Auto merge of #6880 - alexcrichton:cache, r=Eh2406

Parse less JSON on null builds

This commit fixes a performance pathology in Cargo today. Whenever Cargo
generates a lock file (which happens on all invocations of `cargo build`
for example) Cargo will parse the crates.io index to learn about
dependencies. Currently, however, when it parses a crate it parses the
JSON blob for every single version of the crate. With a lock file,
however, or with incremental builds only one of these lines of JSON is
relevant. Measured today Cargo building Cargo parses 3700 JSON
dependencies in the registry.

This commit implements an optimization that brings down the number of
parsed JSON lines in the registry to precisely the right number
necessary to build a project. For example Cargo has 150 crates in its
lock file, so now it only parses 150 JSON lines (a 20x reduction from
3700). This in turn can greatly improve Cargo's null build time. Cargo
building Cargo dropped from 120ms to 60ms on a Linux machine and 400ms
to 200ms on a Mac.

The commit internally has a lot more details about how this is done but
the general idea is to have a cache which is optimized for Cargo to read
which is maintained automatically by Cargo.

Closes #6866

Author: bors

Cargo.toml

@@ -44,6 +44,7 @@ lazycell = "1.2.0"
 libc = "0.2"
 log = "0.4.6"
 libgit2-sys = "0.7.9"
+memchr = "2.1.3"
 num_cpus = "1.0"
 opener = "0.4"
 rustfix = "0.4.4"

src/cargo/core/compiler/layout.rs

@@ -160,10 +160,9 @@ impl Layout {
     pub fn prepare(&mut self) -> io::Result<()> {
         if fs::metadata(&self.root).is_err() {
             fs::create_dir_all(&self.root)?;
+            self.exclude_from_backups(&self.root);
         }
 
-        self.exclude_from_backups(&self.root);
-
         mkdir(&self.deps)?;
         mkdir(&self.native)?;
         mkdir(&self.incremental)?;

src/cargo/core/mod.rs

@@ -14,6 +14,7 @@ pub use self::shell::{Shell, Verbosity};
 pub use self::source::{GitReference, Source, SourceId, SourceMap};
 pub use self::summary::{FeatureMap, FeatureValue, Summary};
 pub use self::workspace::{Members, Workspace, WorkspaceConfig, WorkspaceRootConfig};
+pub use self::interning::InternedString;
 
 pub mod compiler;
 pub mod dependency;

src/cargo/core/package.rs

@@ -25,6 +25,7 @@ use crate::ops;
 use crate::util::errors::{CargoResult, CargoResultExt, HttpNot200};
 use crate::util::network::Retry;
 use crate::util::{self, internal, lev_distance, Config, Progress, ProgressStyle};
+use crate::util::config::PackageCacheLock;
 
 /// Information about a package that is available somewhere in the file system.
 ///
@@ -339,6 +340,9 @@ pub struct Downloads<'a, 'cfg: 'a> {
     /// trigger a timeout; reset `next_speed_check` and set this back to the
     /// configured threshold.
     next_speed_check_bytes_threshold: Cell<u64>,
+    /// Global filesystem lock to ensure only one Cargo is downloading at a
+    /// time.
+    _lock: PackageCacheLock<'cfg>,
 }
 
 struct Download<'cfg> {
@@ -437,6 +441,7 @@ impl<'cfg> PackageSet<'cfg> {
             timeout,
             next_speed_check: Cell::new(Instant::now()),
             next_speed_check_bytes_threshold: Cell::new(0),
+            _lock: self.config.acquire_package_cache_lock()?,
         })
     }
 

src/cargo/core/source/source_id.rs

@@ -337,7 +337,7 @@ impl SourceId {
             Kind::Registry => {}
             _ => return false,
         }
-        self.inner.url.to_string() == CRATES_IO_INDEX
+        self.inner.url.as_str() == CRATES_IO_INDEX
     }
 
     /// Hashes `self`.

src/cargo/ops/cargo_generate_lockfile.rs

@@ -40,6 +40,10 @@ pub fn update_lockfile(ws: &Workspace<'_>, opts: &UpdateOptions<'_>) -> CargoRes
         failure::bail!("you can't update in the offline mode");
     }
 
+    // Updates often require a lot of modifications to the registry, so ensure
+    // that we're synchronized against other Cargos.
+    let _lock = ws.config().acquire_package_cache_lock()?;
+
     let previous_resolve = match ops::load_pkg_lockfile(ws)? {
         Some(resolve) => resolve,
         None => return generate_lockfile(ws),
@@ -73,6 +77,7 @@ pub fn update_lockfile(ws: &Workspace<'_>, opts: &UpdateOptions<'_>) -> CargoRes
                 });
             }
         }
+
         registry.add_sources(sources)?;
     }
 

src/cargo/ops/cargo_install.rs

@@ -488,6 +488,11 @@ fn check_yanked_install(ws: &Workspace<'_>) -> CargoResult<()> {
     // wouldn't be available for `compile_ws`.
     let (pkg_set, resolve) = ops::resolve_ws_with_method(ws, Method::Everything, &specs)?;
     let mut sources = pkg_set.sources_mut();
+
+    // Checking the yanked status invovles taking a look at the registry and
+    // maybe updating files, so be sure to lock it here.
+    let _lock = ws.config().acquire_package_cache_lock()?;
+
     for pkg_id in resolve.iter() {
         if let Some(source) = sources.get_mut(pkg_id.source_id()) {
             if source.is_yanked(pkg_id)? {

src/cargo/ops/cargo_package.rs

@@ -548,6 +548,10 @@ fn compare_resolve(
 }
 
 fn check_yanked(config: &Config, pkg_set: &PackageSet<'_>, resolve: &Resolve) -> CargoResult<()> {
+    // Checking the yanked status invovles taking a look at the registry and
+    // maybe updating files, so be sure to lock it here.
+    let _lock = config.acquire_package_cache_lock()?;
+
     let mut sources = pkg_set.sources_mut();
     for pkg_id in resolve.iter() {
         if let Some(source) = sources.get_mut(pkg_id.source_id()) {

src/cargo/ops/common_for_install_and_uninstall.rs

@@ -564,6 +564,11 @@ pub fn select_pkg<'a, T>(
 where
     T: Source + 'a,
 {
+    // This operation may involve updating some sources or making a few queries
+    // which may involve frobbing caches, as a result make sure we synchronize
+    // with other global Cargos
+    let _lock = config.acquire_package_cache_lock()?;
+
     if needs_update {
         source.update()?;
     }

src/cargo/ops/registry.rs

@@ -353,6 +353,7 @@ fn registry(
     let token = token.or(token_config);
     let sid = get_source_id(config, index_config.or(index), registry)?;
     let api_host = {
+        let _lock = config.acquire_package_cache_lock()?;
         let mut src = RegistrySource::remote(sid, &HashSet::new(), config);
         // Only update the index if the config is not available or `force` is set.
         let cfg = src.config();