]> git.proxmox.com Git - rustc.git/blob - compiler/rustc_incremental/src/persist/fs.rs
New upstream version 1.49.0~beta.4+dfsg1
[rustc.git] / compiler / rustc_incremental / src / persist / fs.rs
1 //! This module manages how the incremental compilation cache is represented in
2 //! the file system.
3 //!
4 //! Incremental compilation caches are managed according to a copy-on-write
5 //! strategy: Once a complete, consistent cache version is finalized, it is
6 //! never modified. Instead, when a subsequent compilation session is started,
7 //! the compiler will allocate a new version of the cache that starts out as
8 //! a copy of the previous version. Then only this new copy is modified and it
9 //! will not be visible to other processes until it is finalized. This ensures
10 //! that multiple compiler processes can be executed concurrently for the same
11 //! crate without interfering with each other or blocking each other.
12 //!
13 //! More concretely this is implemented via the following protocol:
14 //!
15 //! 1. For a newly started compilation session, the compiler allocates a
16 //! new `session` directory within the incremental compilation directory.
17 //! This session directory will have a unique name that ends with the suffix
18 //! "-working" and that contains a creation timestamp.
19 //! 2. Next, the compiler looks for the newest finalized session directory,
20 //! that is, a session directory from a previous compilation session that
21 //! has been marked as valid and consistent. A session directory is
22 //! considered finalized if the "-working" suffix in the directory name has
23 //! been replaced by the SVH of the crate.
24 //! 3. Once the compiler has found a valid, finalized session directory, it will
25 //! hard-link/copy its contents into the new "-working" directory. If all
26 //! goes well, it will have its own, private copy of the source directory and
27 //! subsequently not have to worry about synchronizing with other compiler
28 //! processes.
29 //! 4. Now the compiler can do its normal compilation process, which involves
30 //! reading and updating its private session directory.
31 //! 5. When compilation finishes without errors, the private session directory
32 //! will be in a state where it can be used as input for other compilation
33 //! sessions. That is, it will contain a dependency graph and cache artifacts
34 //! that are consistent with the state of the source code it was compiled
35 //! from, with no need to change them ever again. At this point, the compiler
36 //! finalizes and "publishes" its private session directory by renaming it
37 //! from "s-{timestamp}-{random}-working" to "s-{timestamp}-{SVH}".
38 //! 6. At this point the "old" session directory that we copied our data from
39 //! at the beginning of the session has become obsolete because we have just
40 //! published a more current version. Thus the compiler will delete it.
41 //!
42 //! ## Garbage Collection
43 //!
44 //! Naively following the above protocol might lead to old session directories
45 //! piling up if a compiler instance crashes for some reason before its able to
46 //! remove its private session directory. In order to avoid wasting disk space,
47 //! the compiler also does some garbage collection each time it is started in
48 //! incremental compilation mode. Specifically, it will scan the incremental
49 //! compilation directory for private session directories that are not in use
50 //! any more and will delete those. It will also delete any finalized session
51 //! directories for a given crate except for the most recent one.
52 //!
53 //! ## Synchronization
54 //!
55 //! There is some synchronization needed in order for the compiler to be able to
56 //! determine whether a given private session directory is not in used any more.
57 //! This is done by creating a lock file for each session directory and
58 //! locking it while the directory is still being used. Since file locks have
59 //! operating system support, we can rely on the lock being released if the
60 //! compiler process dies for some unexpected reason. Thus, when garbage
61 //! collecting private session directories, the collecting process can determine
62 //! whether the directory is still in use by trying to acquire a lock on the
63 //! file. If locking the file fails, the original process must still be alive.
64 //! If locking the file succeeds, we know that the owning process is not alive
65 //! any more and we can safely delete the directory.
66 //! There is still a small time window between the original process creating the
67 //! lock file and actually locking it. In order to minimize the chance that
68 //! another process tries to acquire the lock in just that instance, only
69 //! session directories that are older than a few seconds are considered for
70 //! garbage collection.
71 //!
72 //! Another case that has to be considered is what happens if one process
73 //! deletes a finalized session directory that another process is currently
74 //! trying to copy from. This case is also handled via the lock file. Before
75 //! a process starts copying a finalized session directory, it will acquire a
76 //! shared lock on the directory's lock file. Any garbage collecting process,
77 //! on the other hand, will acquire an exclusive lock on the lock file.
