#include "tree.h"
#include "delta.h"
#include "pack.h"
+#include "pack-revindex.h"
#include "csum-file.h"
#include "tree-walk.h"
#include "diff.h"
#include "revision.h"
#include "list-objects.h"
#include "progress.h"
+#include "refs.h"
#ifdef THREADED_DELTA_SEARCH
+#include "thread-utils.h"
#include <pthread.h>
#endif
[--window=N] [--window-memory=N] [--depth=N] \n\
[--no-reuse-delta] [--no-reuse-object] [--delta-base-offset] \n\
[--threads=N] [--non-empty] [--revs [--unpacked | --all]*] [--reflog] \n\
- [--stdout | base-name] [--keep-unreachable] [<ref-list | <object-list]";
+ [--stdout | base-name] [--include-tag] [--keep-unreachable] \n\
+ [<ref-list | <object-list]";
struct object_entry {
struct pack_idx_entry idx;
static uint32_t nr_objects, nr_alloc, nr_result, nr_written;
static int non_empty;
-static int no_reuse_delta, no_reuse_object, keep_unreachable;
+static int no_reuse_delta, no_reuse_object, keep_unreachable, include_tag;
static int local;
static int incremental;
static int allow_ofs_delta;
static const char *base_name;
static int progress = 1;
static int window = 10;
-static uint32_t pack_size_limit;
+static uint32_t pack_size_limit, pack_size_limit_cfg;
static int depth = 50;
static int delta_search_threads = 1;
static int pack_to_stdout;
static int *object_ix;
static int object_ix_hashsz;
-/*
- * Pack index for existing packs give us easy access to the offsets into
- * corresponding pack file where each object's data starts, but the entries
- * do not store the size of the compressed representation (uncompressed
- * size is easily available by examining the pack entry header). It is
- * also rather expensive to find the sha1 for an object given its offset.
- *
- * We build a hashtable of existing packs (pack_revindex), and keep reverse
- * index here -- pack index file is sorted by object name mapping to offset;
- * this pack_revindex[].revindex array is a list of offset/index_nr pairs
- * ordered by offset, so if you know the offset of an object, next offset
- * is where its packed representation ends and the index_nr can be used to
- * get the object sha1 from the main index.
- */
-struct revindex_entry {
- off_t offset;
- unsigned int nr;
-};
-struct pack_revindex {
- struct packed_git *p;
- struct revindex_entry *revindex;
-};
-static struct pack_revindex *pack_revindex;
-static int pack_revindex_hashsz;
-
/*
* stats
*/
static uint32_t written, written_delta;
static uint32_t reused, reused_delta;
-static int pack_revindex_ix(struct packed_git *p)
-{
- unsigned long ui = (unsigned long)p;
- int i;
-
- ui = ui ^ (ui >> 16); /* defeat structure alignment */
- i = (int)(ui % pack_revindex_hashsz);
- while (pack_revindex[i].p) {
- if (pack_revindex[i].p == p)
- return i;
- if (++i == pack_revindex_hashsz)
- i = 0;
- }
- return -1 - i;
-}
-
-static void prepare_pack_ix(void)
-{
- int num;
- struct packed_git *p;
- for (num = 0, p = packed_git; p; p = p->next)
- num++;
- if (!num)
- return;
- pack_revindex_hashsz = num * 11;
- pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz);
- for (p = packed_git; p; p = p->next) {
- num = pack_revindex_ix(p);
- num = - 1 - num;
- pack_revindex[num].p = p;
- }
- /* revindex elements are lazily initialized */
-}
-
-static int cmp_offset(const void *a_, const void *b_)
-{
- const struct revindex_entry *a = a_;
- const struct revindex_entry *b = b_;
- return (a->offset < b->offset) ? -1 : (a->offset > b->offset) ? 1 : 0;
-}
-
-/*
- * Ordered list of offsets of objects in the pack.
