1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-25 19:26:38 +02:00
git/commit-graph.c

1093 lines
29 KiB
C
Raw Normal View History

#include "cache.h"
#include "config.h"
#include "dir.h"
#include "git-compat-util.h"
#include "lockfile.h"
#include "pack.h"
#include "packfile.h"
#include "commit.h"
#include "object.h"
#include "refs.h"
#include "revision.h"
#include "sha1-lookup.h"
#include "commit-graph.h"
#include "object-store.h"
#include "alloc.h"
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
#include "progress.h"
#define GRAPH_SIGNATURE 0x43475048 /* "CGPH" */
#define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
#define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
#define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
#define GRAPH_CHUNKID_LARGEEDGES 0x45444745 /* "EDGE" */
#define GRAPH_DATA_WIDTH 36
#define GRAPH_VERSION_1 0x1
#define GRAPH_VERSION GRAPH_VERSION_1
#define GRAPH_OID_VERSION_SHA1 1
#define GRAPH_OID_LEN_SHA1 GIT_SHA1_RAWSZ
#define GRAPH_OID_VERSION GRAPH_OID_VERSION_SHA1
#define GRAPH_OID_LEN GRAPH_OID_LEN_SHA1
#define GRAPH_OCTOPUS_EDGES_NEEDED 0x80000000
#define GRAPH_PARENT_MISSING 0x7fffffff
#define GRAPH_EDGE_LAST_MASK 0x7fffffff
#define GRAPH_PARENT_NONE 0x70000000
#define GRAPH_LAST_EDGE 0x80000000
#define GRAPH_HEADER_SIZE 8
#define GRAPH_FANOUT_SIZE (4 * 256)
#define GRAPH_CHUNKLOOKUP_WIDTH 12
#define GRAPH_MIN_SIZE (GRAPH_HEADER_SIZE + 4 * GRAPH_CHUNKLOOKUP_WIDTH \
+ GRAPH_FANOUT_SIZE + GRAPH_OID_LEN)
char *get_commit_graph_filename(const char *obj_dir)
{
return xstrfmt("%s/info/commit-graph", obj_dir);
}
static struct commit_graph *alloc_commit_graph(void)
{
struct commit_graph *g = xcalloc(1, sizeof(*g));
g->graph_fd = -1;
return g;
}
struct commit_graph *load_commit_graph_one(const char *graph_file)
{
void *graph_map;
const unsigned char *data, *chunk_lookup;
size_t graph_size;
struct stat st;
uint32_t i;
struct commit_graph *graph;
int fd = git_open(graph_file);
uint64_t last_chunk_offset;
uint32_t last_chunk_id;
uint32_t graph_signature;
unsigned char graph_version, hash_version;
if (fd < 0)
return NULL;
if (fstat(fd, &st)) {
close(fd);
return NULL;
}
graph_size = xsize_t(st.st_size);
if (graph_size < GRAPH_MIN_SIZE) {
close(fd);
die(_("graph file %s is too small"), graph_file);
}
graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0);
data = (const unsigned char *)graph_map;
graph_signature = get_be32(data);
if (graph_signature != GRAPH_SIGNATURE) {
error(_("graph signature %X does not match signature %X"),
graph_signature, GRAPH_SIGNATURE);
goto cleanup_fail;
}
graph_version = *(unsigned char*)(data + 4);
if (graph_version != GRAPH_VERSION) {
error(_("graph version %X does not match version %X"),
graph_version, GRAPH_VERSION);
goto cleanup_fail;
}
hash_version = *(unsigned char*)(data + 5);
if (hash_version != GRAPH_OID_VERSION) {
error(_("hash version %X does not match version %X"),
hash_version, GRAPH_OID_VERSION);
goto cleanup_fail;
}
graph = alloc_commit_graph();
graph->hash_len = GRAPH_OID_LEN;
graph->num_chunks = *(unsigned char*)(data + 6);
graph->graph_fd = fd;
graph->data = graph_map;
graph->data_len = graph_size;
last_chunk_id = 0;
last_chunk_offset = 8;
chunk_lookup = data + 8;
for (i = 0; i < graph->num_chunks; i++) {
uint32_t chunk_id = get_be32(chunk_lookup + 0);
uint64_t chunk_offset = get_be64(chunk_lookup + 4);
int chunk_repeated = 0;
chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH;
if (chunk_offset > graph_size - GIT_MAX_RAWSZ) {
error(_("improper chunk offset %08x%08x"), (uint32_t)(chunk_offset >> 32),
(uint32_t)chunk_offset);
goto cleanup_fail;
}
switch (chunk_id) {
case GRAPH_CHUNKID_OIDFANOUT:
if (graph->chunk_oid_fanout)
chunk_repeated = 1;
else
graph->chunk_oid_fanout = (uint32_t*)(data + chunk_offset);
break;
case GRAPH_CHUNKID_OIDLOOKUP:
if (graph->chunk_oid_lookup)
chunk_repeated = 1;
else
graph->chunk_oid_lookup = data + chunk_offset;
break;
case GRAPH_CHUNKID_DATA:
if (graph->chunk_commit_data)
chunk_repeated = 1;
else
graph->chunk_commit_data = data + chunk_offset;
break;
case GRAPH_CHUNKID_LARGEEDGES:
if (graph->chunk_large_edges)
chunk_repeated = 1;
else
graph->chunk_large_edges = data + chunk_offset;
break;
}
if (chunk_repeated) {
error(_("chunk id %08x appears multiple times"), chunk_id);
goto cleanup_fail;
}
if (last_chunk_id == GRAPH_CHUNKID_OIDLOOKUP)
{
graph->num_commits = (chunk_offset - last_chunk_offset)
