Merge branch 'en/ort-perf-batch-13'

Performance tweaks of "git merge -sort" around lazy fetching of objects.

* en/ort-perf-batch-13:
  merge-ort: add prefetching for content merges
  diffcore-rename: use a different prefetch for basename comparisons
  diffcore-rename: allow different missing_object_cb functions
  t6421: add tests checking for excessive object downloads during merge
  promisor-remote: output trace2 statistics for number of objects fetched
This commit is contained in:
Junio C Hamano
2021-07-16 17:42:45 -07:00
4 changed files with 612 additions and 34 deletions

View File

@@ -87,13 +87,13 @@ struct diff_score {
short name_score;
};
struct prefetch_options {
struct inexact_prefetch_options {
struct repository *repo;
int skip_unmodified;
};
static void prefetch(void *prefetch_options)
static void inexact_prefetch(void *prefetch_options)
{
struct prefetch_options *options = prefetch_options;
struct inexact_prefetch_options *options = prefetch_options;
int i;
struct oid_array to_fetch = OID_ARRAY_INIT;
@@ -126,7 +126,7 @@ static int estimate_similarity(struct repository *r,
struct diff_filespec *src,
struct diff_filespec *dst,
int minimum_score,
int skip_unmodified)
struct diff_populate_filespec_options *dpf_opt)
{
/* src points at a file that existed in the original tree (or
* optionally a file in the destination tree) and dst points
@@ -143,15 +143,6 @@ static int estimate_similarity(struct repository *r,
*/
unsigned long max_size, delta_size, base_size, src_copied, literal_added;
int score;
struct diff_populate_filespec_options dpf_options = {
.check_size_only = 1
};
struct prefetch_options prefetch_options = {r, skip_unmodified};
if (r == the_repository && has_promisor_remote()) {
dpf_options.missing_object_cb = prefetch;
dpf_options.missing_object_data = &prefetch_options;
}
/* We deal only with regular files. Symlink renames are handled
* only when they are exact matches --- in other words, no edits
@@ -169,11 +160,13 @@ static int estimate_similarity(struct repository *r,
* is a possible size - we really should have a flag to
* say whether the size is valid or not!)
*/
dpf_opt->check_size_only = 1;
if (!src->cnt_data &&
diff_populate_filespec(r, src, &dpf_options))
diff_populate_filespec(r, src, dpf_opt))
return 0;
if (!dst->cnt_data &&
diff_populate_filespec(r, dst, &dpf_options))
diff_populate_filespec(r, dst, dpf_opt))
return 0;
max_size = ((src->size > dst->size) ? src->size : dst->size);
@@ -191,11 +184,11 @@ static int estimate_similarity(struct repository *r,
if (max_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
return 0;
dpf_options.check_size_only = 0;
dpf_opt->check_size_only = 0;
if (!src->cnt_data && diff_populate_filespec(r, src, &dpf_options))
if (!src->cnt_data && diff_populate_filespec(r, src, dpf_opt))
return 0;
if (!dst->cnt_data && diff_populate_filespec(r, dst, &dpf_options))
if (!dst->cnt_data && diff_populate_filespec(r, dst, dpf_opt))
return 0;
if (diffcore_count_changes(r, src, dst,
@@ -823,6 +816,78 @@ static int idx_possible_rename(char *filename, struct dir_rename_info *info)
return idx;
}
struct basename_prefetch_options {
struct repository *repo;
struct strintmap *relevant_sources;
struct strintmap *sources;
struct strintmap *dests;
struct dir_rename_info *info;
};
static void basename_prefetch(void *prefetch_options)
{
struct basename_prefetch_options *options = prefetch_options;
struct strintmap *relevant_sources = options->relevant_sources;
struct strintmap *sources = options->sources;
struct strintmap *dests = options->dests;
struct dir_rename_info *info = options->info;
int i;
struct oid_array to_fetch = OID_ARRAY_INIT;
/*
* TODO: The following loops mirror the code/logic from
* find_basename_matches(), though not quite exactly. Maybe
* abstract the iteration logic out somehow?
*/
for (i = 0; i < rename_src_nr; ++i) {
char *filename = rename_src[i].p->one->path;
const char *base = NULL;
intptr_t src_index;
intptr_t dst_index;
/* Skip irrelevant sources */
if (relevant_sources &&
!strintmap_contains(relevant_sources, filename))
continue;
/*
* If the basename is unique among remaining sources, then
* src_index will equal 'i' and we can attempt to match it
