git/commit.h

391 lines
13 KiB
C
Raw Normal View History

#ifndef COMMIT_H
#define COMMIT_H
#include "object.h"
#include "tree.h"
#include "strbuf.h"
#include "decorate.h"
#include "gpg-interface.h"
#include "string-list.h"
struct commit_list {
struct commit *item;
struct commit_list *next;
};
struct commit {
struct object object;
void *util;
unsigned int index;
unsigned long date;
struct commit_list *parents;
struct tree *tree;
};
[PATCH] Avoid wasting memory in git-rev-list As pointed out on the list, git-rev-list can use a lot of memory. One low-hanging fruit is to free the commit buffer for commits that we parse. By default, parse_commit() will save away the buffer, since a lot of cases do want it, and re-reading it continually would be unnecessary. However, in many cases the buffer isn't actually necessary and saving it just wastes memory. We could just free the buffer ourselves, but especially in git-rev-list, we actually end up using the helper functions that automatically add parent commits to the commit lists, so we don't actually control the commit parsing directly. Instead, just make this behaviour of "parse_commit()" a global flag. Maybe this is a bit tasteless, but it's very simple, and it makes a noticable difference in memory usage. Before the change: [torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null 0.26user 0.02system 0:00.28elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+3714minor)pagefaults 0swaps after the change: [torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null 0.26user 0.00system 0:00.27elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2433minor)pagefaults 0swaps note how the minor faults have decreased from 3714 pages to 2433 pages. That's all due to the fewer anonymous pages allocated to hold the comment buffers and their metadata. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2005-09-16 05:43:17 +08:00
extern int save_commit_buffer;
extern const char *commit_type;
/* While we can decorate any object with a name, it's only used for commits.. */
struct name_decoration {
struct name_decoration *next;
int type;
char name[FLEX_ARRAY];
};
enum decoration_type {
DECORATION_NONE = 0,
DECORATION_REF_LOCAL,
DECORATION_REF_REMOTE,
DECORATION_REF_TAG,
DECORATION_REF_STASH,
DECORATION_REF_HEAD,
DECORATION_GRAFTED,
};
void add_name_decoration(enum decoration_type type, const char *name, struct object *obj);
const struct name_decoration *get_name_decoration(const struct object *obj);
struct commit *lookup_commit(const unsigned char *sha1);
struct commit *lookup_commit_reference(const unsigned char *sha1);
struct commit *lookup_commit_reference_gently(const unsigned char *sha1,
int quiet);
struct commit *lookup_commit_reference_by_name(const char *name);
/*
* Look up object named by "sha1", dereference tag as necessary,
* get a commit and return it. If "sha1" does not dereference to
* a commit, use ref_name to report an error and die.
*/
struct commit *lookup_commit_or_die(const unsigned char *sha1, const char *ref_name);
int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long size);
int parse_commit_gently(struct commit *item, int quiet_on_missing);
static inline int parse_commit(struct commit *item)
{
return parse_commit_gently(item, 0);
}
void parse_commit_or_die(struct commit *item);
/*
* Associate an object buffer with the commit. The ownership of the
* memory is handed over to the commit, and must be free()-able.
*/
void set_commit_buffer(struct commit *, void *buffer, unsigned long size);
/*
* Get any cached object buffer associated with the commit. Returns NULL
* if none. The resulting memory should not be freed.
*/
const void *get_cached_commit_buffer(const struct commit *, unsigned long *size);
/*
* Get the commit's object contents, either from cache or by reading the object
* from disk. The resulting memory should not be modified, and must be given
* to unuse_commit_buffer when the caller is done.
*/
const void *get_commit_buffer(const struct commit *, unsigned long *size);
/*
* Tell the commit subsytem that we are done with a particular commit buffer.
* The commit and buffer should be the input and return value, respectively,
* from an earlier call to get_commit_buffer. The buffer may or may not be
* freed by this call; callers should not access the memory afterwards.
*/
void unuse_commit_buffer(const struct commit *, const void *buffer);
/*
* Free any cached object buffer associated with the commit.
*/
void free_commit_buffer(struct commit *);
/*
* Disassociate any cached object buffer from the commit, but do not free it.
* The buffer (or NULL, if none) is returned.
