aboutsummaryrefslogtreecommitdiffstats
path: root/dir.c
diff options
context:
space:
mode:
authorDerrick Stolee <dstolee@microsoft.com>2019-11-21 22:04:41 +0000
committerJunio C Hamano <gitster@pobox.com>2019-11-22 16:11:44 +0900
commit96cc8ab5318cd57c8bc203b8f064b35883b2386f (patch)
tree34c7c46a9525f853ba710fe070fd191060ac2cdd /dir.c
parent879321eb0bec25779386445d65242452825155be (diff)
downloadgit-96cc8ab5318cd57c8bc203b8f064b35883b2386f.tar.gz
sparse-checkout: use hashmaps for cone patterns
The parent and recursive patterns allowed by the "cone mode" option in sparse-checkout are restrictive enough that we can avoid using the regex parsing. Everything is based on prefix matches, so we can use hashsets to store the prefixes from the sparse-checkout file. When checking a path, we can strip path entries from the path and check the hashset for an exact match. As a test, I created a cone-mode sparse-checkout file for the Linux repository that actually includes every file. This was constructed by taking every folder in the Linux repo and creating the pattern pairs here: /$folder/ !/$folder/*/ This resulted in a sparse-checkout file sith 8,296 patterns. Running 'git read-tree -mu HEAD' on this file had the following performance: core.sparseCheckout=false: 0.21 s (0.00 s) core.sparseCheckout=true: 3.75 s (3.50 s) core.sparseCheckoutCone=true: 0.23 s (0.01 s) The times in parentheses above correspond to the time spent in the first clear_ce_flags() call, according to the trace2 performance traces. While this example is contrived, it demonstrates how these patterns can slow the sparse-checkout feature. Helped-by: Eric Wong <e@80x24.org> Helped-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'dir.c')
-rw-r--r--dir.c207
1 files changed, 199 insertions, 8 deletions
diff --git a/dir.c b/dir.c
index 61f559f980..dfabf9982f 100644
--- a/dir.c
+++ b/dir.c
@@ -611,6 +611,150 @@ void parse_path_pattern(const char **pattern,
*patternlen = len;
}
+static int pl_hashmap_cmp(const void *unused_cmp_data,
+ const struct hashmap_entry *a,
+ const struct hashmap_entry *b,
+ const void *key)
+{
+ const struct pattern_entry *ee1 =
+ container_of(a, struct pattern_entry, ent);
+ const struct pattern_entry *ee2 =
+ container_of(b, struct pattern_entry, ent);
+
+ size_t min_len = ee1->patternlen <= ee2->patternlen
+ ? ee1->patternlen
+ : ee2->patternlen;
+
+ return strncmp(ee1->pattern, ee2->pattern, min_len);
+}
+
+static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern *given)
+{
+ struct pattern_entry *translated;
+ char *truncated;
+ char *data = NULL;
+
+ if (!pl->use_cone_patterns)
+ return;
+
+ if (given->flags & PATTERN_FLAG_NEGATIVE &&
+ given->flags & PATTERN_FLAG_MUSTBEDIR &&
+ !strcmp(given->pattern, "/*")) {
+ pl->full_cone = 0;
+ return;
+ }
+
+ if (!given->flags && !strcmp(given->pattern, "/*")) {
+ pl->full_cone = 1;
+ return;
+ }
+
+ if (given->patternlen > 2 &&
+ !strcmp(given->pattern + given->patternlen - 2, "/*")) {
+ if (!(given->flags & PATTERN_FLAG_NEGATIVE)) {
+ /* Not a cone pattern. */
+ pl->use_cone_patterns = 0;
+ warning(_("unrecognized pattern: '%s'"), given->pattern);
+ goto clear_hashmaps;
+ }
+
+ truncated = xstrdup(given->pattern);
+ truncated[given->patternlen - 2] = 0;
+
+ translated = xmalloc(sizeof(struct pattern_entry));
+ translated->pattern = truncated;
+ translated->patternlen = given->patternlen - 2;
+ hashmap_entry_init(&translated->ent,
+ memhash(translated->pattern, translated->patternlen));
+
+ if (!hashmap_get_entry(&pl->recursive_hashmap,
+ translated, ent, NULL)) {
+ /* We did not see the "parent" included */
+ warning(_("unrecognized negative pattern: '%s'"),
+ given->pattern);
+ free(truncated);
+ free(translated);
+ goto clear_hashmaps;
+ }
+
+ hashmap_add(&pl->parent_hashmap, &translated->ent);
+ hashmap_remove(&pl->recursive_hashmap, &translated->ent, &data);
+ free(data);
+ return;
+ }
+
+ if (given->flags & PATTERN_FLAG_NEGATIVE) {
+ warning(_("unrecognized negative pattern: '%s'"),
