plus hashseq children) that answers "not
found" for the rest. Ticket export records standing serve-consent for
that hash; trust changes take effect on new connections. ShapedStore
implements the full iroh-blobs Store trait to charge provider reads to
an upload token bucket and downloader writes to a download bucket;
upload cap 0 closes incoming connections at accept. Subscribe now
streams transfer_progress both ways, peer_joined, and pin_complete.

Tests: forged-ticket trust gating (denied untrusted, served after
trust), 256 KiB/s upload cap enforced by wall clock, event stream
during a transfer, and real-mdns auto-sync between two daemons
(skips where multicast is unavailable).

Dependencies: n0-future, async-channel, futures-lite, bytes — all
already in the tree via iroh; needed directly to name types in
iroh-blobs trait signatures and channels. iroh feature
discovery-local-network for MdnsDiscovery.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-14 22:27:58 +02:00

457 lines
16 KiB
Rust

//! Blob store operations on top of the iroh-blobs persistent fs store.
use std::collections::BTreeSet;
use std::path::{Path, PathBuf};
use anyhow::Context;
use iroh_blobs::format::collection::Collection;
use iroh_blobs::hashseq::HashSeq;
use iroh_blobs::store::{
EntryStatus, ImportMode, Map, MapEntry, MapMut, ReadableStore, Store as _,
};
use iroh_blobs::util::local_pool::{LocalPool, LocalPoolHandle};
use iroh_blobs::util::progress::IgnoreProgressSender;
use iroh_blobs::{BlobFormat, Hash, HashAndFormat};
use iroh_io::{AsyncSliceReader, AsyncSliceReaderExt};
use tokio::io::AsyncWriteExt;
use tracing::{debug, info};
use varde_proto::MaterializeMode;
use crate::meta::StoredFormat;
/// Operation errors that map onto protocol error codes.
#[derive(Debug, thiserror::Error)]
pub enum OpError {
#[error("{0}")]
NotFound(String),
#[error("{0}")]
InvalidArgument(String),
#[error(transparent)]
Io(#[from] std::io::Error),
#[error(transparent)]
Internal(#[from] anyhow::Error),
#[error("{0}")]
Unimplemented(String),
}
/// The daemon's blob store: an iroh-blobs fs store rooted at
/// `<store_dir>/blobs`.
///
/// Reads from store entries yield non-`Send` futures, so those operations
/// run on a dedicated [`LocalPool`] — the same pattern iroh-blobs itself
/// uses for its provider and GC tasks.
#[derive(Debug, Clone)]
pub struct BlobStore {
store: iroh_blobs::store::fs::Store,
data_dir: PathBuf,
pool: LocalPoolHandle,
// Owns the pool threads; dropped when the last clone goes away.
_pool: std::sync::Arc<LocalPool>,
}
/// Reading a blob entry for a streaming copy happens in chunks this size.
const COPY_CHUNK: u64 = 1024 * 1024;
impl BlobStore {
pub async fn open(store_dir: &Path) -> anyhow::Result<BlobStore> {
let blobs_dir = store_dir.join("blobs");
let store = iroh_blobs::store::fs::Store::load(&blobs_dir)
.await
.with_context(|| format!("opening blob store at {}", blobs_dir.display()))?;
let pool = LocalPool::default();
Ok(BlobStore {
store,
data_dir: blobs_dir.join("data"),
pool: pool.handle().clone(),
_pool: std::sync::Arc::new(pool),
})
}
/// Run a non-`Send` store operation on the local pool.
async fn on_pool<T, F, Fut>(&self, f: F) -> Result<T, OpError>
where
F: FnOnce(BlobStore) -> Fut + Send + 'static,
Fut: std::future::Future<Output = Result<T, OpError>> + 'static,
T: Send + 'static,
{
let this = self.clone();
self.pool
.spawn(move || f(this))
.await
.map_err(|e| OpError::Internal(anyhow::anyhow!("local pool: {e}")))?