78 //! Thus, if a directory is being collected, any reader process will fail
79 //! acquiring the shared lock and will leave the directory alone. Conversely,
80 //! if a collecting process can't acquire the exclusive lock because the
81 //! directory is currently being read from, it will leave collecting that
82 //! directory to another process at a later point in time.
83 //! The exact same scheme is also used when reading the metadata hashes file
84 //! from an extern crate. When a crate is compiled, the hash values of its
85 //! metadata are stored in a file in its session directory. When the
86 //! compilation session of another crate imports the first crate's metadata,
87 //! it also has to read in the accompanying metadata hashes. It thus will access
88 //! the finalized session directory of all crates it links to and while doing
89 //! so, it will also place a read lock on that the respective session directory
90 //! so that it won't be deleted while the metadata hashes are loaded.
91 //!
92 //! ## Preconditions
93 //!
94 //! This system relies on two features being available in the file system in
95 //! order to work really well: file locking and hard linking.
96 //! If hard linking is not available (like on FAT) the data in the cache
97 //! actually has to be copied at the beginning of each session.
98 //! If file locking does not work reliably (like on NFS), some of the
99 //! synchronization will go haywire.
100 //! In both cases we recommend to locate the incremental compilation directory
101 //! on a file system that supports these things.
102 //! It might be a good idea though to try and detect whether we are on an
103 //! unsupported file system and emit a warning in that case. This is not yet
104 //! implemented.
105
106 use rustc_data_structures::fx::{FxHashMap, FxHashSet};
107 use rustc_data_structures::svh::Svh;
108 use rustc_data_structures::{base_n, flock};
109 use rustc_fs_util::{link_or_copy, LinkOrCopy};
110 use rustc_session::{CrateDisambiguator, Session};
111
112 use std::fs as std_fs;
113 use std::io;
114 use std::mem;
115 use std::path::{Path, PathBuf};
116 use std::time::{Duration, SystemTime, UNIX_EPOCH};
117
118 use rand::{thread_rng, RngCore};
119
120 #[cfg(test)]
121 mod tests;
122
123 const LOCK_FILE_EXT: &str = ".lock";
124 const DEP_GRAPH_FILENAME: &str = "dep-graph.bin";
125 const WORK_PRODUCTS_FILENAME: &str = "work-products.bin";
126 const QUERY_CACHE_FILENAME: &str = "query-cache.bin";
127
128 // We encode integers using the following base, so they are shorter than decimal
129 // or hexadecimal numbers (we want short file and directory names). Since these
130 // numbers will be used in file names, we choose an encoding that is not
131 // case-sensitive (as opposed to base64, for example).
132 const INT_ENCODE_BASE: usize = base_n::CASE_INSENSITIVE;
133
134 pub fn dep_graph_path(sess: &Session) -> PathBuf {
135 in_incr_comp_dir_sess(sess, DEP_GRAPH_FILENAME)
136 }
137 pub fn dep_graph_path_from(incr_comp_session_dir: &Path) -> PathBuf {
138 in_incr_comp_dir(incr_comp_session_dir, DEP_GRAPH_FILENAME)
139 }
140
141 pub fn work_products_path(sess: &Session) -> PathBuf {
142 in_incr_comp_dir_sess(sess, WORK_PRODUCTS_FILENAME)
143 }
144
145 pub fn query_cache_path(sess: &Session) -> PathBuf {
146 in_incr_comp_dir_sess(sess, QUERY_CACHE_FILENAME)
147 }
148
149 pub fn lock_file_path(session_dir: &Path) -> PathBuf {
150 let crate_dir = session_dir.parent().unwrap();
151
152 let directory_name = session_dir.file_name().unwrap().to_string_lossy();
153 assert_no_characters_lost(&directory_name);
154
155 let dash_indices: Vec<_> = directory_name.match_indices('-').map(|(idx, _)| idx).collect();
156 if dash_indices.len() != 3 {
157 bug!(
158 "Encountered incremental compilation session directory with \
159 malformed name: {}",
160 session_dir.display()
161 )
162 }
163
164 crate_dir.join(&directory_name[0..dash_indices[2]]).with_extension(&LOCK_FILE_EXT[1..])
165 }
166
167 pub fn in_incr_comp_dir_sess(sess: &Session, file_name: &str) -> PathBuf {
168 in_incr_comp_dir(&sess.incr_comp_session_dir(), file_name)
169 }
170
171 pub fn in_incr_comp_dir(incr_comp_session_dir: &Path, file_name: &str) -> PathBuf {
172 incr_comp_session_dir.join(file_name)
173 }
174
175 /// Allocates the private session directory. The boolean in the Ok() result
176 /// indicates whether we should try loading a dep graph from the successfully
177 /// initialized directory, or not.
