@matheusbsbs / matheus-bagliano / commits / 30598ccc4d

describe: use oidset in finish_depth_computation()

Depth computation can end early if all remaining commits are flagged. The current code determines if that's the case by checking all queue items each time it dequeues a flagged commit. This can cause quadratic complexity. We could simply count the flagged items in the queue and then update that number as we add and remove items. That would provide a general speedup, but leave one case where we have to scan the whole queue: When we flag a previously seen, but unflagged commit. It could be on the queue and then we'd have to decrease our count. We could dedicate an object flag to track queue membership, but that would leave less for candidate tags, affecting the results. So use a hash table, specifically an oidset of commit hashes, to track that. This avoids quadratic behaviour in all cases and provides a nice performance boost over the previous commit, 08bb69d70f (describe: use prio_queue_replace(), 2025-08-03): Benchmark 1: ./git_08bb69d70f describe $(git rev-list v2.41.0..v2.47.0) Time (mean ± σ): 855.3 ms ± 1.3 ms [User: 790.8 ms, System: 49.9 ms] Range (min … max): 853.7 ms … 857.8 ms 10 runs Benchmark 2: ./git describe $(git rev-list v2.41.0..v2.47.0) Time (mean ± σ): 610.8 ms ± 1.7 ms [User: 546.9 ms, System: 49.3 ms] Range (min … max): 608.9 ms … 613.3 ms 10 runs Summary ./git describe $(git rev-list v2.41.0..v2.47.0) ran 1.40 ± 0.00 times faster than ./git_08bb69d70f describe $(git rev-list v2.41.0..v2.47.0) Helped-by: Jeff King <peff@peff.net> Signed-off-by: René Scharfe <l.s.r@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>

René Scharfe committed Sep 2, 2025 at 20:24 UTC 30598ccc4d93bb235e0807c04835cd00ba63577b

1 file changed +22 -12

builtin/describe.c

+22 -12

@@ -24,6 +24,7 @@

24 #include "commit-slab.h"

25 #include "wildmatch.h"

26 #include "prio-queue.h"

27 +#include "oidset.h"

29 #define MAX_TAGS (FLAG_BITS - 1)

30 #define DEFAULT_CANDIDATES 10

@@ -286,38 +287,47 @@ static void lazy_queue_clear(struct lazy_queue *queue)

287 queue->get_pending = false;

288 }

289

289 -static bool all_have_flag(const struct lazy_queue *queue, unsigned flag)

290 +static unsigned long finish_depth_computation(struct lazy_queue *queue,

291 + struct possible_tag *best)

292 {

293 + unsigned long seen_commits = 0;

294 + struct oidset unflagged = OIDSET_INIT;

295 +

296 for (size_t i = queue->get_pending ? 1 : 0; i < queue->queue.nr; i++) {

297 struct commit *commit = queue->queue.array[i].data;

293 - if (!(commit->object.flags & flag))

294 - return false;

298 + if (!(commit->object.flags & best->flag_within))

299 + oidset_insert(&unflagged, &commit->object.oid);

300 }

296 - return true;

297 -}

301

299 -static unsigned long finish_depth_computation(struct lazy_queue *queue,

300 - struct possible_tag *best)

301 -{

302 - unsigned long seen_commits = 0;

302 while (!lazy_queue_empty(queue)) {

303 struct commit *c = lazy_queue_get(queue);

304 struct commit_list *parents = c->parents;

305 seen_commits++;

306 if (c->object.flags & best->flag_within) {

308 - if (all_have_flag(queue, best->flag_within))

307 + if (!oidset_size(&unflagged))

308 break;

310 - } else

309 + } else {

310 + oidset_remove(&unflagged, &c->object.oid);

311 best->depth++;

312 + }

313 while (parents) {

314 + unsigned seen, flag_before, flag_after;

315 struct commit *p = parents->item;

316 repo_parse_commit(the_repository, p);

315 - if (!(p->object.flags & SEEN))

317 + seen = p->object.flags & SEEN;

318 + if (!seen)

319 lazy_queue_put(queue, p);

320 + flag_before = p->object.flags & best->flag_within;

321 p->object.flags |= c->object.flags;

322 + flag_after = p->object.flags & best->flag_within;

323 + if (!seen && !flag_after)

324 + oidset_insert(&unflagged, &p->object.oid);

325 + if (seen && !flag_before && flag_after)

326 + oidset_remove(&unflagged, &p->object.oid);

327 parents = parents->next;

328 }

329 }

330 + oidset_clear(&unflagged);

331 return seen_commits;

332 }

333