git/midx.c

1480 lines
38 KiB
C
Raw Normal View History

#include "cache.h"
#include "config.h"
#include "csum-file.h"
#include "dir.h"
#include "lockfile.h"
#include "packfile.h"
#include "object-store.h"
#include "hash-lookup.h"
#include "midx.h"
#include "progress.h"
#include "trace2.h"
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
#include "run-command.h"
#include "repository.h"
#define MIDX_SIGNATURE 0x4d494458 /* "MIDX" */
#define MIDX_VERSION 1
#define MIDX_BYTE_FILE_VERSION 4
#define MIDX_BYTE_HASH_VERSION 5
#define MIDX_BYTE_NUM_CHUNKS 6
#define MIDX_BYTE_NUM_PACKS 8
#define MIDX_HEADER_SIZE 12
#define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + the_hash_algo->rawsz)
#define MIDX_MAX_CHUNKS 5
#define MIDX_CHUNK_ALIGNMENT 4
#define MIDX_CHUNKID_PACKNAMES 0x504e414d /* "PNAM" */
#define MIDX_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
#define MIDX_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
#define MIDX_CHUNKID_OBJECTOFFSETS 0x4f4f4646 /* "OOFF" */
#define MIDX_CHUNKID_LARGEOFFSETS 0x4c4f4646 /* "LOFF" */
#define MIDX_CHUNKLOOKUP_WIDTH (sizeof(uint32_t) + sizeof(uint64_t))
#define MIDX_CHUNK_FANOUT_SIZE (sizeof(uint32_t) * 256)
#define MIDX_CHUNK_OFFSET_WIDTH (2 * sizeof(uint32_t))
#define MIDX_CHUNK_LARGE_OFFSET_WIDTH (sizeof(uint64_t))
#define MIDX_LARGE_OFFSET_NEEDED 0x80000000
#define PACK_EXPIRED UINT_MAX
multi-pack-index: use hash version byte Similar to the commit-graph format, the multi-pack-index format has a byte in the header intended to track the hash version used to write the file. This allows one to interpret the hash length without having the context of the repository config specifying the hash length. This was not modified as part of the SHA-256 work because the hash length was automatically up-shifted due to that config. Since we have this byte available, we can make the file formats more obviously incompatible instead of relying on other context from the repository. Add a new oid_version() method in midx.c similar to the one in commit-graph.c. This is specifically made separate from that implementation to avoid artificially linking the formats. The test impact requires a few more things than the corresponding change in the commit-graph format. Specifically, 'test-tool read-midx' was not writing anything about this header value to output. Since the value available in 'struct multi_pack_index' is hash_len instead of a version value, we output "20" or "32" instead of "1" or "2". Since we want a user to not have their Git commands fail if their multi-pack-index has the incorrect hash version compared to the repository's hash version, we relax the die() to an error() in load_multi_pack_index(). This has some effect on 'git multi-pack-index verify' as we need to check that a failed parse of a file that exists is actually a verify error. For that test that checks the hash version matches, we change the corrupted byte from "2" to "3" to ensure the test fails for both hash algorithms. Helped-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-17 14:04:48 +00:00
static uint8_t oid_version(void)
{
switch (hash_algo_by_ptr(the_hash_algo)) {
case GIT_HASH_SHA1:
return 1;
case GIT_HASH_SHA256:
return 2;
default:
die(_("invalid hash version"));
}
}
static char *get_midx_filename(const char *object_dir)
{
return xstrfmt("%s/pack/multi-pack-index", object_dir);
}
struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local)
{
struct multi_pack_index *m = NULL;
int fd;
struct stat st;
size_t midx_size;
void *midx_map = NULL;
uint32_t hash_version;
char *midx_name = get_midx_filename(object_dir);
uint32_t i;
const char *cur_pack_name;
fd = git_open(midx_name);
if (fd < 0)
goto cleanup_fail;
if (fstat(fd, &st)) {
error_errno(_("failed to read %s"), midx_name);
goto cleanup_fail;
}
midx_size = xsize_t(st.st_size);
if (midx_size < MIDX_MIN_SIZE) {
error(_("multi-pack-index file %s is too small"), midx_name);
goto cleanup_fail;
}
FREE_AND_NULL(midx_name);
midx_map = xmmap(NULL, midx_size, PROT_READ, MAP_PRIVATE, fd, 0);
close(fd);
FLEX_ALLOC_STR(m, object_dir, object_dir);
m->data = midx_map;
m->data_len = midx_size;
m->local = local;
m->signature = get_be32(m->data);
if (m->signature != MIDX_SIGNATURE)
die(_("multi-pack-index signature 0x%08x does not match signature 0x%08x"),
m->signature, MIDX_SIGNATURE);
m->version = m->data[MIDX_BYTE_FILE_VERSION];
if (m->version != MIDX_VERSION)
die(_("multi-pack-index version %d not recognized"),
m->version);
hash_version = m->data[MIDX_BYTE_HASH_VERSION];
multi-pack-index: use hash version byte Similar to the commit-graph format, the multi-pack-index format has a byte in the header intended to track the hash version used to write the file. This allows one to interpret the hash length without having the context of the repository config specifying the hash length. This was not modified as part of the SHA-256 work because the hash length was automatically up-shifted due to that config. Since we have this byte available, we can make the file formats more obviously incompatible instead of relying on other context from the repository. Add a new oid_version() method in midx.c similar to the one in commit-graph.c. This is specifically made separate from that implementation to avoid artificially linking the formats. The test impact requires a few more things than the corresponding change in the commit-graph format. Specifically, 'test-tool read-midx' was not writing anything about this header value to output. Since the value available in 'struct multi_pack_index' is hash_len instead of a version value, we output "20" or "32" instead of "1" or "2". Since we want a user to not have their Git commands fail if their multi-pack-index has the incorrect hash version compared to the repository's hash version, we relax the die() to an error() in load_multi_pack_index(). This has some effect on 'git multi-pack-index verify' as we need to check that a failed parse of a file that exists is actually a verify error. For that test that checks the hash version matches, we change the corrupted byte from "2" to "3" to ensure the test fails for both hash algorithms. Helped-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-17 14:04:48 +00:00
if (hash_version != oid_version()) {
error(_("multi-pack-index hash version %u does not match version %u"),
hash_version, oid_version());
goto cleanup_fail;
}
m->hash_len = the_hash_algo->rawsz;
m->num_chunks = m->data[MIDX_BYTE_NUM_CHUNKS];
m->num_packs = get_be32(m->data + MIDX_BYTE_NUM_PACKS);
for (i = 0; i < m->num_chunks; i++) {
uint32_t chunk_id = get_be32(m->data + MIDX_HEADER_SIZE +
MIDX_CHUNKLOOKUP_WIDTH * i);
uint64_t chunk_offset = get_be64(m->data + MIDX_HEADER_SIZE + 4 +
MIDX_CHUNKLOOKUP_WIDTH * i);
if (chunk_offset >= m->data_len)
die(_("invalid chunk offset (too large)"));
switch (chunk_id) {
case MIDX_CHUNKID_PACKNAMES:
m->chunk_pack_names = m->data + chunk_offset;
break;
case MIDX_CHUNKID_OIDFANOUT:
m->chunk_oid_fanout = (uint32_t *)(m->data + chunk_offset);
break;
case MIDX_CHUNKID_OIDLOOKUP:
m->chunk_oid_lookup = m->data + chunk_offset;
break;
case MIDX_CHUNKID_OBJECTOFFSETS:
m->chunk_object_offsets = m->data + chunk_offset;
break;
case MIDX_CHUNKID_LARGEOFFSETS:
m->chunk_large_offsets = m->data + chunk_offset;
break;
case 0:
die(_("terminating multi-pack-index chunk id appears earlier than expected"));
break;
default:
/*
* Do nothing on unrecognized chunks, allowing future
* extensions to add optional chunks.