/ graph->hash_len;
}
last_chunk_id = chunk_id;
last_chunk_offset = chunk_offset;
}
return graph;
cleanup_fail:
munmap(graph_map, graph_size);
close(fd);
exit(1);
}
static void prepare_commit_graph_one(struct repository *r, const char *obj_dir)
{
char *graph_name;
if (r->objects->commit_graph)
return;
graph_name = get_commit_graph_filename(obj_dir);
r->objects->commit_graph =
load_commit_graph_one(graph_name);
FREE_AND_NULL(graph_name);
}
/*
* Return 1 if commit_graph is non-NULL, and 0 otherwise.
*
* On the first invocation, this function attemps to load the commit
* graph if the_repository is configured to have one.
*/
static int prepare_commit_graph(struct repository *r)
{
struct alternate_object_database *alt;
char *obj_dir;
int config_value;
if (r->objects->commit_graph_attempted)
return !!r->objects->commit_graph;
r->objects->commit_graph_attempted = 1;
if (repo_config_get_bool(r, "core.commitgraph", &config_value) ||
!config_value)
/*
* This repository is not configured to use commit graphs, so
* do not load one. (But report commit_graph_attempted anyway
* so that commit graph loading is not attempted again for this
* repository.)
*/
return 0;
obj_dir = r->objects->objectdir;
prepare_commit_graph_one(r, obj_dir);
prepare_alt_odb(r);
for (alt = r->objects->alt_odb_list;
!r->objects->commit_graph && alt;
alt = alt->next)
prepare_commit_graph_one(r, alt->path);
return !!r->objects->commit_graph;
}
static void close_commit_graph(void)
{
free_commit_graph(the_repository->objects->commit_graph);
the_repository->objects->commit_graph = NULL;
}
static int bsearch_graph(struct commit_graph *g, struct object_id *oid, uint32_t *pos)
{
return bsearch_hash(oid->hash, g->chunk_oid_fanout,
g->chunk_oid_lookup, g->hash_len, pos);
}
static struct commit_list **insert_parent_or_die(struct commit_graph *g,
uint64_t pos,
struct commit_list **pptr)
{
struct commit *c;
struct object_id oid;
if (pos >= g->num_commits)
die("invalid parent position %"PRIu64, pos);
hashcpy(oid.hash, g->chunk_oid_lookup + g->hash_len * pos);
c = lookup_commit(the_repository, &oid);
if (!c)
die(_("could not find commit %s"), oid_to_hex(&oid));
c->graph_pos = pos;
return &commit_list_insert(c, pptr)->next;
}
static void fill_commit_graph_info(struct commit *item, struct commit_graph *g, uint32_t pos)
{
const unsigned char *commit_data = g->chunk_commit_data + GRAPH_DATA_WIDTH * pos;
item->graph_pos = pos;
item->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
}
static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t pos)
{
uint32_t edge_value;
uint32_t *parent_data_ptr;
uint64_t date_low, date_high;
struct commit_list **pptr;
const unsigned char *commit_data = g->chunk_commit_data + (g->hash_len + 16) * pos;
item->object.parsed = 1;
item->graph_pos = pos;
item->maybe_tree = NULL;
date_high = get_be32(commit_data + g->hash_len + 8) & 0x3;
date_low = get_be32(commit_data + g->hash_len + 12);
item->date = (timestamp_t)((date_high << 32) | date_low);
item->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
pptr = &item->parents;
edge_value = get_be32(commit_data + g->hash_len);
if (edge_value == GRAPH_PARENT_NONE)
return 1;
pptr = insert_parent_or_die(g, edge_value, pptr);
edge_value = get_be32(commit_data + g->hash_len + 4);
if (edge_value == GRAPH_PARENT_NONE)
return 1;
if (!(edge_value & GRAPH_OCTOPUS_EDGES_NEEDED)) {
pptr = insert_parent_or_die(g, edge_value, pptr);
return 1;
}
parent_data_ptr = (uint32_t*)(g->chunk_large_edges +
4 * (uint64_t)(edge_value & GRAPH_EDGE_LAST_MASK));
do {
edge_value = get_be32(parent_data_ptr);
pptr = insert_parent_or_die(g,
edge_value & GRAPH_EDGE_LAST_MASK,
pptr);
parent_data_ptr++;
} while (!(edge_value & GRAPH_LAST_EDGE));
return 1;
}
static int find_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t *pos)
{
if (item->graph_pos != COMMIT_NOT_FROM_GRAPH) {
*pos = item->graph_pos;
return 1;
} else {
return bsearch_graph(g, &(item->object.oid), pos);
}
}
static int parse_commit_in_graph_one(struct commit_graph *g, struct commit *item)
{
uint32_t pos;
if (item->object.parsed)
return 1;
if (find_commit_in_graph(item, g, &pos))
return fill_commit_in_graph(item, g, pos);
return 0;
}
int parse_commit_in_graph(struct repository *r, struct commit *item)
{
if (!prepare_commit_graph(r))
return 0;
return parse_commit_in_graph_one(r->objects->commit_graph, item);
}
void load_commit_graph_info(struct repository *r, struct commit *item)