*/
const void *detach_commit_buffer(struct commit *, unsigned long *sizep);
/* Find beginning and length of commit subject. */
int find_commit_subject(const char *commit_buffer, const char **subject);
struct commit_list *commit_list_insert(struct commit *item,
struct commit_list **list);
struct commit_list **commit_list_append(struct commit *commit,
struct commit_list **next);
unsigned commit_list_count(const struct commit_list *l);
struct commit_list *commit_list_insert_by_date(struct commit *item,
struct commit_list **list);
void commit_list_sort_by_date(struct commit_list **list);
log: use true parents for diff even when rewriting When using pathspec filtering in combination with diff-based log output, parent simplification happens before the diff is computed. The diff is therefore against the *simplified* parents. This works okay, arguably by accident, in the normal case: simplification reduces to one parent as long as the commit is TREESAME to it. So the simplified parent of any given commit must have the same tree contents on the filtered paths as its true (unfiltered) parent. However, --full-diff breaks this guarantee, and indeed gives pretty spectacular results when comparing the output of git log --graph --stat ... git log --graph --full-diff --stat ... (--graph internally kicks in parent simplification, much like --parents). To fix it, store a copy of the parent list before simplification (in a slab) whenever --full-diff is in effect. Then use the stored parents instead of the simplified ones in the commit display code paths. The latter do not actually check for --full-diff to avoid duplicated code; they just grab the original parents if save_parents() has not been called for this revision walk. For ordinary commits it should be obvious that this is the right thing to do. Merge commits are a bit subtle. Observe that with default simplification, merge simplification is an all-or-nothing decision: either the merge is TREESAME to one parent and disappears, or it is different from all parents and the parent list remains intact. Redundant parents are not pruned, so the existing code also shows them as a merge. So if we do show a merge commit, the parent list just consists of the rewrite result on each parent. Running, e.g., --cc on this in --full-diff mode is not very useful: if any commits were skipped, some hunks will disagree with all sides of the merge (with one side, because commits were skipped; with the others, because they didn't have those changes in the first place). This triggers --cc showing these hunks spuriously. Therefore I believe that even for merge commits it is better to show the diffs wrt. the original parents. Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Thomas Rast <trast@inf.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-01 04:13:20 +08:00
/* Shallow copy of the input list */
struct commit_list *copy_commit_list(struct commit_list *list);
void free_commit_list(struct commit_list *list);
/* Commit formats */
enum cmit_fmt {
CMIT_FMT_RAW,
CMIT_FMT_MEDIUM,
CMIT_FMT_DEFAULT = CMIT_FMT_MEDIUM,
CMIT_FMT_SHORT,
CMIT_FMT_FULL,
CMIT_FMT_FULLER,
CMIT_FMT_ONELINE,
CMIT_FMT_EMAIL,
CMIT_FMT_USERFORMAT,
CMIT_FMT_UNSPECIFIED
};
struct pretty_print_context {
/*
* Callers should tweak these to change the behavior of pp_* functions.
*/
enum cmit_fmt fmt;
int abbrev;
const char *subject;
const char *after_subject;
int preserve_subject;
convert "enum date_mode" into a struct In preparation for adding date modes that may carry extra information beyond the mode itself, this patch converts the date_mode enum into a struct. Most of the conversion is fairly straightforward; we pass the struct as a pointer and dereference the type field where necessary. Locations that declare a date_mode can use a "{}" constructor. However, the tricky case is where we use the enum labels as constants, like: show_date(t, tz, DATE_NORMAL); Ideally we could say: show_date(t, tz, &{ DATE_NORMAL }); but of course C does not allow that. Likewise, we cannot cast the constant to a struct, because we need to pass an actual address. Our options are basically: 1. Manually add a "struct date_mode d = { DATE_NORMAL }" definition to each caller, and pass "&d". This makes the callers uglier, because they sometimes do not even have their own scope (e.g., they are inside a switch statement). 2. Provide a pre-made global "date_normal" struct that can be passed by address. We'd also need "date_rfc2822", "date_iso8601", and so forth. But at least the ugliness is defined in one place. 3. Provide a wrapper that generates the correct struct on the fly. The big downside is that we end up pointing to a single global, which makes our wrapper non-reentrant. But show_date is already not reentrant, so it does not matter. This patch implements 3, along with a minor macro to keep the size of the callers sane. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-06-26 00:55:02 +08:00
struct date_mode date_mode;
unsigned date_mode_explicit:1;
int expand_tabs_in_log;
int need_8bit_cte;
char *notes_message;
struct reflog_walk_info *reflog_info;
const char *output_encoding;
struct string_list *mailmap;
int color;
struct ident_split *from_ident;
/*
* Fields below here are manipulated internally by pp_* functions and
* should not be counted on by callers.
*/
struct string_list in_body_headers;
};
struct userformat_want {
unsigned notes:1;
};
extern int has_non_ascii(const char *text);
struct rev_info; /* in revision.h, it circularly uses enum cmit_fmt */
extern const char *logmsg_reencode(const struct commit *commit,
char **commit_encoding,
const char *output_encoding);
extern void get_commit_format(const char *arg, struct rev_info *);
extern const char *format_subject(struct strbuf *sb, const char *msg,
const char *line_separator);
extern void userformat_find_requirements(const char *fmt, struct userformat_want *w);
extern int commit_format_is_empty(enum cmit_fmt);
extern void format_commit_message(const struct commit *commit,
const char *format, struct strbuf *sb,
const struct pretty_print_context *context);
extern void pretty_print_commit(struct pretty_print_context *pp,
const struct commit *commit,
struct strbuf *sb);
extern void pp_commit_easy(enum cmit_fmt fmt, const struct commit *commit,
struct strbuf *sb);
void pp_user_info(struct pretty_print_context *pp,
const char *what, struct strbuf *sb,
const char *line, const char *encoding);
void pp_title_line(struct pretty_print_context *pp,
const char **msg_p,
struct strbuf *sb,
const char *encoding,
int need_8bit_cte);
void pp_remainder(struct pretty_print_context *pp,
const char **msg_p,
struct strbuf *sb,
int indent);
/** Removes the first commit from a list sorted by date, and adds all
* of its parents.
