1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-11-14 13:13:01 +01:00
git/unpack-trees.c

1864 lines
48 KiB
C
Raw Normal View History

#define NO_THE_INDEX_COMPATIBILITY_MACROS
#include "cache.h"
#include "dir.h"
#include "tree.h"
#include "tree-walk.h"
#include "cache-tree.h"
#include "unpack-trees.h"
#include "progress.h"
#include "refs.h"
#include "attr.h"
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
/*
* Error messages expected by scripts out of plumbing commands such as
* read-tree. Non-scripted Porcelain is not required to use these messages
* and in fact are encouraged to reword them to better suit their particular
* situation better. See how "git checkout" and "git merge" replaces
* them using setup_unpack_trees_porcelain(), for example.
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
*/
Fix sparse warnings Fix warnings from 'make check'. - These files don't include 'builtin.h' causing sparse to complain that cmd_* isn't declared: builtin/clone.c:364, builtin/fetch-pack.c:797, builtin/fmt-merge-msg.c:34, builtin/hash-object.c:78, builtin/merge-index.c:69, builtin/merge-recursive.c:22 builtin/merge-tree.c:341, builtin/mktag.c:156, builtin/notes.c:426 builtin/notes.c:822, builtin/pack-redundant.c:596, builtin/pack-refs.c:10, builtin/patch-id.c:60, builtin/patch-id.c:149, builtin/remote.c:1512, builtin/remote-ext.c:240, builtin/remote-fd.c:53, builtin/reset.c:236, builtin/send-pack.c:384, builtin/unpack-file.c:25, builtin/var.c:75 - These files have symbols which should be marked static since they're only file scope: submodule.c:12, diff.c:631, replace_object.c:92, submodule.c:13, submodule.c:14, trace.c:78, transport.c:195, transport-helper.c:79, unpack-trees.c:19, url.c:3, url.c:18, url.c:104, url.c:117, url.c:123, url.c:129, url.c:136, thread-utils.c:21, thread-utils.c:48 - These files redeclare symbols to be different types: builtin/index-pack.c:210, parse-options.c:564, parse-options.c:571, usage.c:49, usage.c:58, usage.c:63, usage.c:72 - These files use a literal integer 0 when they really should use a NULL pointer: daemon.c:663, fast-import.c:2942, imap-send.c:1072, notes-merge.c:362 While we're in the area, clean up some unused #includes in builtin files (mostly exec_cmd.h). Signed-off-by: Stephen Boyd <bebarino@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-03-22 08:51:05 +01:00
static const char *unpack_plumbing_errors[NB_UNPACK_TREES_ERROR_TYPES] = {
/* ERROR_WOULD_OVERWRITE */
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
"Entry '%s' would be overwritten by merge. Cannot merge.",
/* ERROR_NOT_UPTODATE_FILE */
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
"Entry '%s' not uptodate. Cannot merge.",
/* ERROR_NOT_UPTODATE_DIR */
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
"Updating '%s' would lose untracked files in it",
/* ERROR_WOULD_LOSE_UNTRACKED_OVERWRITTEN */
"Untracked working tree file '%s' would be overwritten by merge.",
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
/* ERROR_WOULD_LOSE_UNTRACKED_REMOVED */
"Untracked working tree file '%s' would be removed by merge.",
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
/* ERROR_BIND_OVERLAP */
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
"Entry '%s' overlaps with '%s'. Cannot bind.",
/* ERROR_SPARSE_NOT_UPTODATE_FILE */
"Entry '%s' not uptodate. Cannot update sparse checkout.",
/* ERROR_WOULD_LOSE_ORPHANED_OVERWRITTEN */
"Working tree file '%s' would be overwritten by sparse checkout update.",
/* ERROR_WOULD_LOSE_ORPHANED_REMOVED */
"Working tree file '%s' would be removed by sparse checkout update.",
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
};
#define ERRORMSG(o,type) \
( ((o) && (o)->msgs[(type)]) \
? ((o)->msgs[(type)]) \
: (unpack_plumbing_errors[(type)]) )
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
void setup_unpack_trees_porcelain(struct unpack_trees_options *opts,
const char *cmd)
{
int i;
const char **msgs = opts->msgs;
const char *msg;
char *tmp;
const char *cmd2 = strcmp(cmd, "checkout") ? cmd : "switch branches";
if (advice_commit_before_merge)
msg = "Your local changes to the following files would be overwritten by %s:\n%%s"
"Please, commit your changes or stash them before you can %s.";
else
msg = "Your local changes to the following files would be overwritten by %s:\n%%s";
tmp = xmalloc(strlen(msg) + strlen(cmd) + strlen(cmd2) - 2);
sprintf(tmp, msg, cmd, cmd2);
msgs[ERROR_WOULD_OVERWRITE] = tmp;
msgs[ERROR_NOT_UPTODATE_FILE] = tmp;
msgs[ERROR_NOT_UPTODATE_DIR] =
"Updating the following directories would lose untracked files in it:\n%s";
if (advice_commit_before_merge)
msg = "The following untracked working tree files would be %s by %s:\n%%s"
"Please move or remove them before you can %s.";
else
msg = "The following untracked working tree files would be %s by %s:\n%%s";
tmp = xmalloc(strlen(msg) + strlen(cmd) + strlen("removed") + strlen(cmd2) - 4);
sprintf(tmp, msg, "removed", cmd, cmd2);
msgs[ERROR_WOULD_LOSE_UNTRACKED_REMOVED] = tmp;
tmp = xmalloc(strlen(msg) + strlen(cmd) + strlen("overwritten") + strlen(cmd2) - 4);
sprintf(tmp, msg, "overwritten", cmd, cmd2);
msgs[ERROR_WOULD_LOSE_UNTRACKED_OVERWRITTEN] = tmp;
/*
* Special case: ERROR_BIND_OVERLAP refers to a pair of paths, we
* cannot easily display it as a list.
*/
msgs[ERROR_BIND_OVERLAP] = "Entry '%s' overlaps with '%s'. Cannot bind.";
msgs[ERROR_SPARSE_NOT_UPTODATE_FILE] =
"Cannot update sparse checkout: the following entries are not up-to-date:\n%s";
msgs[ERROR_WOULD_LOSE_ORPHANED_OVERWRITTEN] =
"The following Working tree files would be overwritten by sparse checkout update:\n%s";
msgs[ERROR_WOULD_LOSE_ORPHANED_REMOVED] =
"The following Working tree files would be removed by sparse checkout update:\n%s";
opts->show_all_errors = 1;
/* rejected paths may not have a static buffer */
for (i = 0; i < ARRAY_SIZE(opts->unpack_rejects); i++)
opts->unpack_rejects[i].strdup_strings = 1;
}
static void do_add_entry(struct unpack_trees_options *o, struct cache_entry *ce,
unsigned int set, unsigned int clear)
{
clear |= CE_HASHED | CE_UNHASHED;
if (set & CE_REMOVE)
set |= CE_WT_REMOVE;
ce->next = NULL;
ce->ce_flags = (ce->ce_flags & ~clear) | set;
add_index_entry(&o->result, ce,
ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE);
}
static struct cache_entry *dup_entry(const struct cache_entry *ce)
{
unsigned int size = ce_size(ce);
struct cache_entry *new = xmalloc(size);
memcpy(new, ce, size);
return new;
}
static void add_entry(struct unpack_trees_options *o,
const struct cache_entry *ce,
unsigned int set, unsigned int clear)
{
do_add_entry(o, dup_entry(ce), set, clear);
}
/*
* add error messages on path <path>
* corresponding to the type <e> with the message <msg>
* indicating if it should be display in porcelain or not
*/
static int add_rejected_path(struct unpack_trees_options *o,
enum unpack_trees_error_types e,
const char *path)
{
if (!o->show_all_errors)
return error(ERRORMSG(o, e), path);
/*
* Otherwise, insert in a list for future display by
* display_error_msgs()
*/
string_list_append(&o->unpack_rejects[e], path);
return -1;
}
/*
* display all the error messages stored in a nice way
*/
static void display_error_msgs(struct unpack_trees_options *o)
{
int e, i;
int something_displayed = 0;
for (e = 0; e < NB_UNPACK_TREES_ERROR_TYPES; e++) {
struct string_list *rejects = &o->unpack_rejects[e];
if (rejects->nr > 0) {
struct strbuf path = STRBUF_INIT;
something_displayed = 1;
for (i = 0; i < rejects->nr; i++)
strbuf_addf(&path, "\t%s\n", rejects->items[i].string);
error(ERRORMSG(o, e), path.buf);
strbuf_release(&path);
}
string_list_clear(rejects, 0);
}
if (something_displayed)
fprintf(stderr, "Aborting\n");
}
/*
* Unlink the last component and schedule the leading directories for
* removal, such that empty directories get removed.