*/
break;
}
}
if (!m->chunk_pack_names)
die(_("multi-pack-index missing required pack-name chunk"));
if (!m->chunk_oid_fanout)
die(_("multi-pack-index missing required OID fanout chunk"));
if (!m->chunk_oid_lookup)
die(_("multi-pack-index missing required OID lookup chunk"));
if (!m->chunk_object_offsets)
die(_("multi-pack-index missing required object offsets chunk"));
m->num_objects = ntohl(m->chunk_oid_fanout[255]);
m->pack_names = xcalloc(m->num_packs, sizeof(*m->pack_names));
m->packs = xcalloc(m->num_packs, sizeof(*m->packs));
cur_pack_name = (const char *)m->chunk_pack_names;
for (i = 0; i < m->num_packs; i++) {
m->pack_names[i] = cur_pack_name;
cur_pack_name += strlen(cur_pack_name) + 1;
if (i && strcmp(m->pack_names[i], m->pack_names[i - 1]) <= 0)
die(_("multi-pack-index pack names out of order: '%s' before '%s'"),
m->pack_names[i - 1],
m->pack_names[i]);
}
trace2_data_intmax("midx", the_repository, "load/num_packs", m->num_packs);
trace2_data_intmax("midx", the_repository, "load/num_objects", m->num_objects);
return m;
cleanup_fail:
free(m);
free(midx_name);
if (midx_map)
munmap(midx_map, midx_size);
if (0 <= fd)
close(fd);
return NULL;
}
void close_midx(struct multi_pack_index *m)
{
uint32_t i;
if (!m)
return;
munmap((unsigned char *)m->data, m->data_len);
for (i = 0; i < m->num_packs; i++) {
midx: add packs to packed_git linked list The multi-pack-index allows searching for objects across multiple packs using one object list. The original design gains many of these performance benefits by keeping the packs in the multi-pack-index out of the packed_git list. Unfortunately, this has one major drawback. If the multi-pack-index covers thousands of packs, and a command loads many of those packs, then we can hit the limit for open file descriptors. The close_one_pack() method is used to limit this resource, but it only looks at the packed_git list, and uses an LRU cache to prevent thrashing. Instead of complicating this close_one_pack() logic to include direct references to the multi-pack-index, simply add the packs opened by the multi-pack-index to the packed_git list. This immediately solves the file-descriptor limit problem, but requires some extra steps to avoid performance issues or other problems: 1. Create a multi_pack_index bit in the packed_git struct that is one if and only if the pack was loaded from a multi-pack-index. 2. Skip packs with the multi_pack_index bit when doing object lookups and abbreviations. These algorithms already check the multi-pack-index before the packed_git struct. This has a very small performance hit, as we need to walk more packed_git structs. This is acceptable, since these operations run binary search on the other packs, so this walk-and-ignore logic is very fast by comparison. 3. When closing a multi-pack-index file, do not close its packs, as those packs will be closed using close_all_packs(). In some cases, such as 'git repack', we run 'close_midx()' without also closing the packs, so we need to un-set the multi_pack_index bit in those packs. This is necessary, and caught by running t6501-freshen-objects.sh with GIT_TEST_MULTI_PACK_INDEX=1. To manually test this change, I inserted trace2 logging into close_pack_fd() and set pack_max_fds to 10, then ran 'git rev-list --all --objects' on a copy of the Git repo with 300+ pack-files and a multi-pack-index. The logs verified the packs are closed as we read them beyond the file descriptor limit. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-04-29 16:18:56 +00:00
if (m->packs[i])
m->packs[i]->multi_pack_index = 0;
}
FREE_AND_NULL(m->packs);
FREE_AND_NULL(m->pack_names);
}
int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, uint32_t pack_int_id)
{
struct strbuf pack_name = STRBUF_INIT;
midx: add packs to packed_git linked list The multi-pack-index allows searching for objects across multiple packs using one object list. The original design gains many of these performance benefits by keeping the packs in the multi-pack-index out of the packed_git list. Unfortunately, this has one major drawback. If the multi-pack-index covers thousands of packs, and a command loads many of those packs, then we can hit the limit for open file descriptors. The close_one_pack() method is used to limit this resource, but it only looks at the packed_git list, and uses an LRU cache to prevent thrashing. Instead of complicating this close_one_pack() logic to include direct references to the multi-pack-index, simply add the packs opened by the multi-pack-index to the packed_git list. This immediately solves the file-descriptor limit problem, but requires some extra steps to avoid performance issues or other problems: 1. Create a multi_pack_index bit in the packed_git struct that is one if and only if the pack was loaded from a multi-pack-index. 2. Skip packs with the multi_pack_index bit when doing object lookups and abbreviations. These algorithms already check the multi-pack-index before the packed_git struct. This has a very small performance hit, as we need to walk more packed_git structs. This is acceptable, since these operations run binary search on the other packs, so this walk-and-ignore logic is very fast by comparison. 3. When closing a multi-pack-index file, do not close its packs, as those packs will be closed using close_all_packs(). In some cases, such as 'git repack', we run 'close_midx()' without also closing the packs, so we need to un-set the multi_pack_index bit in those packs. This is necessary, and caught by running t6501-freshen-objects.sh with GIT_TEST_MULTI_PACK_INDEX=1. To manually test this change, I inserted trace2 logging into close_pack_fd() and set pack_max_fds to 10, then ran 'git rev-list --all --objects' on a copy of the Git repo with 300+ pack-files and a multi-pack-index. The logs verified the packs are closed as we read them beyond the file descriptor limit. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-04-29 16:18:56 +00:00
struct packed_git *p;
if (pack_int_id >= m->num_packs)
die(_("bad pack-int-id: %u (%u total packs)"),
pack_int_id, m->num_packs);
if (m->packs[pack_int_id])
return 0;
strbuf_addf(&pack_name, "%s/pack/%s", m->object_dir,
m->pack_names[pack_int_id]);
midx: add packs to packed_git linked list The multi-pack-index allows searching for objects across multiple packs using one object list. The original design gains many of these performance benefits by keeping the packs in the multi-pack-index out of the packed_git list. Unfortunately, this has one major drawback. If the multi-pack-index covers thousands of packs, and a command loads many of those packs, then we can hit the limit for open file descriptors. The close_one_pack() method is used to limit this resource, but it only looks at the packed_git list, and uses an LRU cache to prevent thrashing. Instead of complicating this close_one_pack() logic to include direct references to the multi-pack-index, simply add the packs opened by the multi-pack-index to the packed_git list. This immediately solves the file-descriptor limit problem, but requires some extra steps to avoid performance issues or other problems: 1. Create a multi_pack_index bit in the packed_git struct that is one if and only if the pack was loaded from a multi-pack-index. 2. Skip packs with the multi_pack_index bit when doing object lookups and abbreviations. These algorithms already check the multi-pack-index before the packed_git struct. This has a very small performance hit, as we need to walk more packed_git structs. This is acceptable, since these operations run binary search on the other packs, so this walk-and-ignore logic is very fast by comparison. 3. When closing a multi-pack-index file, do not close its packs, as those packs will be closed using close_all_packs(). In some cases, such as 'git repack', we run 'close_midx()' without also closing the packs, so we need to un-set the multi_pack_index bit in those packs. This is necessary, and caught by running t6501-freshen-objects.sh with GIT_TEST_MULTI_PACK_INDEX=1. To manually test this change, I inserted trace2 logging into close_pack_fd() and set pack_max_fds to 10, then ran 'git rev-list --all --objects' on a copy of the Git repo with 300+ pack-files and a multi-pack-index. The logs verified the packs are closed as we read them beyond the file descriptor limit. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-04-29 16:18:56 +00:00