{
uint32_t pos;
if (!prepare_commit_graph(r))
return;
if (find_commit_in_graph(item, r->objects->commit_graph, &pos))
fill_commit_graph_info(item, r->objects->commit_graph, pos);
}
static struct tree *load_tree_for_commit(struct commit_graph *g, struct commit *c)
{
struct object_id oid;
const unsigned char *commit_data = g->chunk_commit_data +
GRAPH_DATA_WIDTH * (c->graph_pos);
hashcpy(oid.hash, commit_data);
c->maybe_tree = lookup_tree(the_repository, &oid);
return c->maybe_tree;
}
static struct tree *get_commit_tree_in_graph_one(struct commit_graph *g,
const struct commit *c)
{
if (c->maybe_tree)
return c->maybe_tree;
if (c->graph_pos == COMMIT_NOT_FROM_GRAPH)
BUG("get_commit_tree_in_graph_one called from non-commit-graph commit");
return load_tree_for_commit(g, (struct commit *)c);
}
struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit *c)
{
return get_commit_tree_in_graph_one(r->objects->commit_graph, c);
}
static void write_graph_chunk_fanout(struct hashfile *f,
struct commit **commits,
int nr_commits)
{
int i, count = 0;
struct commit **list = commits;
/*
* Write the first-level table (the list is sorted,
* but we use a 256-entry lookup to be able to avoid
* having to do eight extra binary search iterations).
*/
for (i = 0; i < 256; i++) {
while (count < nr_commits) {
if ((*list)->object.oid.hash[0] != i)
break;
count++;
list++;
}
hashwrite_be32(f, count);
}
}
static void write_graph_chunk_oids(struct hashfile *f, int hash_len,
struct commit **commits, int nr_commits)
{
struct commit **list = commits;
int count;
for (count = 0; count < nr_commits; count++, list++)
hashwrite(f, (*list)->object.oid.hash, (int)hash_len);
}
static const unsigned char *commit_to_sha1(size_t index, void *table)
{
struct commit **commits = table;
return commits[index]->object.oid.hash;
}
static void write_graph_chunk_data(struct hashfile *f, int hash_len,
struct commit **commits, int nr_commits)
{
struct commit **list = commits;
struct commit **last = commits + nr_commits;
uint32_t num_extra_edges = 0;
while (list < last) {
struct commit_list *parent;
int edge_value;
uint32_t packedDate[2];
parse_commit(*list);
hashwrite(f, get_commit_tree_oid(*list)->hash, hash_len);
parent = (*list)->parents;
if (!parent)
edge_value = GRAPH_PARENT_NONE;
else {
edge_value = sha1_pos(parent->item->object.oid.hash,
commits,
nr_commits,
commit_to_sha1);
if (edge_value < 0)
edge_value = GRAPH_PARENT_MISSING;
}
hashwrite_be32(f, edge_value);
if (parent)
parent = parent->next;
if (!parent)
edge_value = GRAPH_PARENT_NONE;
else if (parent->next)
edge_value = GRAPH_OCTOPUS_EDGES_NEEDED | num_extra_edges;
else {
edge_value = sha1_pos(parent->item->object.oid.hash,
commits,
nr_commits,
commit_to_sha1);
if (edge_value < 0)
edge_value = GRAPH_PARENT_MISSING;
}
hashwrite_be32(f, edge_value);
if (edge_value & GRAPH_OCTOPUS_EDGES_NEEDED) {
do {
num_extra_edges++;
parent = parent->next;
} while (parent);
}
if (sizeof((*list)->date) > 4)
packedDate[0] = htonl(((*list)->date >> 32) & 0x3);
else
packedDate[0] = 0;
packedDate[0] |= htonl((*list)->generation << 2);
packedDate[1] = htonl((*list)->date);
hashwrite(f, packedDate, 8);
list++;
}
}
static void write_graph_chunk_large_edges(struct hashfile *f,
struct commit **commits,
int nr_commits)
{
struct commit **list = commits;
struct commit **last = commits + nr_commits;
struct commit_list *parent;
while (list < last) {
int num_parents = 0;
for (parent = (*list)->parents; num_parents < 3 && parent;
parent = parent->next)
num_parents++;
if (num_parents <= 2) {
list++;
continue;
}
/* Since num_parents > 2, this initializer is safe. */
for (parent = (*list)->parents->next; parent; parent = parent->next) {
int edge_value = sha1_pos(parent->item->object.oid.hash,
commits,
nr_commits,
commit_to_sha1);
if (edge_value < 0)
edge_value = GRAPH_PARENT_MISSING;
else if (!parent->next)
edge_value |= GRAPH_LAST_EDGE;
hashwrite_be32(f, edge_value);
}
list++;
}
}
static int commit_compare(const void *_a, const void *_b)
{
const struct object_id *a = (const struct object_id *)_a;
const struct object_id *b = (const struct object_id *)_b;
return oidcmp(a, b);
}
struct packed_commit_list {
struct commit **list;
int nr;
int alloc;
};
struct packed_oid_list {
struct object_id *list;
int nr;
int alloc;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
struct progress *progress;
int progress_done;
};
static int add_packed_commits(const struct object_id *oid,