*/
Optimize symlink/directory detection This is the base for making symlink detection in the middle fo a pathname saner and (much) more efficient. Under various loads, we want to verify that the full path leading up to a filename is a real directory tree, and that when we successfully do an 'lstat()' on a filename, we don't get a false positive due to a symlink in the middle of the path that git should have seen as a symlink, not as a normal path component. The 'has_symlink_leading_path()' function already did this, and cached a single level of symlink information, but didn't cache the _lack_ of a symlink, so the normal behaviour was actually the wrong way around, and we ended up doing an 'lstat()' on each path component to check that it was a real directory. This caches the last detected full directory and symlink entries, and speeds up especially deep directory structures a lot by avoiding to lstat() all the directories leading up to each entry in the index. [ This can - and should - probably be extended upon so that we eventually never do a bare 'lstat()' on any path entries at *all* when checking the index, but always check the full path carefully. Right now we do not generally check the whole path for all our normal quick index revalidation. We should also make sure that we're careful about all the invalidation, ie when we remove a link and replace it by a directory we should invalidate the symlink cache if it matches (and vice versa for the directory cache). But regardless, the basic function needs to be sane to do that. The old 'has_symlink_leading_path()' was not capable enough - or indeed the code readable enough - to really do that sanely. So I'm pushing this as not just an optimization, but as a base for further work. ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-09 18:21:07 +02:00
static void unlink_entry(struct cache_entry *ce)
{
if (!check_leading_path(ce->name, ce_namelen(ce)))
return;
if (remove_or_warn(ce->ce_mode, ce->name))
return;
schedule_dir_for_removal(ce->name, ce_namelen(ce));
}
static struct checkout state;
static int check_updates(struct unpack_trees_options *o)
{
unsigned cnt = 0, total = 0;
struct progress *progress = NULL;
struct index_state *index = &o->result;
int i;
int errs = 0;
if (o->update && o->verbose_update) {
for (total = cnt = 0; cnt < index->cache_nr; cnt++) {
struct cache_entry *ce = index->cache[cnt];
if (ce->ce_flags & (CE_UPDATE | CE_WT_REMOVE))
total++;
}
progress = start_progress_delay("Checking out files",
total, 50, 1);
cnt = 0;
}
if (o->update)
git_attr_set_direction(GIT_ATTR_CHECKOUT, &o->result);
for (i = 0; i < index->cache_nr; i++) {
struct cache_entry *ce = index->cache[i];
if (ce->ce_flags & CE_WT_REMOVE) {
display_progress(progress, ++cnt);
if (o->update && !o->dry_run)
unlink_entry(ce);
continue;
}
}
check_updates(): effective removal of cache entries marked CE_REMOVE Below is oprofile output from GIT command 'git chekcout -q my-v2.6.25' (move from tag v2.6.27 to tag v2.6.25 of the Linux kernel): CPU: Core 2, speed 1999.95 MHz (estimated) Counted CPU_CLK_UNHALTED events (Clock cycles when not halted) with a unit mask of 0x00 (Unhalted core cycles) count 20000 Counted INST_RETIRED_ANY_P events (number of instructions retired) with a unit mask of 0x00 (No unit mask) count 20000 CPU_CLK_UNHALT...|INST_RETIRED:2...| samples| %| samples| %| ------------------------------------ 409247 100.000 342878 100.000 git CPU_CLK_UNHALT...|INST_RETIRED:2...| samples| %| samples| %| ------------------------------------ 260476 63.6476 257843 75.1996 libz.so.1.2.3 100876 24.6492 64378 18.7758 kernel-2.6.28.4_2.vmlinux 30850 7.5382 7874 2.2964 libc-2.9.so 14775 3.6103 8390 2.4469 git 2020 0.4936 4325 1.2614 libcrypto.so.0.9.8 191 0.0467 32 0.0093 libpthread-2.9.so 58 0.0142 36 0.0105 ld-2.9.so 1 2.4e-04 0 0 libldap-2.3.so.0.2.31 Detail list of the top 20 function entries (libz counted in one blob): CPU_CLK_UNHALTED INST_RETIRED_ANY_P samples % samples % image name symbol name 260476 63.6862 257843 75.2725 libz.so.1.2.3 /lib/libz.so.1.2.3 16587 4.0555 3636 1.0615 libc-2.9.so memcpy 7710 1.8851 277 0.0809 libc-2.9.so memmove 3679 0.8995 1108 0.3235 kernel-2.6.28.4_2.vmlinux d_validate 3546 0.8670 2607 0.7611 kernel-2.6.28.4_2.vmlinux __getblk 3174 0.7760 1813 0.5293 libc-2.9.so _int_malloc 2396 0.5858 3681 1.0746 kernel-2.6.28.4_2.vmlinux copy_to_user 2270 0.5550 2528 0.7380 kernel-2.6.28.4_2.vmlinux __link_path_walk 2205 0.5391 1797 0.5246 kernel-2.6.28.4_2.vmlinux ext4_mark_iloc_dirty 2103 0.5142 1203 0.3512 kernel-2.6.28.4_2.vmlinux find_first_zero_bit 2077 0.5078 997 0.2911 kernel-2.6.28.4_2.vmlinux do_get_write_access 2070 0.5061 514 0.1501 git cache_name_compare 2043 0.4995 1501 0.4382 kernel-2.6.28.4_2.vmlinux rcu_irq_exit 2022 0.4944 1732 0.5056 kernel-2.6.28.4_2.vmlinux __ext4_get_inode_loc 2020 0.4939 4325 1.2626 libcrypto.so.0.9.8 /usr/lib/libcrypto.so.0.9.8 1965 0.4804 1384 0.4040 git patch_delta 1708 0.4176 984 0.2873 kernel-2.6.28.4_2.vmlinux rcu_sched_grace_period 1682 0.4112 727 0.2122 kernel-2.6.28.4_2.vmlinux sysfs_slab_alias 1659 0.4056 290 0.0847 git find_pack_entry_one 1480 0.3619 1307 0.3816 kernel-2.6.28.4_2.vmlinux ext4_writepage_trans_blocks Notice the memmove line, where the CPU did 7710 / 277 = 27.8 cycles per instruction, and compared to the total cycles spent inside the source code of GIT for this command, all the memmove() calls translates to (7710 * 100) / 14775 = 52.2% of this. Retesting with a GIT program compiled for gcov usage, I found out that the memmove() calls came from remove_index_entry_at() in read-cache.c, where we have: memmove(istate->cache + pos, istate->cache + pos + 1, (istate->cache_nr - pos) * sizeof(struct cache_entry *)); remove_index_entry_at() is called 4902 times from check_updates() in unpack-trees.c, and each time called we move each cache_entry pointers (from the removed one) one step to the left. Since we have 28828 entries in the cache this time, and if we on average move half of them each time, we in total move approximately 4902 * 0.5 * 28828 * 4 = 282 629 712 bytes, or twice this amount if each pointer is 8 bytes (64 bit). OK, is seems that the function check_updates() is called 28 times, so the estimated guess above had been more correct if check_updates() had been called only once, but the point is: we get lots of bytes moved. To fix this, and use an O(N) algorithm instead, where N is the number of cache_entries, we delete/remove all entries in one loop through all entries. From a retest, the new remove_marked_cache_entries() from the patch below, ended up with the following output line from oprofile: 46 0.0105 15 0.0041 git remove_marked_cache_entries If we can trust the numbers from oprofile in this case, we saved approximately ((7710 - 46) * 20000) / (2 * 1000 * 1000 * 1000) = 0.077 seconds CPU time with this fix for this particular test. And notice that now the CPU did only 46 / 15 = 3.1 cycles/instruction. Signed-off-by: Kjetil Barvik <barvik@broadpark.no> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-02-18 23:18:03 +01:00
remove_marked_cache_entries(&o->result);
remove_scheduled_dirs();
for (i = 0; i < index->cache_nr; i++) {
struct cache_entry *ce = index->cache[i];
if (ce->ce_flags & CE_UPDATE) {
display_progress(progress, ++cnt);
ce->ce_flags &= ~CE_UPDATE;
if (o->update && !o->dry_run) {
errs |= checkout_entry(ce, &state, NULL);
}
}
}
stop_progress(&progress);
if (o->update)
git_attr_set_direction(GIT_ATTR_CHECKIN, NULL);
return errs != 0;
}
static int verify_uptodate_sparse(const struct cache_entry *ce,
struct unpack_trees_options *o);
static int verify_absent_sparse(const struct cache_entry *ce,
enum unpack_trees_error_types,
struct unpack_trees_options *o);
static int apply_sparse_checkout(struct cache_entry *ce, struct unpack_trees_options *o)
{
int was_skip_worktree = ce_skip_worktree(ce);
if (ce->ce_flags & CE_NEW_SKIP_WORKTREE)
ce->ce_flags |= CE_SKIP_WORKTREE;
else
ce->ce_flags &= ~CE_SKIP_WORKTREE;
/*
* if (!was_skip_worktree && !ce_skip_worktree()) {
* This is perfectly normal. Move on;
* }
*/
/*
* Merge strategies may set CE_UPDATE|CE_REMOVE outside checkout
* area as a result of ce_skip_worktree() shortcuts in
* verify_absent() and verify_uptodate().
* Make sure they don't modify worktree if they are already
* outside checkout area
*/
if (was_skip_worktree && ce_skip_worktree(ce)) {
ce->ce_flags &= ~CE_UPDATE;
/*
* By default, when CE_REMOVE is on, CE_WT_REMOVE is also
* on to get that file removed from both index and worktree.
* If that file is already outside worktree area, don't
* bother remove it.
*/
if (ce->ce_flags & CE_REMOVE)
ce->ce_flags &= ~CE_WT_REMOVE;
}
if (!was_skip_worktree && ce_skip_worktree(ce)) {
/*
* If CE_UPDATE is set, verify_uptodate() must be called already
* also stat info may have lost after merged_entry() so calling
* verify_uptodate() again may fail
*/
if (!(ce->ce_flags & CE_UPDATE) && verify_uptodate_sparse(ce, o))
return -1;
ce->ce_flags |= CE_WT_REMOVE;
}
if (was_skip_worktree && !ce_skip_worktree(ce)) {
if (verify_absent_sparse(ce, ERROR_WOULD_LOSE_UNTRACKED_OVERWRITTEN, o))
return -1;
ce->ce_flags |= CE_UPDATE;
}
return 0;
}
static inline int call_unpack_fn(const struct cache_entry * const *src,
struct unpack_trees_options *o)
{
int ret = o->fn(src, o);
if (ret > 0)
ret = 0;
return ret;
}
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
static void mark_ce_used(struct cache_entry *ce, struct unpack_trees_options *o)
{
ce->ce_flags |= CE_UNPACKED;
if (o->cache_bottom < o->src_index->cache_nr &&
o->src_index->cache[o->cache_bottom] == ce) {
int bottom = o->cache_bottom;
while (bottom < o->src_index->cache_nr &&
o->src_index->cache[bottom]->ce_flags & CE_UNPACKED)
bottom++;
o->cache_bottom = bottom;
}
}
static void mark_all_ce_unused(struct index_state *index)
{
int i;
for (i = 0; i < index->cache_nr; i++)
index->cache[i]->ce_flags &= ~(CE_UNPACKED | CE_ADDED | CE_NEW_SKIP_WORKTREE);
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
}
static int locate_in_src_index(const struct cache_entry *ce,
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
struct unpack_trees_options *o)
{
struct index_state *index = o->src_index;
int len = ce_namelen(ce);
int pos = index_name_pos(index, ce->name, len);
if (pos < 0)
pos = -1 - pos;
return pos;
}
/*
* We call unpack_index_entry() with an unmerged cache entry
* only in diff-index, and it wants a single callback. Skip
* the other unmerged entry with the same name.
*/
static void mark_ce_used_same_name(struct cache_entry *ce,
struct unpack_trees_options *o)
{
struct index_state *index = o->src_index;
int len = ce_namelen(ce);
int pos;
for (pos = locate_in_src_index(ce, o); pos < index->cache_nr; pos++) {
struct cache_entry *next = index->cache[pos];
if (len != ce_namelen(next) ||
memcmp(ce->name, next->name, len))
break;
mark_ce_used(next, o);
}
}
static struct cache_entry *next_cache_entry(struct unpack_trees_options *o)
{
const struct index_state *index = o->src_index;
int pos = o->cache_bottom;
while (pos < index->cache_nr) {
struct cache_entry *ce = index->cache[pos];
if (!(ce->ce_flags & CE_UNPACKED))
return ce;
pos++;
}
return NULL;
}
static void add_same_unmerged(struct cache_entry *ce,
struct unpack_trees_options *o)
{
struct index_state *index = o->src_index;
int len = ce_namelen(ce);
int pos = index_name_pos(index, ce->name, len);
if (0 <= pos)
die("programming error in a caller of mark_ce_used_same_name");
for (pos = -pos - 1; pos < index->cache_nr; pos++) {
struct cache_entry *next = index->cache[pos];
if (len != ce_namelen(next) ||
memcmp(ce->name, next->name, len))
break;
add_entry(o, next, 0, 0);
mark_ce_used(next, o);
}
}
static int unpack_index_entry(struct cache_entry *ce,
struct unpack_trees_options *o)
{
const struct cache_entry *src[MAX_UNPACK_TREES + 1] = { NULL, };
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
int ret;
src[0] = ce;
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
mark_ce_used(ce, o);
if (ce_stage(ce)) {
if (o->skip_unmerged) {
add_entry(o, ce, 0, 0);
return 0;
}
}
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
ret = call_unpack_fn(src, o);
if (ce_stage(ce))
mark_ce_used_same_name(ce, o);
return ret;
}
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 09:03:39 +02:00
static int find_cache_pos(struct traverse_info *, const struct name_entry *);
static void restore_cache_bottom(struct traverse_info *info, int bottom)
{
struct unpack_trees_options *o = info->data;
if (o->diff_index_cached)
return;
o->cache_bottom = bottom;
}
static int switch_cache_bottom(struct traverse_info *info)
{
struct unpack_trees_options *o = info->data;
int ret, pos;
if (o->diff_index_cached)
return 0;
ret = o->cache_bottom;
pos = find_cache_pos(info->prev, &info->name);
if (pos < -1)
o->cache_bottom = -2 - pos;
else if (pos < 0)
o->cache_bottom = o->src_index->cache_nr;
return ret;
}
static int traverse_trees_recursive(int n, unsigned long dirmask,
unsigned long df_conflicts,
struct name_entry *names,
struct traverse_info *info)
{
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 09:03:39 +02:00
int i, ret, bottom;
struct tree_desc t[MAX_UNPACK_TREES];
void *buf[MAX_UNPACK_TREES];
struct traverse_info newinfo;
struct name_entry *p;
p = names;
while (!p->mode)
p++;
newinfo = *info;
newinfo.prev = info;
newinfo.pathspec = info->pathspec;
newinfo.name = *p;
newinfo.pathlen += tree_entry_len(p) + 1;
newinfo.df_conflicts |= df_conflicts;
for (i = 0; i < n; i++, dirmask >>= 1) {
const unsigned char *sha1 = NULL;
if (dirmask & 1)
sha1 = names[i].sha1;
buf[i] = fill_tree_descriptor(t+i, sha1);
}
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 09:03:39 +02:00
bottom = switch_cache_bottom(&newinfo);
ret = traverse_trees(n, t, &newinfo);
restore_cache_bottom(&newinfo, bottom);
for (i = 0; i < n; i++)
free(buf[i]);
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 09:03:39 +02:00
return ret;
}
/*
* Compare the traverse-path to the cache entry without actually
* having to generate the textual representation of the traverse
* path.