}
/// Access to the underlying iroh-blobs store (used by the transfer
/// layer).
pub fn inner(&self) -> &iroh_blobs::store::fs::Store {
&self.store
}
/// The local pool the transfer layer shares for non-`Send` blob work.
pub fn pool_handle(&self) -> LocalPoolHandle {
self.pool.clone()
}
/// Import a file or directory. Returns the root hash, total imported
/// bytes, and the resulting format (`Raw` for files, `HashSeq` for
/// directories).
pub async fn add_path(
&self,
path: &Path,
recursive: bool,
) -> Result<(Hash, u64, StoredFormat), OpError> {
if !path.is_absolute() {
return Err(OpError::InvalidArgument(format!(
"path must be absolute: {}",
path.display()
)));
}
let meta = std::fs::metadata(path)?;
if meta.is_file() {
let (tag, size) = self.import_one(path.to_owned()).await?;
info!(hash = %tag.hash().to_hex(), size, "imported file");
return Ok((*tag.hash(), size, StoredFormat::Raw));
}
if !meta.is_dir() {
return Err(OpError::InvalidArgument(format!(
"not a file or directory: {}",
path.display()
)));
}
if !recursive {
return Err(OpError::InvalidArgument(format!(
"{} is a directory; pass recursive=true",
path.display()
)));
}
let mut files = Vec::new();
collect_files(path, path, &mut files)?;
if files.is_empty() {
return Err(OpError::InvalidArgument(format!(
"directory {} contains no files",
path.display()
)));
}
// Temp tags keep the children alive until the collection root is
// stored (and this method's caller records/pins the root).
let mut children = Vec::new();
let mut total = 0u64;
for (name, file_path) in files {
let (tag, size) = self.import_one(file_path).await?;
total += size;
children.push((name, tag));
}
let collection: Collection = children
.iter()
.map(|(name, tag)| (name.clone(), *tag.hash()))
.collect();
let root_tag = collection
.store(&self.store)
.await
.context("storing collection")?;
let root = *root_tag.hash();
info!(hash = %root.to_hex(), files = children.len(), total, "imported directory");
Ok((root, total, StoredFormat::HashSeq))
}
async fn import_one(&self, path: PathBuf) -> Result<(iroh_blobs::TempTag, u64), OpError> {
let (tag, size) = self
.store
.import_file(
path,
ImportMode::Copy,
BlobFormat::Raw,
IgnoreProgressSender::default(),
)
.await?;
Ok((tag, size))
}
/// Export `hash` to `dest`. Returns bytes written and whether at least
/// one file was reflinked.
pub async fn materialize(
&self,
hash: Hash,
format: StoredFormat,
dest: &Path,
mode: MaterializeMode,
) -> Result<(u64, bool), OpError> {
if !dest.is_absolute() {
return Err(OpError::InvalidArgument(format!(
"dest must be absolute: {}",
dest.display()
)));
}
let dest = dest.to_owned();
self.on_pool(
move |this| async move { this.materialize_local(hash, format, &dest, mode).await },
)
.await
}
async fn materialize_local(
&self,
hash: Hash,
format: StoredFormat,
dest: &Path,
mode: MaterializeMode,
) -> Result<(u64, bool), OpError> {
let allow_reflink = matches!(mode, MaterializeMode::ReflinkOrCopy);
match format {
StoredFormat::Raw => self.export_blob(hash, dest, allow_reflink).await,
StoredFormat::HashSeq => {
let collection = Collection::load_db(&self.store, &hash)
.await
.map_err(|e| OpError::NotFound(format!("loading collection: {e}")))?;
let mut total = 0u64;
let mut any_reflink = false;
tokio::fs::create_dir_all(dest).await?;
for (name, child) in collection.iter() {
let rel = sanitize_collection_name(name)?;
let (bytes, reflinked) = self
.export_blob(*child, &dest.join(rel), allow_reflink)
.await?;
total += bytes;
any_reflink |= reflinked;
}
Ok((total, any_reflink))
}
}
}
/// Export one blob. Tries `FICLONE` via reflink first (zero-copy on
/// btrfs/XFS when store and dest share a filesystem), falls back to a
/// streaming copy. Never hardlinks: store files must stay immutable.