p = add_packed_git(pack_name.buf, pack_name.len, m->local);
strbuf_release(&pack_name);
midx: add packs to packed_git linked list The multi-pack-index allows searching for objects across multiple packs using one object list. The original design gains many of these performance benefits by keeping the packs in the multi-pack-index out of the packed_git list. Unfortunately, this has one major drawback. If the multi-pack-index covers thousands of packs, and a command loads many of those packs, then we can hit the limit for open file descriptors. The close_one_pack() method is used to limit this resource, but it only looks at the packed_git list, and uses an LRU cache to prevent thrashing. Instead of complicating this close_one_pack() logic to include direct references to the multi-pack-index, simply add the packs opened by the multi-pack-index to the packed_git list. This immediately solves the file-descriptor limit problem, but requires some extra steps to avoid performance issues or other problems: 1. Create a multi_pack_index bit in the packed_git struct that is one if and only if the pack was loaded from a multi-pack-index. 2. Skip packs with the multi_pack_index bit when doing object lookups and abbreviations. These algorithms already check the multi-pack-index before the packed_git struct. This has a very small performance hit, as we need to walk more packed_git structs. This is acceptable, since these operations run binary search on the other packs, so this walk-and-ignore logic is very fast by comparison. 3. When closing a multi-pack-index file, do not close its packs, as those packs will be closed using close_all_packs(). In some cases, such as 'git repack', we run 'close_midx()' without also closing the packs, so we need to un-set the multi_pack_index bit in those packs. This is necessary, and caught by running t6501-freshen-objects.sh with GIT_TEST_MULTI_PACK_INDEX=1. To manually test this change, I inserted trace2 logging into close_pack_fd() and set pack_max_fds to 10, then ran 'git rev-list --all --objects' on a copy of the Git repo with 300+ pack-files and a multi-pack-index. The logs verified the packs are closed as we read them beyond the file descriptor limit. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-04-29 16:18:56 +00:00
if (!p)
return 1;
p->multi_pack_index = 1;
m->packs[pack_int_id] = p;
install_packed_git(r, p);
list_add_tail(&p->mru, &r->objects->packed_git_mru);
return 0;
}
int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m, uint32_t *result)
{
return bsearch_hash(oid->hash, m->chunk_oid_fanout, m->chunk_oid_lookup,
the_hash_algo->rawsz, result);
}
struct object_id *nth_midxed_object_oid(struct object_id *oid,
struct multi_pack_index *m,
uint32_t n)
{
if (n >= m->num_objects)
return NULL;
hashcpy(oid->hash, m->chunk_oid_lookup + m->hash_len * n);
return oid;
}
static off_t nth_midxed_offset(struct multi_pack_index *m, uint32_t pos)
{
const unsigned char *offset_data;
uint32_t offset32;
offset_data = m->chunk_object_offsets + pos * MIDX_CHUNK_OFFSET_WIDTH;
offset32 = get_be32(offset_data + sizeof(uint32_t));
if (m->chunk_large_offsets && offset32 & MIDX_LARGE_OFFSET_NEEDED) {
if (sizeof(off_t) < sizeof(uint64_t))
die(_("multi-pack-index stores a 64-bit offset, but off_t is too small"));
offset32 ^= MIDX_LARGE_OFFSET_NEEDED;
return get_be64(m->chunk_large_offsets + sizeof(uint64_t) * offset32);
}
return offset32;
}
static uint32_t nth_midxed_pack_int_id(struct multi_pack_index *m, uint32_t pos)
{
return get_be32(m->chunk_object_offsets + pos * MIDX_CHUNK_OFFSET_WIDTH);
}
static int nth_midxed_pack_entry(struct repository *r,
struct multi_pack_index *m,
struct pack_entry *e,
uint32_t pos)
{
uint32_t pack_int_id;
struct packed_git *p;
if (pos >= m->num_objects)
return 0;
pack_int_id = nth_midxed_pack_int_id(m, pos);
if (prepare_midx_pack(r, m, pack_int_id))
midx.c: protect against disappearing packs When a packed object is stored in a multi-pack index, but that pack has racily gone away, the MIDX code simply calls die(), when it could be returning an error to the caller, which would in turn lead to re-scanning the pack directory. A pack can racily disappear, for example, due to a simultaneous 'git repack -ad', You can also reproduce this with two terminals, where one is running: git init while true; do git commit -q --allow-empty -m foo git repack -ad git multi-pack-index write done (in effect, constantly writing new MIDXs), and the other is running: obj=$(git rev-parse HEAD) while true; do echo $obj | git cat-file --batch-check='%(objectsize:disk)' || break done That will sometimes hit the error preparing packfile from multi-pack-index message, which this patch fixes. Right now, that path to discovering a missing pack looks something like 'find_pack_entry()' calling 'fill_midx_entry()' and eventually making its way to call 'nth_midxed_pack_entry()'. 'nth_midxed_pack_entry()' already checks 'is_pack_valid()' and propagates an error if the pack is invalid. So, this works if the pack has gone away between calling 'prepare_midx_pack()' and before calling 'is_pack_valid()', but not if it disappears before then. Catch the case where the pack has already disappeared before 'prepare_midx_pack()' by returning an error in that case, too. Co-authored-by: Jeff King <peff@peff.net> Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-11-25 17:17:33 +00:00
return 0;
p = m->packs[pack_int_id];
/*
* We are about to tell the caller where they can locate the
* requested object. We better make sure the packfile is
* still here and can be accessed before supplying that
* answer, as it may have been deleted since the MIDX was
* loaded!
*/
if (!is_pack_valid(p))
return 0;
if (p->num_bad_objects) {
uint32_t i;
struct object_id oid;
nth_midxed_object_oid(&oid, m, pos);
for (i = 0; i < p->num_bad_objects; i++)
if (hasheq(oid.hash,
p->bad_object_sha1 + the_hash_algo->rawsz * i))
return 0;
}
e->offset = nth_midxed_offset(m, pos);
e->p = p;
return 1;
}
int fill_midx_entry(struct repository * r,
const struct object_id *oid,
struct pack_entry *e,
struct multi_pack_index *m)
{
uint32_t pos;
if (!bsearch_midx(oid, m, &pos))
return 0;
return nth_midxed_pack_entry(r, m, e, pos);
}
/* Match "foo.idx" against either "foo.pack" _or_ "foo.idx". */
static int cmp_idx_or_pack_name(const char *idx_or_pack_name,
const char *idx_name)
{
/* Skip past any initial matching prefix. */
while (*idx_name && *idx_name == *idx_or_pack_name) {
idx_name++;
idx_or_pack_name++;
}
/*
* If we didn't match completely, we may have matched "pack-1234." and
* be left with "idx" and "pack" respectively, which is also OK. We do
* not have to check for "idx" and "idx", because that would have been
* a complete match (and in that case these strcmps will be false, but
* we'll correctly return 0 from the final strcmp() below.
*
* Technically this matches "fooidx" and "foopack", but we'd never have
* such names in the first place.
*/
if (!strcmp(idx_name, "idx") && !strcmp(idx_or_pack_name, "pack"))
return 0;
/*
* This not only checks for a complete match, but also orders based on
* the first non-identical character, which means our ordering will
* match a raw strcmp(). That makes it OK to use this to binary search
* a naively-sorted list.