**/
struct commit *pop_most_recent_commit(struct commit_list **list,
unsigned int mark);
[PATCH] Modify git-rev-list to linearise the commit history in merge order. This patch linearises the GIT commit history graph into merge order which is defined by invariants specified in Documentation/git-rev-list.txt. The linearisation produced by this patch is superior in an objective sense to that produced by the existing git-rev-list implementation in that the linearisation produced is guaranteed to have the minimum number of discontinuities, where a discontinuity is defined as an adjacent pair of commits in the output list which are not related in a direct child-parent relationship. With this patch a graph like this: a4 --- | \ \ | b4 | |/ | | a3 | | | | | a2 | | | | c3 | | | | | c2 | b3 | | | /| | b2 | | | c1 | | / | b1 a1 | | | a0 | | / root Sorts like this: = a4 | c3 | c2 | c1 ^ b4 | b3 | b2 | b1 ^ a3 | a2 | a1 | a0 = root Instead of this: = a4 | c3 ^ b4 | a3 ^ c2 ^ b3 ^ a2 ^ b2 ^ c1 ^ a1 ^ b1 ^ a0 = root A test script, t/t6000-rev-list.sh, includes a test which demonstrates that the linearisation produced by --merge-order has less discontinuities than the linearisation produced by git-rev-list without the --merge-order flag specified. To see this, do the following: cd t ./t6000-rev-list.sh cd trash cat actual-default-order cat actual-merge-order The existing behaviour of git-rev-list is preserved, by default. To obtain the modified behaviour, specify --merge-order or --merge-order --show-breaks on the command line. This version of the patch has been tested on the git repository and also on the linux-2.6 repository and has reasonable performance on both - ~50-100% slower than the original algorithm. This version of the patch has incorporated a functional equivalent of the Linus' output limiting algorithm into the merge-order algorithm itself. This operates per the notes associated with Linus' commit 337cb3fb8da45f10fe9a0c3cf571600f55ead2ce. This version has incorporated Linus' feedback regarding proposed changes to rev-list.c. (see: [PATCH] Factor out filtering in rev-list.c) This version has improved the way sort_first_epoch marks commits as uninteresting. For more details about this change, refer to Documentation/git-rev-list.txt and http://blackcubes.dyndns.org/epoch/. Signed-off-by: Jon Seymour <jon.seymour@gmail.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-06 23:39:40 +08:00
struct commit *pop_commit(struct commit_list **stack);
void clear_commit_marks(struct commit *commit, unsigned int mark);
void clear_commit_marks_many(int nr, struct commit **commit, unsigned int mark);
void clear_commit_marks_for_object_array(struct object_array *a, unsigned mark);
toposort: rename "lifo" field The primary invariant of sort_in_topological_order() is that a parent commit is not emitted until all children of it are. When traversing a forked history like this with "git log C E": A----B----C \ D----E we ensure that A is emitted after all of B, C, D, and E are done, B has to wait until C is done, and D has to wait until E is done. In some applications, however, we would further want to control how these child commits B, C, D and E on two parallel ancestry chains are shown. Most of the time, we would want to see C and B emitted together, and then E and D, and finally A (i.e. the --topo-order output). The "lifo" parameter of the sort_in_topological_order() function is used to control this behaviour. We start the traversal by knowing two commits, C and E. While keeping in mind that we also need to inspect E later, we pick C first to inspect, and we notice and record that B needs to be inspected. By structuring the "work to be done" set as a LIFO stack, we ensure that B is inspected next, before other in-flight commits we had known that we will need to inspect, e.g. E. When showing in --date-order, we would want to see commits ordered by timestamps, i.e. show C, E, B and D in this order before showing A, possibly mixing commits from two parallel histories together. When "lifo" parameter is set to false, the function keeps the "work to be done" set sorted in the date order to realize this semantics. After inspecting C, we add B to the "work to be done" set, but the next commit we inspect from the set is E which is newer than B. The name "lifo", however, is too strongly tied to the way how the function implements its behaviour, and does not describe what the behaviour _means_. Replace this field with an enum rev_sort_order, with two possible values: REV_SORT_IN_GRAPH_ORDER and REV_SORT_BY_COMMIT_DATE, and update the existing code. The mechanical replacement rule is: "lifo == 0" is equivalent to "sort_order == REV_SORT_BY_COMMIT_DATE" "lifo == 1" is equivalent to "sort_order == REV_SORT_IN_GRAPH_ORDER" Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-07 07:07:14 +08:00
enum rev_sort_order {
REV_SORT_IN_GRAPH_ORDER = 0,
REV_SORT_BY_COMMIT_DATE,
REV_SORT_BY_AUTHOR_DATE
toposort: rename "lifo" field The primary invariant of sort_in_topological_order() is that a parent commit is not emitted until all children of it are. When traversing a forked history like this with "git log C E": A----B----C \ D----E we ensure that A is emitted after all of B, C, D, and E are done, B has to wait until C is done, and D has to wait until E is done. In some applications, however, we would further want to control how these child commits B, C, D and E on two parallel ancestry chains are shown. Most of the time, we would want to see C and B emitted together, and then E and D, and finally A (i.e. the --topo-order output). The "lifo" parameter of the sort_in_topological_order() function is used to control this behaviour. We start the traversal by knowing two commits, C and E. While keeping in mind that we also need to inspect E later, we pick C first to inspect, and we notice and record that B needs to be inspected. By structuring the "work to be done" set as a LIFO stack, we ensure that B is inspected next, before other in-flight commits we had known that we will need to inspect, e.g. E. When showing in --date-order, we would want to see commits ordered by timestamps, i.e. show C, E, B and D in this order before showing A, possibly mixing commits from two parallel histories together. When "lifo" parameter is set to false, the function keeps the "work to be done" set sorted in the date order to realize this semantics. After inspecting C, we add B to the "work to be done" set, but the next commit we inspect from the set is E which is newer than B. The name "lifo", however, is too strongly tied to the way how the function implements its behaviour, and does not describe what the behaviour _means_. Replace this field with an enum rev_sort_order, with two possible values: REV_SORT_IN_GRAPH_ORDER and REV_SORT_BY_COMMIT_DATE, and update the existing code. The mechanical replacement rule is: "lifo == 0" is equivalent to "sort_order == REV_SORT_BY_COMMIT_DATE" "lifo == 1" is equivalent to "sort_order == REV_SORT_IN_GRAPH_ORDER" Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-07 07:07:14 +08:00
};
/*
* Performs an in-place topological sort of list supplied.
