git-commit-vandalism/list-objects.c

368 lines
9.9 KiB
C
Raw Normal View History

#include "cache.h"
#include "tag.h"
#include "commit.h"
#include "tree.h"
#include "blob.h"
#include "diff.h"
#include "tree-walk.h"
#include "revision.h"
#include "list-objects.h"
#include "list-objects-filter.h"
#include "list-objects-filter-options.h"
#include "packfile.h"
#include "object-store.h"
#include "trace.h"
struct traversal_context {
struct rev_info *revs;
show_object_fn show_object;
show_commit_fn show_commit;
void *show_data;
filter_object_fn filter_fn;
void *filter_data;
};
static void process_blob(struct traversal_context *ctx,
struct blob *blob,
struct strbuf *path,
const char *name)
{
struct object *obj = &blob->object;
size_t pathlen;
enum list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_DO_SHOW;
if (!ctx->revs->blob_objects)
return;
if (!obj)
die("bad blob object");
if (obj->flags & (UNINTERESTING | SEEN))
return;
/*
* Pre-filter known-missing objects when explicitly requested.
* Otherwise, a missing object error message may be reported
* later (depending on other filtering criteria).
*
* Note that this "--exclude-promisor-objects" pre-filtering
* may cause the actual filter to report an incomplete list
* of missing objects.
*/
if (ctx->revs->exclude_promisor_objects &&
!has_object_file(&obj->oid) &&
is_promisor_object(&obj->oid))
return;
pathlen = path->len;
strbuf_addstr(path, name);
if ((obj->flags & NOT_USER_GIVEN) && ctx->filter_fn)
r = ctx->filter_fn(LOFS_BLOB, obj,
path->buf, &path->buf[pathlen],
ctx->filter_data);
if (r & LOFR_MARK_SEEN)
obj->flags |= SEEN;
if (r & LOFR_DO_SHOW)
ctx->show_object(obj, path->buf, ctx->show_data);
strbuf_setlen(path, pathlen);
}
/*
* Processing a gitlink entry currently does nothing, since
* we do not recurse into the subproject.
*
* We *could* eventually add a flag that actually does that,
* which would involve:
* - is the subproject actually checked out?
* - if so, see if the subproject has already been added
* to the alternates list, and add it if not.
* - process the commit (or tag) the gitlink points to
* recursively.
*
* However, it's unclear whether there is really ever any
* reason to see superprojects and subprojects as such a
* "unified" object pool (potentially resulting in a totally
* humongous pack - avoiding which was the whole point of
* having gitlinks in the first place!).
*
* So for now, there is just a note that we *could* follow
* the link, and how to do it. Whether it necessarily makes
* any sense what-so-ever to ever do that is another issue.
*/
static void process_gitlink(struct traversal_context *ctx,
const unsigned char *sha1,
struct strbuf *path,
const char *name)
{
/* Nothing to do */
}
static void process_tree(struct traversal_context *ctx,
struct tree *tree,
struct strbuf *base,
const char *name);
static void process_tree_contents(struct traversal_context *ctx,
struct tree *tree,
struct strbuf *base)
{
struct tree_desc desc;
struct name_entry entry;
enum interesting match = ctx->revs->diffopt.pathspec.nr == 0 ?