178 /// The post-condition of this fn is that we have a valid incremental
179 /// compilation session directory, if the result is `Ok`. A valid session
180 /// directory is one that contains a locked lock file. It may or may not contain
181 /// a dep-graph and work products from a previous session.
182 /// If the call fails, the fn may leave behind an invalid session directory.
183 /// The garbage collection will take care of it.
184 pub fn prepare_session_directory(
185 sess: &Session,
186 crate_name: &str,
187 crate_disambiguator: CrateDisambiguator,
188 ) {
189 if sess.opts.incremental.is_none() {
190 return;
191 }
192
193 let _timer = sess.timer("incr_comp_prepare_session_directory");
194
195 debug!("prepare_session_directory");
196
197 // {incr-comp-dir}/{crate-name-and-disambiguator}
198 let crate_dir = crate_path(sess, crate_name, crate_disambiguator);
199 debug!("crate-dir: {}", crate_dir.display());
200 if create_dir(sess, &crate_dir, "crate").is_err() {
201 return;
202 }
203
204 // Hack: canonicalize the path *after creating the directory*
205 // because, on windows, long paths can cause problems;
206 // canonicalization inserts this weird prefix that makes windows
207 // tolerate long paths.
208 let crate_dir = match crate_dir.canonicalize() {
209 Ok(v) => v,
210 Err(err) => {
211 sess.err(&format!(
212 "incremental compilation: error canonicalizing path `{}`: {}",
213 crate_dir.display(),
214 err
215 ));
216 return;
217 }
218 };
219
220 let mut source_directories_already_tried = FxHashSet::default();
221
222 loop {
223 // Generate a session directory of the form:
224 //
225 // {incr-comp-dir}/{crate-name-and-disambiguator}/s-{timestamp}-{random}-working
226 let session_dir = generate_session_dir_path(&crate_dir);
227 debug!("session-dir: {}", session_dir.display());
228
229 // Lock the new session directory. If this fails, return an
230 // error without retrying
231 let (directory_lock, lock_file_path) = match lock_directory(sess, &session_dir) {
232 Ok(e) => e,
233 Err(_) => return,
234 };
235
236 // Now that we have the lock, we can actually create the session
237 // directory
238 if create_dir(sess, &session_dir, "session").is_err() {
239 return;
240 }
241
242 // Find a suitable source directory to copy from. Ignore those that we
243 // have already tried before.
244 let source_directory = find_source_directory(&crate_dir, &source_directories_already_tried);
245
246 let source_directory = if let Some(dir) = source_directory {
247 dir
248 } else {
249 // There's nowhere to copy from, we're done
250 debug!(
251 "no source directory found. Continuing with empty session \
252 directory."
253 );
254
255 sess.init_incr_comp_session(session_dir, directory_lock, false);
256 return;
257 };
258
259 debug!("attempting to copy data from source: {}", source_directory.display());
260
261 // Try copying over all files from the source directory
262 if let Ok(allows_links) = copy_files(sess, &session_dir, &source_directory) {
263 debug!("successfully copied data from: {}", source_directory.display());
264
265 if !allows_links {
266 sess.warn(&format!(
267 "Hard linking files in the incremental \
268 compilation cache failed. Copying files \
269 instead. Consider moving the cache \
270 directory to a file system which supports \
271 hard linking in session dir `{}`",
272 session_dir.display()
273 ));
274 }
275
276 sess.init_incr_comp_session(session_dir, directory_lock, true);
277 return;
278 } else {
279 debug!("copying failed - trying next directory");
280
281 // Something went wrong while trying to copy/link files from the
282 // source directory. Try again with a different one.
283 source_directories_already_tried.insert(source_directory);
284
285 // Try to remove the session directory we just allocated. We don't
286 // know if there's any garbage in it from the failed copy action.
287 if let Err(err) = safe_remove_dir_all(&session_dir) {
288 sess.warn(&format!(
289 "Failed to delete partly initialized \
290 session dir `{}`: {}",
291 session_dir.display(),
292 err
293 ));
294 }
295
296 delete_session_dir_lock_file(sess, &lock_file_path);
297 mem::drop(directory_lock);
298 }
299 }
300 }
301
302 /// This function finalizes and thus 'publishes' the session directory by
303 /// renaming it to `s-{timestamp}-{svh}` and releasing the file lock.