*
* NOTE! This *only* compares up to the size of the traverse path
* itself - the caller needs to do the final check for the cache
* entry having more data at the end!
*/
static int do_compare_entry(const struct cache_entry *ce, const struct traverse_info *info, const struct name_entry *n)
{
int len, pathlen, ce_len;
const char *ce_name;
if (info->prev) {
int cmp = do_compare_entry(ce, info->prev, &info->name);
if (cmp)
return cmp;
}
pathlen = info->pathlen;
ce_len = ce_namelen(ce);
/* If ce_len < pathlen then we must have previously hit "name == directory" entry */
if (ce_len < pathlen)
return -1;
ce_len -= pathlen;
ce_name = ce->name + pathlen;
len = tree_entry_len(n);
return df_name_compare(ce_name, ce_len, S_IFREG, n->path, len, n->mode);
}
static int compare_entry(const struct cache_entry *ce, const struct traverse_info *info, const struct name_entry *n)
{
int cmp = do_compare_entry(ce, info, n);
if (cmp)
return cmp;
/*
* Even if the beginning compared identically, the ce should
* compare as bigger than a directory leading up to it!
*/
return ce_namelen(ce) > traverse_path_len(info, n);
}
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
static int ce_in_traverse_path(const struct cache_entry *ce,
const struct traverse_info *info)
{
if (!info->prev)
return 1;
if (do_compare_entry(ce, info->prev, &info->name))
return 0;
/*
* If ce (blob) is the same name as the path (which is a tree
* we will be descending into), it won't be inside it.
*/
return (info->pathlen < ce_namelen(ce));
}
static struct cache_entry *create_ce_entry(const struct traverse_info *info, const struct name_entry *n, int stage)
{
int len = traverse_path_len(info, n);
struct cache_entry *ce = xcalloc(1, cache_entry_size(len));
ce->ce_mode = create_ce_mode(n->mode);
ce->ce_flags = create_ce_flags(stage);
ce->ce_namelen = len;
hashcpy(ce->sha1, n->sha1);
make_traverse_path(ce->name, info, n);
return ce;
}
static int unpack_nondirectories(int n, unsigned long mask,
unsigned long dirmask,
struct cache_entry **src,
const struct name_entry *names,
const struct traverse_info *info)
{
int i;
struct unpack_trees_options *o = info->data;
unsigned long conflicts = info->df_conflicts | dirmask;
/* Do we have *only* directories? Nothing to do */
if (mask == dirmask && !src[0])
return 0;
/*
* Ok, we've filled in up to any potential index entry in src[0],
* now do the rest.
*/
for (i = 0; i < n; i++) {
int stage;
unsigned int bit = 1ul << i;
if (conflicts & bit) {
src[i + o->merge] = o->df_conflict_entry;
continue;
}
if (!(mask & bit))
continue;
if (!o->merge)
stage = 0;
else if (i + 1 < o->head_idx)
stage = 1;
else if (i + 1 > o->head_idx)
stage = 3;
else
stage = 2;
src[i + o->merge] = create_ce_entry(info, names + i, stage);
}
if (o->merge) {
int rc = call_unpack_fn((const struct cache_entry * const *)src,
o);
for (i = 0; i < n; i++) {
struct cache_entry *ce = src[i + o->merge];
if (ce != o->df_conflict_entry)
free(ce);
}
return rc;
}
for (i = 0; i < n; i++)
if (src[i] && src[i] != o->df_conflict_entry)
do_add_entry(o, src[i], 0, 0);
return 0;
}
static int unpack_failed(struct unpack_trees_options *o, const char *message)
{
discard_index(&o->result);
if (!o->gently && !o->exiting_early) {
if (message)
return error("%s", message);
return -1;
}
return -1;
}
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 09:03:39 +02:00
/* NEEDSWORK: give this a better name and share with tree-walk.c */
static int name_compare(const char *a, int a_len,
const char *b, int b_len)
{
int len = (a_len < b_len) ? a_len : b_len;
int cmp = memcmp(a, b, len);
if (cmp)
return cmp;
return (a_len - b_len);
}
/*
* The tree traversal is looking at name p. If we have a matching entry,
* return it. If name p is a directory in the index, do not return
* anything, as we will want to match it when the traversal descends into
* the directory.
*/
static int find_cache_pos(struct traverse_info *info,
const struct name_entry *p)
{
int pos;
struct unpack_trees_options *o = info->data;
struct index_state *index = o->src_index;
int pfxlen = info->pathlen;
int p_len = tree_entry_len(p);
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 09:03:39 +02:00
for (pos = o->cache_bottom; pos < index->cache_nr; pos++) {
struct cache_entry *ce = index->cache[pos];
const char *ce_name, *ce_slash;
int cmp, ce_len;
unpack-trees: Make index lookahead less pessimal When traversing trees with an index, the current index pointer (o->cache_bottom) occasionally has to be temporarily advanced forwards to match the traversal order of the tree, which is not the same as the sort order of the index. The existing algorithm that did this (introduced in 730f72840cc50c523fe4cdd796ea2d2fc4571a28) would get "stuck" when the cache_bottom was popped and then repeatedly check the same index entries over and over. This represents a serious performance regression for large repositories compared to the old "broken" traversal order. This commit makes a simple change to mitigate this. Whenever find_cache_pos sees that the current pos is also the cache_bottom, and it has already been unpacked, it advances the cache_bottom as well as the current pos. This prevents the above "sticking" behavior without dramatically changing the algorithm. In addition, this commit moves the unpacked check above the ce_in_traverse_path() check. The simple bitmask check is cheaper, and in the case described above will be firing quite a bit to advance the cache_bottom after a tree pop. This yields considerable performance improvements for large trees. The following are the number of function calls for "git diff HEAD" on the Linux kernel tree, with 33,307 files: Symbol Calls Before Calls After ------------------- ------------ ----------- unpack_callback 35,332 35,332 find_cache_pos 37,357 37,357 ce_in_traverse_path 4,979,473 37,357 do_compare_entry 6,828,181 251,925 df_name_compare 6,828,181 251,925 And on a repository of 187,456 files: Symbol Calls Before Calls After ------------------- ------------ ----------- unpack_callback 197,958 197,958 find_cache_pos 208,460 208,460 ce_in_traverse_path 37,308,336 208,460 do_compare_entry 156,950,469 2,690,626 df_name_compare 156,950,469 2,690,626 On the latter repository, user time for "git diff HEAD" was reduced from 5.58 to 0.42 seconds. This is compared to 0.30 seconds before the traversal order fix was implemented. Signed-off-by: Brian Downing <bdowning@lavos.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-06-11 04:59:07 +02:00
if (ce->ce_flags & CE_UNPACKED) {
/*
* cache_bottom entry is already unpacked, so
* we can never match it; don't check it
* again.
*/
if (pos == o->cache_bottom)
++o->cache_bottom;
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 09:03:39 +02:00
continue;
unpack-trees: Make index lookahead less pessimal When traversing trees with an index, the current index pointer (o->cache_bottom) occasionally has to be temporarily advanced forwards to match the traversal order of the tree, which is not the same as the sort order of the index. The existing algorithm that did this (introduced in 730f72840cc50c523fe4cdd796ea2d2fc4571a28) would get "stuck" when the cache_bottom was popped and then repeatedly check the same index entries over and over. This represents a serious performance regression for large repositories compared to the old "broken" traversal order. This commit makes a simple change to mitigate this. Whenever find_cache_pos sees that the current pos is also the cache_bottom, and it has already been unpacked, it advances the cache_bottom as well as the current pos. This prevents the above "sticking" behavior without dramatically changing the algorithm. In addition, this commit moves the unpacked check above the ce_in_traverse_path() check. The simple bitmask check is cheaper, and in the case described above will be firing quite a bit to advance the cache_bottom after a tree pop. This yields considerable performance improvements for large trees. The following are the number of function calls for "git diff HEAD" on the Linux kernel tree, with 33,307 files: Symbol Calls Before Calls After ------------------- ------------ ----------- unpack_callback 35,332 35,332 find_cache_pos 37,357 37,357 ce_in_traverse_path 4,979,473 37,357 do_compare_entry 6,828,181 251,925 df_name_compare 6,828,181 251,925 And on a repository of 187,456 files: Symbol Calls Before Calls After ------------------- ------------ ----------- unpack_callback 197,958 197,958 find_cache_pos 208,460 208,460 ce_in_traverse_path 37,308,336 208,460 do_compare_entry 156,950,469 2,690,626 df_name_compare 156,950,469 2,690,626 On the latter repository, user time for "git diff HEAD" was reduced from 5.58 to 0.42 seconds. This is compared to 0.30 seconds before the traversal order fix was implemented. Signed-off-by: Brian Downing <bdowning@lavos.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-06-11 04:59:07 +02:00
}
if (!ce_in_traverse_path(ce, info))
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 09:03:39 +02:00
continue;
ce_name = ce->name + pfxlen;
ce_slash = strchr(ce_name, '/');
if (ce_slash)
ce_len = ce_slash - ce_name;
else
ce_len = ce_namelen(ce) - pfxlen;
cmp = name_compare(p->path, p_len, ce_name, ce_len);
/*
* Exact match; if we have a directory we need to
* delay returning it.
*/
if (!cmp)
return ce_slash ? -2 - pos : pos;
if (0 < cmp)
continue; /* keep looking */
/*
* ce_name sorts after p->path; could it be that we
* have files under p->path directory in the index?