all_entries_interesting : entry_not_interesting;
init_tree_desc(&desc, tree->buffer, tree->size);
while (tree_entry(&desc, &entry)) {
if (match != all_entries_interesting) {
match = tree_entry_interesting(&entry, base, 0,
&ctx->revs->diffopt.pathspec);
if (match == all_entries_not_interesting)
break;
if (match == entry_not_interesting)
continue;
}
if (S_ISDIR(entry.mode)) {
struct tree *t = lookup_tree(the_repository, entry.oid);
t->object.flags |= NOT_USER_GIVEN;
process_tree(ctx, t, base, entry.path);
}
else if (S_ISGITLINK(entry.mode))
process_gitlink(ctx, entry.oid->hash,
base, entry.path);
else {
struct blob *b = lookup_blob(the_repository, entry.oid);
b->object.flags |= NOT_USER_GIVEN;
process_blob(ctx, b, base, entry.path);
}
}
}
static void process_tree(struct traversal_context *ctx,
struct tree *tree,
struct strbuf *base,
const char *name)
{
struct object *obj = &tree->object;
struct rev_info *revs = ctx->revs;
int baselen = base->len;
enum list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_DO_SHOW;
int failed_parse;
if (!revs->tree_objects)
return;
if (!obj)
die("bad tree object");
if (obj->flags & (UNINTERESTING | SEEN))
return;
failed_parse = parse_tree_gently(tree, 1);
if (failed_parse) {
add `ignore_missing_links` mode to revwalk When pack-objects is computing the reachability bitmap to serve a fetch request, it can erroneously die() if some of the UNINTERESTING objects are not present. Upload-pack throws away HAVE lines from the client for objects we do not have, but we may have a tip object without all of its ancestors (e.g., if the tip is no longer reachable and was new enough to survive a `git prune`, but some of its reachable objects did get pruned). In the non-bitmap case, we do a revision walk with the HAVE objects marked as UNINTERESTING. The revision walker explicitly ignores errors in accessing UNINTERESTING commits to handle this case (and we do not bother looking at UNINTERESTING trees or blobs at all). When we have bitmaps, however, the process is quite different. The bitmap index for a pack-objects run is calculated in two separate steps: First, we perform an extensive walk from all the HAVEs to find the full set of objects reachable from them. This walk is usually optimized away because we are expected to hit an object with a bitmap during the traversal, which allows us to terminate early. Secondly, we perform an extensive walk from all the WANTs, which usually also terminates early because we hit a commit with an existing bitmap. Once we have the resulting bitmaps from the two walks, we AND-NOT them together to obtain the resulting set of objects we need to pack. When we are walking the HAVE objects, the revision walker does not know that we are walking it only to mark the results as uninteresting. We strip out the UNINTERESTING flag, because those objects _are_ interesting to us during the first walk. We want to keep going to get a complete set of reachable objects if we can. We need some way to tell the revision walker that it's OK to silently truncate the HAVE walk, just like it does for the UNINTERESTING case. This patch introduces a new `ignore_missing_links` flag to the `rev_info` struct, which we set only for the HAVE walk. It also adds tests to cover UNINTERESTING objects missing from several positions: a missing blob, a missing tree, and a missing parent commit. The missing blob already worked (as we do not care about its contents at all), but the other two cases caused us to die(). Note that there are a few cases we do not need to test: 1. We do not need to test a missing tree, with the blob still present. Without the tree that refers to it, we would not know that the blob is relevant to our walk. 2. We do not need to test a tip commit that is missing. Upload-pack omits these for us (and in fact, we complain even in the non-bitmap case if it fails to do so). Reported-by: Siddharth Agarwal <sid0@fb.com> Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-03-28 11:00:43 +01:00
if (revs->ignore_missing_links)
return;
/*
* Pre-filter known-missing tree objects when explicitly
* requested. This may cause the actual filter to report
* an incomplete list of missing objects.
*/
if (revs->exclude_promisor_objects &&
is_promisor_object(&obj->oid))
return;
if (!revs->do_not_die_on_missing_tree)
die("bad tree object %s", oid_to_hex(&obj->oid));
add `ignore_missing_links` mode to revwalk When pack-objects is computing the reachability bitmap to serve a fetch request, it can erroneously die() if some of the UNINTERESTING objects are not present. Upload-pack throws away HAVE lines from the client for objects we do not have, but we may have a tip object without all of its ancestors (e.g., if the tip is no longer reachable and was new enough to survive a `git prune`, but some of its reachable objects did get pruned). In the non-bitmap case, we do a revision walk with the HAVE objects marked as UNINTERESTING. The revision walker explicitly ignores errors in accessing UNINTERESTING commits to handle this case (and we do not bother looking at UNINTERESTING trees or blobs at all). When we have bitmaps, however, the process is quite different. The bitmap index for a pack-objects run is calculated in two separate steps: First, we perform an extensive walk from all the HAVEs to find the full set of objects reachable from them. This walk is usually optimized away because we are expected to hit an object with a bitmap during the traversal, which allows us to terminate early. Secondly, we perform an extensive walk from all the WANTs, which usually also terminates early because we hit a commit with an existing bitmap. Once we have the resulting bitmaps from the two walks, we AND-NOT them together to obtain the resulting set of objects we need to pack. When we are walking the HAVE objects, the revision walker does not know that we are walking it only to mark the results as uninteresting. We strip out the UNINTERESTING flag, because those objects _are_ interesting to us during the first walk. We want to keep going to get a complete set of reachable objects if we can. We need some way to tell the revision walker that it's OK to silently truncate the HAVE walk, just like it does for the UNINTERESTING case. This patch introduces a new `ignore_missing_links` flag to the `rev_info` struct, which we set only for the HAVE walk. It also adds tests to cover UNINTERESTING objects missing from several positions: a missing blob, a missing tree, and a missing parent commit. The missing blob already worked (as we do not care about its contents at all), but the other two cases caused us to die(). Note that there are a few cases we do not need to test: 1. We do not need to test a missing tree, with the blob still present. Without the tree that refers to it, we would not know that the blob is relevant to our walk. 2. We do not need to test a tip commit that is missing. Upload-pack omits these for us (and in fact, we complain even in the non-bitmap case if it fails to do so). Reported-by: Siddharth Agarwal <sid0@fb.com> Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-03-28 11:00:43 +01:00
}
list-objects: convert name_path to a strbuf The "struct name_path" data is examined in only two places: we generate it in process_tree(), and we convert it to a single string in path_name(). Everyone else just passes it through to those functions. We can further note that process_tree() already keeps a single strbuf with the leading tree path, for use with tree_entry_interesting(). Instead of building a separate name_path linked list, let's just use the one we already build in "base". This reduces the amount of code (especially tricky code in path_name() which did not check for integer overflows caused by deep or large pathnames). It is also more efficient in some instances. Any time we were using tree_entry_interesting, we were building up the strbuf anyway, so this is an immediate and obvious win there. In cases where we were not, we trade off storing "pathname/" in a strbuf on the heap for each level of the path, instead of two pointers and an int on the stack (with one pointer into the tree object). On a 64-bit system, the latter is 20 bytes; so if path components are less than that on average, this has lower peak memory usage. In practice it probably doesn't matter either way; we are already holding in memory all of the tree objects leading up to each pathname, and for normal-depth pathnames, we are only talking about hundreds of bytes. This patch leaves "struct name_path" as a thin wrapper around the strbuf, to avoid disrupting callbacks. We should fix them, but leaving it out makes this diff easier to view. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-02-11 23:26:18 +01:00
strbuf_addstr(base, name);
if ((obj->flags & NOT_USER_GIVEN) && ctx->filter_fn)
r = ctx->filter_fn(LOFS_BEGIN_TREE, obj,
base->buf, &base->buf[baselen],
ctx->filter_data);
if (r & LOFR_MARK_SEEN)
obj->flags |= SEEN;
if (r & LOFR_DO_SHOW)
ctx->show_object(obj, base->buf, ctx->show_data);
list-objects: convert name_path to a strbuf The "struct name_path" data is examined in only two places: we generate it in process_tree(), and we convert it to a single string in path_name(). Everyone else just passes it through to those functions. We can further note that process_tree() already keeps a single strbuf with the leading tree path, for use with tree_entry_interesting(). Instead of building a separate name_path linked list, let's just use the one we already build in "base". This reduces the amount of code (especially tricky code in path_name() which did not check for integer overflows caused by deep or large pathnames). It is also more efficient in some instances. Any time we were using tree_entry_interesting, we were building up the strbuf anyway, so this is an immediate and obvious win there. In cases where we were not, we trade off storing "pathname/" in a strbuf on the heap for each level of the path, instead of two pointers and an int on the stack (with one pointer into the tree object). On a 64-bit system, the latter is 20 bytes; so if path components are less than that on average, this has lower peak memory usage. In practice it probably doesn't matter either way; we are already holding in memory all of the tree objects leading up to each pathname, and for normal-depth pathnames, we are only talking about hundreds of bytes. This patch leaves "struct name_path" as a thin wrapper around the strbuf, to avoid disrupting callbacks. We should fix them, but leaving it out makes this diff easier to view. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-02-11 23:26:18 +01:00