*
* invariant of resulting list is:
* a reachable from b => ord(b) < ord(a)
toposort: rename "lifo" field The primary invariant of sort_in_topological_order() is that a parent commit is not emitted until all children of it are. When traversing a forked history like this with "git log C E": A----B----C \ D----E we ensure that A is emitted after all of B, C, D, and E are done, B has to wait until C is done, and D has to wait until E is done. In some applications, however, we would further want to control how these child commits B, C, D and E on two parallel ancestry chains are shown. Most of the time, we would want to see C and B emitted together, and then E and D, and finally A (i.e. the --topo-order output). The "lifo" parameter of the sort_in_topological_order() function is used to control this behaviour. We start the traversal by knowing two commits, C and E. While keeping in mind that we also need to inspect E later, we pick C first to inspect, and we notice and record that B needs to be inspected. By structuring the "work to be done" set as a LIFO stack, we ensure that B is inspected next, before other in-flight commits we had known that we will need to inspect, e.g. E. When showing in --date-order, we would want to see commits ordered by timestamps, i.e. show C, E, B and D in this order before showing A, possibly mixing commits from two parallel histories together. When "lifo" parameter is set to false, the function keeps the "work to be done" set sorted in the date order to realize this semantics. After inspecting C, we add B to the "work to be done" set, but the next commit we inspect from the set is E which is newer than B. The name "lifo", however, is too strongly tied to the way how the function implements its behaviour, and does not describe what the behaviour _means_. Replace this field with an enum rev_sort_order, with two possible values: REV_SORT_IN_GRAPH_ORDER and REV_SORT_BY_COMMIT_DATE, and update the existing code. The mechanical replacement rule is: "lifo == 0" is equivalent to "sort_order == REV_SORT_BY_COMMIT_DATE" "lifo == 1" is equivalent to "sort_order == REV_SORT_IN_GRAPH_ORDER" Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-07 07:07:14 +08:00
* sort_order further specifies:
* REV_SORT_IN_GRAPH_ORDER: try to show a commit on a single-parent
* chain together.
* REV_SORT_BY_COMMIT_DATE: show eligible commits in committer-date order.
*/
toposort: rename "lifo" field The primary invariant of sort_in_topological_order() is that a parent commit is not emitted until all children of it are. When traversing a forked history like this with "git log C E": A----B----C \ D----E we ensure that A is emitted after all of B, C, D, and E are done, B has to wait until C is done, and D has to wait until E is done. In some applications, however, we would further want to control how these child commits B, C, D and E on two parallel ancestry chains are shown. Most of the time, we would want to see C and B emitted together, and then E and D, and finally A (i.e. the --topo-order output). The "lifo" parameter of the sort_in_topological_order() function is used to control this behaviour. We start the traversal by knowing two commits, C and E. While keeping in mind that we also need to inspect E later, we pick C first to inspect, and we notice and record that B needs to be inspected. By structuring the "work to be done" set as a LIFO stack, we ensure that B is inspected next, before other in-flight commits we had known that we will need to inspect, e.g. E. When showing in --date-order, we would want to see commits ordered by timestamps, i.e. show C, E, B and D in this order before showing A, possibly mixing commits from two parallel histories together. When "lifo" parameter is set to false, the function keeps the "work to be done" set sorted in the date order to realize this semantics. After inspecting C, we add B to the "work to be done" set, but the next commit we inspect from the set is E which is newer than B. The name "lifo", however, is too strongly tied to the way how the function implements its behaviour, and does not describe what the behaviour _means_. Replace this field with an enum rev_sort_order, with two possible values: REV_SORT_IN_GRAPH_ORDER and REV_SORT_BY_COMMIT_DATE, and update the existing code. The mechanical replacement rule is: "lifo == 0" is equivalent to "sort_order == REV_SORT_BY_COMMIT_DATE" "lifo == 1" is equivalent to "sort_order == REV_SORT_IN_GRAPH_ORDER" Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-07 07:07:14 +08:00
void sort_in_topological_order(struct commit_list **, enum rev_sort_order);
struct commit_graft {
struct object_id oid;
int nr_parent; /* < 0 if shallow commit */
struct object_id parent[FLEX_ARRAY]; /* more */
};
typedef int (*each_commit_graft_fn)(const struct commit_graft *, void *);
struct commit_graft *read_graft_line(char *buf, int len);
int register_commit_graft(struct commit_graft *, int);
struct commit_graft *lookup_commit_graft(const unsigned char *sha1);
extern struct commit_list *get_merge_bases(struct commit *rev1, struct commit *rev2);
extern struct commit_list *get_merge_bases_many(struct commit *one, int n, struct commit **twos);
extern struct commit_list *get_octopus_merge_bases(struct commit_list *in);
/* To be used only when object flags after this call no longer matter */
extern struct commit_list *get_merge_bases_many_dirty(struct commit *one, int n, struct commit **twos);
/* largest positive number a signed 32-bit integer can contain */
#define INFINITE_DEPTH 0x7fffffff