struct packed_git *pack,
uint32_t pos,
void *data)
{
struct packed_oid_list *list = (struct packed_oid_list*)data;
enum object_type type;
off_t offset = nth_packed_object_offset(pack, pos);
struct object_info oi = OBJECT_INFO_INIT;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
if (list->progress)
display_progress(list->progress, ++list->progress_done);
oi.typep = &type;
if (packed_object_info(the_repository, pack, offset, &oi) < 0)
die(_("unable to get type of object %s"), oid_to_hex(oid));
if (type != OBJ_COMMIT)
return 0;
ALLOC_GROW(list->list, list->nr + 1, list->alloc);
oidcpy(&(list->list[list->nr]), oid);
list->nr++;
return 0;
}
static void add_missing_parents(struct packed_oid_list *oids, struct commit *commit)
{
struct commit_list *parent;
for (parent = commit->parents; parent; parent = parent->next) {
if (!(parent->item->object.flags & UNINTERESTING)) {
ALLOC_GROW(oids->list, oids->nr + 1, oids->alloc);
oidcpy(&oids->list[oids->nr], &(parent->item->object.oid));
oids->nr++;
parent->item->object.flags |= UNINTERESTING;
}
}
}
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
static void close_reachable(struct packed_oid_list *oids, int report_progress)
{
int i;
struct commit *commit;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
struct progress *progress = NULL;
int j = 0;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
if (report_progress)
progress = start_delayed_progress(
_("Annotating commits in commit graph"), 0);
for (i = 0; i < oids->nr; i++) {
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
display_progress(progress, ++j);
commit = lookup_commit(the_repository, &oids->list[i]);
if (commit)
commit->object.flags |= UNINTERESTING;
}
/*
* As this loop runs, oids->nr may grow, but not more
* than the number of missing commits in the reachable
* closure.
*/
for (i = 0; i < oids->nr; i++) {
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
display_progress(progress, ++j);
commit = lookup_commit(the_repository, &oids->list[i]);
if (commit && !parse_commit(commit))
add_missing_parents(oids, commit);
}
for (i = 0; i < oids->nr; i++) {
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
display_progress(progress, ++j);
commit = lookup_commit(the_repository, &oids->list[i]);
if (commit)
commit->object.flags &= ~UNINTERESTING;
}
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
stop_progress(&progress);
}
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
static void compute_generation_numbers(struct packed_commit_list* commits,
int report_progress)
{
int i;
struct commit_list *list = NULL;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
struct progress *progress = NULL;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
if (report_progress)
progress = start_progress(
_("Computing commit graph generation numbers"),
commits->nr);
for (i = 0; i < commits->nr; i++) {
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
display_progress(progress, i + 1);
if (commits->list[i]->generation != GENERATION_NUMBER_INFINITY &&
commits->list[i]->generation != GENERATION_NUMBER_ZERO)
continue;
commit_list_insert(commits->list[i], &list);
while (list) {
struct commit *current = list->item;
struct commit_list *parent;
int all_parents_computed = 1;
uint32_t max_generation = 0;
for (parent = current->parents; parent; parent = parent->next) {
if (parent->item->generation == GENERATION_NUMBER_INFINITY ||
parent->item->generation == GENERATION_NUMBER_ZERO) {
all_parents_computed = 0;
commit_list_insert(parent->item, &list);
break;
} else if (parent->item->generation > max_generation) {
max_generation = parent->item->generation;
}
}
if (all_parents_computed) {
current->generation = max_generation + 1;
pop_commit(&list);
if (current->generation > GENERATION_NUMBER_MAX)
current->generation = GENERATION_NUMBER_MAX;
}
}
}
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
stop_progress(&progress);
}
static int add_ref_to_list(const char *refname,
const struct object_id *oid,
int flags, void *cb_data)
{
struct string_list *list = (struct string_list *)cb_data;
string_list_append(list, oid_to_hex(oid));
return 0;
}
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
void write_commit_graph_reachable(const char *obj_dir, int append,
int report_progress)
{
struct string_list list;
string_list_init(&list, 1);
for_each_ref(add_ref_to_list, &list);
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