if (base->len)
strbuf_addch(base, '/');
if (r & LOFR_SKIP_TREE)
trace_printf("Skipping contents of tree %s...\n", base->buf);
else if (!failed_parse)
process_tree_contents(ctx, tree, base);
if ((obj->flags & NOT_USER_GIVEN) && ctx->filter_fn) {
r = ctx->filter_fn(LOFS_END_TREE, obj,
base->buf, &base->buf[baselen],
ctx->filter_data);
if (r & LOFR_MARK_SEEN)
obj->flags |= SEEN;
if (r & LOFR_DO_SHOW)
ctx->show_object(obj, base->buf, ctx->show_data);
}
strbuf_setlen(base, baselen);
free_tree_buffer(tree);
}
static void mark_edge_parents_uninteresting(struct commit *commit,
struct rev_info *revs,
show_edge_fn show_edge)
{
struct commit_list *parents;
for (parents = commit->parents; parents; parents = parents->next) {
struct commit *parent = parents->item;
if (!(parent->object.flags & UNINTERESTING))
continue;
mark_tree_uninteresting(revs->repo, get_commit_tree(parent));
if (revs->edge_hint && !(parent->object.flags & SHOWN)) {
parent->object.flags |= SHOWN;
show_edge(parent);
}
}
}
void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge)
{
struct commit_list *list;
list-objects: mark more commits as edges in mark_edges_uninteresting The purpose of edge commits is to let pack-objects know what objects it can use as base, but does not need to include in the thin pack because the other side is supposed to already have them. So far we mark uninteresting parents of interesting commits as edges. But even an unrelated uninteresting commit (that the other side has) may become a good base for pack-objects and help produce more efficient packs. This is especially true for shallow clone, when the client issues a fetch with a depth smaller or equal to the number of commits the server is ahead of the client. For example, in this commit history the client has up to "A" and the server has up to "B": -------A---B have--^ ^ / want--+ If depth 1 is requested, the commit list to send to the client includes only B. The way m_e_u is working, it checks if parent commits of B are uninteresting, if so mark them as edges. Due to shallow effect, commit B is grafted to have no parents and the revision walker never sees A as the parent of B. In fact it marks no edges at all in this simple case and sends everything B has to the client even if it could have excluded what A and also the client already have. In a slightly different case where A is not a direct parent of B (iow there are commits in between A and B), marking A as an edge can still save some because B may still have stuff from the far ancestor A. There is another case from the earlier patch, when we deepen a ref from C->E to A->E: ---A---B C---D---E want--^ ^ ^ shallow-+ / have-------+ In this case we need to send A and B to the client, and C (i.e. the current shallow point that the client informs the server) is a very good base because it's closet to A and B. Normal m_e_u won't recognize C as an edge because it only looks back to parents (i.e. A<-B) not the opposite way B->C even if C is already marked as uninteresting commit by the previous patch. This patch includes all uninteresting commits from command line as edges and lets pack-objects decide what's best to do. The upside is we have better chance of producing better packs in certain cases. The downside is we may need to process some extra objects on the server side. For the shallow case on git.git, when the client is 5 commits behind and does "fetch --depth=3", the result pack is 99.26 KiB instead of 4.92 MiB. Reported-and-analyzed-by: Matthijs Kooijman <matthijs@stdin.nl> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-16 11:52:07 +02:00
int i;
for (list = revs->commits; list; list = list->next) {
struct commit *commit = list->item;
if (commit->object.flags & UNINTERESTING) {
mark_tree_uninteresting(revs->repo,
get_commit_tree(commit));
if (revs->edge_hint_aggressive && !(commit->object.flags & SHOWN)) {
list-objects: mark more commits as edges in mark_edges_uninteresting The purpose of edge commits is to let pack-objects know what objects it can use as base, but does not need to include in the thin pack because the other side is supposed to already have them. So far we mark uninteresting parents of interesting commits as edges. But even an unrelated uninteresting commit (that the other side has) may become a good base for pack-objects and help produce more efficient packs. This is especially true for shallow clone, when the client issues a fetch with a depth smaller or equal to the number of commits the server is ahead of the client. For example, in this commit history the client has up to "A" and the server has up to "B": -------A---B have--^ ^ / want--+ If depth 1 is requested, the commit list to send to the client includes only B. The way m_e_u is working, it checks if parent commits of B are uninteresting, if so mark them as edges. Due to shallow effect, commit B is grafted to have no parents and the revision walker never sees A as the parent of B. In fact it marks no edges at all in this simple case and sends everything B has to the client even if it could have excluded what