shallow.c: the 8 steps to select new commits for .git/shallow Suppose a fetch or push is requested between two shallow repositories (with no history deepening or shortening). A pack that contains necessary objects is transferred over together with .git/shallow of the sender. The receiver has to determine whether it needs to update .git/shallow if new refs needs new shallow comits. The rule here is avoid updating .git/shallow by default. But we don't want to waste the received pack. If the pack contains two refs, one needs new shallow commits installed in .git/shallow and one does not, we keep the latter and reject/warn about the former. Even if .git/shallow update is allowed, we only add shallow commits strictly necessary for the former ref (remember the sender can send more shallow commits than necessary) and pay attention not to accidentally cut the receiver history short (no history shortening is asked for) So the steps to figure out what ref need what new shallow commits are: 1. Split the sender shallow commit list into "ours" and "theirs" list by has_sha1_file. Those that exist in current repo in "ours", the remaining in "theirs". 2. Check the receiver .git/shallow, remove from "ours" the ones that also exist in .git/shallow. 3. Fetch the new pack. Either install or unpack it. 4. Do has_sha1_file on "theirs" list again. Drop the ones that fail has_sha1_file. Obviously the new pack does not need them. 5. If the pack is kept, remove from "ours" the ones that do not exist in the new pack. 6. Walk the new refs to answer the question "what shallow commits, both ours and theirs, are required in .git/shallow in order to add this ref?". Shallow commits not associated to any refs are removed from their respective list. 7. (*) Check reachability (from the current refs) of all remaining commits in "ours". Those reachable are removed. We do not want to cut any part of our (reachable) history. We only check up commits. True reachability test is done by check_everything_connected() at the end as usual. 8. Combine the final "ours" and "theirs" and add them all to .git/shallow. Install new refs. The case where some hook rejects some refs on a push is explained in more detail in the push patches. Of these steps, #6 and #7 are expensive. Both require walking through some commits, or in the worst case all commits. And we rather avoid them in at least common case, where the transferred pack does not contain any shallow commits that the sender advertises. Let's look at each scenario: 1) the sender has longer history than the receiver All shallow commits from the sender will be put into "theirs" list at step 1 because none of them exists in current repo. In the common case, "theirs" becomes empty at step 4 and exit early. 2) the sender has shorter history than the receiver All shallow commits from the sender are likely in "ours" list at step 1. In the common case, if the new pack is kept, we could empty "ours" and exit early at step 5. If the pack is not kept, we hit the expensive step 6 then exit after "ours" is emptied. There'll be only a handful of objects to walk in fast-forward case. If it's forced update, we may need to walk to the bottom. 3) the sender has same .git/shallow as the receiver This is similar to case 2 except that "ours" should be emptied at step 2 and exit early. A fetch after "clone --depth=X" is case 1. A fetch after "clone" (from a shallow repo) is case 3. Luckily they're cheap for the common case. A push from "clone --depth=X" falls into case 2, which is expensive. Some more work may be done at the sender/client side to avoid more work on the server side: if the transferred pack does not contain any shallow commits, send-pack should not send any shallow commits to the receive-pack, effectively turning it into a normal push and avoid all steps. This patch implements all steps except #3, already handled by fetch-pack and receive-pack, #6 and #7, which has their own patch due to their size. (*) in previous versions step 7 was put before step 3. I reorder it so that the common case that keeps the pack does not need to walk commits at all. In future if we implement faster commit reachability check (maybe with the help of pack bitmaps or commit cache), step 7 could become cheap and be moved up before 6 again. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-05 21:02:35 +08:00
struct sha1_array;
struct ref;
extern int register_shallow(const unsigned char *sha1);
extern int unregister_shallow(const unsigned char *sha1);
extern int for_each_commit_graft(each_commit_graft_fn, void *);
extern int is_repository_shallow(void);
extern struct commit_list *get_shallow_commits(struct object_array *heads,
int depth, int shallow_flag, int not_shallow_flag);
extern void set_alternate_shallow_file(const char *path, int override);
extern int write_shallow_commits(struct strbuf *out, int use_pack_protocol,
const struct sha1_array *extra);
extern void setup_alternate_shallow(struct lock_file *shallow_lock,
const char **alternate_shallow_file,
const struct sha1_array *extra);
extern const char *setup_temporary_shallow(const struct sha1_array *extra);
make the sender advertise shallow commits to the receiver If either receive-pack or upload-pack is called on a shallow repository, shallow commits (*) will be sent after the ref advertisement (but before the packet flush), so that the receiver has the full "shape" of the sender's commit graph. This will be needed for the receiver to update its .git/shallow if necessary. This breaks the protocol for all clients trying to push to a shallow repo, or fetch from one. Which is basically the same end result as today's "is_repository_shallow() && die()" in receive-pack and upload-pack. New clients will be made aware of shallow upstream and can make use of this information. The sender must send all shallow commits that are sent in the following pack. It may send more shallow commits than necessary. upload-pack for example may choose to advertise no shallow commits if it knows in advance that the pack it's going to send contains no shallow commits. But upload-pack is the server, so we choose the cheaper way, send full .git/shallow and let the client deal with it. Smart HTTP is not affected by this patch. Shallow support on smart-http comes later separately. (*) A shallow commit is a commit that terminates the revision walker. It is usually put in .git/shallow in order to keep the revision walker from going out of bound because there is no guarantee that objects behind this commit is available. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-05 21:02:32 +08:00
extern void advertise_shallow_grafts(int);