304 /// If there have been compilation errors, however, this function will just
305 /// delete the presumably invalid session directory.
306 pub fn finalize_session_directory(sess: &Session, svh: Svh) {
307 if sess.opts.incremental.is_none() {
308 return;
309 }
310
311 let _timer = sess.timer("incr_comp_finalize_session_directory");
312
313 let incr_comp_session_dir: PathBuf = sess.incr_comp_session_dir().clone();
314
315 if sess.has_errors_or_delayed_span_bugs() {
316 // If there have been any errors during compilation, we don't want to
317 // publish this session directory. Rather, we'll just delete it.
318
319 debug!(
320 "finalize_session_directory() - invalidating session directory: {}",
321 incr_comp_session_dir.display()
322 );
323
324 if let Err(err) = safe_remove_dir_all(&*incr_comp_session_dir) {
325 sess.warn(&format!(
326 "Error deleting incremental compilation \
327 session directory `{}`: {}",
328 incr_comp_session_dir.display(),
329 err
330 ));
331 }
332
333 let lock_file_path = lock_file_path(&*incr_comp_session_dir);
334 delete_session_dir_lock_file(sess, &lock_file_path);
335 sess.mark_incr_comp_session_as_invalid();
336 }
337
338 debug!("finalize_session_directory() - session directory: {}", incr_comp_session_dir.display());
339
340 let old_sub_dir_name = incr_comp_session_dir.file_name().unwrap().to_string_lossy();
341 assert_no_characters_lost(&old_sub_dir_name);
342
343 // Keep the 's-{timestamp}-{random-number}' prefix, but replace the
344 // '-working' part with the SVH of the crate
345 let dash_indices: Vec<_> = old_sub_dir_name.match_indices('-').map(|(idx, _)| idx).collect();
346 if dash_indices.len() != 3 {
347 bug!(
348 "Encountered incremental compilation session directory with \
349 malformed name: {}",
350 incr_comp_session_dir.display()
351 )
352 }
353
354 // State: "s-{timestamp}-{random-number}-"
355 let mut new_sub_dir_name = String::from(&old_sub_dir_name[..=dash_indices[2]]);
356
357 // Append the svh
358 base_n::push_str(svh.as_u64() as u128, INT_ENCODE_BASE, &mut new_sub_dir_name);
359
360 // Create the full path
361 let new_path = incr_comp_session_dir.parent().unwrap().join(new_sub_dir_name);
362 debug!("finalize_session_directory() - new path: {}", new_path.display());
363
364 match std_fs::rename(&*incr_comp_session_dir, &new_path) {
365 Ok(_) => {
366 debug!("finalize_session_directory() - directory renamed successfully");
367
368 // This unlocks the directory
369 sess.finalize_incr_comp_session(new_path);
370 }
371 Err(e) => {
372 // Warn about the error. However, no need to abort compilation now.
373 sess.warn(&format!(
374 "Error finalizing incremental compilation \
375 session directory `{}`: {}",
376 incr_comp_session_dir.display(),
377 e
378 ));
379
380 debug!("finalize_session_directory() - error, marking as invalid");
381 // Drop the file lock, so we can garage collect
382 sess.mark_incr_comp_session_as_invalid();
383 }
384 }
385
386 let _ = garbage_collect_session_directories(sess);
387 }
388
389 pub fn delete_all_session_dir_contents(sess: &Session) -> io::Result<()> {
390 let sess_dir_iterator = sess.incr_comp_session_dir().read_dir()?;
391 for entry in sess_dir_iterator {
392 let entry = entry?;
393 safe_remove_file(&entry.path())?
394 }
395 Ok(())
396 }
397
398 fn copy_files(sess: &Session, target_dir: &Path, source_dir: &Path) -> Result<bool, ()> {
399 // We acquire a shared lock on the lock file of the directory, so that
400 // nobody deletes it out from under us while we are reading from it.