*/
return strcmp(idx_or_pack_name, idx_name);
}
int midx_contains_pack(struct multi_pack_index *m, const char *idx_or_pack_name)
{
uint32_t first = 0, last = m->num_packs;
while (first < last) {
uint32_t mid = first + (last - first) / 2;
const char *current;
int cmp;
current = m->pack_names[mid];
cmp = cmp_idx_or_pack_name(idx_or_pack_name, current);
if (!cmp)
return 1;
if (cmp > 0) {
first = mid + 1;
continue;
}
last = mid;
}
return 0;
}
int prepare_multi_pack_index_one(struct repository *r, const char *object_dir, int local)
{
struct multi_pack_index *m;
struct multi_pack_index *m_search;
prepare_repo_settings(r);
if (!r->settings.core_multi_pack_index)
return 0;
for (m_search = r->objects->multi_pack_index; m_search; m_search = m_search->next)
if (!strcmp(object_dir, m_search->object_dir))
return 1;
m = load_multi_pack_index(object_dir, local);
if (m) {
midx: traverse the local MIDX first When a repository has an alternate object directory configured, callers can traverse through each alternate's MIDX by walking the '->next' pointer. But, when 'prepare_multi_pack_index_one()' loads multiple MIDXs, it places the new ones at the front of this pointer chain, not at the end. This can be confusing for callers such as 'git repack -ad', causing test failures like in t7700.6 with 'GIT_TEST_MULTI_PACK_INDEX=1'. The occurs when dropping a pack known to the local MIDX with alternates configured that have their own MIDX. Since the alternate's MIDX is returned via 'get_multi_pack_index()', 'midx_contains_pack()' returns true (which is correct, since it traverses through the '->next' pointer to find the MIDX in the chain that does contain the requested object). But, we call 'clear_midx_file()' on 'the_repository', which drops the MIDX at the path of the first MIDX in the chain, which (in the case of t7700.6 is the one in the alternate). This patch addresses that by: - placing the local MIDX first in the chain when calling 'prepare_multi_pack_index_one()', and - introducing a new 'get_local_multi_pack_index()', which explicitly returns the repository-local MIDX, if any. Don't impose an additional order on the MIDX's '->next' pointer beyond that the first item in the chain must be local if one exists so that we avoid a quadratic insertion. Likewise, use 'get_local_multi_pack_index()' in 'remove_redundant_pack()' to fix the formerly broken t7700.6 when run with 'GIT_TEST_MULTI_PACK_INDEX=1'. Finally, note that the MIDX ordering invariant is only preserved by the insertion order in 'prepare_packed_git()', which traverses through the ODB's '->next' pointer, meaning we visit the local object store first. This fragility makes this an undesirable long-term solution if more callers are added, but it is acceptable for now since this is the only caller. Helped-by: Jeff King <peff@peff.net> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-28 20:22:13 +00:00
struct multi_pack_index *mp = r->objects->multi_pack_index;
if (mp) {
m->next = mp->next;
mp->next = m;
} else
r->objects->multi_pack_index = m;
return 1;
}
return 0;
}
static size_t write_midx_header(struct hashfile *f,
unsigned char num_chunks,
uint32_t num_packs)
{
hashwrite_be32(f, MIDX_SIGNATURE);
hashwrite_u8(f, MIDX_VERSION);
hashwrite_u8(f, oid_version());
hashwrite_u8(f, num_chunks);
hashwrite_u8(f, 0); /* unused */
hashwrite_be32(f, num_packs);
return MIDX_HEADER_SIZE;
}
struct pack_info {
uint32_t orig_pack_int_id;
char *pack_name;
struct packed_git *p;
unsigned expired : 1;
};
static int pack_info_compare(const void *_a, const void *_b)
{
struct pack_info *a = (struct pack_info *)_a;
struct pack_info *b = (struct pack_info *)_b;
return strcmp(a->pack_name, b->pack_name);
}
struct pack_list {
struct pack_info *info;
uint32_t nr;
uint32_t alloc;
struct multi_pack_index *m;
struct progress *progress;
unsigned pack_paths_checked;
};
static void add_pack_to_midx(const char *full_path, size_t full_path_len,
const char *file_name, void *data)
{
struct pack_list *packs = (struct pack_list *)data;
if (ends_with(file_name, ".idx")) {
display_progress(packs->progress, ++packs->pack_paths_checked);
if (packs->m && midx_contains_pack(packs->m, file_name))
return;
ALLOC_GROW(packs->info, packs->nr + 1, packs->alloc);
packs->info[packs->nr].p = add_packed_git(full_path,
full_path_len,
0);
if (!packs->info[packs->nr].p) {
warning(_("failed to add packfile '%s'"),
full_path);
return;
}
if (open_pack_index(packs->info[packs->nr].p)) {
warning(_("failed to open pack-index '%s'"),
full_path);
close_pack(packs->info[packs->nr].p);
FREE_AND_NULL(packs->info[packs->nr].p);
return;
}
packs->info[packs->nr].pack_name = xstrdup(file_name);
packs->info[packs->nr].orig_pack_int_id = packs->nr;
packs->info[packs->nr].expired = 0;
packs->nr++;
}
}
struct pack_midx_entry {
struct object_id oid;
uint32_t pack_int_id;
time_t pack_mtime;
uint64_t offset;
};
static int midx_oid_compare(const void *_a, const void *_b)
{
const struct pack_midx_entry *a = (const struct pack_midx_entry *)_a;
const struct pack_midx_entry *b = (const struct pack_midx_entry *)_b;
int cmp = oidcmp(&a->oid, &b->oid);
if (cmp)
return cmp;
if (a->pack_mtime > b->pack_mtime)
return -1;
else if (a->pack_mtime < b->pack_mtime)
return 1;
return a->pack_int_id - b->pack_int_id;
}
static int nth_midxed_pack_midx_entry(struct multi_pack_index *m,
struct pack_midx_entry *e,
uint32_t pos)
{
if (pos >= m->num_objects)
return 1;
nth_midxed_object_oid(&e->oid, m, pos);
e->pack_int_id = nth_midxed_pack_int_id(m, pos);
e->offset = nth_midxed_offset(m, pos);
/* consider objects in midx to be from "old" packs */
e->pack_mtime = 0;
return 0;
}
static void fill_pack_entry(uint32_t pack_int_id,
struct packed_git *p,
uint32_t cur_object,
struct pack_midx_entry *entry)
{
if (nth_packed_object_id(&entry->oid, p, cur_object) < 0)
die(_("failed to locate object %d in packfile"), cur_object);
entry->pack_int_id = pack_int_id;
entry->pack_mtime = p->mtime;
entry->offset = nth_packed_object_offset(p, cur_object);
}
/*
* It is possible to artificially get into a state where there are many
* duplicate copies of objects. That can create high memory pressure if
* we are to create a list of all objects before de-duplication. To reduce
* this memory pressure without a significant performance drop, automatically
* group objects by the first byte of their object id. Use the IDX fanout
* tables to group the data, copy to a local array, then sort.
*
* Copy only the de-duplicated entries (selected by most-recent modified time
* of a packfile containing the object).
*/
static struct pack_midx_entry *get_sorted_entries(struct multi_pack_index *m,
struct pack_info *info,
uint32_t nr_packs,
uint32_t *nr_objects)
{
uint32_t cur_fanout, cur_pack, cur_object;
uint32_t alloc_fanout, alloc_objects, total_objects = 0;
struct pack_midx_entry *entries_by_fanout = NULL;
struct pack_midx_entry *deduplicated_entries = NULL;
uint32_t start_pack = m ? m->num_packs : 0;
for (cur_pack = start_pack; cur_pack < nr_packs; cur_pack++)
total_objects += info[cur_pack].p->num_objects;
/*
* As we de-duplicate by fanout value, we expect the fanout
* slices to be evenly distributed, with some noise. Hence,
* allocate slightly more than one 256th.
*/
alloc_objects = alloc_fanout = total_objects > 3200 ? total_objects / 200 : 16;
ALLOC_ARRAY(entries_by_fanout, alloc_fanout);
ALLOC_ARRAY(deduplicated_entries, alloc_objects);
*nr_objects = 0;
for (cur_fanout = 0; cur_fanout < 256; cur_fanout++) {
uint32_t nr_fanout = 0;
if (m) {
uint32_t start = 0, end;
if (cur_fanout)
start = ntohl(m->chunk_oid_fanout[cur_fanout - 1]);
end = ntohl(m->chunk_oid_fanout[cur_fanout]);
for (cur_object = start; cur_object < end; cur_object++) {
ALLOC_GROW(entries_by_fanout, nr_fanout + 1, alloc_fanout);
nth_midxed_pack_midx_entry(m,
&entries_by_fanout[nr_fanout],
cur_object);
nr_fanout++;
}
}
for (cur_pack = start_pack; cur_pack < nr_packs; cur_pack++) {
uint32_t start = 0, end;
if (cur_fanout)
start = get_pack_fanout(info[cur_pack].p, cur_fanout - 1);
end = get_pack_fanout(info[cur_pack].p, cur_fanout);
for (cur_object = start; cur_object < end; cur_object++) {
ALLOC_GROW(entries_by_fanout, nr_fanout + 1, alloc_fanout);
fill_pack_entry(cur_pack, info[cur_pack].p, cur_object, &entries_by_fanout[nr_fanout]);
nr_fanout++;
}
}
QSORT(entries_by_fanout, nr_fanout, midx_oid_compare);
/*
* The batch is now sorted by OID and then mtime (descending).
* Take only the first duplicate.