shallow.c: the 8 steps to select new commits for .git/shallow Suppose a fetch or push is requested between two shallow repositories (with no history deepening or shortening). A pack that contains necessary objects is transferred over together with .git/shallow of the sender. The receiver has to determine whether it needs to update .git/shallow if new refs needs new shallow comits. The rule here is avoid updating .git/shallow by default. But we don't want to waste the received pack. If the pack contains two refs, one needs new shallow commits installed in .git/shallow and one does not, we keep the latter and reject/warn about the former. Even if .git/shallow update is allowed, we only add shallow commits strictly necessary for the former ref (remember the sender can send more shallow commits than necessary) and pay attention not to accidentally cut the receiver history short (no history shortening is asked for) So the steps to figure out what ref need what new shallow commits are: 1. Split the sender shallow commit list into "ours" and "theirs" list by has_sha1_file. Those that exist in current repo in "ours", the remaining in "theirs". 2. Check the receiver .git/shallow, remove from "ours" the ones that also exist in .git/shallow. 3. Fetch the new pack. Either install or unpack it. 4. Do has_sha1_file on "theirs" list again. Drop the ones that fail has_sha1_file. Obviously the new pack does not need them. 5. If the pack is kept, remove from "ours" the ones that do not exist in the new pack. 6. Walk the new refs to answer the question "what shallow commits, both ours and theirs, are required in .git/shallow in order to add this ref?". Shallow commits not associated to any refs are removed from their respective list. 7. (*) Check reachability (from the current refs) of all remaining commits in "ours". Those reachable are removed. We do not want to cut any part of our (reachable) history. We only check up commits. True reachability test is done by check_everything_connected() at the end as usual. 8. Combine the final "ours" and "theirs" and add them all to .git/shallow. Install new refs. The case where some hook rejects some refs on a push is explained in more detail in the push patches. Of these steps, #6 and #7 are expensive. Both require walking through some commits, or in the worst case all commits. And we rather avoid them in at least common case, where the transferred pack does not contain any shallow commits that the sender advertises. Let's look at each scenario: 1) the sender has longer history than the receiver All shallow commits from the sender will be put into "theirs" list at step 1 because none of them exists in current repo. In the common case, "theirs" becomes empty at step 4 and exit early. 2) the sender has shorter history than the receiver All shallow commits from the sender are likely in "ours" list at step 1. In the common case, if the new pack is kept, we could empty "ours" and exit early at step 5. If the pack is not kept, we hit the expensive step 6 then exit after "ours" is emptied. There'll be only a handful of objects to walk in fast-forward case. If it's forced update, we may need to walk to the bottom. 3) the sender has same .git/shallow as the receiver This is similar to case 2 except that "ours" should be emptied at step 2 and exit early. A fetch after "clone --depth=X" is case 1. A fetch after "clone" (from a shallow repo) is case 3. Luckily they're cheap for the common case. A push from "clone --depth=X" falls into case 2, which is expensive. Some more work may be done at the sender/client side to avoid more work on the server side: if the transferred pack does not contain any shallow commits, send-pack should not send any shallow commits to the receive-pack, effectively turning it into a normal push and avoid all steps. This patch implements all steps except #3, already handled by fetch-pack and receive-pack, #6 and #7, which has their own patch due to their size. (*) in previous versions step 7 was put before step 3. I reorder it so that the common case that keeps the pack does not need to walk commits at all. In future if we implement faster commit reachability check (maybe with the help of pack bitmaps or commit cache), step 7 could become cheap and be moved up before 6 again. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-05 21:02:35 +08:00
struct shallow_info {
struct sha1_array *shallow;
int *ours, nr_ours;
int *theirs, nr_theirs;
struct sha1_array *ref;
/* for receive-pack */
uint32_t **used_shallow;
int *need_reachability_test;
int *reachable;
int *shallow_ref;
struct commit **commits;
int nr_commits;
shallow.c: the 8 steps to select new commits for .git/shallow Suppose a fetch or push is requested between two shallow repositories (with no history deepening or shortening). A pack that contains necessary objects is transferred over together with .git/shallow of the sender. The receiver has to determine whether it needs to update .git/shallow if new refs needs new shallow comits. The rule here is avoid updating .git/shallow by default. But we don't want to waste the received pack. If the pack contains two refs, one needs new shallow commits installed in .git/shallow and one does not, we keep the latter and reject/warn about the former. Even if .git/shallow update is allowed, we only add shallow commits strictly necessary for the former ref (remember the sender can send more shallow commits than necessary) and pay attention not to accidentally cut the receiver history short (no history shortening is asked for) So the steps to figure out what ref need what new shallow commits are: 1. Split the sender shallow commit list into "ours" and "theirs" list by has_sha1_file. Those that exist in current repo in "ours", the remaining in "theirs". 2. Check the receiver .git/shallow, remove from "ours" the ones that also exist in .git/shallow. 3. Fetch the new pack. Either install or unpack it. 4. Do has_sha1_file on "theirs" list again. Drop the ones that fail has_sha1_file. Obviously the new pack does not need them. 5. If the pack is kept, remove from "ours" the ones that do not exist in the new pack. 6. Walk the new refs to answer the question "what shallow commits, both ours and theirs, are required in .git/shallow in order to add this ref?". Shallow commits not associated to any refs are removed from their respective list. 7. (*) Check reachability (from the current refs) of all remaining commits in "ours". Those reachable are removed. We do not want to cut any part of our (reachable) history. We only check up commits. True reachability test is done by check_everything_connected() at the end as usual. 