* E.g. ce_name == "t-i", and p->path == "t"; we may
* have "t/a" in the index.
*/
if (p_len < ce_len && !memcmp(ce_name, p->path, p_len) &&
ce_name[p_len] < '/')
continue; /* keep looking */
break;
}
return -1;
}
static struct cache_entry *find_cache_entry(struct traverse_info *info,
const struct name_entry *p)
{
int pos = find_cache_pos(info, p);
struct unpack_trees_options *o = info->data;
if (0 <= pos)
return o->src_index->cache[pos];
else
return NULL;
}
static void debug_path(struct traverse_info *info)
{
if (info->prev) {
debug_path(info->prev);
if (*info->prev->name.path)
putchar('/');
}
printf("%s", info->name.path);
}
static void debug_name_entry(int i, struct name_entry *n)
{
printf("ent#%d %06o %s\n", i,
n->path ? n->mode : 0,
n->path ? n->path : "(missing)");
}
static void debug_unpack_callback(int n,
unsigned long mask,
unsigned long dirmask,
struct name_entry *names,
struct traverse_info *info)
{
int i;
printf("* unpack mask %lu, dirmask %lu, cnt %d ",
mask, dirmask, n);
debug_path(info);
putchar('\n');
for (i = 0; i < n; i++)
debug_name_entry(i, names + i);
}
static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, struct name_entry *names, struct traverse_info *info)
{
struct cache_entry *src[MAX_UNPACK_TREES + 1] = { NULL, };
struct unpack_trees_options *o = info->data;
const struct name_entry *p = names;
/* Find first entry with a real name (we could use "mask" too) */
while (!p->mode)
p++;
if (o->debug_unpack)
debug_unpack_callback(n, mask, dirmask, names, info);
/* Are we supposed to look at the index too? */
if (o->merge) {
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
while (1) {
int cmp;
unpack-trees.c: look ahead in the index This makes the traversal of index be in sync with the tree traversal. When unpack_callback() is fed a set of tree entries from trees, it inspects the name of the entry and checks if the an index entry with the same name could be hiding behind the current index entry, and (1) if the name appears in the index as a leaf node, it is also fed to the n_way_merge() callback function; (2) if the name is a directory in the index, i.e. there are entries in that are underneath it, then nothing is fed to the n_way_merge() callback function; (3) otherwise, if the name comes before the first eligible entry in the index, the index entry is first unpacked alone. When traverse_trees_recursive() descends into a subdirectory, the cache_bottom pointer is moved to walk index entries within that directory. All of these are omitted for diff-index, which does not even want to be fed an index entry and a tree entry with D/F conflicts. This fixes 3-way read-tree and exposes a bug in other parts of the system in t6035, test #5. The test prepares these three trees: O = HEAD^ 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x A = HEAD 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b/c/d 100644 blob 587be6b4c3f93f93c489c0111bba5596147a26cb a/x B = master 120000 blob a36b77384451ea1de7bd340ffca868249626bc52 a/b 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/b-2/c/d 100644 blob e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 a/x With a clean index that matches HEAD, running git read-tree -m -u --aggressive $O $A $B now yields 120000 a36b77384451ea1de7bd340ffca868249626bc52 3 a/b 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0 a/b-2/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 1 a/b/c/d 100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 2 a/b/c/d 100644 587be6b4c3f93f93c489c0111bba5596147a26cb 0 a/x which is correct. "master" created "a/b" symlink that did not exist, and removed "a/b/c/d" while HEAD did not do touch either path. Before this series, read-tree did not notice the situation and resolved addition of "a/b" and removal of "a/b/c/d" independently. If A = HEAD had another path "a/b/c/e" added, this merge should conflict but instead it silently resolved "a/b" and then immediately overwrote it to add "a/b/c/e", which was quite bogus. Tests in t1012 start to work with this. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-09-20 09:03:39 +02:00
struct cache_entry *ce;
if (o->diff_index_cached)
ce = next_cache_entry(o);
else
ce = find_cache_entry(info, p);
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
if (!ce)
break;
cmp = compare_entry(ce, info, p);
if (cmp < 0) {
if (unpack_index_entry(ce, o) < 0)
return unpack_failed(o, NULL);
continue;
}
if (!cmp) {
if (ce_stage(ce)) {
/*
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
* If we skip unmerged index
* entries, we'll skip this
* entry *and* the tree
* entries associated with it!
*/
if (o->skip_unmerged) {
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
add_same_unmerged(ce, o);
return mask;
}
}
src[0] = ce;
}
break;
}
}
if (unpack_nondirectories(n, mask, dirmask, src, names, info) < 0)
return -1;
if (o->merge && src[0]) {
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
if (ce_stage(src[0]))
mark_ce_used_same_name(src[0], o);
else
mark_ce_used(src[0], o);
}
/* Now handle any directories.. */
if (dirmask) {
Optimize "diff-index --cached" using cache-tree When running "diff-index --cached" after making a change to only a small portion of the index, there is no point unpacking unchanged subtrees into the index recursively, only to find that all entries match anyway. Tweak unpack_trees() logic that is used to read in the tree object to catch the case where the tree entry we are looking at matches the index as a whole by looking at the cache-tree. As an exercise, after modifying a few paths in the kernel tree, here are a few numbers on my Athlon 64X2 3800+: (without patch, hot cache) $ /usr/bin/time git diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.07user 0.02system 0:00.09elapsed 102%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+9407minor)pagefaults 0swaps (with patch, hot cache) $ /usr/bin/time ../git.git/git-diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.02user 0.00system 0:00.02elapsed 103%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2446minor)pagefaults 0swaps Cold cache numbers are very impressive, but it does not matter very much in practice: (without patch, cold cache) $ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches' $ /usr/bin/time git diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.06user 0.17system 0:10.26elapsed 2%CPU (0avgtext+0avgdata 0maxresident)k 247032inputs+0outputs (1172major+8237minor)pagefaults 0swaps (with patch, cold cache) $ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches' $ /usr/bin/time ../git.git/git-diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.02user 0.01system 0:01.01elapsed 3%CPU (0avgtext+0avgdata 0maxresident)k 18440inputs+0outputs (79major+2369minor)pagefaults 0swaps This of course helps "git status" as well. (without patch, hot cache) $ /usr/bin/time ../git.git/git-status >/dev/null 0.17user 0.18system 0:00.35elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+5336outputs (0major+10970minor)pagefaults 0swaps (with patch, hot cache) $ /usr/bin/time ../git.git/git-status >/dev/null 0.10user 0.16system 0:00.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+5336outputs (0major+3921minor)pagefaults 0swaps Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-05-21 00:57:22 +02:00
/* special case: "diff-index --cached" looking at a tree */
if (o->diff_index_cached &&
n == 1 && dirmask == 1 && S_ISDIR(names->mode)) {
int matches;
matches = cache_tree_matches_traversal(o->src_index->cache_tree,
names, info);
/*
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
* Everything under the name matches; skip the
* entire hierarchy. diff_index_cached codepath
* special cases D/F conflicts in such a way that
* it does not do any look-ahead, so this is safe.
Optimize "diff-index --cached" using cache-tree When running "diff-index --cached" after making a change to only a small portion of the index, there is no point unpacking unchanged subtrees into the index recursively, only to find that all entries match anyway. Tweak unpack_trees() logic that is used to read in the tree object to catch the case where the tree entry we are looking at matches the index as a whole by looking at the cache-tree. As an exercise, after modifying a few paths in the kernel tree, here are a few numbers on my Athlon 64X2 3800+: (without patch, hot cache) $ /usr/bin/time git diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.07user 0.02system 0:00.09elapsed 102%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+9407minor)pagefaults 0swaps (with patch, hot cache) $ /usr/bin/time ../git.git/git-diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.02user 0.00system 0:00.02elapsed 103%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2446minor)pagefaults 0swaps Cold cache numbers are very impressive, but it does not matter very much in practice: (without patch, cold cache) $ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches' $ /usr/bin/time git diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.06user 0.17system 0:10.26elapsed 2%CPU (0avgtext+0avgdata 0maxresident)k 247032inputs+0outputs (1172major+8237minor)pagefaults 0swaps (with patch, cold cache) $ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches' $ /usr/bin/time ../git.git/git-diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.02user 0.01system 0:01.01elapsed 3%CPU (0avgtext+0avgdata 0maxresident)k 18440inputs+0outputs (79major+2369minor)pagefaults 0swaps This of course helps "git status" as well. (without patch, hot cache) $ /usr/bin/time ../git.git/git-status >/dev/null 0.17user 0.18system 0:00.35elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+5336outputs (0major+10970minor)pagefaults 0swaps (with patch, hot cache) $ /usr/bin/time ../git.git/git-status >/dev/null 0.10user 0.16system 0:00.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+5336outputs (0major+3921minor)pagefaults 0swaps Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-05-21 00:57:22 +02:00
*/
if (matches) {
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
o->cache_bottom += matches;
Optimize "diff-index --cached" using cache-tree When running "diff-index --cached" after making a change to only a small portion of the index, there is no point unpacking unchanged subtrees into the index recursively, only to find that all entries match anyway. Tweak unpack_trees() logic that is used to read in the tree object to catch the case where the tree entry we are looking at matches the index as a whole by looking at the cache-tree. As an exercise, after modifying a few paths in the kernel tree, here are a few numbers on my Athlon 64X2 3800+: (without patch, hot cache) $ /usr/bin/time git diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.07user 0.02system 0:00.09elapsed 102%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+9407minor)pagefaults 0swaps (with patch, hot cache) $ /usr/bin/time ../git.git/git-diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.02user 0.00system 0:00.02elapsed 103%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2446minor)pagefaults 0swaps Cold cache numbers are very impressive, but it does not matter very much in practice: (without patch, cold cache) $ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches' $ /usr/bin/time git diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.06user 0.17system 0:10.26elapsed 2%CPU (0avgtext+0avgdata 0maxresident)k 247032inputs+0outputs (1172major+8237minor)pagefaults 0swaps (with patch, cold cache) $ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches' $ /usr/bin/time ../git.git/git-diff --cached --raw :100644 100644 b57e1f5... e69de29... M Makefile :100644 000000 8c86b72... 0000000... D arch/x86/Makefile :000000 100644 0000000... e69de29... A arche 0.02user 0.01system 0:01.01elapsed 3%CPU (0avgtext+0avgdata 0maxresident)k 18440inputs+0outputs (79major+2369minor)pagefaults 0swaps This of course helps "git status" as well. (without patch, hot cache) $ /usr/bin/time ../git.git/git-status >/dev/null 0.17user 0.18system 0:00.35elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+5336outputs (0major+10970minor)pagefaults 0swaps (with patch, hot cache) $ /usr/bin/time ../git.git/git-status >/dev/null 0.10user 0.16system 0:00.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+5336outputs (0major+3921minor)pagefaults 0swaps Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-05-21 00:57:22 +02:00
return mask;
}
}
if (traverse_trees_recursive(n, dirmask, mask & ~dirmask,
names, info) < 0)
return -1;
return mask;
}
return mask;
}
static int clear_ce_flags_1(struct cache_entry **cache, int nr,
char *prefix, int prefix_len,
int select_mask, int clear_mask,
struct exclude_list *el, int defval);
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
/* Whole directory matching */
static int clear_ce_flags_dir(struct cache_entry **cache, int nr,
char *prefix, int prefix_len,
char *basename,
int select_mask, int clear_mask,
struct exclude_list *el, int defval)
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
{
struct cache_entry **cache_end;
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
int dtype = DT_DIR;
int ret = is_excluded_from_list(prefix, prefix_len,
basename, &dtype, el);
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
prefix[prefix_len++] = '/';
/* If undecided, use matching result of parent dir in defval */
if (ret < 0)
ret = defval;
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
for (cache_end = cache; cache_end != cache + nr; cache_end++) {
struct cache_entry *ce = *cache_end;
if (strncmp(ce->name, prefix, prefix_len))
break;
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
}
/*
* TODO: check el, if there are no patterns that may conflict
* with ret (iow, we know in advance the incl/excl
* decision for the entire directory), clear flag here without
* calling clear_ce_flags_1(). That function will call
* the expensive is_excluded_from_list() on every entry.