401 let lock_file_path = lock_file_path(source_dir);
402 let _lock = if let Ok(lock) = flock::Lock::new(
403 &lock_file_path,
404 false, // don't wait,
405 false, // don't create
406 false,
407 ) {
408 // not exclusive
409 lock
410 } else {
411 // Could not acquire the lock, don't try to copy from here
412 return Err(());
413 };
414
415 let source_dir_iterator = match source_dir.read_dir() {
416 Ok(it) => it,
417 Err(_) => return Err(()),
418 };
419
420 let mut files_linked = 0;
421 let mut files_copied = 0;
422
423 for entry in source_dir_iterator {
424 match entry {
425 Ok(entry) => {
426 let file_name = entry.file_name();
427
428 let target_file_path = target_dir.join(file_name);
429 let source_path = entry.path();
430
431 debug!("copying into session dir: {}", source_path.display());
432 match link_or_copy(source_path, target_file_path) {
433 Ok(LinkOrCopy::Link) => files_linked += 1,
434 Ok(LinkOrCopy::Copy) => files_copied += 1,
435 Err(_) => return Err(()),
436 }
437 }
438 Err(_) => return Err(()),
439 }
440 }
441
442 if sess.opts.debugging_opts.incremental_info {
443 println!(
444 "[incremental] session directory: \
445 {} files hard-linked",
446 files_linked
447 );
448 println!(
449 "[incremental] session directory: \
450 {} files copied",
451 files_copied
452 );
453 }
454
455 Ok(files_linked > 0 || files_copied == 0)
456 }
457
458 /// Generates unique directory path of the form:
459 /// {crate_dir}/s-{timestamp}-{random-number}-working
460 fn generate_session_dir_path(crate_dir: &Path) -> PathBuf {
461 let timestamp = timestamp_to_string(SystemTime::now());
462 debug!("generate_session_dir_path: timestamp = {}", timestamp);
463 let random_number = thread_rng().next_u32();
464 debug!("generate_session_dir_path: random_number = {}", random_number);
465
466 let directory_name = format!(
467 "s-{}-{}-working",
468 timestamp,
469 base_n::encode(random_number as u128, INT_ENCODE_BASE)
470 );
471 debug!("generate_session_dir_path: directory_name = {}", directory_name);
472 let directory_path = crate_dir.join(directory_name);
473 debug!("generate_session_dir_path: directory_path = {}", directory_path.display());
474 directory_path
475 }
476
477 fn create_dir(sess: &Session, path: &Path, dir_tag: &str) -> Result<(), ()> {
478 match std_fs::create_dir_all(path) {
479 Ok(()) => {
480 debug!("{} directory created successfully", dir_tag);
481 Ok(())
482 }
483 Err(err) => {
484 sess.err(&format!(
485 "Could not create incremental compilation {} \
486 directory `{}`: {}",
487 dir_tag,
488 path.display(),
489 err
490 ));
491 Err(())
492 }
493 }
494 }
495
496 /// Allocate the lock-file and lock it.
497 fn lock_directory(sess: &Session, session_dir: &Path) -> Result<(flock::Lock, PathBuf), ()> {
498 let lock_file_path = lock_file_path(session_dir);
499 debug!("lock_directory() - lock_file: {}", lock_file_path.display());
500
501 match flock::Lock::new(
502 &lock_file_path,
503 false, // don't wait
504 true, // create the lock file
505 true,
506 ) {
507 // the lock should be exclusive
508 Ok(lock) => Ok((lock, lock_file_path)),
509 Err(err) => {
510 sess.err(&format!(
511 "incremental compilation: could not create \
512 session directory lock file: {}",
513 err
514 ));
515 Err(())
516 }
517 }
518 }
519
520 fn delete_session_dir_lock_file(sess: &Session, lock_file_path: &Path) {
521 if let Err(err) = safe_remove_file(&lock_file_path) {
522 sess.warn(&format!(
523 "Error deleting lock file for incremental \
524 compilation session directory `{}`: {}",
525 lock_file_path.display(),
526 err
527 ));
528 }
529 }
530
531 /// Finds the most recent published session directory that is not in the
532 /// ignore-list.