8. Combine the final "ours" and "theirs" and add them all to .git/shallow. Install new refs. The case where some hook rejects some refs on a push is explained in more detail in the push patches. Of these steps, #6 and #7 are expensive. Both require walking through some commits, or in the worst case all commits. And we rather avoid them in at least common case, where the transferred pack does not contain any shallow commits that the sender advertises. Let's look at each scenario: 1) the sender has longer history than the receiver All shallow commits from the sender will be put into "theirs" list at step 1 because none of them exists in current repo. In the common case, "theirs" becomes empty at step 4 and exit early. 2) the sender has shorter history than the receiver All shallow commits from the sender are likely in "ours" list at step 1. In the common case, if the new pack is kept, we could empty "ours" and exit early at step 5. If the pack is not kept, we hit the expensive step 6 then exit after "ours" is emptied. There'll be only a handful of objects to walk in fast-forward case. If it's forced update, we may need to walk to the bottom. 3) the sender has same .git/shallow as the receiver This is similar to case 2 except that "ours" should be emptied at step 2 and exit early. A fetch after "clone --depth=X" is case 1. A fetch after "clone" (from a shallow repo) is case 3. Luckily they're cheap for the common case. A push from "clone --depth=X" falls into case 2, which is expensive. Some more work may be done at the sender/client side to avoid more work on the server side: if the transferred pack does not contain any shallow commits, send-pack should not send any shallow commits to the receive-pack, effectively turning it into a normal push and avoid all steps. This patch implements all steps except #3, already handled by fetch-pack and receive-pack, #6 and #7, which has their own patch due to their size. (*) in previous versions step 7 was put before step 3. I reorder it so that the common case that keeps the pack does not need to walk commits at all. In future if we implement faster commit reachability check (maybe with the help of pack bitmaps or commit cache), step 7 could become cheap and be moved up before 6 again. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-05 21:02:35 +08:00
};
extern void prepare_shallow_info(struct shallow_info *, struct sha1_array *);
extern void clear_shallow_info(struct shallow_info *);
extern void remove_nonexistent_theirs_shallow(struct shallow_info *);
extern void assign_shallow_commits_to_refs(struct shallow_info *info,
uint32_t **used,
int *ref_status);
extern int delayed_reachability_test(struct shallow_info *si, int c);
extern void prune_shallow(int show_only);
extern struct trace_key trace_shallow;
int is_descendant_of(struct commit *, struct commit_list *);
int in_merge_bases(struct commit *, struct commit *);
int in_merge_bases_many(struct commit *, int, struct commit **);
extern int interactive_add(int argc, const char **argv, const char *prefix, int patch);
extern int run_add_interactive(const char *revision, const char *patch_mode,
const struct pathspec *pathspec);
static inline int single_parent(struct commit *commit)
{
return commit->parents && !commit->parents->next;
}
struct commit_list *reduce_heads(struct commit_list *heads);
struct commit_extra_header {
struct commit_extra_header *next;
char *key;
char *value;
size_t len;
};
extern void append_merge_tag_headers(struct commit_list *parents,
struct commit_extra_header ***tail);
extern int commit_tree(const char *msg, size_t msg_len,
const unsigned char *tree,
struct commit_list *parents, unsigned char *ret,
commit: teach --gpg-sign option This uses the gpg-interface.[ch] to allow signing the commit, i.e. $ git commit --gpg-sign -m foo You need a passphrase to unlock the secret key for user: "Junio C Hamano <gitster@pobox.com>" 4096-bit RSA key, ID 96AFE6CB, created 2011-10-03 (main key ID 713660A7) [master 8457d13] foo 1 files changed, 1 insertions(+), 0 deletions(-) The lines of GPG detached signature are placed in a new multi-line header field, instead of tucking the signature block at the end of the commit log message text (similar to how signed tag is done), for multiple reasons: - The signature won't clutter output from "git log" and friends if it is in the extra header. If we place it at the end of the log message, we would need to teach "git log" and friends to strip the signature block with an option. - Teaching new versions of "git log" and "gitk" to optionally verify and show signatures is cleaner if we structurally know where the signature block is (instead of scanning in the commit log message). - The signature needs to be stripped upon various commit rewriting operations, e.g. rebase, filter-branch, etc. They all already ignore unknown headers, but if we place signature in the log message, all of these tools (and third-party tools) also need to learn how a signature block would look like. - When we added the optional encoding header, all the tools (both in tree and third-party) that acts on the raw commit object should have been fixed to ignore headers they do not understand, so it is not like that new header would be more likely to break than extra text in the commit. A commit made with the above sample sequence would look like this: $ git cat-file commit HEAD tree 3cd71d90e3db4136e5260ab54599791c4f883b9d parent b87755351a47b09cb27d6913e6e0e17e6254a4d4 author Junio C Hamano <gitster@pobox.com> 1317862251 -0700 committer Junio C Hamano <gitster@pobox.com> 1317862251 -0700 gpgsig -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (GNU/Linux) iQIcBAABAgAGBQJOjPtrAAoJELC16IaWr+bL4TMP/RSe2Y/jYnCkds9unO5JEnfG ... =dt98 -----END PGP SIGNATURE----- foo but "git log" (unless you ask for it with --pretty=raw) output is not cluttered with the signature information. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-06 08:23:20 +08:00
const char *author, const char *sign_commit);
extern int commit_tree_extended(const char *msg, size_t msg_len,
const unsigned char *tree,
struct commit_list *parents, unsigned char *ret,