write_commit_graph(obj_dir, NULL, &list, append, report_progress);
}
void write_commit_graph(const char *obj_dir,
struct string_list *pack_indexes,
struct string_list *commit_hex,
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
int append, int report_progress)
{
struct packed_oid_list oids;
struct packed_commit_list commits;
struct hashfile *f;
uint32_t i, count_distinct = 0;
char *graph_name;
struct lock_file lk = LOCK_INIT;
uint32_t chunk_ids[5];
uint64_t chunk_offsets[5];
int num_chunks;
int num_extra_edges;
struct commit_list *parent;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
struct progress *progress = NULL;
oids.nr = 0;
oids.alloc = approximate_object_count() / 4;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
oids.progress = NULL;
oids.progress_done = 0;
if (append) {
prepare_commit_graph_one(the_repository, obj_dir);
if (the_repository->objects->commit_graph)
oids.alloc += the_repository->objects->commit_graph->num_commits;
}
if (oids.alloc < 1024)
oids.alloc = 1024;
ALLOC_ARRAY(oids.list, oids.alloc);
if (append && the_repository->objects->commit_graph) {
struct commit_graph *commit_graph =
the_repository->objects->commit_graph;
for (i = 0; i < commit_graph->num_commits; i++) {
const unsigned char *hash = commit_graph->chunk_oid_lookup +
commit_graph->hash_len * i;
hashcpy(oids.list[oids.nr++].hash, hash);
}
}
if (pack_indexes) {
struct strbuf packname = STRBUF_INIT;
int dirlen;
strbuf_addf(&packname, "%s/pack/", obj_dir);
dirlen = packname.len;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
if (report_progress) {
oids.progress = start_delayed_progress(
_("Finding commits for commit graph"), 0);
oids.progress_done = 0;
}
for (i = 0; i < pack_indexes->nr; i++) {
struct packed_git *p;
strbuf_setlen(&packname, dirlen);
strbuf_addstr(&packname, pack_indexes->items[i].string);
p = add_packed_git(packname.buf, packname.len, 1);
if (!p)
die(_("error adding pack %s"), packname.buf);
if (open_pack_index(p))
die(_("error opening index for %s"), packname.buf);
for_each_packed_object: support iterating in pack-order We currently iterate over objects within a pack in .idx order, which uses the object hashes. That means that it is effectively random with respect to the location of the object within the pack. If you're going to access the actual object data, there are two reasons to move linearly through the pack itself: 1. It improves the locality of access in the packfile. In the cold-cache case, this may mean fewer disk seeks, or better usage of disk cache. 2. We store related deltas together in the packfile. Which means that the delta base cache can operate much more efficiently if we visit all of those related deltas in sequence, as the earlier items are likely to still be in the cache. Whereas if we visit the objects in random order, our cache entries are much more likely to have been evicted by unrelated deltas in the meantime. So in general, if you're going to access the object contents pack order is generally going to end up more efficient. But if you're simply generating a list of object names, or if you're going to end up sorting the result anyway, you're better off just using the .idx order, as finding the pack order means generating the in-memory pack-revindex. According to the numbers in 8b8dfd5132 (pack-revindex: radix-sort the revindex, 2013-07-11), that takes about 200ms for linux.git, and 20ms for git.git (those numbers are a few years old but are still a good ballpark). That makes it a good optimization for some cases (we can save tens of seconds in git.git by having good locality of delta access, for a 20ms cost), but a bad one for others (e.g., right now "cat-file --batch-all-objects --batch-check="%(objectname)" is 170ms in git.git, so adding 20ms to that is noticeable). Hence this patch makes it an optional flag. You can't actually do any interesting timings yet, as it's not plumbed through to any user-facing tools like cat-file. That will come in a later patch. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-08-11 01:15:49 +02:00
for_each_object_in_pack(p, add_packed_commits, &oids, 0);
close_pack(p);
}
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
stop_progress(&oids.progress);
strbuf_release(&packname);
}
if (commit_hex) {
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
if (report_progress)
progress = start_delayed_progress(
_("Finding commits for commit graph"),