*/
return clear_ce_flags_1(cache, cache_end - cache,
prefix, prefix_len,
select_mask, clear_mask,
el, ret);
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
}
/*
* Traverse the index, find every entry that matches according to
* o->el. Do "ce_flags &= ~clear_mask" on those entries. Return the
* number of traversed entries.
*
* If select_mask is non-zero, only entries whose ce_flags has on of
* those bits enabled are traversed.
*
* cache : pointer to an index entry
* prefix_len : an offset to its path
*
* The current path ("prefix") including the trailing '/' is
* cache[0]->name[0..(prefix_len-1)]
* Top level path has prefix_len zero.
*/
static int clear_ce_flags_1(struct cache_entry **cache, int nr,
char *prefix, int prefix_len,
int select_mask, int clear_mask,
struct exclude_list *el, int defval)
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
{
struct cache_entry **cache_end = cache + nr;
/*
* Process all entries that have the given prefix and meet
* select_mask condition
*/
while(cache != cache_end) {
struct cache_entry *ce = *cache;
const char *name, *slash;
int len, dtype, ret;
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
if (select_mask && !(ce->ce_flags & select_mask)) {
cache++;
continue;
}
if (prefix_len && strncmp(ce->name, prefix, prefix_len))
break;
name = ce->name + prefix_len;
slash = strchr(name, '/');
/* If it's a directory, try whole directory match first */
if (slash) {
int processed;
len = slash - name;
memcpy(prefix + prefix_len, name, len);
/*
* terminate the string (no trailing slash),
* clear_c_f_dir needs it
*/
prefix[prefix_len + len] = '\0';
processed = clear_ce_flags_dir(cache, cache_end - cache,
prefix, prefix_len + len,
prefix + prefix_len,
select_mask, clear_mask,
el, defval);
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
/* clear_c_f_dir eats a whole dir already? */
if (processed) {
cache += processed;
continue;
}
prefix[prefix_len + len++] = '/';
cache += clear_ce_flags_1(cache, cache_end - cache,
prefix, prefix_len + len,
select_mask, clear_mask, el, defval);
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
continue;
}
/* Non-directory */
dtype = ce_to_dtype(ce);
ret = is_excluded_from_list(ce->name, ce_namelen(ce),
name, &dtype, el);
if (ret < 0)
ret = defval;
if (ret > 0)
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
ce->ce_flags &= ~clear_mask;
cache++;
}
return nr - (cache_end - cache);
}
static int clear_ce_flags(struct cache_entry **cache, int nr,
int select_mask, int clear_mask,
struct exclude_list *el)
{
char prefix[PATH_MAX];
return clear_ce_flags_1(cache, nr,
prefix, 0,
select_mask, clear_mask,
el, 0);
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
}
/*
* Set/Clear CE_NEW_SKIP_WORKTREE according to $GIT_DIR/info/sparse-checkout
*/
static void mark_new_skip_worktree(struct exclude_list *el,
struct index_state *the_index,
int select_flag, int skip_wt_flag)
{
int i;
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
/*
* 1. Pretend the narrowest worktree: only unmerged entries
* are checked out
*/
for (i = 0; i < the_index->cache_nr; i++) {
struct cache_entry *ce = the_index->cache[i];
if (select_flag && !(ce->ce_flags & select_flag))
continue;
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
if (!ce_stage(ce))
ce->ce_flags |= skip_wt_flag;
else
ce->ce_flags &= ~skip_wt_flag;
}
unpack-trees: fix sparse checkout's "unable to match directories" Matching index entries against an excludes file currently has two problems. First, there's no function to do it. Code paths (like sparse checkout) that wanted to try it would iterate over index entries and for each index entry pass that path to excluded_from_list(). But that is not how excluded_from_list() works; one is supposed to feed in each ancester of a path before a given path to find out if it was excluded because of some parent or grandparent matching a bigsubdirectory/ pattern despite the path not matching any .gitignore pattern directly. Second, it's inefficient. The excludes mechanism is supposed to let us block off vast swaths of the filesystem as uninteresting; separately checking every index entry doesn't fit that model. Introduce a new function to take care of both these problems. This traverses the index in depth-first order (well, that's what order the index is in) to mark un-excluded entries. Maybe some day the in-core index format will be restructured to make this sort of operation easier. Or maybe we will want to try some binary search based thing. The interface is simple enough to allow all those things. Example: clear_ce_flags(the_index.cache, the_index.cache_nr, CE_CANDIDATE, CE_CLEARME, exclude_list); would clear the CE_CLEARME flag on all index entries with CE_CANDIDATE flag and not matched by exclude_list. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-11-26 19:17:46 +01:00
/*
* 2. Widen worktree according to sparse-checkout file.
* Matched entries will have skip_wt_flag cleared (i.e. "in")
*/
clear_ce_flags(the_index->cache, the_index->cache_nr,
select_flag, skip_wt_flag, el);
}
static int verify_absent(const struct cache_entry *,
enum unpack_trees_error_types,
struct unpack_trees_options *);
/*
* N-way merge "len" trees. Returns 0 on success, -1 on failure to manipulate the
* resulting index, -2 on failure to reflect the changes to the work tree.
*
* CE_ADDED, CE_UNPACKED and CE_NEW_SKIP_WORKTREE are used internally
*/
int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options *o)
{
int i, ret;
static struct cache_entry *dfc;
struct exclude_list el;
if (len > MAX_UNPACK_TREES)
die("unpack_trees takes at most %d trees", MAX_UNPACK_TREES);
memset(&state, 0, sizeof(state));
state.base_dir = "";
state.force = 1;
state.quiet = 1;
state.refresh_cache = 1;
memset(&el, 0, sizeof(el));
if (!core_apply_sparse_checkout || !o->update)
o->skip_sparse_checkout = 1;
if (!o->skip_sparse_checkout) {
if (add_excludes_from_file_to_list(git_path("info/sparse-checkout"), "", 0, &el, 0) < 0)
o->skip_sparse_checkout = 1;
else
o->el = &el;
}
memset(&o->result, 0, sizeof(o->result));
unpack_trees(): protect the handcrafted in-core index from read_cache() unpack_trees() rebuilds the in-core index from scratch by allocating a new structure and finishing it off by copying the built one to the final index. The resulting in-core index is Ok for most use, but read_cache() does not recognize it as such. The function is meant to be no-op if you already have loaded the index, until you call discard_cache(). This change the way read_cache() detects an already initialized in-core index, by introducing an extra bit, and marks the handcrafted in-core index as initialized, to avoid this problem. A better fix in the longer term would be to change the read_cache() API so that it will always discard and re-read from the on-disk index to avoid confusion. But there are higher level API that have relied on the current semantics, and they and their users all need to get converted, which is outside the scope of 'maint' track. An example of such a higher level API is write_cache_as_tree(), which is used by git-write-tree as well as later Porcelains like git-merge, revert and cherry-pick. In the longer term, we should remove read_cache() from there and add one to cmd_write_tree(); other callers expect that the in-core index they prepared is what gets written as a tree so no other change is necessary for this particular codepath. The original version of this patch marked the index by pointing an otherwise wasted malloc'ed memory with o->result.alloc, but this version uses Linus's idea to use a new "initialized" bit, which is conceptually much cleaner. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-08-23 21:57:30 +02:00
o->result.initialized = 1;
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
o->result.timestamp.sec = o->src_index->timestamp.sec;
o->result.timestamp.nsec = o->src_index->timestamp.nsec;
o->result.version = o->src_index->version;
o->merge_size = len;
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
mark_all_ce_unused(o->src_index);
/*
* Sparse checkout loop #1: set NEW_SKIP_WORKTREE on existing entries
*/
if (!o->skip_sparse_checkout)
mark_new_skip_worktree(o->el, o->src_index, 0, CE_NEW_SKIP_WORKTREE);
if (!dfc)
dfc = xcalloc(1, cache_entry_size(0));
o->df_conflict_entry = dfc;
if (len) {
const char *prefix = o->prefix ? o->prefix : "";
struct traverse_info info;
setup_traverse_info(&info, prefix);
info.fn = unpack_callback;
info.data = o;
info.show_all_errors = o->show_all_errors;
info.pathspec = o->pathspec;
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
if (o->prefix) {
/*
* Unpack existing index entries that sort before the
* prefix the tree is spliced into. Note that o->merge
* is always true in this case.
*/
while (1) {
struct cache_entry *ce = next_cache_entry(o);
if (!ce)
break;
if (ce_in_traverse_path(ce, &info))
break;
if (unpack_index_entry(ce, o) < 0)
goto return_failed;
}
}
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
if (traverse_trees(len, t, &info) < 0)
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
goto return_failed;
}
/* Any left-over entries in the index? */
if (o->merge) {
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
while (1) {
struct cache_entry *ce = next_cache_entry(o);
if (!ce)
break;
if (unpack_index_entry(ce, o) < 0)
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
goto return_failed;
}
}
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
mark_all_ce_unused(o->src_index);
if (o->trivial_merges_only && o->nontrivial_merge) {
ret = unpack_failed(o, "Merge requires file-level merging");
goto done;
}
if (!o->skip_sparse_checkout) {
int empty_worktree = 1;
/*
* Sparse checkout loop #2: set NEW_SKIP_WORKTREE on entries not in loop #1
* If the will have NEW_SKIP_WORKTREE, also set CE_SKIP_WORKTREE
* so apply_sparse_checkout() won't attempt to remove it from worktree
*/
mark_new_skip_worktree(o->el, &o->result, CE_ADDED, CE_SKIP_WORKTREE | CE_NEW_SKIP_WORKTREE);
ret = 0;
for (i = 0; i < o->result.cache_nr; i++) {
struct cache_entry *ce = o->result.cache[i];
/*
* Entries marked with CE_ADDED in merged_entry() do not have
* verify_absent() check (the check is effectively disabled
* because CE_NEW_SKIP_WORKTREE is set unconditionally).
*
* Do the real check now because we have had
* correct CE_NEW_SKIP_WORKTREE
*/
if (ce->ce_flags & CE_ADDED &&
verify_absent(ce, ERROR_WOULD_LOSE_UNTRACKED_OVERWRITTEN, o)) {
if (!o->show_all_errors)
goto return_failed;
ret = -1;
}
if (apply_sparse_checkout(ce, o)) {
if (!o->show_all_errors)
goto return_failed;
ret = -1;
}
if (!ce_skip_worktree(ce))
empty_worktree = 0;
}
if (ret < 0)
goto return_failed;
/*
* Sparse checkout is meant to narrow down checkout area
* but it does not make sense to narrow down to empty working
* tree. This is usually a mistake in sparse checkout rules.