533 fn find_source_directory(
534 crate_dir: &Path,
535 source_directories_already_tried: &FxHashSet<PathBuf>,
536 ) -> Option<PathBuf> {
537 let iter = crate_dir
538 .read_dir()
539 .unwrap() // FIXME
540 .filter_map(|e| e.ok().map(|e| e.path()));
541
542 find_source_directory_in_iter(iter, source_directories_already_tried)
543 }
544
545 fn find_source_directory_in_iter<I>(
546 iter: I,
547 source_directories_already_tried: &FxHashSet<PathBuf>,
548 ) -> Option<PathBuf>
549 where
550 I: Iterator<Item = PathBuf>,
551 {
552 let mut best_candidate = (UNIX_EPOCH, None);
553
554 for session_dir in iter {
555 debug!("find_source_directory_in_iter - inspecting `{}`", session_dir.display());
556
557 let directory_name = session_dir.file_name().unwrap().to_string_lossy();
558 assert_no_characters_lost(&directory_name);
559
560 if source_directories_already_tried.contains(&session_dir)
561 || !is_session_directory(&directory_name)
562 || !is_finalized(&directory_name)
563 {
564 debug!("find_source_directory_in_iter - ignoring");
565 continue;
566 }
567
568 let timestamp = extract_timestamp_from_session_dir(&directory_name).unwrap_or_else(|_| {
569 bug!("unexpected incr-comp session dir: {}", session_dir.display())
570 });
571
572 if timestamp > best_candidate.0 {
573 best_candidate = (timestamp, Some(session_dir.clone()));
574 }
575 }
576
577 best_candidate.1
578 }
579
580 fn is_finalized(directory_name: &str) -> bool {
581 !directory_name.ends_with("-working")
582 }
583
584 fn is_session_directory(directory_name: &str) -> bool {
585 directory_name.starts_with("s-") && !directory_name.ends_with(LOCK_FILE_EXT)
586 }
587
588 fn is_session_directory_lock_file(file_name: &str) -> bool {
589 file_name.starts_with("s-") && file_name.ends_with(LOCK_FILE_EXT)
590 }
591
592 fn extract_timestamp_from_session_dir(directory_name: &str) -> Result<SystemTime, ()> {
593 if !is_session_directory(directory_name) {
594 return Err(());
595 }
596
597 let dash_indices: Vec<_> = directory_name.match_indices('-').map(|(idx, _)| idx).collect();
598 if dash_indices.len() != 3 {
599 return Err(());
600 }
601
602 string_to_timestamp(&directory_name[dash_indices[0] + 1..dash_indices[1]])
603 }
604
605 fn timestamp_to_string(timestamp: SystemTime) -> String {
606 let duration = timestamp.duration_since(UNIX_EPOCH).unwrap();
607 let micros = duration.as_secs() * 1_000_000 + (duration.subsec_nanos() as u64) / 1000;
608 base_n::encode(micros as u128, INT_ENCODE_BASE)
609 }
610
611 fn string_to_timestamp(s: &str) -> Result<SystemTime, ()> {
612 let micros_since_unix_epoch = u64::from_str_radix(s, INT_ENCODE_BASE as u32);
613
614 if micros_since_unix_epoch.is_err() {
615 return Err(());
616 }
617
618 let micros_since_unix_epoch = micros_since_unix_epoch.unwrap();
619
620 let duration = Duration::new(
621 micros_since_unix_epoch / 1_000_000,
622 1000 * (micros_since_unix_epoch % 1_000_000) as u32,
623 );
624 Ok(UNIX_EPOCH + duration)
625 }
626
627 fn crate_path(
628 sess: &Session,
629 crate_name: &str,
630 crate_disambiguator: CrateDisambiguator,
631 ) -> PathBuf {
632 let incr_dir = sess.opts.incremental.as_ref().unwrap().clone();
633
634 // The full crate disambiguator is really long. 64 bits of it should be
635 // sufficient.
636 let crate_disambiguator = crate_disambiguator.to_fingerprint().to_smaller_hash();
637 let crate_disambiguator = base_n::encode(crate_disambiguator as u128, INT_ENCODE_BASE);
638
639 let crate_name = format!("{}-{}", crate_name, crate_disambiguator);
640 incr_dir.join(crate_name)
641 }
642
643 fn assert_no_characters_lost(s: &str) {
644 if s.contains('\u{FFFD}') {
645 bug!("Could not losslessly convert '{}'.", s)
646 }
647 }
648
649 fn is_old_enough_to_be_collected(timestamp: SystemTime) -> bool {
650 timestamp < SystemTime::now() - Duration::from_secs(10)
651 }
652
653 pub fn garbage_collect_session_directories(sess: &Session) -> io::Result<()> {
654 debug!("garbage_collect_session_directories() - begin");
655
656 let session_directory = sess.incr_comp_session_dir();
657 debug!(
658 "garbage_collect_session_directories() - session directory: {}",
659 session_directory.display()
660 );
661
662 let crate_directory = session_directory.parent().unwrap();
663 debug!(
664 "garbage_collect_session_directories() - crate directory: {}",
665 crate_directory.display()
666 );
667
668 // First do a pass over the crate directory, collecting lock files and
669 // session directories
670 let mut session_directories = FxHashSet::default();