commit_hex->nr);
for (i = 0; i < commit_hex->nr; i++) {
const char *end;
struct object_id oid;
struct commit *result;
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
display_progress(progress, i + 1);
if (commit_hex->items[i].string &&
parse_oid_hex(commit_hex->items[i].string, &oid, &end))
continue;
result = lookup_commit_reference_gently(the_repository, &oid, 1);
if (result) {
ALLOC_GROW(oids.list, oids.nr + 1, oids.alloc);
oidcpy(&oids.list[oids.nr], &(result->object.oid));
oids.nr++;
}
}
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
stop_progress(&progress);
}
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
if (!pack_indexes && !commit_hex) {
if (report_progress)
oids.progress = start_delayed_progress(
_("Finding commits for commit graph"), 0);
for_each_packed_object(add_packed_commits, &oids, 0);
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
stop_progress(&oids.progress);
}
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
close_reachable(&oids, report_progress);
QSORT(oids.list, oids.nr, commit_compare);
count_distinct = 1;
for (i = 1; i < oids.nr; i++) {
if (oidcmp(&oids.list[i-1], &oids.list[i]))
count_distinct++;
}
if (count_distinct >= GRAPH_PARENT_MISSING)
die(_("the commit graph format cannot write %d commits"), count_distinct);
commits.nr = 0;
commits.alloc = count_distinct;
ALLOC_ARRAY(commits.list, commits.alloc);
num_extra_edges = 0;
for (i = 0; i < oids.nr; i++) {
int num_parents = 0;
if (i > 0 && !oidcmp(&oids.list[i-1], &oids.list[i]))
continue;
commits.list[commits.nr] = lookup_commit(the_repository, &oids.list[i]);
parse_commit(commits.list[commits.nr]);
for (parent = commits.list[commits.nr]->parents;
parent; parent = parent->next)
num_parents++;
if (num_parents > 2)
num_extra_edges += num_parents - 1;
commits.nr++;
}
num_chunks = num_extra_edges ? 4 : 3;
if (commits.nr >= GRAPH_PARENT_MISSING)
die(_("too many commits to write graph"));
commit-graph write: add progress output Before this change the "commit-graph write" command didn't report any progress. On my machine this command takes more than 10 seconds to write the graph for linux.git, and around 1m30s on the 2015-04-03-1M-git.git[1] test repository (a test case for a large monorepository). Furthermore, since the gc.writeCommitGraph setting was added in d5d5d7b641 ("gc: automatically write commit-graph files", 2018-06-27), there was no indication at all from a "git gc" run that anything was different. This why one of the progress bars being added here uses start_progress() instead of start_delayed_progress(), so that it's guaranteed to be seen. E.g. on my tiny 867 commit dotfiles.git repository: $ git -c gc.writeCommitGraph=true gc Enumerating objects: 2821, done. [...] Computing commit graph generation numbers: 100% (867/867), done. On larger repositories, such as linux.git the delayed progress bar(s) will kick in, and we'll show what's going on instead of, as was previously happening, printing nothing while we write the graph: $ git -c gc.writeCommitGraph=true gc [...] Annotating commits in commit graph: 1565573, done. Computing commit graph generation numbers: 100% (782484/782484), done. Note that here we don't show "Finding commits for commit graph", this is because under "git gc" we seed the search with the commit references in the repository, and that set is too small to show any progress, but would e.g. on a smaller repo such as git.git with --stdin-commits: $ git rev-list --all | git -c gc.writeCommitGraph=true write --stdin-commits Finding commits for commit graph: 100% (162576/162576), done. Computing commit graph generation numbers: 100% (162576/162576), done. With --stdin-packs we don't show any estimation of how much is left to do. This is because we might be processing more than one pack. We could be less lazy here and show progress, either by detecting that we're only processing one pack, or by first looping over the packs to discover how many commits they have. I don't see the point in doing that work. So instead we get (on 2015-04-03-1M-git.git): $ echo pack-<HASH>.idx | git -c gc.writeCommitGraph=true --exec-path=$PWD commit-graph write --stdin-packs Finding commits for commit graph: 13064614, done. Annotating commits in commit graph: 3001341, done. Computing commit graph generation numbers: 100% (1000447/1000447), done. No GC mode uses --stdin-packs. It's what they use at Microsoft to manually