- */
-static void prepare_pack_revindex(struct pack_revindex *rix)
-{
- struct packed_git *p = rix->p;
- int num_ent = p->num_objects;
- int i;
- const char *index = p->index_data;
-
- rix->revindex = xmalloc(sizeof(*rix->revindex) * (num_ent + 1));
- index += 4 * 256;
-
- if (p->index_version > 1) {
- const uint32_t *off_32 =
- (uint32_t *)(index + 8 + p->num_objects * (20 + 4));
- const uint32_t *off_64 = off_32 + p->num_objects;
- for (i = 0; i < num_ent; i++) {
- uint32_t off = ntohl(*off_32++);
- if (!(off & 0x80000000)) {
- rix->revindex[i].offset = off;
- } else {
- rix->revindex[i].offset =
- ((uint64_t)ntohl(*off_64++)) << 32;
- rix->revindex[i].offset |=
- ntohl(*off_64++);
- }
- rix->revindex[i].nr = i;
- }
- } else {
- for (i = 0; i < num_ent; i++) {
- uint32_t hl = *((uint32_t *)(index + 24 * i));
- rix->revindex[i].offset = ntohl(hl);
- rix->revindex[i].nr = i;
- }
- }
-
- /* This knows the pack format -- the 20-byte trailer
- * follows immediately after the last object data.
- */
- rix->revindex[num_ent].offset = p->pack_size - 20;
- rix->revindex[num_ent].nr = -1;
- qsort(rix->revindex, num_ent, sizeof(*rix->revindex), cmp_offset);
-}
-
-static struct revindex_entry * find_packed_object(struct packed_git *p,
- off_t ofs)
-{
- int num;
- int lo, hi;
- struct pack_revindex *rix;
- struct revindex_entry *revindex;
- num = pack_revindex_ix(p);
- if (num < 0)
- die("internal error: pack revindex uninitialized");
- rix = &pack_revindex[num];
- if (!rix->revindex)
- prepare_pack_revindex(rix);
- revindex = rix->revindex;
- lo = 0;
- hi = p->num_objects + 1;
- do {
- int mi = (lo + hi) / 2;
- if (revindex[mi].offset == ofs) {
- return revindex + mi;
- }
- else if (ofs < revindex[mi].offset)
- hi = mi;
- else
- lo = mi + 1;
- } while (lo < hi);
- die("internal error: pack revindex corrupt");
-}
-
-static const unsigned char *find_packed_object_name(struct packed_git *p,
- off_t ofs)
-{
- struct revindex_entry *entry = find_packed_object(p, ofs);
- return nth_packed_object_sha1(p, entry->nr);
-}
static void *delta_against(void *buf, unsigned long size, struct object_entry *entry)
{
/* nothing */;
deflateEnd(&stream);
datalen = stream.total_out;
- deflateEnd(&stream);
+
/*
* The object header is a byte of 'type' followed by zero or
* more bytes of length.
}
hdrlen = encode_header(obj_type, entry->size, header);
offset = entry->in_pack_offset;
- revidx = find_packed_object(p, offset);
+ revidx = find_pack_revindex(p, offset);
datalen = revidx[1].offset - offset;
if (!pack_to_stdout && p->index_version > 1 &&
check_pack_crc(p, &w_curs, offset, datalen, revidx->nr))
struct pack_header hdr;
int do_progress = progress >> pack_to_stdout;
uint32_t nr_remaining = nr_result;
+ time_t last_mtime = 0;
if (do_progress)
progress_state = start_progress("Writing objects", nr_result);
if (!pack_to_stdout) {
mode_t mode = umask(0);
+ struct stat st;
char *idx_tmp_name, tmpname[PATH_MAX];
umask(mode);
idx_tmp_name = write_idx_file(NULL, written_list,
nr_written, sha1);
+
snprintf(tmpname, sizeof(tmpname), "%s-%s.pack",
base_name, sha1_to_hex(sha1));
if (adjust_perm(pack_tmp_name, mode))
if (rename(pack_tmp_name, tmpname))
die("unable to rename temporary pack file: %s",
strerror(errno));
+
+ /*
+ * Packs are runtime accessed in their mtime
+ * order since newer packs are more likely to contain
+ * younger objects. So if we are creating multiple
+ * packs then we should modify the mtime of later ones
+ * to preserve this property.