* to a unique basename in the destinations. Otherwise,
* use directory rename heuristics, if possible.
*/
base = get_basename(filename);
src_index = strintmap_get(sources, base);
assert(src_index == -1 || src_index == i);
if (strintmap_contains(dests, base)) {
struct diff_filespec *one, *two;
/* Find a matching destination, if possible */
dst_index = strintmap_get(dests, base);
if (src_index == -1 || dst_index == -1) {
src_index = i;
dst_index = idx_possible_rename(filename, info);
}
if (dst_index == -1)
continue;
/* Ignore this dest if already used in a rename */
if (rename_dst[dst_index].is_rename)
continue; /* already used previously */
one = rename_src[src_index].p->one;
two = rename_dst[dst_index].p->two;
/* Add the pairs */
diff_add_if_missing(options->repo, &to_fetch, two);
diff_add_if_missing(options->repo, &to_fetch, one);
}
}
promisor_remote_get_direct(options->repo, to_fetch.oid, to_fetch.nr);
oid_array_clear(&to_fetch);
}
static int find_basename_matches(struct diff_options *options,
int minimum_score,
struct dir_rename_info *info,
@@ -862,18 +927,18 @@ static int find_basename_matches(struct diff_options *options,
int i, renames = 0;
struct strintmap sources;
struct strintmap dests;
/*
* The prefeteching stuff wants to know if it can skip prefetching
* blobs that are unmodified...and will then do a little extra work
* to verify that the oids are indeed different before prefetching.
* Unmodified blobs are only relevant when doing copy detection;
* when limiting to rename detection, diffcore_rename[_extended]()
* will never be called with unmodified source paths fed to us, so
* the extra work necessary to check if rename_src entries are
* unmodified would be a small waste.
*/
int skip_unmodified = 0;
struct diff_populate_filespec_options dpf_options = {
.check_binary = 0,
.missing_object_cb = NULL,
.missing_object_data = NULL
};
struct basename_prefetch_options prefetch_options = {
.repo = options->repo,
.relevant_sources = relevant_sources,
.sources = &sources,
.dests = &dests,
.info = info
};
/*
* Create maps of basename -> fullname(s) for remaining sources and
@@ -910,6 +975,11 @@ static int find_basename_matches(struct diff_options *options,
strintmap_set(&dests, base, i);
}
if (options->repo == the_repository && has_promisor_remote()) {
dpf_options.missing_object_cb = basename_prefetch;
dpf_options.missing_object_data = &prefetch_options;
}
/* Now look for basename matchups and do similarity estimation */
for (i = 0; i < rename_src_nr; ++i) {
char *filename = rename_src[i].p->one->path;
@@ -953,7 +1023,7 @@ static int find_basename_matches(struct diff_options *options,
one = rename_src[src_index].p->one;
two = rename_dst[dst_index].p->two;
score = estimate_similarity(options->repo, one, two,
minimum_score, skip_unmodified);
minimum_score, &dpf_options);
/* If sufficiently similar, record as rename pair */
if (score < minimum_score)
@@ -1272,6 +1342,14 @@ void diffcore_rename_extended(struct diff_options *options,
int num_sources, want_copies;
struct progress *progress = NULL;
struct dir_rename_info info;
struct diff_populate_filespec_options dpf_options = {
.check_binary = 0,
.missing_object_cb = NULL,
.missing_object_data = NULL
};
struct inexact_prefetch_options prefetch_options = {
.repo = options->repo
};
trace2_region_enter("diff", "setup", options->repo);
info.setup = 0;
@@ -1433,6 +1511,13 @@ void diffcore_rename_extended(struct diff_options *options,
(uint64_t)num_destinations * (uint64_t)num_sources);
}
/* Finish setting up dpf_options */
prefetch_options.skip_unmodified = skip_unmodified;
if (options->repo == the_repository && has_promisor_remote()) {
dpf_options.missing_object_cb = inexact_prefetch;
dpf_options.missing_object_data = &prefetch_options;
}
CALLOC_ARRAY(mx, st_mult(NUM_CANDIDATE_PER_DST, num_destinations));
for (dst_cnt = i = 0; i < rename_dst_nr; i++) {
struct diff_filespec *two = rename_dst[i].p->two;
@@ -1458,7 +1543,7 @@ void diffcore_rename_extended(struct diff_options *options,
this_src.score = estimate_similarity(options->repo,
one, two,
minimum_score,
skip_unmodified);
&dpf_options);
this_src.name_score = basename_same(one, two);
this_src.dst = i;
this_src.src = j;