async fn export_blob(
&self,
hash: Hash,
dest: &Path,
allow_reflink: bool,
) -> Result<(u64, bool), OpError> {
let entry =
self.store.get(&hash).await?.ok_or_else(|| {
OpError::NotFound(format!("{} is not in the store", hash.to_hex()))
})?;
if !entry.is_complete() {
return Err(OpError::NotFound(format!(
"{} is only partially present",
hash.to_hex()
)));
}
let size = entry.size().value();
if let Some(parent) = dest.parent() {
tokio::fs::create_dir_all(parent).await?;
}
// Materialize replaces the destination, it never appends.
match tokio::fs::remove_file(dest).await {
Ok(()) => {}
Err(e) if e.kind() == std::io::ErrorKind::NotFound => {}
Err(e) => return Err(e.into()),
}
if allow_reflink {
// Complete blobs above the inline threshold live as plain
// files at data/<hex>.data; those we can clone directly.
// Inline (small) blobs have no backing file and are copied.
let src = self.data_dir.join(format!("{}.data", hash.to_hex()));
let src_ok = std::fs::metadata(&src)
.map(|m| m.len() == size)
.unwrap_or(false);
if src_ok {
match reflink_copy::reflink(&src, dest) {
Ok(()) => {
debug!(hash = %hash.to_hex(), dest = %dest.display(), "reflinked");
return Ok((size, true));
}
Err(e) => {
debug!(error = %e, "reflink failed, falling back to copy");
}
}
}
}
let mut reader = entry.data_reader();
let mut file = tokio::fs::File::create(dest).await?;
let mut offset = 0u64;
while offset < size {
let len = (size - offset).min(COPY_CHUNK) as usize;
let chunk = reader.read_at(offset, len).await?;
if chunk.is_empty() {
return Err(OpError::Io(std::io::Error::new(
std::io::ErrorKind::UnexpectedEof,
format!("blob {} truncated at {offset}", hash.to_hex()),
)));
}
file.write_all(&chunk).await?;
offset += chunk.len() as u64;
}
file.flush().await?;
Ok((size, false))
}
/// Presence of `hash`: (have_bytes, total_bytes, complete).
pub async fn presence(&self, hash: Hash) -> Result<(u64, Option<u64>, bool), OpError> {
match self.store.entry_status(&hash).await? {
EntryStatus::NotFound => Ok((0, None, false)),
EntryStatus::Partial => {
let total = self.store.get(&hash).await?.map(|e| e.size().value());
// Valid-range accounting for partials arrives with the
// transfer milestone; absence of data is the safe report.
Ok((0, total, false))
}
EntryStatus::Complete => {
let entry = self
.store
.get(&hash)
.await?
.ok_or_else(|| OpError::NotFound(hash.to_hex().to_string()))?;
let size = entry.size().value();
Ok((size, Some(size), true))
}
}
}
/// The child hashes of a complete HashSeq root (empty for absent or
/// partial roots).
pub async fn hashseq_children(&self, root: Hash) -> Result<Vec<Hash>, OpError> {
self.on_pool(move |this| async move {
let Some(entry) = this.store.get(&root).await? else {
return Ok(Vec::new());
};
if !entry.is_complete() {
return Ok(Vec::new());
}
let mut reader = entry.data_reader();
let bytes = reader.read_to_end().await?;
let seq = HashSeq::try_from(bytes)
.map_err(|e| OpError::Internal(anyhow::anyhow!("invalid hashseq: {e}")))?;
Ok(seq.iter().collect())
})
.await
}
/// Drop every blob not reachable from `roots` (mark and sweep).