+ */
+ if (stat(tmpname, &st) < 0) {
+ warning("failed to stat %s: %s",
+ tmpname, strerror(errno));
+ } else if (!last_mtime) {
+ last_mtime = st.st_mtime;
+ } else {
+ struct utimbuf utb;
+ utb.actime = st.st_atime;
+ utb.modtime = --last_mtime;
+ if (utime(tmpname, &utb) < 0)
+ warning("failed utime() on %s: %s",
+ tmpname, strerror(errno));
+ }
+
snprintf(tmpname, sizeof(tmpname), "%s-%s.idx",
base_name, sha1_to_hex(sha1));
if (adjust_perm(idx_tmp_name, mode))
if (rename(idx_tmp_name, tmpname))
die("unable to rename temporary index file: %s",
strerror(errno));
+
free(idx_tmp_name);
free(pack_tmp_name);
puts(sha1_to_hex(sha1));
die("delta base offset out of bound for %s",
sha1_to_hex(entry->idx.sha1));
ofs = entry->in_pack_offset - ofs;
- if (!no_reuse_delta && !entry->preferred_base)
- base_ref = find_packed_object_name(p, ofs);
+ if (!no_reuse_delta && !entry->preferred_base) {
+ struct revindex_entry *revidx;
+ revidx = find_pack_revindex(p, ofs);
+ base_ref = nth_packed_object_sha1(p, revidx->nr);
+ }
entry->in_pack_header_size = used + used_0;
break;
}
sorted_by_offset[i] = objects + i;
qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort);
- prepare_pack_ix();
+ init_pack_revindex();
+
for (i = 0; i < nr_objects; i++)
check_object(sorted_by_offset[i]);
+
free(sorted_by_offset);
}
* accounting lock. Compiler will optimize the strangeness
* away when THREADED_DELTA_SEARCH is not defined.
*/
- if (trg_entry->delta_data)
- free(trg_entry->delta_data);
+ free(trg_entry->delta_data);
cache_lock();
if (trg_entry->delta_data) {
delta_cache_size -= trg_entry->delta_size;
#ifdef THREADED_DELTA_SEARCH
+/*
+ * The main thread waits on the condition that (at least) one of the workers
+ * has stopped working (which is indicated in the .working member of
+ * struct thread_params).
+ * When a work thread has completed its work, it sets .working to 0 and
+ * signals the main thread and waits on the condition that .data_ready
+ * becomes 1.
+ */
+
struct thread_params {
pthread_t thread;
struct object_entry **list;
unsigned remaining;
int window;
int depth;
+ int working;
+ int data_ready;
+ pthread_mutex_t mutex;
+ pthread_cond_t cond;
unsigned *processed;
};
-static pthread_mutex_t data_request = PTHREAD_MUTEX_INITIALIZER;
-static pthread_mutex_t data_ready = PTHREAD_MUTEX_INITIALIZER;
-static pthread_mutex_t data_provider = PTHREAD_MUTEX_INITIALIZER;
-static struct thread_params *data_requester;
+static pthread_cond_t progress_cond = PTHREAD_COND_INITIALIZER;
static void *threaded_find_deltas(void *arg)
{
struct thread_params *me = arg;
- for (;;) {
- pthread_mutex_lock(&data_request);
- data_requester = me;
- pthread_mutex_unlock(&data_provider);
- pthread_mutex_lock(&data_ready);
- pthread_mutex_unlock(&data_request);
-
- if (!me->remaining)
- return NULL;
-
+ while (me->remaining) {
find_deltas(me->list, &me->remaining,
me->window, me->depth, me->processed);
+
+ progress_lock();
+ me->working = 0;
+ pthread_cond_signal(&progress_cond);
+ progress_unlock();
+
+ /*
+ * We must not set ->data_ready before we wait on the
+ * condition because the main thread may have set it to 1
+ * before we get here. In order to be sure that new
+ * work is available if we see 1 in ->data_ready, it
+ * was initialized to 0 before this thread was spawned
+ * and we reset it to 0 right away.