671 let mut lock_files = FxHashSet::default();
672
673 for dir_entry in crate_directory.read_dir()? {
674 let dir_entry = match dir_entry {
675 Ok(dir_entry) => dir_entry,
676 _ => {
677 // Ignore any errors
678 continue;
679 }
680 };
681
682 let entry_name = dir_entry.file_name();
683 let entry_name = entry_name.to_string_lossy();
684
685 if is_session_directory_lock_file(&entry_name) {
686 assert_no_characters_lost(&entry_name);
687 lock_files.insert(entry_name.into_owned());
688 } else if is_session_directory(&entry_name) {
689 assert_no_characters_lost(&entry_name);
690 session_directories.insert(entry_name.into_owned());
691 } else {
692 // This is something we don't know, leave it alone
693 }
694 }
695
696 // Now map from lock files to session directories
697 let lock_file_to_session_dir: FxHashMap<String, Option<String>> = lock_files
698 .into_iter()
699 .map(|lock_file_name| {
700 assert!(lock_file_name.ends_with(LOCK_FILE_EXT));
701 let dir_prefix_end = lock_file_name.len() - LOCK_FILE_EXT.len();
702 let session_dir = {
703 let dir_prefix = &lock_file_name[0..dir_prefix_end];
704 session_directories.iter().find(|dir_name| dir_name.starts_with(dir_prefix))
705 };
706 (lock_file_name, session_dir.map(String::clone))
707 })
708 .collect();
709
710 // Delete all lock files, that don't have an associated directory. They must
711 // be some kind of leftover
712 for (lock_file_name, directory_name) in &lock_file_to_session_dir {
713 if directory_name.is_none() {
714 let timestamp = match extract_timestamp_from_session_dir(lock_file_name) {
715 Ok(timestamp) => timestamp,
716 Err(()) => {
717 debug!(
718 "found lock-file with malformed timestamp: {}",
719 crate_directory.join(&lock_file_name).display()
720 );
721 // Ignore it
722 continue;
723 }
724 };
725
726 let lock_file_path = crate_directory.join(&**lock_file_name);
727
728 if is_old_enough_to_be_collected(timestamp) {
729 debug!(
730 "garbage_collect_session_directories() - deleting \
731 garbage lock file: {}",
732 lock_file_path.display()
733 );
734 delete_session_dir_lock_file(sess, &lock_file_path);
735 } else {
736 debug!(
737 "garbage_collect_session_directories() - lock file with \
738 no session dir not old enough to be collected: {}",
739 lock_file_path.display()
740 );
741 }
742 }
743 }
744
745 // Filter out `None` directories
746 let lock_file_to_session_dir: FxHashMap<String, String> = lock_file_to_session_dir
747 .into_iter()
748 .filter_map(|(lock_file_name, directory_name)| directory_name.map(|n| (lock_file_name, n)))
749 .collect();
750
751 // Delete all session directories that don't have a lock file.
752 for directory_name in session_directories {
753 if !lock_file_to_session_dir.values().any(|dir| *dir == directory_name) {
754 let path = crate_directory.join(directory_name);
755 if let Err(err) = safe_remove_dir_all(&path) {
756 sess.warn(&format!(
757 "Failed to garbage collect invalid incremental \
758 compilation session directory `{}`: {}",
759 path.display(),
760 err
761 ));
762 }
763 }
764 }
765
766 // Now garbage collect the valid session directories.
767 let mut deletion_candidates = vec![];
768
769 for (lock_file_name, directory_name) in &lock_file_to_session_dir {
770 debug!("garbage_collect_session_directories() - inspecting: {}", directory_name);
771
772 let timestamp = match extract_timestamp_from_session_dir(directory_name) {
773 Ok(timestamp) => timestamp,
774 Err(()) => {
775 debug!(
776 "found session-dir with malformed timestamp: {}",
777 crate_directory.join(directory_name).display()
778 );
779 // Ignore it
780 continue;
781 }
782 };
783
784 if is_finalized(directory_name) {
785 let lock_file_path = crate_directory.join(lock_file_name);
786 match flock::Lock::new(
787 &lock_file_path,
788 false, // don't wait
789 false, // don't create the lock-file
790 true,
791 ) {
792 // get an exclusive lock
793 Ok(lock) => {
794 debug!(
795 "garbage_collect_session_directories() - \
796 successfully acquired lock"
797 );
798 debug!(
799 "garbage_collect_session_directories() - adding \
800 deletion candidate: {}",
801 directory_name
802 );
803
804 // Note that we are holding on to the lock
805 deletion_candidates.push((
806 timestamp,
807 crate_directory.join(directory_name),
808 Some(lock),
809 ));
810 }
811 Err(_) => {
812 debug!(
813 "garbage_collect_session_directories() - \
814 not collecting, still in use"
815 );
816 }
817 }
818 } else if is_old_enough_to_be_collected(timestamp) {
819 // When cleaning out "-working" session directories, i.e.