*/
for (cur_object = 0; cur_object < nr_fanout; cur_object++) {
if (cur_object && oideq(&entries_by_fanout[cur_object - 1].oid,
&entries_by_fanout[cur_object].oid))
continue;
ALLOC_GROW(deduplicated_entries, *nr_objects + 1, alloc_objects);
memcpy(&deduplicated_entries[*nr_objects],
&entries_by_fanout[cur_object],
sizeof(struct pack_midx_entry));
(*nr_objects)++;
}
}
free(entries_by_fanout);
return deduplicated_entries;
}
static size_t write_midx_pack_names(struct hashfile *f,
struct pack_info *info,
uint32_t num_packs)
{
uint32_t i;
unsigned char padding[MIDX_CHUNK_ALIGNMENT];
size_t written = 0;
for (i = 0; i < num_packs; i++) {
size_t writelen;
if (info[i].expired)
continue;
if (i && strcmp(info[i].pack_name, info[i - 1].pack_name) <= 0)
BUG("incorrect pack-file order: %s before %s",
info[i - 1].pack_name,
info[i].pack_name);
writelen = strlen(info[i].pack_name) + 1;
hashwrite(f, info[i].pack_name, writelen);
written += writelen;
}
/* add padding to be aligned */
i = MIDX_CHUNK_ALIGNMENT - (written % MIDX_CHUNK_ALIGNMENT);
if (i < MIDX_CHUNK_ALIGNMENT) {
memset(padding, 0, sizeof(padding));
hashwrite(f, padding, i);
written += i;
}
return written;
}
static size_t write_midx_oid_fanout(struct hashfile *f,
struct pack_midx_entry *objects,
uint32_t nr_objects)
{
struct pack_midx_entry *list = objects;
struct pack_midx_entry *last = objects + nr_objects;
uint32_t count = 0;
uint32_t i;
/*
* 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++) {
struct pack_midx_entry *next = list;
while (next < last && next->oid.hash[0] == i) {
count++;
next++;
}
hashwrite_be32(f, count);
list = next;
}
return MIDX_CHUNK_FANOUT_SIZE;
}
static size_t write_midx_oid_lookup(struct hashfile *f, unsigned char hash_len,
struct pack_midx_entry *objects,
uint32_t nr_objects)
{
struct pack_midx_entry *list = objects;
uint32_t i;
size_t written = 0;
for (i = 0; i < nr_objects; i++) {
struct pack_midx_entry *obj = list++;
if (i < nr_objects - 1) {
struct pack_midx_entry *next = list;
if (oidcmp(&obj->oid, &next->oid) >= 0)
BUG("OIDs not in order: %s >= %s",
oid_to_hex(&obj->oid),
oid_to_hex(&next->oid));
}
hashwrite(f, obj->oid.hash, (int)hash_len);
written += hash_len;
}
return written;
}
static size_t write_midx_object_offsets(struct hashfile *f, int large_offset_needed,
uint32_t *perm,
struct pack_midx_entry *objects, uint32_t nr_objects)
{
struct pack_midx_entry *list = objects;
uint32_t i, nr_large_offset = 0;
size_t written = 0;
for (i = 0; i < nr_objects; i++) {
struct pack_midx_entry *obj = list++;
if (perm[obj->pack_int_id] == PACK_EXPIRED)
BUG("object %s is in an expired pack with int-id %d",
oid_to_hex(&obj->oid),
obj->pack_int_id);
hashwrite_be32(f, perm[obj->pack_int_id]);
if (large_offset_needed && obj->offset >> 31)
hashwrite_be32(f, MIDX_LARGE_OFFSET_NEEDED | nr_large_offset++);
else if (!large_offset_needed && obj->offset >> 32)
BUG("object %s requires a large offset (%"PRIx64") but the MIDX is not writing large offsets!",
oid_to_hex(&obj->oid),
obj->offset);
else
hashwrite_be32(f, (uint32_t)obj->offset);
written += MIDX_CHUNK_OFFSET_WIDTH;
}
return written;
}
static size_t write_midx_large_offsets(struct hashfile *f, uint32_t nr_large_offset,
struct pack_midx_entry *objects, uint32_t nr_objects)
{
struct pack_midx_entry *list = objects, *end = objects + nr_objects;
size_t written = 0;
while (nr_large_offset) {
struct pack_midx_entry *obj;
uint64_t offset;
if (list >= end)
BUG("too many large-offset objects");
obj = list++;
offset = obj->offset;
if (!(offset >> 31))
continue;
written += hashwrite_be64(f, offset);
nr_large_offset--;
}
return written;
}
static int write_midx_internal(const char *object_dir, struct multi_pack_index *m,
struct string_list *packs_to_drop, unsigned flags)
{
unsigned char cur_chunk, num_chunks = 0;
char *midx_name;
uint32_t i;
struct hashfile *f = NULL;
struct lock_file lk;
struct pack_list packs;
uint32_t *pack_perm = NULL;
uint64_t written = 0;
uint32_t chunk_ids[MIDX_MAX_CHUNKS + 1];
uint64_t chunk_offsets[MIDX_MAX_CHUNKS + 1];
uint32_t nr_entries, num_large_offsets = 0;
struct pack_midx_entry *entries = NULL;
struct progress *progress = NULL;
int large_offsets_needed = 0;
int pack_name_concat_len = 0;
int dropped_packs = 0;
int result = 0;
midx_name = get_midx_filename(object_dir);
if (safe_create_leading_directories(midx_name))
die_errno(_("unable to create leading directories of %s"),
midx_name);
if (m)
packs.m = m;
else
packs.m = load_multi_pack_index(object_dir, 1);
packs.nr = 0;
packs.alloc = packs.m ? packs.m->num_packs : 16;
packs.info = NULL;
ALLOC_ARRAY(packs.info, packs.alloc);
if (packs.m) {
for (i = 0; i < packs.m->num_packs; i++) {
ALLOC_GROW(packs.info, packs.nr + 1, packs.alloc);
packs.info[packs.nr].orig_pack_int_id = i;
packs.info[packs.nr].pack_name = xstrdup(packs.m->pack_names[i]);
packs.info[packs.nr].p = NULL;
packs.info[packs.nr].expired = 0;
packs.nr++;
}
}
packs.pack_paths_checked = 0;
if (flags & MIDX_PROGRESS)
packs.progress = start_delayed_progress(_("Adding packfiles to multi-pack-index"), 0);
else
packs.progress = NULL;
for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &packs);
stop_progress(&packs.progress);
if (packs.m && packs.nr == packs.m->num_packs && !packs_to_drop)
goto cleanup;
entries = get_sorted_entries(packs.m, packs.info, packs.nr, &nr_entries);
for (i = 0; i < nr_entries; i++) {
if (entries[i].offset > 0x7fffffff)
num_large_offsets++;
if (entries[i].offset > 0xffffffff)
large_offsets_needed = 1;
}
QSORT(packs.info, packs.nr, pack_info_compare);
if (packs_to_drop && packs_to_drop->nr) {
int drop_index = 0;
int missing_drops = 0;
for (i = 0; i < packs.nr && drop_index < packs_to_drop->nr; i++) {
int cmp = strcmp(packs.info[i].pack_name,
packs_to_drop->items[drop_index].string);
if (!cmp) {
drop_index++;
packs.info[i].expired = 1;
} else if (cmp > 0) {
error(_("did not see pack-file %s to drop"),
packs_to_drop->items[drop_index].string);
drop_index++;
missing_drops++;
i--;
} else {
packs.info[i].expired = 0;
}
}
if (missing_drops) {
result = 1;
goto cleanup;
}
}
/*
* pack_perm stores a permutation between pack-int-ids from the
* previous multi-pack-index to the new one we are writing:
*
* pack_perm[old_id] = new_id
*/
ALLOC_ARRAY(pack_perm, packs.nr);
for (i = 0; i < packs.nr; i++) {
if (packs.info[i].expired) {
dropped_packs++;
pack_perm[packs.info[i].orig_pack_int_id] = PACK_EXPIRED;
} else {
pack_perm[packs.info[i].orig_pack_int_id] = i - dropped_packs;
}
}
for (i = 0; i < packs.nr; i++) {
if (!packs.info[i].expired)
pack_name_concat_len += strlen(packs.info[i].pack_name) + 1;
}
if (pack_name_concat_len % MIDX_CHUNK_ALIGNMENT)
pack_name_concat_len += MIDX_CHUNK_ALIGNMENT -
(pack_name_concat_len % MIDX_CHUNK_ALIGNMENT);
hold_lock_file_for_update(&lk, midx_name, LOCK_DIE_ON_ERROR);
f = hashfd(get_lock_file_fd(&lk), get_lock_file_path(&lk));
FREE_AND_NULL(midx_name);
if (packs.m)
close_midx(packs.m);
cur_chunk = 0;
num_chunks = large_offsets_needed ? 5 : 4;
if (packs.nr - dropped_packs == 0) {
error(_("no pack files to index."));