+ */
+ pthread_mutex_lock(&me->mutex);
+ while (!me->data_ready)
+ pthread_cond_wait(&me->cond, &me->mutex);
+ me->data_ready = 0;
+ pthread_mutex_unlock(&me->mutex);
}
+ /* leave ->working 1 so that this doesn't get more work assigned */
+ return NULL;
}
static void ll_find_deltas(struct object_entry **list, unsigned list_size,
int window, int depth, unsigned *processed)
{
- struct thread_params *target, p[delta_search_threads];
+ struct thread_params p[delta_search_threads];
int i, ret, active_threads = 0;
if (delta_search_threads <= 1) {
return;
}
- pthread_mutex_lock(&data_provider);
- pthread_mutex_lock(&data_ready);
-
- /* Start work threads. */
+ /* Partition the work amongst work threads. */
for (i = 0; i < delta_search_threads; i++) {
+ unsigned sub_size = list_size / (delta_search_threads - i);
+
p[i].window = window;
p[i].depth = depth;
p[i].processed = processed;
- p[i].remaining = 0;
- ret = pthread_create(&p[i].thread, NULL,
- threaded_find_deltas, &p[i]);
- if (ret)
- die("unable to create thread: %s", strerror(ret));
- active_threads++;
- }
-
- /* Then partition the work amongst them. */
- for (i = 0; i < delta_search_threads; i++) {
- unsigned sub_size = list_size / (delta_search_threads - i);
-
- pthread_mutex_lock(&data_provider);
- target = data_requester;
- if (!sub_size) {
- pthread_mutex_unlock(&data_ready);
- pthread_join(target->thread, NULL);
- active_threads--;
- continue;
- }
+ p[i].working = 1;
+ p[i].data_ready = 0;
/* try to split chunks on "path" boundaries */
- while (sub_size < list_size && list[sub_size]->hash &&
+ while (sub_size && sub_size < list_size &&
+ list[sub_size]->hash &&
list[sub_size]->hash == list[sub_size-1]->hash)
sub_size++;
- target->list = list;
- target->list_size = sub_size;
- target->remaining = sub_size;
- pthread_mutex_unlock(&data_ready);
+ p[i].list = list;
+ p[i].list_size = sub_size;
+ p[i].remaining = sub_size;
list += sub_size;
list_size -= sub_size;
}
+ /* Start work threads. */
+ for (i = 0; i < delta_search_threads; i++) {
+ if (!p[i].list_size)
+ continue;
+ pthread_mutex_init(&p[i].mutex, NULL);
+ pthread_cond_init(&p[i].cond, NULL);
+ ret = pthread_create(&p[i].thread, NULL,
+ threaded_find_deltas, &p[i]);
+ if (ret)
+ die("unable to create thread: %s", strerror(ret));
+ active_threads++;
+ }
+
/*
* Now let's wait for work completion. Each time a thread is done
* with its work, we steal half of the remaining work from the
* until the remaining object list segments are simply too short
* to be worth splitting anymore.
*/
- do {
+ while (active_threads) {
+ struct thread_params *target = NULL;
struct thread_params *victim = NULL;
unsigned sub_size = 0;
- pthread_mutex_lock(&data_provider);
- target = data_requester;
progress_lock();
+ for (;;) {
+ for (i = 0; !target && i < delta_search_threads; i++)
+ if (!p[i].working)
+ target = &p[i];
+ if (target)
+ break;
+ pthread_cond_wait(&progress_cond, &progress_mutex);
+ }
+
for (i = 0; i < delta_search_threads; i++)
if (p[i].remaining > 2*window &&
(!victim || victim->remaining < p[i].remaining))
victim->list_size -= sub_size;
victim->remaining -= sub_size;
}
- progress_unlock();
-
target->list_size = sub_size;
target->remaining = sub_size;
- pthread_mutex_unlock(&data_ready);
+ target->working = 1;
+ progress_unlock();
+
+ pthread_mutex_lock(&target->mutex);
+ target->data_ready = 1;
+ pthread_cond_signal(&target->cond);