* Do not allow users to do that.
*/
if (o->result.cache_nr && empty_worktree) {
ret = unpack_failed(o, "Sparse checkout leaves no entry on working directory");
goto done;
}
}
o->src_index = NULL;
ret = check_updates(o) ? (-2) : 0;
if (o->dst_index)
*o->dst_index = o->result;
done:
clear_exclude_list(&el);
return ret;
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
return_failed:
if (o->show_all_errors)
display_error_msgs(o);
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
mark_all_ce_unused(o->src_index);
ret = unpack_failed(o, NULL);
if (o->exiting_early)
ret = 0;
goto done;
}
/* Here come the merge functions */
static int reject_merge(const struct cache_entry *ce,
struct unpack_trees_options *o)
{
return add_rejected_path(o, ERROR_WOULD_OVERWRITE, ce->name);
}
static int same(const struct cache_entry *a, const struct cache_entry *b)
{
if (!!a != !!b)
return 0;
if (!a && !b)
return 1;
"reset --merge": fix unmerged case Commit 9e8ecea (Add 'merge' mode to 'git reset', 2008-12-01) disallowed "git reset --merge" when there was unmerged entries. But it wished if unmerged entries were reset as if --hard (instead of --merge) has been used. This makes sense because all "mergy" operations makes sure that any path involved in the merge does not have local modifications before starting, so resetting such a path away won't lose any information. The previous commit changed the behavior of --merge to accept resetting unmerged entries if they are reset to a different state than HEAD, but it did not reset the changes in the work tree, leaving the conflict markers in the resulting file in the work tree. Fix it by doing three things: - Update the documentation to match the wish of original "reset --merge" better, namely, "An unmerged entry is a sign that the path didn't have any local modification and can be safely resetted to whatever the new HEAD records"; - Update read_index_unmerged(), which reads the index file into the cache while dropping any higher-stage entries down to stage #0, not to copy the object name from the higher stage entry. The code used to take the object name from the a stage entry ("base" if you happened to have stage #1, or "ours" if both sides added, etc.), which essentially meant that you are getting random results depending on what the merge did. The _only_ reason we want to keep a previously unmerged entry in the index at stage #0 is so that we don't forget the fact that we have corresponding file in the work tree in order to be able to remove it when the tree we are resetting to does not have the path. In order to differentiate such an entry from ordinary cache entry, the cache entry added by read_index_unmerged() is marked as CE_CONFLICTED. - Update merged_entry() and deleted_entry() so that they pay attention to cache entries marked as CE_CONFLICTED. They are previously unmerged entries, and the files in the work tree that correspond to them are resetted away by oneway_merge() to the version from the tree we are resetting to. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-01 08:04:04 +01:00
if ((a->ce_flags | b->ce_flags) & CE_CONFLICTED)
return 0;
return a->ce_mode == b->ce_mode &&
!hashcmp(a->sha1, b->sha1);
}
/*
* When a CE gets turned into an unmerged entry, we
* want it to be up-to-date
*/
static int verify_uptodate_1(const struct cache_entry *ce,
struct unpack_trees_options *o,
enum unpack_trees_error_types error_type)
{
struct stat st;
if (o->index_only)
return 0;
/*
* CE_VALID and CE_SKIP_WORKTREE cheat, we better check again
* if this entry is truly up-to-date because this file may be
* overwritten.
*/
if ((ce->ce_flags & CE_VALID) || ce_skip_worktree(ce))
; /* keep checking */
else if (o->reset || ce_uptodate(ce))
return 0;
if (!lstat(ce->name, &st)) {
int flags = CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE;
unsigned changed = ie_match_stat(o->src_index, ce, &st, flags);
if (!changed)
return 0;
unpack-trees.c: assume submodules are clean during check-out Sven originally raised this issue: If you have a submodule checked out and you go back (or forward) to a revision of the supermodule that contains a different revision of the submodule and then switch to another revision, it will complain that the submodule is not uptodate, because git simply didn't update the submodule in the first move. The current policy is to consider it is perfectly normal that checked-out submodule is out-of-sync wrt the supermodule index. At least until we introduce a superproject repository configuration option that says "in this repository, I do care about this submodule and at any time I move around in the superproject, recursively check out the submodule to match", it is a reasonable policy, as we currently do not recursively checkout the submodules at all. The most extreme case of this policy is that the superproject index knows about the submodule but the subdirectory does not even have to be checked out. The function verify_uptodate(), called during the two-way merge aka branch switching, is about "make sure the filesystem entity that corresponds to this cache entry is up to date, lest we lose the local modifications". As we explicitly allow submodule checkout to drift from the supermodule index entry, the check should say "Ok, for submodules, not matching is the norm" for now. Later when we have the ability to mark "I care about this submodule to be always in sync with the superproject" (thereby implementing automatic recursive checkout and perhaps diff, among other things), we should check if the submodule in question is marked as such and perform the current test. Acked-by: Lars Hjemli <hjemli@gmail.com> Acked-by: Sven Verdoolaege <skimo@kotnet.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-08-04 07:13:09 +02:00
/*
* NEEDSWORK: the current default policy is to allow
* submodule to be out of sync wrt the superproject
unpack-trees.c: assume submodules are clean during check-out Sven originally raised this issue: If you have a submodule checked out and you go back (or forward) to a revision of the supermodule that contains a different revision of the submodule and then switch to another revision, it will complain that the submodule is not uptodate, because git simply didn't update the submodule in the first move. The current policy is to consider it is perfectly normal that checked-out submodule is out-of-sync wrt the supermodule index. At least until we introduce a superproject repository configuration option that says "in this repository, I do care about this submodule and at any time I move around in the superproject, recursively check out the submodule to match", it is a reasonable policy, as we currently do not recursively checkout the submodules at all. The most extreme case of this policy is that the superproject index knows about the submodule but the subdirectory does not even have to be checked out. The function verify_uptodate(), called during the two-way merge aka branch switching, is about "make sure the filesystem entity that corresponds to this cache entry is up to date, lest we lose the local modifications". As we explicitly allow submodule checkout to drift from the supermodule index entry, the check should say "Ok, for submodules, not matching is the norm" for now. Later when we have the ability to mark "I care about this submodule to be always in sync with the superproject" (thereby implementing automatic recursive checkout and perhaps diff, among other things), we should check if the submodule in question is marked as such and perform the current test. Acked-by: Lars Hjemli <hjemli@gmail.com> Acked-by: Sven Verdoolaege <skimo@kotnet.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-08-04 07:13:09 +02:00
* index. This needs to be tightened later for
* submodules that are marked to be automatically
* checked out.
*/
if (S_ISGITLINK(ce->ce_mode))
return 0;
errno = 0;
}
if (errno == ENOENT)
return 0;
return o->gently ? -1 :
add_rejected_path(o, error_type, ce->name);
}
static int verify_uptodate(const struct cache_entry *ce,
struct unpack_trees_options *o)
{
if (!o->skip_sparse_checkout && (ce->ce_flags & CE_NEW_SKIP_WORKTREE))
return 0;
return verify_uptodate_1(ce, o, ERROR_NOT_UPTODATE_FILE);
}
static int verify_uptodate_sparse(const struct cache_entry *ce,
struct unpack_trees_options *o)
{
return verify_uptodate_1(ce, o, ERROR_SPARSE_NOT_UPTODATE_FILE);
}
static void invalidate_ce_path(const struct cache_entry *ce,
struct unpack_trees_options *o)
{
if (ce)
cache_tree_invalidate_path(o->src_index->cache_tree, ce->name);
}
/*
* Check that checking out ce->sha1 in subdir ce->name is not
* going to overwrite any working files.
*
* Currently, git does not checkout subprojects during a superproject
* checkout, so it is not going to overwrite anything.
*/
static int verify_clean_submodule(const struct cache_entry *ce,
enum unpack_trees_error_types error_type,
struct unpack_trees_options *o)
{
return 0;
}
static int verify_clean_subdirectory(const struct cache_entry *ce,
enum unpack_trees_error_types error_type,
struct unpack_trees_options *o)
{
/*
* we are about to extract "ce->name"; we would not want to lose
* anything in the existing directory there.
*/
int namelen;
int i;
struct dir_struct d;
char *pathbuf;
int cnt = 0;
unsigned char sha1[20];
if (S_ISGITLINK(ce->ce_mode) &&
resolve_gitlink_ref(ce->name, "HEAD", sha1) == 0) {
/* If we are not going to update the submodule, then
* we don't care.
*/
if (!hashcmp(sha1, ce->sha1))
return 0;
return verify_clean_submodule(ce, error_type, o);
}
/*
* First let's make sure we do not have a local modification
* in that directory.
*/
namelen = ce_namelen(ce);
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
for (i = locate_in_src_index(ce, o);
i < o->src_index->cache_nr;
i++) {
struct cache_entry *ce2 = o->src_index->cache[i];
int len = ce_namelen(ce2);
if (len < namelen ||
strncmp(ce->name, ce2->name, namelen) ||
ce2->name[namelen] != '/')
break;
/*
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
* ce2->name is an entry in the subdirectory to be
* removed.
*/
if (!ce_stage(ce2)) {
if (verify_uptodate(ce2, o))
return -1;
add_entry(o, ce2, CE_REMOVE, 0);
unpack-trees.c: prepare for looking ahead in the index This prepares but does not yet implement a look-ahead in the index entries when traverse-trees.c decides to give us tree entries in an order that does not match what is in the index. A case where a look-ahead in the index is necessary happens when merging branch B into branch A while the index matches the current branch A, using a tree O as their common ancestor, and these three trees looks like this: O A B t t t-i t-i t-i t-j t-j t/1 t/2 The traverse_trees() function gets "t", "t-i" and "t" from trees O, A and B first, and notices that A may have a matching "t" behind "t-i" and "t-j" (indeed it does), and tells A to give that entry instead. After unpacking blob "t" from tree B (as it hasn't changed since O in B and A removed it, it will result in its removal), it descends into directory "t/". The side that walked index in parallel to the tree traversal used to be implemented with one pointer, o->pos, that points at the next index entry to be processed. When this happens, the pointer o->pos still points at "t-i" that is the first entry. We should be able to skip "t-i" and "t-j" and locate "t/1" from the index while the recursive invocation of traverse_trees() walks and match entries found there, and later come back to process "t-i". While that look-ahead is not implemented yet, this adds a flag bit, CE_UNPACKED, to mark the entries in the index that has already been processed. o->pos pointer has been renamed to o->cache_bottom and it points at the first entry that may still need to be processed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-07 23:59:54 +01:00
mark_ce_used(ce2, o);
}
cnt++;
}
/*
* Then we need to make sure that we do not lose a locally
* present file that is not ignored.
*/
pathbuf = xmalloc(namelen + 2);
memcpy(pathbuf, ce->name, namelen);
strcpy(pathbuf+namelen, "/");
memset(&d, 0, sizeof(d));
if (o->dir)
d.exclude_per_dir = o->dir->exclude_per_dir;
i = read_directory(&d, pathbuf, namelen+1, NULL);
if (i)
return o->gently ? -1 :
add_rejected_path(o, ERROR_NOT_UPTODATE_DIR, ce->name);
free(pathbuf);
return cnt;
}
/*
* This gets called when there was no index entry for the tree entry 'dst',
* but we found a file in the working tree that 'lstat()' said was fine,
* and we're on a case-insensitive filesystem.