result = 1;
goto cleanup;
}
written = write_midx_header(f, num_chunks, packs.nr - dropped_packs);
chunk_ids[cur_chunk] = MIDX_CHUNKID_PACKNAMES;
chunk_offsets[cur_chunk] = written + (num_chunks + 1) * MIDX_CHUNKLOOKUP_WIDTH;
cur_chunk++;
chunk_ids[cur_chunk] = MIDX_CHUNKID_OIDFANOUT;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + pack_name_concat_len;
cur_chunk++;
chunk_ids[cur_chunk] = MIDX_CHUNKID_OIDLOOKUP;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + MIDX_CHUNK_FANOUT_SIZE;
cur_chunk++;
chunk_ids[cur_chunk] = MIDX_CHUNKID_OBJECTOFFSETS;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + nr_entries * the_hash_algo->rawsz;
cur_chunk++;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + nr_entries * MIDX_CHUNK_OFFSET_WIDTH;
if (large_offsets_needed) {
chunk_ids[cur_chunk] = MIDX_CHUNKID_LARGEOFFSETS;
cur_chunk++;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] +
num_large_offsets * MIDX_CHUNK_LARGE_OFFSET_WIDTH;
}
chunk_ids[cur_chunk] = 0;
for (i = 0; i <= num_chunks; i++) {
if (i && chunk_offsets[i] < chunk_offsets[i - 1])
BUG("incorrect chunk offsets: %"PRIu64" before %"PRIu64,
chunk_offsets[i - 1],
chunk_offsets[i]);
if (chunk_offsets[i] % MIDX_CHUNK_ALIGNMENT)
BUG("chunk offset %"PRIu64" is not properly aligned",
chunk_offsets[i]);
hashwrite_be32(f, chunk_ids[i]);
hashwrite_be64(f, chunk_offsets[i]);
written += MIDX_CHUNKLOOKUP_WIDTH;
}
if (flags & MIDX_PROGRESS)
progress = start_delayed_progress(_("Writing chunks to multi-pack-index"),
num_chunks);
for (i = 0; i < num_chunks; i++) {
if (written != chunk_offsets[i])
BUG("incorrect chunk offset (%"PRIu64" != %"PRIu64") for chunk id %"PRIx32,
chunk_offsets[i],
written,
chunk_ids[i]);
switch (chunk_ids[i]) {
case MIDX_CHUNKID_PACKNAMES:
written += write_midx_pack_names(f, packs.info, packs.nr);
break;
case MIDX_CHUNKID_OIDFANOUT:
written += write_midx_oid_fanout(f, entries, nr_entries);
break;
case MIDX_CHUNKID_OIDLOOKUP:
written += write_midx_oid_lookup(f, the_hash_algo->rawsz, entries, nr_entries);
break;
case MIDX_CHUNKID_OBJECTOFFSETS:
written += write_midx_object_offsets(f, large_offsets_needed, pack_perm, entries, nr_entries);
break;
case MIDX_CHUNKID_LARGEOFFSETS:
written += write_midx_large_offsets(f, num_large_offsets, entries, nr_entries);
break;
default:
BUG("trying to write unknown chunk id %"PRIx32,
chunk_ids[i]);
}
display_progress(progress, i + 1);
}
stop_progress(&progress);
if (written != chunk_offsets[num_chunks])
BUG("incorrect final offset %"PRIu64" != %"PRIu64,
written,
chunk_offsets[num_chunks]);
finalize_hashfile(f, NULL, CSUM_FSYNC | CSUM_HASH_IN_STREAM);
commit_lock_file(&lk);
cleanup:
for (i = 0; i < packs.nr; i++) {
if (packs.info[i].p) {
close_pack(packs.info[i].p);
free(packs.info[i].p);
}
free(packs.info[i].pack_name);
}
free(packs.info);
free(entries);
free(pack_perm);
free(midx_name);
return result;
}
int write_midx_file(const char *object_dir, unsigned flags)
{
return write_midx_internal(object_dir, NULL, NULL, flags);
}
void clear_midx_file(struct repository *r)
{
char *midx = get_midx_filename(r->objects->odb->path);
if (r->objects && r->objects->multi_pack_index) {
close_midx(r->objects->multi_pack_index);
r->objects->multi_pack_index = NULL;
}
if (remove_path(midx))
die(_("failed to clear multi-pack-index at %s"), midx);
free(midx);
}
static int verify_midx_error;
static void midx_report(const char *fmt, ...)
{
va_list ap;
verify_midx_error = 1;
va_start(ap, fmt);
vfprintf(stderr, fmt, ap);
fprintf(stderr, "\n");
va_end(ap);
}
struct pair_pos_vs_id
{
uint32_t pos;
uint32_t pack_int_id;
};
static int compare_pair_pos_vs_id(const void *_a, const void *_b)
{
struct pair_pos_vs_id *a = (struct pair_pos_vs_id *)_a;
struct pair_pos_vs_id *b = (struct pair_pos_vs_id *)_b;
return b->pack_int_id - a->pack_int_id;
}
/*
* Limit calls to display_progress() for performance reasons.
* The interval here was arbitrarily chosen.
*/
#define SPARSE_PROGRESS_INTERVAL (1 << 12)
#define midx_display_sparse_progress(progress, n) \
do { \
uint64_t _n = (n); \
if ((_n & (SPARSE_PROGRESS_INTERVAL - 1)) == 0) \
display_progress(progress, _n); \
} while (0)
int verify_midx_file(struct repository *r, const char *object_dir, unsigned flags)
{
struct pair_pos_vs_id *pairs = NULL;
uint32_t i;
struct progress *progress = NULL;
struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
verify_midx_error = 0;
multi-pack-index: use hash version byte Similar to the commit-graph format, the multi-pack-index format has a byte in the header intended to track the hash version used to write the file. This allows one to interpret the hash length without having the context of the repository config specifying the hash length. This was not modified as part of the SHA-256 work because the hash length was automatically up-shifted due to that config. Since we have this byte available, we can make the file formats more obviously incompatible instead of relying on other context from the repository. Add a new oid_version() method in midx.c similar to the one in commit-graph.c. This is specifically made separate from that implementation to avoid artificially linking the formats. The test impact requires a few more things than the corresponding change in the commit-graph format. Specifically, 'test-tool read-midx' was not writing anything about this header value to output. Since the value available in 'struct multi_pack_index' is hash_len instead of a version value, we output "20" or "32" instead of "1" or "2". Since we want a user to not have their Git commands fail if their multi-pack-index has the incorrect hash version compared to the repository's hash version, we relax the die() to an error() in load_multi_pack_index(). This has some effect on 'git multi-pack-index verify' as we need to check that a failed parse of a file that exists is actually a verify error. For that test that checks the hash version matches, we change the corrupted byte from "2" to "3" to ensure the test fails for both hash algorithms. Helped-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-17 14:04:48 +00:00
if (!m) {
int result = 0;
struct stat sb;
char *filename = get_midx_filename(object_dir);
if (!stat(filename, &sb)) {
error(_("multi-pack-index file exists, but failed to parse"));
result = 1;
}
free(filename);
return result;
}
if (flags & MIDX_PROGRESS)
progress = start_delayed_progress(_("Looking for referenced packfiles"),
m->num_packs);
for (i = 0; i < m->num_packs; i++) {
if (prepare_midx_pack(r, m, i))
midx_report("failed to load pack in position %d", i);
display_progress(progress, i + 1);
}
stop_progress(&progress);
for (i = 0; i < 255; i++) {
uint32_t oid_fanout1 = ntohl(m->chunk_oid_fanout[i]);
uint32_t oid_fanout2 = ntohl(m->chunk_oid_fanout[i + 1]);
if (oid_fanout1 > oid_fanout2)
midx_report(_("oid fanout out of order: fanout[%d] = %"PRIx32" > %"PRIx32" = fanout[%d]"),
i, oid_fanout1, oid_fanout2, i + 1);
}
if (m->num_objects == 0) {
midx_report(_("the midx contains no oid"));
/*
* Remaining tests assume that we have objects, so we can
* return here.