/// In-flight imports are protected by their temp tags; tags stored in
/// the blob database are honored too.
pub async fn gc(&self, roots: Vec<HashAndFormat>) -> Result<u64, OpError> {
self.on_pool(move |this| async move { this.gc_local(roots).await })
.await
}
async fn gc_local(&self, roots: Vec<HashAndFormat>) -> Result<u64, OpError> {
let mut live: BTreeSet<Hash> = BTreeSet::new();
let mut all_roots = roots;
all_roots.extend(self.store.temp_tags());
for item in self.store.tags(None, None).await.context(TAGS_CONTEXT)? {
let (_name, haf) = item.context(TAGS_CONTEXT)?;
all_roots.push(haf);
}
for HashAndFormat { hash, format } in all_roots {
if !live.insert(hash) || format.is_raw() {
continue;
}
// HashSeq root: its children are live too. A partial root
// can't be expanded; its bytes are still protected.
let Some(entry) = self.store.get(&hash).await? else {
continue;
};
if !entry.is_complete() {
continue;
}
let mut reader = entry.data_reader();
let bytes = reader.read_to_end().await?;
let seq = HashSeq::try_from(bytes)
.map_err(|e| OpError::Internal(anyhow::anyhow!("invalid hashseq: {e}")))?;
live.extend(seq.iter());
}
let mut doomed = Vec::new();
for hash in self
.store
.blobs()
.await?
.chain(self.store.partial_blobs().await?)
{
let hash = hash?;
if !live.contains(&hash) {
doomed.push(hash);
}
}
let removed = doomed.len() as u64;
if !doomed.is_empty() {
self.store.delete(doomed).await?;
}
info!(removed, live = live.len(), "gc done");
Ok(removed)
}
/// Flush and shut down the store actor.
pub async fn shutdown(&self) {
self.store.shutdown().await;
}
}
const TAGS_CONTEXT: &str = "listing tags";
/// Recursively collect regular files under `dir` as (relative-name, path),
/// sorted for deterministic collection hashes. Symlinks are followed for
/// files; symlinked directories are rejected to avoid cycles.
fn collect_files(root: &Path, dir: &Path, out: &mut Vec<(String, PathBuf)>) -> Result<(), OpError> {
let mut entries: Vec<_> =
std::fs::read_dir(dir)?.collect::<Result<Vec<_>, std::io::Error>>()?;
entries.sort_by_key(|e| e.file_name());
for entry in entries {
let path = entry.path();
let file_type = entry.file_type()?;
if file_type.is_dir() {
collect_files(root, &path, out)?;
} else if file_type.is_symlink() && std::fs::metadata(&path)?.is_dir() {
return Err(OpError::InvalidArgument(format!(
"symlinked directory not supported: {}",
path.display()
)));
} else {
let rel = path
.strip_prefix(root)
.expect("walked path is under root")
.components()
.map(|c| c.as_os_str().to_string_lossy())
.collect::<Vec<_>>()
.join("/");
out.push((rel, path));
}
}
Ok(())
}
/// Turn a collection entry name into a safe relative path.
fn sanitize_collection_name(name: &str) -> Result<PathBuf, OpError> {
let mut path = PathBuf::new();
for comp in name.split('/') {
if comp.is_empty() || comp == "." || comp == ".." {
return Err(OpError::InvalidArgument(format!(
"unsafe name in collection: {name:?}"
)));
}
path.push(comp);
}
Ok(path)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn collection_names_are_sanitized() {
assert!(sanitize_collection_name("a/b.txt").is_ok());
assert!(sanitize_collection_name("../etc/passwd").is_err());
assert!(sanitize_collection_name("/abs").is_err());
assert!(sanitize_collection_name("a//b").is_err());
assert!(sanitize_collection_name("a/./b").is_err());
}
}