compute the generation numbers for their collection of large packs which are never coalesced. The reason we need a "report_progress" variable passed down from "git gc" is so that we don't report this output when we're running in the process "git gc --auto" detaches from the terminal. Since we write the commit graph from the "git gc" process itself (as opposed to what we do with say the "git repack" phase), we'd end up writing the output to .git/gc.log and reporting it to the user next time as part of the "The last gc run reported the following[...]" error, see 329e6e8794 ("gc: save log from daemonized gc --auto and print it next time", 2015-09-19). So we must keep track of whether or not we're running in that demonized mode, and if so print no progress. See [2] and subsequent replies for a discussion of an approach not taken in compute_generation_numbers(). I.e. we're saying "Computing commit graph generation numbers", even though on an established history we're mostly skipping over all the work we did in the past. This is similar to the white lie we tell in the "Writing objects" phase (not all are objects being written). Always showing progress is considered more important than accuracy. I.e. on a repository like 2015-04-03-1M-git.git we'd hang for 6 seconds with no output on the second "git gc" if no changes were made to any objects in the interim if we'd take the approach in [2]. 1. https://github.com/avar/2015-04-03-1M-git 2. <c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com> (https://public-inbox.org/git/c6960252-c095-fb2b-e0bc-b1e6bb261614@gmail.com/) Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-17 17:33:35 +02:00
compute_generation_numbers(&commits, report_progress);
graph_name = get_commit_graph_filename(obj_dir);
if (safe_create_leading_directories(graph_name))
die_errno(_("unable to create leading directories of %s"),
graph_name);
hold_lock_file_for_update(&lk, graph_name, LOCK_DIE_ON_ERROR);
f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
hashwrite_be32(f, GRAPH_SIGNATURE);
hashwrite_u8(f, GRAPH_VERSION);
hashwrite_u8(f, GRAPH_OID_VERSION);
hashwrite_u8(f, num_chunks);
hashwrite_u8(f, 0); /* unused padding byte */
chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT;
chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP;
chunk_ids[2] = GRAPH_CHUNKID_DATA;
if (num_extra_edges)
chunk_ids[3] = GRAPH_CHUNKID_LARGEEDGES;
else
chunk_ids[3] = 0;
chunk_ids[4] = 0;
chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE;
chunk_offsets[2] = chunk_offsets[1] + GRAPH_OID_LEN * commits.nr;
chunk_offsets[3] = chunk_offsets[2] + (GRAPH_OID_LEN + 16) * commits.nr;
chunk_offsets[4] = chunk_offsets[3] + 4 * num_extra_edges;
for (i = 0; i <= num_chunks; i++) {
uint32_t chunk_write[3];
chunk_write[0] = htonl(chunk_ids[i]);
chunk_write[1] = htonl(chunk_offsets[i] >> 32);
chunk_write[2] = htonl(chunk_offsets[i] & 0xffffffff);
hashwrite(f, chunk_write, 12);
}
write_graph_chunk_fanout(f, commits.list, commits.nr);
write_graph_chunk_oids(f, GRAPH_OID_LEN, commits.list, commits.nr);
write_graph_chunk_data(f, GRAPH_OID_LEN, commits.list, commits.nr);
write_graph_chunk_large_edges(f, commits.list, commits.nr);
close_commit_graph();
finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC);
commit_lock_file(&lk);
free(oids.list);
oids.alloc = 0;
oids.nr = 0;
}
#define VERIFY_COMMIT_GRAPH_ERROR_HASH 2
static int verify_commit_graph_error;
static void graph_report(const char *fmt, ...)
{
va_list ap;
verify_commit_graph_error = 1;
va_start(ap, fmt);
vfprintf(stderr, fmt, ap);
fprintf(stderr, "\n");
va_end(ap);
}
#define GENERATION_ZERO_EXISTS 1
#define GENERATION_NUMBER_EXISTS 2
int verify_commit_graph(struct repository *r, struct commit_graph *g)
{
uint32_t i, cur_fanout_pos = 0;
struct object_id prev_oid, cur_oid, checksum;
int generation_zero = 0;
struct hashfile *f;
int devnull;
struct progress *progress = NULL;
if (!g) {
graph_report("no commit-graph file loaded");
return 1;
}
verify_commit_graph_error = 0;
if (!g->chunk_oid_fanout)
graph_report("commit-graph is missing the OID Fanout chunk");
if (!g->chunk_oid_lookup)
graph_report("commit-graph is missing the OID Lookup chunk");
if (!g->chunk_commit_data)
graph_report("commit-graph is missing the Commit Data chunk");
if (verify_commit_graph_error)
return verify_commit_graph_error;
devnull = open("/dev/null", O_WRONLY);
f = hashfd(devnull, NULL);