*/
return verify_midx_error;
}
if (flags & MIDX_PROGRESS)
progress = start_sparse_progress(_("Verifying OID order in multi-pack-index"),
m->num_objects - 1);
for (i = 0; i < m->num_objects - 1; i++) {
struct object_id oid1, oid2;
nth_midxed_object_oid(&oid1, m, i);
nth_midxed_object_oid(&oid2, m, i + 1);
if (oidcmp(&oid1, &oid2) >= 0)
midx_report(_("oid lookup out of order: oid[%d] = %s >= %s = oid[%d]"),
i, oid_to_hex(&oid1), oid_to_hex(&oid2), i + 1);
midx_display_sparse_progress(progress, i + 1);
}
stop_progress(&progress);
/*
* Create an array mapping each object to its packfile id. Sort it
* to group the objects by packfile. Use this permutation to visit
* each of the objects and only require 1 packfile to be open at a
* time.
*/
ALLOC_ARRAY(pairs, m->num_objects);
for (i = 0; i < m->num_objects; i++) {
pairs[i].pos = i;
pairs[i].pack_int_id = nth_midxed_pack_int_id(m, i);
}
if (flags & MIDX_PROGRESS)
progress = start_sparse_progress(_("Sorting objects by packfile"),
m->num_objects);
display_progress(progress, 0); /* TODO: Measure QSORT() progress */
QSORT(pairs, m->num_objects, compare_pair_pos_vs_id);
stop_progress(&progress);
if (flags & MIDX_PROGRESS)
progress = start_sparse_progress(_("Verifying object offsets"), m->num_objects);
for (i = 0; i < m->num_objects; i++) {
struct object_id oid;
struct pack_entry e;
off_t m_offset, p_offset;
if (i > 0 && pairs[i-1].pack_int_id != pairs[i].pack_int_id &&
m->packs[pairs[i-1].pack_int_id])
{
close_pack_fd(m->packs[pairs[i-1].pack_int_id]);
close_pack_index(m->packs[pairs[i-1].pack_int_id]);
}
nth_midxed_object_oid(&oid, m, pairs[i].pos);
if (!fill_midx_entry(r, &oid, &e, m)) {
midx_report(_("failed to load pack entry for oid[%d] = %s"),
pairs[i].pos, oid_to_hex(&oid));
continue;
}
if (open_pack_index(e.p)) {
midx_report(_("failed to load pack-index for packfile %s"),
e.p->pack_name);
break;
}
m_offset = e.offset;
p_offset = find_pack_entry_one(oid.hash, e.p);
if (m_offset != p_offset)
midx_report(_("incorrect object offset for oid[%d] = %s: %"PRIx64" != %"PRIx64),
pairs[i].pos, oid_to_hex(&oid), m_offset, p_offset);
midx_display_sparse_progress(progress, i + 1);
}
stop_progress(&progress);
free(pairs);
return verify_midx_error;
}
int expire_midx_packs(struct repository *r, const char *object_dir, unsigned flags)
{
uint32_t i, *count, result = 0;
struct string_list packs_to_drop = STRING_LIST_INIT_DUP;
struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
struct progress *progress = NULL;
if (!m)
return 0;
count = xcalloc(m->num_packs, sizeof(uint32_t));
if (flags & MIDX_PROGRESS)
progress = start_delayed_progress(_("Counting referenced objects"),
m->num_objects);
for (i = 0; i < m->num_objects; i++) {
int pack_int_id = nth_midxed_pack_int_id(m, i);
count[pack_int_id]++;
display_progress(progress, i + 1);
}
stop_progress(&progress);
if (flags & MIDX_PROGRESS)
progress = start_delayed_progress(_("Finding and deleting unreferenced packfiles"),
m->num_packs);
for (i = 0; i < m->num_packs; i++) {
char *pack_name;
display_progress(progress, i + 1);
if (count[i])
continue;
if (prepare_midx_pack(r, m, i))
continue;
if (m->packs[i]->pack_keep)
continue;
pack_name = xstrdup(m->packs[i]->pack_name);
close_pack(m->packs[i]);
string_list_insert(&packs_to_drop, m->pack_names[i]);
unlink_pack_path(pack_name, 0);
free(pack_name);
}
stop_progress(&progress);
free(count);
if (packs_to_drop.nr)
result = write_midx_internal(object_dir, m, &packs_to_drop, flags);
string_list_clear(&packs_to_drop, 0);
return result;
}
multi-pack-index: prepare 'repack' subcommand In an environment where the multi-pack-index is useful, it is due to many pack-files and an inability to repack the object store into a single pack-file. However, it is likely that many of these pack-files are rather small, and could be repacked into a slightly larger pack-file without too much effort. It may also be important to ensure the object store is highly available and the repack operation does not interrupt concurrent git commands. Introduce a 'repack' subcommand to 'git multi-pack-index' that takes a '--batch-size' option. The subcommand will inspect the multi-pack-index for referenced pack-files whose size is smaller than the batch size, until collecting a list of pack-files whose sizes sum to larger than the batch size. Then, a new pack-file will be created containing the objects from those pack-files that are referenced by the multi-pack-index. The resulting pack is likely to actually be smaller than the batch size due to compression and the fact that there may be objects in the pack- files that have duplicate copies in other pack-files. The current change introduces the command-line arguments, and we add a test that ensures we parse these options properly. Since we specify a small batch size, we will guarantee that future implementations do not change the list of pack-files. In addition, we hard-code the modified times of the packs in the pack directory to ensure the list of packs sorted by modified time matches the order if sorted by size (ascending). This will be important in a future test. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:26 +00:00
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
struct repack_info {
timestamp_t mtime;
uint32_t referenced_objects;
uint32_t pack_int_id;
};
static int compare_by_mtime(const void *a_, const void *b_)
multi-pack-index: prepare 'repack' subcommand In an environment where the multi-pack-index is useful, it is due to many pack-files and an inability to repack the object store into a single pack-file. However, it is likely that many of these pack-files are rather small, and could be repacked into a slightly larger pack-file without too much effort. It may also be important to ensure the object store is highly available and the repack operation does not interrupt concurrent git commands. Introduce a 'repack' subcommand to 'git multi-pack-index' that takes a '--batch-size' option. The subcommand will inspect the multi-pack-index for referenced pack-files whose size is smaller than the batch size, until collecting a list of pack-files whose sizes sum to larger than the batch size. Then, a new pack-file will be created containing the objects from those pack-files that are referenced by the multi-pack-index. The resulting pack is likely to actually be smaller than the batch size due to compression and the fact that there may be objects in the pack- files that have duplicate copies in other pack-files. The current change introduces the command-line arguments, and we add a test that ensures we parse these options properly. Since we specify a small batch size, we will guarantee that future implementations do not change the list of pack-files. In addition, we hard-code the modified times of the packs in the pack directory to ensure the list of packs sorted by modified time matches the order if sorted by size (ascending). This will be important in a future test. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:26 +00:00
{
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
const struct repack_info *a, *b;
a = (const struct repack_info *)a_;
b = (const struct repack_info *)b_;
if (a->mtime < b->mtime)
return -1;
if (a->mtime > b->mtime)
return 1;
return 0;
}
static int fill_included_packs_all(struct repository *r,
struct multi_pack_index *m,
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
unsigned char *include_pack)
{
uint32_t i, count = 0;
int pack_kept_objects = 0;
repo_config_get_bool(r, "repack.packkeptobjects", &pack_kept_objects);
for (i = 0; i < m->num_packs; i++) {
if (prepare_midx_pack(r, m, i))
continue;
if (!pack_kept_objects && m->packs[i]->pack_keep)
continue;
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
include_pack[i] = 1;
count++;
}
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
return count < 2;
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
}
static int fill_included_packs_batch(struct repository *r,
struct multi_pack_index *m,
unsigned char *include_pack,
size_t batch_size)
{
uint32_t i, packs_to_repack;
size_t total_size;
struct repack_info *pack_info = xcalloc(m->num_packs, sizeof(struct repack_info));
int pack_kept_objects = 0;
repo_config_get_bool(r, "repack.packkeptobjects", &pack_kept_objects);
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
for (i = 0; i < m->num_packs; i++) {
pack_info[i].pack_int_id = i;
if (prepare_midx_pack(r, m, i))