+ pthread_mutex_unlock(&target->mutex);
if (!sub_size) {
pthread_join(target->thread, NULL);
+ pthread_cond_destroy(&target->cond);
+ pthread_mutex_destroy(&target->mutex);
active_threads--;
}
- } while (active_threads);
+ }
}
#else
#define ll_find_deltas(l, s, w, d, p) find_deltas(l, &s, w, d, p)
#endif
+static int add_ref_tag(const char *path, const unsigned char *sha1, int flag, void *cb_data)
+{
+ unsigned char peeled[20];
+
+ if (!prefixcmp(path, "refs/tags/") && /* is a tag? */
+ !peel_ref(path, peeled) && /* peelable? */
+ !is_null_sha1(peeled) && /* annotated tag? */
+ locate_object_entry(peeled)) /* object packed? */
+ add_object_entry(sha1, OBJ_TAG, NULL, 0);
+ return 0;
+}
+
static void prepare_pack(int window, int depth)
{
struct object_entry **delta_list;
}
if (!strcmp(k, "pack.threads")) {
delta_search_threads = git_config_int(k, v);
- if (delta_search_threads < 1)
+ if (delta_search_threads < 0)
die("invalid number of threads specified (%d)",
delta_search_threads);
#ifndef THREADED_DELTA_SEARCH
- if (delta_search_threads > 1)
+ if (delta_search_threads != 1)
warning("no threads support, ignoring %s", k);
#endif
return 0;
die("bad pack.indexversion=%d", pack_idx_default_version);
return 0;
}
+ if (!strcmp(k, "pack.packsizelimit")) {
+ pack_size_limit_cfg = git_config_ulong(k, v);
+ return 0;
+ }
return git_default_config(k, v);
}
init_revisions(&revs, NULL);
save_commit_buffer = 0;
- track_object_refs = 0;
setup_revisions(ac, av, &revs, NULL);
while (fgets(line, sizeof(line), stdin) != NULL) {
int len = strlen(line);
- if (line[len - 1] == '\n')
+ if (len && line[len - 1] == '\n')
line[--len] = 0;
if (!len)
break;
die("bad revision '%s'", line);
}
- prepare_revision_walk(&revs);
+ if (prepare_revision_walk(&revs))
+ die("revision walk setup failed");
mark_edges_uninteresting(revs.commits, &revs, show_edge);
traverse_commit_list(&revs, show_commit, show_object);
}
if (!prefixcmp(arg, "--max-pack-size=")) {
char *end;
+ pack_size_limit_cfg = 0;
pack_size_limit = strtoul(arg+16, &end, 0) * 1024 * 1024;
if (!arg[16] || *end)
usage(pack_usage);
if (!prefixcmp(arg, "--threads=")) {
char *end;
delta_search_threads = strtoul(arg+10, &end, 0);
- if (!arg[10] || *end || delta_search_threads < 1)
+ if (!arg[10] || *end || delta_search_threads < 0)
usage(pack_usage);
#ifndef THREADED_DELTA_SEARCH
- if (delta_search_threads > 1)
+ if (delta_search_threads != 1)
warning("no threads support, "
"ignoring %s", arg);
#endif
keep_unreachable = 1;
continue;
}
+ if (!strcmp("--include-tag", arg)) {
+ include_tag = 1;
+ continue;
+ }
if (!strcmp("--unpacked", arg) ||
!prefixcmp(arg, "--unpacked=") ||
!strcmp("--reflog", arg) ||
if (pack_to_stdout != !base_name)
usage(pack_usage);
+ if (!pack_to_stdout && !pack_size_limit)
+ pack_size_limit = pack_size_limit_cfg;
+
if (pack_to_stdout && pack_size_limit)
die("--max-pack-size cannot be used to build a pack for transfer.");
if (!pack_to_stdout && thin)
die("--thin cannot be used to build an indexable pack.");
+#ifdef THREADED_DELTA_SEARCH
+ if (!delta_search_threads) /* --threads=0 means autodetect */
+ delta_search_threads = online_cpus();
+#endif
+
prepare_packed_git();
if (progress)
rp_av[rp_ac] = NULL;
get_object_list(rp_ac, rp_av);
}
+ if (include_tag && nr_result)
+ for_each_ref(add_ref_tag, NULL);
stop_progress(&progress_state);
if (non_empty && !nr_result)