*
* See if we can find a case-insensitive match in the index that also
* matches the stat information, and assume it's that other file!
*/
static int icase_exists(struct unpack_trees_options *o, const char *name, int len, struct stat *st)
{
struct cache_entry *src;
src = index_name_exists(o->src_index, name, len, 1);
return src && !ie_match_stat(o->src_index, src, st, CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE);
}
static int check_ok_to_remove(const char *name, int len, int dtype,
const struct cache_entry *ce, struct stat *st,
enum unpack_trees_error_types error_type,
struct unpack_trees_options *o)
{
struct cache_entry *result;
/*
* It may be that the 'lstat()' succeeded even though
* target 'ce' was absent, because there is an old
* entry that is different only in case..
*
* Ignore that lstat() if it matches.
*/
if (ignore_case && icase_exists(o, name, len, st))
return 0;
if (o->dir &&
is_excluded(o->dir, name, &dtype))
/*
* ce->name is explicitly excluded, so it is Ok to
* overwrite it.
*/
return 0;
if (S_ISDIR(st->st_mode)) {
/*
* We are checking out path "foo" and
* found "foo/." in the working tree.
* This is tricky -- if we have modified
* files that are in "foo/" we would lose
* them.
*/
if (verify_clean_subdirectory(ce, error_type, o) < 0)
return -1;
return 0;
}
/*
* The previous round may already have decided to
* delete this path, which is in a subdirectory that
* is being replaced with a blob.
*/
result = index_name_exists(&o->result, name, len, 0);
if (result) {
if (result->ce_flags & CE_REMOVE)
return 0;
}
return o->gently ? -1 :
add_rejected_path(o, error_type, name);
}
/*
* We do not want to remove or overwrite a working tree file that
* is not tracked, unless it is ignored.
*/
static int verify_absent_1(const struct cache_entry *ce,
enum unpack_trees_error_types error_type,
struct unpack_trees_options *o)
{
int len;
struct stat st;
if (o->index_only || o->reset || !o->update)
return 0;
len = check_leading_path(ce->name, ce_namelen(ce));
if (!len)
return 0;
else if (len > 0) {
char path[PATH_MAX + 1];
memcpy(path, ce->name, len);
path[len] = 0;
if (lstat(path, &st))
return error("cannot stat '%s': %s", path,
strerror(errno));
return check_ok_to_remove(path, len, DT_UNKNOWN, NULL, &st,
error_type, o);
} else if (lstat(ce->name, &st)) {
if (errno != ENOENT)
return error("cannot stat '%s': %s", ce->name,
strerror(errno));
return 0;
} else {
return check_ok_to_remove(ce->name, ce_namelen(ce),
ce_to_dtype(ce), ce, &st,
error_type, o);
}
}
static int verify_absent(const struct cache_entry *ce,
enum unpack_trees_error_types error_type,
struct unpack_trees_options *o)
{
if (!o->skip_sparse_checkout && (ce->ce_flags & CE_NEW_SKIP_WORKTREE))
return 0;
return verify_absent_1(ce, error_type, o);
}
static int verify_absent_sparse(const struct cache_entry *ce,
enum unpack_trees_error_types error_type,
struct unpack_trees_options *o)
{
enum unpack_trees_error_types orphaned_error = error_type;
if (orphaned_error == ERROR_WOULD_LOSE_UNTRACKED_OVERWRITTEN)
orphaned_error = ERROR_WOULD_LOSE_ORPHANED_OVERWRITTEN;
return verify_absent_1(ce, orphaned_error, o);
}
static int merged_entry(const struct cache_entry *ce,
const struct cache_entry *old,
struct unpack_trees_options *o)
{
int update = CE_UPDATE;
struct cache_entry *merge = dup_entry(ce);
"reset --merge": fix unmerged case Commit 9e8ecea (Add 'merge' mode to 'git reset', 2008-12-01) disallowed "git reset --merge" when there was unmerged entries. But it wished if unmerged entries were reset as if --hard (instead of --merge) has been used. This makes sense because all "mergy" operations makes sure that any path involved in the merge does not have local modifications before starting, so resetting such a path away won't lose any information. The previous commit changed the behavior of --merge to accept resetting unmerged entries if they are reset to a different state than HEAD, but it did not reset the changes in the work tree, leaving the conflict markers in the resulting file in the work tree. Fix it by doing three things: - Update the documentation to match the wish of original "reset --merge" better, namely, "An unmerged entry is a sign that the path didn't have any local modification and can be safely resetted to whatever the new HEAD records"; - Update read_index_unmerged(), which reads the index file into the cache while dropping any higher-stage entries down to stage #0, not to copy the object name from the higher stage entry. The code used to take the object name from the a stage entry ("base" if you happened to have stage #1, or "ours" if both sides added, etc.), which essentially meant that you are getting random results depending on what the merge did. The _only_ reason we want to keep a previously unmerged entry in the index at stage #0 is so that we don't forget the fact that we have corresponding file in the work tree in order to be able to remove it when the tree we are resetting to does not have the path. In order to differentiate such an entry from ordinary cache entry, the cache entry added by read_index_unmerged() is marked as CE_CONFLICTED. - Update merged_entry() and deleted_entry() so that they pay attention to cache entries marked as CE_CONFLICTED. They are previously unmerged entries, and the files in the work tree that correspond to them are resetted away by oneway_merge() to the version from the tree we are resetting to. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-01 08:04:04 +01:00
if (!old) {
/*
* New index entries. In sparse checkout, the following
* verify_absent() will be delayed until after
* traverse_trees() finishes in unpack_trees(), then:
*
* - CE_NEW_SKIP_WORKTREE will be computed correctly
* - verify_absent() be called again, this time with
* correct CE_NEW_SKIP_WORKTREE
*
* verify_absent() call here does nothing in sparse
* checkout (i.e. o->skip_sparse_checkout == 0)
*/
update |= CE_ADDED;
merge->ce_flags |= CE_NEW_SKIP_WORKTREE;
if (verify_absent(merge,
ERROR_WOULD_LOSE_UNTRACKED_OVERWRITTEN, o)) {
free(merge);
"reset --merge": fix unmerged case Commit 9e8ecea (Add 'merge' mode to 'git reset', 2008-12-01) disallowed "git reset --merge" when there was unmerged entries. But it wished if unmerged entries were reset as if --hard (instead of --merge) has been used. This makes sense because all "mergy" operations makes sure that any path involved in the merge does not have local modifications before starting, so resetting such a path away won't lose any information. The previous commit changed the behavior of --merge to accept resetting unmerged entries if they are reset to a different state than HEAD, but it did not reset the changes in the work tree, leaving the conflict markers in the resulting file in the work tree. Fix it by doing three things: - Update the documentation to match the wish of original "reset --merge" better, namely, "An unmerged entry is a sign that the path didn't have any local modification and can be safely resetted to whatever the new HEAD records"; - Update read_index_unmerged(), which reads the index file into the cache while dropping any higher-stage entries down to stage #0, not to copy the object name from the higher stage entry. The code used to take the object name from the a stage entry ("base" if you happened to have stage #1, or "ours" if both sides added, etc.), which essentially meant that you are getting random results depending on what the merge did. The _only_ reason we want to keep a previously unmerged entry in the index at stage #0 is so that we don't forget the fact that we have corresponding file in the work tree in order to be able to remove it when the tree we are resetting to does not have the path. In order to differentiate such an entry from ordinary cache entry, the cache entry added by read_index_unmerged() is marked as CE_CONFLICTED. - Update merged_entry() and deleted_entry() so that they pay attention to cache entries marked as CE_CONFLICTED. They are previously unmerged entries, and the files in the work tree that correspond to them are resetted away by oneway_merge() to the version from the tree we are resetting to. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-01 08:04:04 +01:00
return -1;
}
"reset --merge": fix unmerged case Commit 9e8ecea (Add 'merge' mode to 'git reset', 2008-12-01) disallowed "git reset --merge" when there was unmerged entries. But it wished if unmerged entries were reset as if --hard (instead of --merge) has been used. This makes sense because all "mergy" operations makes sure that any path involved in the merge does not have local modifications before starting, so resetting such a path away won't lose any information. The previous commit changed the behavior of --merge to accept resetting unmerged entries if they are reset to a different state than HEAD, but it did not reset the changes in the work tree, leaving the conflict markers in the resulting file in the work tree. Fix it by doing three things: - Update the documentation to match the wish of original "reset --merge" better, namely, "An unmerged entry is a sign that the path didn't have any local modification and can be safely resetted to whatever the new HEAD records"; - Update read_index_unmerged(), which reads the index file into the cache while dropping any higher-stage entries down to stage #0, not to copy the object name from the higher stage entry. The code used to take the object name from the a stage entry ("base" if you happened to have stage #1, or "ours" if both sides added, etc.), which essentially meant that you are getting random results depending on what the merge did. The _only_ reason we want to keep a previously unmerged entry in the index at stage #0 is so that we don't forget the fact that we have corresponding file in the work tree in order to be able to remove it when the tree we are resetting to does not have the path. In order to differentiate such an entry from ordinary cache entry, the cache entry added by read_index_unmerged() is marked as CE_CONFLICTED. - Update merged_entry() and deleted_entry() so that they pay attention to cache entries marked as CE_CONFLICTED. They are previously unmerged entries, and the files in the work tree that correspond to them are resetted away by oneway_merge() to the version from the tree we are resetting to. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-01 08:04:04 +01:00
invalidate_ce_path(merge, o);
} else if (!(old->ce_flags & CE_CONFLICTED)) {
/*
* See if we can re-use the old CE directly?
* That way we get the uptodate stat info.
*
* This also removes the UPDATE flag on a match; otherwise
* we will end up overwriting local changes in the work tree.
