Skip to content

configurable num updates for repo info file #1479

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
dcherian wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

configurable num updates for repo info file #1479

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 16 additions & 10 deletions icechunk-python/src/repository.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2079,9 +2079,10 @@ impl PyRepository {
py.detach(move || {
let result =
pyo3_async_runtimes::tokio::get_runtime().block_on(async move {
let asset_manager = {
let (asset_manager, num_updates) = {
let lock = self.0.read().await;
Arc::clone(lock.asset_manager())
let num_updates = lock.config().num_updates_per_repo_info_file();
(Arc::clone(lock.asset_manager()), num_updates)
};

let result = expire(
Expand All @@ -2097,6 +2098,7 @@ impl PyRepository {
} else {
ExpiredRefAction::Ignore
},
num_updates,
)
.await
.map_err(PyIcechunkStoreError::GCError)?;
Expand All @@ -2123,9 +2125,10 @@ impl PyRepository {
) -> PyResult<Bound<'py, PyAny>> {
let repository = self.0.clone();
pyo3_async_runtimes::tokio::future_into_py::<_, HashSet<String>>(py, async move {
let asset_manager = {
let (asset_manager, num_updates) = {
let lock = repository.read().await;
Arc::clone(lock.asset_manager())
let num_updates = lock.config().num_updates_per_repo_info_file();
(Arc::clone(lock.asset_manager()), num_updates)
};

let result = expire(
Expand All @@ -2141,6 +2144,7 @@ impl PyRepository {
} else {
ExpiredRefAction::Ignore
},
num_updates,
)
.await
.map_err(PyIcechunkStoreError::GCError)?;
Expand Down Expand Up @@ -2170,11 +2174,12 @@ impl PyRepository {
max_concurrent_manifest_fetches,
dry_run,
);
let asset_manager = {
let (asset_manager, num_updates) = {
let lock = self.0.read().await;
Arc::clone(lock.asset_manager())
let num_updates = lock.config().num_updates_per_repo_info_file();
(Arc::clone(lock.asset_manager()), num_updates)
};
let result = garbage_collect(asset_manager, &gc_config)
let result = garbage_collect(asset_manager, &gc_config, num_updates)
.await
.map_err(PyIcechunkStoreError::GCError)?;
Ok::<_, PyIcechunkStoreError>(result.into())
Expand Down Expand Up @@ -2204,11 +2209,12 @@ impl PyRepository {
max_concurrent_manifest_fetches,
dry_run,
);
let asset_manager = {
let (asset_manager, num_updates) = {
let lock = repository.read().await;
Arc::clone(lock.asset_manager())
let num_updates = lock.config().num_updates_per_repo_info_file();
(Arc::clone(lock.asset_manager()), num_updates)
};
let result = garbage_collect(asset_manager, &gc_config)
let result = garbage_collect(asset_manager, &gc_config, num_updates)
.await
.map_err(PyIcechunkStoreError::GCError)?;
Ok(result.into())
Expand Down
19 changes: 19 additions & 0 deletions icechunk/src/config.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -402,12 +402,17 @@ pub struct RepositoryConfig {

#[serde(default)]
pub previous_file: Option<String>,

#[serde(default)]
pub num_updates_per_repo_info_file: Option<usize>,
}

static DEFAULT_COMPRESSION: OnceLock<CompressionConfig> = OnceLock::new();
static DEFAULT_CACHING: OnceLock<CachingConfig> = OnceLock::new();
static DEFAULT_MANIFEST_CONFIG: OnceLock<ManifestConfig> = OnceLock::new();
pub const DEFAULT_MAX_CONCURRENT_REQUESTS: u16 = 256;
// usize?
pub const DEFAULT_NUM_UPDATES_PER_REPO_INFO_FILE: usize = 100;

impl RepositoryConfig {
pub fn inline_chunk_threshold_bytes(&self) -> u16 {
Expand Down Expand Up @@ -441,6 +446,11 @@ impl RepositoryConfig {
self.max_concurrent_requests.unwrap_or(DEFAULT_MAX_CONCURRENT_REQUESTS)
}

pub fn num_updates_per_repo_info_file(&self) -> usize {
self.num_updates_per_repo_info_file
.unwrap_or(DEFAULT_NUM_UPDATES_PER_REPO_INFO_FILE)
}

pub fn merge(&self, other: Self) -> Self {
Self {
inline_chunk_threshold_bytes: other
Expand Down Expand Up @@ -501,6 +511,15 @@ impl RepositoryConfig {
(Some(c), None) => Some(c.clone()),
(Some(_), Some(theirs)) => Some(theirs),
},
num_updates_per_repo_info_file: match (
&self.num_updates_per_repo_info_file,
other.num_updates_per_repo_info_file,
) {
(None, None) => None,
(None, Some(c)) => Some(c),
(Some(c), None) => Some(*c),
(Some(_), Some(theirs)) => Some(theirs),
},
}
}
}
Expand Down
Loading
Loading