+ given->pattern);
+ goto clear_hashmaps;
+ }
+
+ translated = xmalloc(sizeof(struct pattern_entry));
+
+ translated->pattern = xstrdup(given->pattern);
+ translated->patternlen = given->patternlen;
+ hashmap_entry_init(&translated->ent,
+ memhash(translated->pattern, translated->patternlen));
+
+ hashmap_add(&pl->recursive_hashmap, &translated->ent);
+
+ if (hashmap_get_entry(&pl->parent_hashmap, translated, ent, NULL)) {
+ /* we already included this at the parent level */
+ warning(_("your sparse-checkout file may have issues: pattern '%s' is repeated"),
+ given->pattern);
+ hashmap_remove(&pl->parent_hashmap, &translated->ent, &data);
+ free(data);
+ free(translated);
+ }
+
+ return;
+
+clear_hashmaps:
+ warning(_("disabling cone pattern matching"));
+ hashmap_free_entries(&pl->parent_hashmap, struct pattern_entry, ent);
+ hashmap_free_entries(&pl->recursive_hashmap, struct pattern_entry, ent);
+ pl->use_cone_patterns = 0;
+}
+
+static int hashmap_contains_path(struct hashmap *map,
+ struct strbuf *pattern)
+{
+ struct pattern_entry p;
+
+ /* Check straight mapping */
+ p.pattern = pattern->buf;
+ p.patternlen = pattern->len;
+ hashmap_entry_init(&p.ent, memhash(p.pattern, p.patternlen));
+ return !!hashmap_get_entry(map, &p, ent, NULL);
+}
+
+int hashmap_contains_parent(struct hashmap *map,
+ const char *path,
+ struct strbuf *buffer)
+{
+ char *slash_pos;
+
+ strbuf_setlen(buffer, 0);
+
+ if (path[0] != '/')
+ strbuf_addch(buffer, '/');
+
+ strbuf_addstr(buffer, path);
+
+ slash_pos = strrchr(buffer->buf, '/');
+
+ while (slash_pos > buffer->buf) {
+ strbuf_setlen(buffer, slash_pos - buffer->buf);
+
+ if (hashmap_contains_path(map, buffer))
+ return 1;
+
+ slash_pos = strrchr(buffer->buf, '/');
+ }
+
+ return 0;
+}
+
void add_pattern(const char *string, const char *base,
int baselen, struct pattern_list *pl, int srcpos)
{
@@ -635,6 +779,8 @@ void add_pattern(const char *string, const char *base,
ALLOC_GROW(pl->patterns, pl->nr + 1, pl->alloc);
pl->patterns[pl->nr++] = pattern;
pattern->pl = pl;
+
+ add_pattern_to_hashsets(pl, pattern);
}
static int read_skip_worktree_file_from_index(const struct index_state *istate,
@@ -860,6 +1006,9 @@ static int add_patterns_from_buffer(char *buf, size_t size,
int i, lineno = 1;
char *entry;
+ hashmap_init(&pl->recursive_hashmap, pl_hashmap_cmp, NULL, 0);
+ hashmap_init(&pl->parent_hashmap, pl_hashmap_cmp, NULL, 0);
+
pl->filebuf = buf;
if (skip_utf8_bom(&buf, size))
@@ -1096,16 +1245,58 @@ enum pattern_match_result path_matches_pattern_list(
struct index_state *istate)
{
struct path_pattern *pattern;
- pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
- dtype, pl, istate);
- if (pattern) {
- if (pattern->flags & PATTERN_FLAG_NEGATIVE)
- return NOT_MATCHED;
- else
- return MATCHED;
+ struct strbuf parent_pathname = STRBUF_INIT;
+ int result = NOT_MATCHED;
+ const char *slash_pos;
+
+ if (!pl->use_cone_patterns) {
+ pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
+ dtype, pl, istate);
+ if (pattern) {
+ if (pattern->flags & PATTERN_FLAG_NEGATIVE)
+ return NOT_MATCHED;
+ else
+ return MATCHED;
+ }
+
+ return UNDECIDED;
+ }
+
+ if (pl->full_cone)
+ return MATCHED;
+
+ strbuf_addch(&parent_pathname, '/');
+ strbuf_add(&parent_pathname, pathname, pathlen);
+
+ if (hashmap_contains_path(&pl->recursive_hashmap,
+ &parent_pathname)) {
+ result = MATCHED;
+ goto done;
+ }
+
+ slash_pos = strrchr(parent_pathname.buf, '/');
+
+ if (slash_pos == parent_pathname.buf) {
+ /* include every file in root */
+ result = MATCHED;
+ goto done;
}
- return UNDECIDED;
+ strbuf_setlen(&parent_pathname, slash_pos - parent_pathname.buf);
+
+ if (hashmap_contains_path(&pl->parent_hashmap, &parent_pathname)) {
+ result = MATCHED;
+ goto done;
+ }
+
+ if (hashmap_contains_parent(&pl->recursive_hashmap,
+ pathname,
+ &parent_pathname))
+ result = MATCHED;
+
+done:
+ strbuf_release(&parent_pathname);
+ return result;
}
static struct path_pattern *last_matching_pattern_from_lists(