*/
if (same(old, merge)) {
copy_cache_entry(merge, old);
update = 0;
} else {
if (verify_uptodate(old, o)) {
free(merge);
return -1;
}
/* Migrate old flags over */
update |= old->ce_flags & (CE_SKIP_WORKTREE | CE_NEW_SKIP_WORKTREE);
invalidate_ce_path(old, o);
}
"reset --merge": fix unmerged case Commit 9e8ecea (Add 'merge' mode to 'git reset', 2008-12-01) disallowed "git reset --merge" when there was unmerged entries. But it wished if unmerged entries were reset as if --hard (instead of --merge) has been used. This makes sense because all "mergy" operations makes sure that any path involved in the merge does not have local modifications before starting, so resetting such a path away won't lose any information. The previous commit changed the behavior of --merge to accept resetting unmerged entries if they are reset to a different state than HEAD, but it did not reset the changes in the work tree, leaving the conflict markers in the resulting file in the work tree. Fix it by doing three things: - Update the documentation to match the wish of original "reset --merge" better, namely, "An unmerged entry is a sign that the path didn't have any local modification and can be safely resetted to whatever the new HEAD records"; - Update read_index_unmerged(), which reads the index file into the cache while dropping any higher-stage entries down to stage #0, not to copy the object name from the higher stage entry. The code used to take the object name from the a stage entry ("base" if you happened to have stage #1, or "ours" if both sides added, etc.), which essentially meant that you are getting random results depending on what the merge did. The _only_ reason we want to keep a previously unmerged entry in the index at stage #0 is so that we don't forget the fact that we have corresponding file in the work tree in order to be able to remove it when the tree we are resetting to does not have the path. In order to differentiate such an entry from ordinary cache entry, the cache entry added by read_index_unmerged() is marked as CE_CONFLICTED. - Update merged_entry() and deleted_entry() so that they pay attention to cache entries marked as CE_CONFLICTED. They are previously unmerged entries, and the files in the work tree that correspond to them are resetted away by oneway_merge() to the version from the tree we are resetting to. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-01 08:04:04 +01:00
} else {
/*
* Previously unmerged entry left as an existence
* marker by read_index_unmerged();
*/
invalidate_ce_path(old, o);
}
do_add_entry(o, merge, update, CE_STAGEMASK);
return 1;
}
static int deleted_entry(const struct cache_entry *ce,
const struct cache_entry *old,
struct unpack_trees_options *o)
{
/* Did it exist in the index? */
if (!old) {
if (verify_absent(ce, ERROR_WOULD_LOSE_UNTRACKED_REMOVED, o))
return -1;
return 0;
}
"reset --merge": fix unmerged case Commit 9e8ecea (Add 'merge' mode to 'git reset', 2008-12-01) disallowed "git reset --merge" when there was unmerged entries. But it wished if unmerged entries were reset as if --hard (instead of --merge) has been used. This makes sense because all "mergy" operations makes sure that any path involved in the merge does not have local modifications before starting, so resetting such a path away won't lose any information. The previous commit changed the behavior of --merge to accept resetting unmerged entries if they are reset to a different state than HEAD, but it did not reset the changes in the work tree, leaving the conflict markers in the resulting file in the work tree. Fix it by doing three things: - Update the documentation to match the wish of original "reset --merge" better, namely, "An unmerged entry is a sign that the path didn't have any local modification and can be safely resetted to whatever the new HEAD records"; - Update read_index_unmerged(), which reads the index file into the cache while dropping any higher-stage entries down to stage #0, not to copy the object name from the higher stage entry. The code used to take the object name from the a stage entry ("base" if you happened to have stage #1, or "ours" if both sides added, etc.), which essentially meant that you are getting random results depending on what the merge did. The _only_ reason we want to keep a previously unmerged entry in the index at stage #0 is so that we don't forget the fact that we have corresponding file in the work tree in order to be able to remove it when the tree we are resetting to does not have the path. In order to differentiate such an entry from ordinary cache entry, the cache entry added by read_index_unmerged() is marked as CE_CONFLICTED. - Update merged_entry() and deleted_entry() so that they pay attention to cache entries marked as CE_CONFLICTED. They are previously unmerged entries, and the files in the work tree that correspond to them are resetted away by oneway_merge() to the version from the tree we are resetting to. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-01-01 08:04:04 +01:00
if (!(old->ce_flags & CE_CONFLICTED) && verify_uptodate(old, o))
return -1;
add_entry(o, ce, CE_REMOVE, 0);
invalidate_ce_path(ce, o);
return 1;
}
static int keep_entry(const struct cache_entry *ce,
struct unpack_trees_options *o)
{
add_entry(o, ce, 0, 0);
return 1;
}
#if DBRT_DEBUG
static void show_stage_entry(FILE *o,
const char *label, const struct cache_entry *ce)
{
if (!ce)
fprintf(o, "%s (missing)\n", label);
else
fprintf(o, "%s%06o %s %d\t%s\n",
label,
ce->ce_mode,
sha1_to_hex(ce->sha1),
ce_stage(ce),
ce->name);
}
#endif
int threeway_merge(const struct cache_entry * const *stages,
struct unpack_trees_options *o)
{
const struct cache_entry *index;
const struct cache_entry *head;
const struct cache_entry *remote = stages[o->head_idx + 1];
int count;
int head_match = 0;
int remote_match = 0;
int df_conflict_head = 0;
int df_conflict_remote = 0;
int any_anc_missing = 0;
int no_anc_exists = 1;
int i;
for (i = 1; i < o->head_idx; i++) {
if (!stages[i] || stages[i] == o->df_conflict_entry)
any_anc_missing = 1;
else
no_anc_exists = 0;
}
index = stages[0];
head = stages[o->head_idx];
if (head == o->df_conflict_entry) {
df_conflict_head = 1;
head = NULL;
}
if (remote == o->df_conflict_entry) {
df_conflict_remote = 1;
remote = NULL;
}
/*
* First, if there's a #16 situation, note that to prevent #13
* and #14.
*/
if (!same(remote, head)) {
for (i = 1; i < o->head_idx; i++) {
if (same(stages[i], head)) {
head_match = i;
}
if (same(stages[i], remote)) {
remote_match = i;
}
}
}
/*
* We start with cases where the index is allowed to match
* something other than the head: #14(ALT) and #2ALT, where it
* is permitted to match the result instead.
*/
/* #14, #14ALT, #2ALT */
if (remote && !df_conflict_head && head_match && !remote_match) {
if (index && !same(index, remote) && !same(index, head))
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
return o->gently ? -1 : reject_merge(index, o);
return merged_entry(remote, index, o);
}
/*
* If we have an entry in the index cache, then we want to
* make sure that it matches head.
*/
if (index && !same(index, head))
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
return o->gently ? -1 : reject_merge(index, o);
if (head) {
/* #5ALT, #15 */
if (same(head, remote))
return merged_entry(head, index, o);
/* #13, #3ALT */
if (!df_conflict_remote && remote_match && !head_match)
return merged_entry(head, index, o);
}
/* #1 */
if (!head && !remote && any_anc_missing)
return 0;
/*
* Under the "aggressive" rule, we resolve mostly trivial
* cases that we historically had git-merge-one-file resolve.
*/
if (o->aggressive) {
int head_deleted = !head;
int remote_deleted = !remote;
const struct cache_entry *ce = NULL;
if (index)
ce = index;
else if (head)
ce = head;
else if (remote)
ce = remote;
else {
for (i = 1; i < o->head_idx; i++) {
if (stages[i] && stages[i] != o->df_conflict_entry) {
ce = stages[i];
break;
}
}
}
/*
* Deleted in both.
* Deleted in one and unchanged in the other.
*/
if ((head_deleted && remote_deleted) ||
(head_deleted && remote && remote_match) ||
(remote_deleted && head && head_match)) {
if (index)
return deleted_entry(index, index, o);
if (ce && !head_deleted) {
if (verify_absent(ce, ERROR_WOULD_LOSE_UNTRACKED_REMOVED, o))
return -1;
}
return 0;
}
/*
* Added in both, identically.
*/
if (no_anc_exists && head && remote && same(head, remote))
return merged_entry(head, index, o);
}
/* Below are "no merge" cases, which require that the index be
* up-to-date to avoid the files getting overwritten with
* conflict resolution files.
*/
if (index) {
if (verify_uptodate(index, o))
return -1;
}
o->nontrivial_merge = 1;
/* #2, #3, #4, #6, #7, #9, #10, #11. */
count = 0;
if (!head_match || !remote_match) {
for (i = 1; i < o->head_idx; i++) {
if (stages[i] && stages[i] != o->df_conflict_entry) {
keep_entry(stages[i], o);
count++;
break;
}
}
}
#if DBRT_DEBUG
else {
fprintf(stderr, "read-tree: warning #16 detected\n");
show_stage_entry(stderr, "head ", stages[head_match]);
show_stage_entry(stderr, "remote ", stages[remote_match]);
}
#endif
if (head) { count += keep_entry(head, o); }
if (remote) { count += keep_entry(remote, o); }
return count;
}
/*
* Two-way merge.
*
* The rule is to "carry forward" what is in the index without losing
* information across a "fast-forward", favoring a successful merge
* over a merge failure when it makes sense. For details of the
* "carry forward" rule, please see <Documentation/git-read-tree.txt>.
*
*/
int twoway_merge(const struct cache_entry * const *src,
struct unpack_trees_options *o)
{
const struct cache_entry *current = src[0];
const struct cache_entry *oldtree = src[1];
const struct cache_entry *newtree = src[2];
if (o->merge_size != 2)
return error("Cannot do a twoway merge of %d trees",
o->merge_size);
if (oldtree == o->df_conflict_entry)
oldtree = NULL;
if (newtree == o->df_conflict_entry)
newtree = NULL;
if (current) {
if ((!oldtree && !newtree) || /* 4 and 5 */
(!oldtree && newtree &&
same(current, newtree)) || /* 6 and 7 */
(oldtree && newtree &&
same(oldtree, newtree)) || /* 14 and 15 */
(oldtree && newtree &&
!same(oldtree, newtree) && /* 18 and 19 */
same(current, newtree))) {
return keep_entry(current, o);
}
else if (oldtree && !newtree && same(current, oldtree)) {
/* 10 or 11 */
return deleted_entry(oldtree, current, o);
}
else if (oldtree && newtree &&
same(current, oldtree) && !same(current, newtree)) {
/* 20 or 21 */
return merged_entry(newtree, current, o);
}
else {
/* all other failures */
if (oldtree)
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
return o->gently ? -1 : reject_merge(oldtree, o);
if (current)
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
return o->gently ? -1 : reject_merge(current, o);
if (newtree)
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-17 21:03:49 +02:00
return o->gently ? -1 : reject_merge(newtree, o);
return -1;
}
}
else if (newtree) {
if (oldtree && !o->initial_checkout) {
/*
* deletion of the path was staged;
*/
if (same(oldtree, newtree))
return 1;
return reject_merge(oldtree, o);
}
return merged_entry(newtree, current, o);
}
return deleted_entry(oldtree, current, o);
}
/*
* Bind merge.
*
* Keep the index entries at stage0, collapse stage1 but make sure
* stage0 does not have anything there.
*/
int bind_merge(const struct cache_entry * const *src,
struct unpack_trees_options *o)
{
const struct cache_entry *old = src[0];
const struct cache_entry *a = src[1];
if (o->merge_size != 1)
return error("Cannot do a bind merge of %d trees",
o->merge_size);
if (a && old)
return o->gently ? -1 :
error(ERRORMSG(o, ERROR_BIND_OVERLAP), a->name, old->name);
if (!a)
return keep_entry(old, o);
else
return merged_entry(a, NULL, o);
}
/*
* One-way merge.
*
* The rule is:
* - take the stat information from stage0, take the data from stage1
*/
int oneway_merge(const struct cache_entry * const *src,
struct unpack_trees_options *o)
{
const struct cache_entry *old = src[0];
const struct cache_entry *a = src[1];
if (o->merge_size != 1)
return error("Cannot do a oneway merge of %d trees",
o->merge_size);
if (!a || a == o->df_conflict_entry)
return deleted_entry(old, old, o);
if (old && same(old, a)) {
int update = 0;
if (o->reset && o->update && !ce_uptodate(old) && !ce_skip_worktree(old)) {
struct stat st;
if (lstat(old->name, &st) ||
ie_match_stat(o->src_index, old, &st, CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE))
update |= CE_UPDATE;
}
add_entry(o, old, update, 0);
return 0;
}
return merged_entry(a, old, o);
}