hashwrite(f, g->data, g->data_len - g->hash_len);
finalize_hashfile(f, checksum.hash, CSUM_CLOSE);
if (hashcmp(checksum.hash, g->data + g->data_len - g->hash_len)) {
graph_report(_("the commit-graph file has incorrect checksum and is likely corrupt"));
verify_commit_graph_error = VERIFY_COMMIT_GRAPH_ERROR_HASH;
}
for (i = 0; i < g->num_commits; i++) {
struct commit *graph_commit;
hashcpy(cur_oid.hash, g->chunk_oid_lookup + g->hash_len * i);
if (i && oidcmp(&prev_oid, &cur_oid) >= 0)
graph_report("commit-graph has incorrect OID order: %s then %s",
oid_to_hex(&prev_oid),
oid_to_hex(&cur_oid));
oidcpy(&prev_oid, &cur_oid);
while (cur_oid.hash[0] > cur_fanout_pos) {
uint32_t fanout_value = get_be32(g->chunk_oid_fanout + cur_fanout_pos);
if (i != fanout_value)
graph_report("commit-graph has incorrect fanout value: fanout[%d] = %u != %u",
cur_fanout_pos, fanout_value, i);
cur_fanout_pos++;
}
graph_commit = lookup_commit(r, &cur_oid);
if (!parse_commit_in_graph_one(g, graph_commit))
graph_report("failed to parse %s from commit-graph",
oid_to_hex(&cur_oid));
}
while (cur_fanout_pos < 256) {
uint32_t fanout_value = get_be32(g->chunk_oid_fanout + cur_fanout_pos);
if (g->num_commits != fanout_value)
graph_report("commit-graph has incorrect fanout value: fanout[%d] = %u != %u",
cur_fanout_pos, fanout_value, i);
cur_fanout_pos++;
}
if (verify_commit_graph_error & ~VERIFY_COMMIT_GRAPH_ERROR_HASH)
return verify_commit_graph_error;
progress = start_progress(_("Verifying commits in commit graph"),
g->num_commits);
for (i = 0; i < g->num_commits; i++) {
struct commit *graph_commit, *odb_commit;
struct commit_list *graph_parents, *odb_parents;
uint32_t max_generation = 0;
display_progress(progress, i + 1);
hashcpy(cur_oid.hash, g->chunk_oid_lookup + g->hash_len * i);
graph_commit = lookup_commit(r, &cur_oid);
odb_commit = (struct commit *)create_object(r, cur_oid.hash, alloc_commit_node(r));
if (parse_commit_internal(odb_commit, 0, 0)) {
graph_report("failed to parse %s from object database",
oid_to_hex(&cur_oid));
continue;
}
if (oidcmp(&get_commit_tree_in_graph_one(g, graph_commit)->object.oid,
get_commit_tree_oid(odb_commit)))
graph_report("root tree OID for commit %s in commit-graph is %s != %s",
oid_to_hex(&cur_oid),
oid_to_hex(get_commit_tree_oid(graph_commit)),
oid_to_hex(get_commit_tree_oid(odb_commit)));
graph_parents = graph_commit->parents;
odb_parents = odb_commit->parents;
while (graph_parents) {
if (odb_parents == NULL) {
graph_report("commit-graph parent list for commit %s is too long",
oid_to_hex(&cur_oid));
break;
}
if (oidcmp(&graph_parents->item->object.oid, &odb_parents->item->object.oid))
graph_report("commit-graph parent for %s is %s != %s",
oid_to_hex(&cur_oid),
oid_to_hex(&graph_parents->item->object.oid),
oid_to_hex(&odb_parents->item->object.oid));
if (graph_parents->item->generation > max_generation)
max_generation = graph_parents->item->generation;
graph_parents = graph_parents->next;
odb_parents = odb_parents->next;
}
if (odb_parents != NULL)
graph_report("commit-graph parent list for commit %s terminates early",
oid_to_hex(&cur_oid));
if (!graph_commit->generation) {
if (generation_zero == GENERATION_NUMBER_EXISTS)
graph_report("commit-graph has generation number zero for commit %s, but non-zero elsewhere",
oid_to_hex(&cur_oid));
generation_zero = GENERATION_ZERO_EXISTS;
} else if (generation_zero == GENERATION_ZERO_EXISTS)
graph_report("commit-graph has non-zero generation number for commit %s, but zero elsewhere",
oid_to_hex(&cur_oid));
if (generation_zero == GENERATION_ZERO_EXISTS)
continue;
/*
* If one of our parents has generation GENERATION_NUMBER_MAX, then
* our generation is also GENERATION_NUMBER_MAX. Decrement to avoid
* extra logic in the following condition.
*/
if (max_generation == GENERATION_NUMBER_MAX)
max_generation--;
if (graph_commit->generation != max_generation + 1)
graph_report("commit-graph generation for commit %s is %u != %u",
oid_to_hex(&cur_oid),
graph_commit->generation,
max_generation + 1);
if (graph_commit->date != odb_commit->date)
graph_report("commit date for commit %s in commit-graph is %"PRItime" != %"PRItime,
oid_to_hex(&cur_oid),
graph_commit->date,
odb_commit->date);
}
stop_progress(&progress);
return verify_commit_graph_error;
}
void free_commit_graph(struct commit_graph *g)
{
if (!g)
return;
if (g->graph_fd >= 0) {
munmap((void *)g->data, g->data_len);
g->data = NULL;
close(g->graph_fd);
}
free(g);
}