commit: teach --gpg-sign option This uses the gpg-interface.[ch] to allow signing the commit, i.e. $ git commit --gpg-sign -m foo You need a passphrase to unlock the secret key for user: "Junio C Hamano <gitster@pobox.com>" 4096-bit RSA key, ID 96AFE6CB, created 2011-10-03 (main key ID 713660A7) [master 8457d13] foo 1 files changed, 1 insertions(+), 0 deletions(-) The lines of GPG detached signature are placed in a new multi-line header field, instead of tucking the signature block at the end of the commit log message text (similar to how signed tag is done), for multiple reasons: - The signature won't clutter output from "git log" and friends if it is in the extra header. If we place it at the end of the log message, we would need to teach "git log" and friends to strip the signature block with an option. - Teaching new versions of "git log" and "gitk" to optionally verify and show signatures is cleaner if we structurally know where the signature block is (instead of scanning in the commit log message). - The signature needs to be stripped upon various commit rewriting operations, e.g. rebase, filter-branch, etc. They all already ignore unknown headers, but if we place signature in the log message, all of these tools (and third-party tools) also need to learn how a signature block would look like. - When we added the optional encoding header, all the tools (both in tree and third-party) that acts on the raw commit object should have been fixed to ignore headers they do not understand, so it is not like that new header would be more likely to break than extra text in the commit. A commit made with the above sample sequence would look like this: $ git cat-file commit HEAD tree 3cd71d90e3db4136e5260ab54599791c4f883b9d parent b87755351a47b09cb27d6913e6e0e17e6254a4d4 author Junio C Hamano <gitster@pobox.com> 1317862251 -0700 committer Junio C Hamano <gitster@pobox.com> 1317862251 -0700 gpgsig -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (GNU/Linux) iQIcBAABAgAGBQJOjPtrAAoJELC16IaWr+bL4TMP/RSe2Y/jYnCkds9unO5JEnfG ... =dt98 -----END PGP SIGNATURE----- foo but "git log" (unless you ask for it with --pretty=raw) output is not cluttered with the signature information. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-06 08:23:20 +08:00
const char *author, const char *sign_commit,
struct commit_extra_header *);
extern struct commit_extra_header *read_commit_extra_headers(struct commit *, const char **);
extern void free_commit_extra_headers(struct commit_extra_header *extra);
/*
* Search the commit object contents given by "msg" for the header "key".
* Returns a pointer to the start of the header contents, or NULL. The length
* of the header, up to the first newline, is returned via out_len.
*
* Note that some headers (like mergetag) may be multi-line. It is the caller's
* responsibility to parse further in this case!
*/
extern const char *find_commit_header(const char *msg, const char *key,
size_t *out_len);
/* Find the end of the log message, the right place for a new trailer. */
extern int ignore_non_trailer(struct strbuf *sb);
typedef void (*each_mergetag_fn)(struct commit *commit, struct commit_extra_header *extra,
void *cb_data);
extern void for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data);
struct merge_remote_desc {
struct object *obj; /* the named object, could be a tag */
const char *name;
};
#define merge_remote_util(commit) ((struct merge_remote_desc *)((commit)->util))
/*
* Given "name" from the command line to merge, find the commit object
* and return it, while storing merge_remote_desc in its ->util field,
* to allow callers to tell if we are told to merge a tag.
*/
struct commit *get_merge_parent(const char *name);
reuse cached commit buffer when parsing signatures When we call show_signature or show_mergetag, we read the commit object fresh via read_sha1_file and reparse its headers. However, in most cases we already have the object data available, attached to the "struct commit". This is partially laziness in dealing with the memory allocation issues, but partially defensive programming, in that we would always want to verify a clean version of the buffer (not one that might have been munged by other users of the commit). However, we do not currently ever munge the commit buffer, and not using the already-available buffer carries a fairly big performance penalty when we are looking at a large number of commits. Here are timings on linux.git: [baseline, no signatures] $ time git log >/dev/null real 0m4.902s user 0m4.784s sys 0m0.120s [before] $ time git log --show-signature >/dev/null real 0m14.735s user 0m9.964s sys 0m0.944s [after] $ time git log --show-signature >/dev/null real 0m9.981s user 0m5.260s sys 0m0.936s Note that our user CPU time drops almost in half, close to the non-signature case, but we do still spend more wall-clock and system time, presumably from dealing with gpg. An alternative to this is to note that most commits do not have signatures (less than 1% in this repo), yet we pay the re-parsing cost for every commit just to find out if it has a mergetag or signature. If we checked that when parsing the commit initially, we could avoid re-examining most commits later on. Even if we did pursue that direction, however, this would still speed up the cases where we _do_ have signatures. So it's probably worth doing either way. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-06-13 14:32:11 +08:00
extern int parse_signed_commit(const struct commit *commit,
struct strbuf *message, struct strbuf *signature);
extern int remove_signature(struct strbuf *buf);
extern void print_commit_list(struct commit_list *list,
const char *format_cur,
const char *format_last);
/*
* Check the signature of the given commit. The result of the check is stored
* in sig->check_result, 'G' for a good signature, 'U' for a good signature
* from an untrusted signer, 'B' for a bad signature and 'N' for no signature
* at all. This may allocate memory for sig->gpg_output, sig->gpg_status,
* sig->signer and sig->key.
*/
extern int check_commit_signature(const struct commit *commit, struct signature_check *sigc);
int compare_commits_by_commit_date(const void *a_, const void *b_, void *unused);
LAST_ARG_MUST_BE_NULL
extern int run_commit_hook(int editor_is_used, const char *index_file, const char *name, ...);
#endif /* COMMIT_H */