about summary refs log tree commit diff
path: root/tvix/eval/src/io.rs
diff options
context:
space:
mode:
authorConnor Brewster <cbrewster@hey.com>2024-03-22T23·52-0500
committerConnor Brewster <cbrewster@hey.com>2024-04-09T17·31+0000
commit63116d8c21afdc50725ae93d13839fe1915b06b7 (patch)
tree4997838251dac809c2917b35e5d32224030ba595 /tvix/eval/src/io.rs
parent17849c5c0033fa1909f0403b5d5e6a5e018b7fee (diff)
fix(tvix): Avoid buffering file into memory in builtins.hashFile r/7882
Right now `builtins.hashFile` always reads the entire file into memory
before hashing, which is not ideal for large files. This replaces
`read_to_string` with `open_file` which allows calculating the hash of
the file without buffering it entirely into memory. Other callers can
continue to buffer into memory if they choose, but they still use the
`open_file` VM request and then call `read_to_string` or `read_to_end`
on the `std::io::Reader`.

Fixes b/380

Change-Id: Ifa1c8324bcee8f751604b0b449feab875c632fda
Reviewed-on: https://cl.tvl.fyi/c/depot/+/11236
Reviewed-by: flokli <flokli@flokli.de>
Tested-by: BuildkiteCI
Diffstat (limited to 'tvix/eval/src/io.rs')
-rw-r--r--tvix/eval/src/io.rs16
1 files changed, 6 insertions, 10 deletions
diff --git a/tvix/eval/src/io.rs b/tvix/eval/src/io.rs
index 1c38bc68de90..f775077af818 100644
--- a/tvix/eval/src/io.rs
+++ b/tvix/eval/src/io.rs
@@ -16,6 +16,7 @@
 //! how store paths are opened and so on.
 
 use std::{
+    fs::File,
     io,
     path::{Path, PathBuf},
 };
@@ -48,13 +49,8 @@ pub trait EvalIO {
     /// * `builtins.pathExists :: path -> bool`
     fn path_exists(&self, path: &Path) -> io::Result<bool>;
 
-    /// Read the file at the specified path to a `Vec<u8>`.
-    ///
-    /// This is used for the following language evaluation cases:
-    ///
-    /// * `builtins.readFile :: path -> string`
-    /// * `builtins.import :: path -> any`
-    fn read_to_end(&self, path: &Path) -> io::Result<Vec<u8>>;
+    /// Open the file at the specified path to a `io::Read`.
+    fn open(&self, path: &Path) -> io::Result<Box<dyn io::Read>>;
 
     /// Read the directory at the specified path and return the names
     /// of its entries associated with their [`FileType`].
@@ -99,8 +95,8 @@ impl EvalIO for StdIO {
         path.try_exists()
     }
 
-    fn read_to_end(&self, path: &Path) -> io::Result<Vec<u8>> {
-        std::fs::read(path)
+    fn open(&self, path: &Path) -> io::Result<Box<dyn io::Read>> {
+        Ok(Box::new(File::open(path)?))
     }
 
     fn read_dir(&self, path: &Path) -> io::Result<Vec<(bytes::Bytes, FileType)>> {
@@ -145,7 +141,7 @@ impl EvalIO for DummyIO {
         ))
     }
 
-    fn read_to_end(&self, _: &Path) -> io::Result<Vec<u8>> {
+    fn open(&self, _: &Path) -> io::Result<Box<dyn io::Read>> {
         Err(io::Error::new(
             io::ErrorKind::Unsupported,
             "I/O methods are not implemented in DummyIO",