820 // session directories that might still be in use by another
821 // compiler instance, we only look a directories that are
822 // at least ten seconds old. This is supposed to reduce the
823 // chance of deleting a directory in the time window where
824 // the process has allocated the directory but has not yet
825 // acquired the file-lock on it.
826
827 // Try to acquire the directory lock. If we can't, it
828 // means that the owning process is still alive and we
829 // leave this directory alone.
830 let lock_file_path = crate_directory.join(lock_file_name);
831 match flock::Lock::new(
832 &lock_file_path,
833 false, // don't wait
834 false, // don't create the lock-file
835 true,
836 ) {
837 // get an exclusive lock
838 Ok(lock) => {
839 debug!(
840 "garbage_collect_session_directories() - \
841 successfully acquired lock"
842 );
843
844 delete_old(sess, &crate_directory.join(directory_name));
845
846 // Let's make it explicit that the file lock is released at this point,
847 // or rather, that we held on to it until here
848 mem::drop(lock);
849 }
850 Err(_) => {
851 debug!(
852 "garbage_collect_session_directories() - \
853 not collecting, still in use"
854 );
855 }
856 }
857 } else {
858 debug!(
859 "garbage_collect_session_directories() - not finalized, not \
860 old enough"
861 );
862 }
863 }
864
865 // Delete all but the most recent of the candidates
866 for (path, lock) in all_except_most_recent(deletion_candidates) {
867 debug!("garbage_collect_session_directories() - deleting `{}`", path.display());
868
869 if let Err(err) = safe_remove_dir_all(&path) {
870 sess.warn(&format!(
871 "Failed to garbage collect finalized incremental \
872 compilation session directory `{}`: {}",
873 path.display(),
874 err
875 ));
876 } else {
877 delete_session_dir_lock_file(sess, &lock_file_path(&path));
878 }
879
880 // Let's make it explicit that the file lock is released at this point,
881 // or rather, that we held on to it until here
882 mem::drop(lock);
883 }
884
885 Ok(())
886 }
887
888 fn delete_old(sess: &Session, path: &Path) {
889 debug!("garbage_collect_session_directories() - deleting `{}`", path.display());
890
891 if let Err(err) = safe_remove_dir_all(&path) {
892 sess.warn(&format!(
893 "Failed to garbage collect incremental compilation session directory `{}`: {}",
894 path.display(),
895 err
896 ));
897 } else {
898 delete_session_dir_lock_file(sess, &lock_file_path(&path));
899 }
900 }
901
902 fn all_except_most_recent(
903 deletion_candidates: Vec<(SystemTime, PathBuf, Option<flock::Lock>)>,
904 ) -> FxHashMap<PathBuf, Option<flock::Lock>> {
905 let most_recent = deletion_candidates.iter().map(|&(timestamp, ..)| timestamp).max();
906
907 if let Some(most_recent) = most_recent {
908 deletion_candidates
909 .into_iter()
910 .filter(|&(timestamp, ..)| timestamp != most_recent)
911 .map(|(_, path, lock)| (path, lock))
912 .collect()
913 } else {
914 FxHashMap::default()
915 }
916 }
917
918 /// Since paths of artifacts within session directories can get quite long, we
919 /// need to support deleting files with very long paths. The regular
920 /// WinApi functions only support paths up to 260 characters, however. In order
921 /// to circumvent this limitation, we canonicalize the path of the directory
922 /// before passing it to std::fs::remove_dir_all(). This will convert the path
923 /// into the '\\?\' format, which supports much longer paths.
924 fn safe_remove_dir_all(p: &Path) -> io::Result<()> {
925 if p.exists() {
926 let canonicalized = p.canonicalize()?;
927 std_fs::remove_dir_all(canonicalized)
928 } else {
929 Ok(())
930 }
931 }
932
933 fn safe_remove_file(p: &Path) -> io::Result<()> {
934 if p.exists() {
935 let canonicalized = p.canonicalize()?;
936 match std_fs::remove_file(canonicalized) {
937 Err(ref err) if err.kind() == io::ErrorKind::NotFound => Ok(()),
938 result => result,
939 }
940 } else {
941 Ok(())
942 }
943 }