continue;
pack_info[i].mtime = m->packs[i]->mtime;
}
for (i = 0; batch_size && i < m->num_objects; i++) {
uint32_t pack_int_id = nth_midxed_pack_int_id(m, i);
pack_info[pack_int_id].referenced_objects++;
}
QSORT(pack_info, m->num_packs, compare_by_mtime);
total_size = 0;
packs_to_repack = 0;
for (i = 0; total_size < batch_size && i < m->num_packs; i++) {
int pack_int_id = pack_info[i].pack_int_id;
struct packed_git *p = m->packs[pack_int_id];
size_t expected_size;
if (!p)
continue;
if (!pack_kept_objects && p->pack_keep)
continue;
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
if (open_pack_index(p) || !p->num_objects)
continue;
expected_size = (size_t)(p->pack_size
* pack_info[i].referenced_objects);
expected_size /= p->num_objects;
if (expected_size >= batch_size)
continue;
packs_to_repack++;
total_size += expected_size;
include_pack[pack_int_id] = 1;
}
free(pack_info);
multi-pack-index: repack batches below --batch-size The --batch-size=<size> option of 'git multi-pack-index repack' is intended to limit the amount of work done by the repack. In the case of a large repository, this command should repack a number of small pack-files but leave the large pack-files alone. Most often, the repository has one large pack-file from a 'git clone' operation and number of smaller pack-files from incremental 'git fetch' operations. The issue with '--batch-size' is that it also _prevents_ the repack from happening if the expected size of the resulting pack-file is too small. This was intended as a way to avoid frequent churn of small pack-files, but it has mostly caused confusion when a repository is of "medium" size. That is, not enormous like the Windows OS repository, but also not so small that this incremental repack isn't valuable. The solution presented here is to collect pack-files for repack if their expected size is smaller than the batch-size parameter until either the total expected size exceeds the batch-size or all pack-files are considered. If there are at least two pack-files, then these are combined to a new pack-file whose size should not be too much larger than the batch-size. This new strategy should succeed in keeping the number of pack-files small in these "medium" size repositories. The concern about churn is likely not interesting, as the real control over that is the frequency in which the repack command is run. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-11 15:30:18 +00:00
if (packs_to_repack < 2)
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
return 1;
multi-pack-index: prepare 'repack' subcommand In an environment where the multi-pack-index is useful, it is due to many pack-files and an inability to repack the object store into a single pack-file. However, it is likely that many of these pack-files are rather small, and could be repacked into a slightly larger pack-file without too much effort. It may also be important to ensure the object store is highly available and the repack operation does not interrupt concurrent git commands. Introduce a 'repack' subcommand to 'git multi-pack-index' that takes a '--batch-size' option. The subcommand will inspect the multi-pack-index for referenced pack-files whose size is smaller than the batch size, until collecting a list of pack-files whose sizes sum to larger than the batch size. Then, a new pack-file will be created containing the objects from those pack-files that are referenced by the multi-pack-index. The resulting pack is likely to actually be smaller than the batch size due to compression and the fact that there may be objects in the pack- files that have duplicate copies in other pack-files. The current change introduces the command-line arguments, and we add a test that ensures we parse these options properly. Since we specify a small batch size, we will guarantee that future implementations do not change the list of pack-files. In addition, we hard-code the modified times of the packs in the pack directory to ensure the list of packs sorted by modified time matches the order if sorted by size (ascending). This will be important in a future test. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:26 +00:00
return 0;
}
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
int midx_repack(struct repository *r, const char *object_dir, size_t batch_size, unsigned flags)
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
{
int result = 0;
uint32_t i;
unsigned char *include_pack;
struct child_process cmd = CHILD_PROCESS_INIT;
FILE *cmd_in;
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
struct strbuf base_name = STRBUF_INIT;
struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
/*
* When updating the default for these configuration
* variables in builtin/repack.c, these must be adjusted
* to match.
*/
int delta_base_offset = 1;
int use_delta_islands = 0;
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
if (!m)
return 0;
include_pack = xcalloc(m->num_packs, sizeof(unsigned char));
if (batch_size) {
if (fill_included_packs_batch(r, m, include_pack, batch_size))
goto cleanup;
} else if (fill_included_packs_all(r, m, include_pack))
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
goto cleanup;
repo_config_get_bool(r, "repack.usedeltabaseoffset", &delta_base_offset);
repo_config_get_bool(r, "repack.usedeltaislands", &use_delta_islands);
strvec_push(&cmd.args, "pack-objects");
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
strbuf_addstr(&base_name, object_dir);
strbuf_addstr(&base_name, "/pack/pack");
strvec_push(&cmd.args, base_name.buf);
if (delta_base_offset)
strvec_push(&cmd.args, "--delta-base-offset");
if (use_delta_islands)
strvec_push(&cmd.args, "--delta-islands");
if (flags & MIDX_PROGRESS)
strvec_push(&cmd.args, "--progress");
else
strvec_push(&cmd.args, "-q");
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
strbuf_release(&base_name);
cmd.git_cmd = 1;
cmd.in = cmd.out = -1;
if (start_command(&cmd)) {
error(_("could not start pack-objects"));
result = 1;
goto cleanup;
}
cmd_in = xfdopen(cmd.in, "w");
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
for (i = 0; i < m->num_objects; i++) {
struct object_id oid;
uint32_t pack_int_id = nth_midxed_pack_int_id(m, i);
if (!include_pack[pack_int_id])
continue;
nth_midxed_object_oid(&oid, m, i);
fprintf(cmd_in, "%s\n", oid_to_hex(&oid));
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
}
fclose(cmd_in);
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
if (finish_command(&cmd)) {
error(_("could not finish pack-objects"));
result = 1;
goto cleanup;
}
result = write_midx_internal(object_dir, m, NULL, flags);
midx: implement midx_repack() To repack with a non-zero batch-size, first sort all pack-files by their modified time. Second, walk those pack-files from oldest to newest, compute their expected size, and add the packs to a list if they are smaller than the given batch-size. Stop when the total expected size is at least the batch size. If the batch size is zero, select all packs in the multi-pack-index. Finally, collect the objects from the multi-pack-index that are in the selected packs and send them to 'git pack-objects'. Write a new multi-pack-index that includes the new pack. Using a batch size of zero is very similar to a standard 'git repack' command, except that we do not delete the old packs and instead rely on the new multi-pack-index to prevent new processes from reading the old packs. This does not disrupt other Git processes that are currently reading the old packs based on the old multi-pack-index. While first designing a 'git multi-pack-index repack' operation, I started by collecting the batches based on the actual size of the objects instead of the size of the pack-files. This allows repacking a large pack-file that has very few referencd objects. However, this came at a significant cost of parsing pack-files instead of simply reading the multi-pack-index and getting the file information for the pack-files. The "expected size" version provides similar behavior, but could skip a pack-file if the average object size is much larger than the actual size of the referenced objects, or can create a large pack if the actual size of the referenced objects is larger than the expected size. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-10 23:35:27 +00:00
m = NULL;
cleanup:
if (m)
close_midx(m);
free(include_pack);
return result;
}