A and also the client already have. In a slightly different case where A is not a direct parent of B (iow there are commits in between A and B), marking A as an edge can still save some because B may still have stuff from the far ancestor A. There is another case from the earlier patch, when we deepen a ref from C->E to A->E: ---A---B C---D---E want--^ ^ ^ shallow-+ / have-------+ In this case we need to send A and B to the client, and C (i.e. the current shallow point that the client informs the server) is a very good base because it's closet to A and B. Normal m_e_u won't recognize C as an edge because it only looks back to parents (i.e. A<-B) not the opposite way B->C even if C is already marked as uninteresting commit by the previous patch. This patch includes all uninteresting commits from command line as edges and lets pack-objects decide what's best to do. The upside is we have better chance of producing better packs in certain cases. The downside is we may need to process some extra objects on the server side. For the shallow case on git.git, when the client is 5 commits behind and does "fetch --depth=3", the result pack is 99.26 KiB instead of 4.92 MiB. Reported-and-analyzed-by: Matthijs Kooijman <matthijs@stdin.nl> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-16 11:52:07 +02:00
commit->object.flags |= SHOWN;
show_edge(commit);
}
continue;
}
mark_edge_parents_uninteresting(commit, revs, show_edge);
}
if (revs->edge_hint_aggressive) {
list-objects: only look at cmdline trees with edge_hint When rev-list is given a command-line like: git rev-list --objects $commit --not --all the most accurate answer is the difference between the set of objects reachable from $commit and the set reachable from all of the existing refs. However, we have not historically provided that answer, because it is very expensive to calculate. We would have to open every tree of every commit in the entire history. Instead, we find the accurate set difference of the reachable commits, and then mark the trees at the boundaries as uninteresting. This misses objects which appear in the trees of both the interesting commits and deep within the uninteresting history. Commit fbd4a70 (list-objects: mark more commits as edges in mark_edges_uninteresting, 2013-08-16) noticed that we miss those objects during pack-objects, and added code to examine the trees of all of the "--not" refs given on the command-line. Note that this is still not the complete set difference, because we look only at the tips of the command-line arguments, not all of their reachable commits. But it increases the set of boundary objects we consider, which is especially important for shallow fetches. So we are trading extra CPU time for a larger set of boundary objects, which can improve the resulting pack size for a --thin pack. This tradeoff probably makes sense in the context of pack-objects, where we have set revs->edge_hint to have the traversal feed us the set of boundary objects. For a regular rev-list, though, it is probably not a good tradeoff. It is true that it makes our list slightly closer to a true set difference, but it is a rare case where this is important. And because we do not have revs->edge_hint set, we do nothing useful with the larger set of boundary objects. This patch therefore ties the extra tree examination to the revs->edge_hint flag; it is the presence of that flag that makes the tradeoff worthwhile. Here is output from the p0001-rev-list showing the improvement in performance: Test HEAD^ HEAD ----------------------------------------------------------------------------------------- 0001.1: rev-list --all 0.69(0.65+0.02) 0.69(0.66+0.02) +0.0% 0001.2: rev-list --all --objects 3.22(3.19+0.03) 3.23(3.20+0.03) +0.3% 0001.4: rev-list $commit --not --all 0.04(0.04+0.00) 0.04(0.04+0.00) +0.0% 0001.5: rev-list --objects $commit --not --all 0.27(0.26+0.01) 0.04(0.04+0.00) -85.2% Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-01-21 03:25:40 +01:00
for (i = 0; i < revs->cmdline.nr; i++) {
struct object *obj = revs->cmdline.rev[i].item;
struct commit *commit = (struct commit *)obj;
if (obj->type != OBJ_COMMIT || !(obj->flags & UNINTERESTING))
continue;
mark_tree_uninteresting(revs->repo,
get_commit_tree(commit));
list-objects: only look at cmdline trees with edge_hint When rev-list is given a command-line like: git rev-list --objects $commit --not --all the most accurate answer is the difference between the set of objects reachable from $commit and the set reachable from all of the existing refs. However, we have not historically provided that answer, because it is very expensive to calculate. We would have to open every tree of every commit in the entire history. Instead, we find the accurate set difference of the reachable commits, and then mark the trees at the boundaries as uninteresting. This misses objects which appear in the trees of both the interesting commits and deep within the uninteresting history. Commit fbd4a70 (list-objects: mark more commits as edges in mark_edges_uninteresting, 2013-08-16) noticed that we miss those objects during pack-objects, and added code to examine the trees of all of the "--not" refs given on the command-line. Note that this is still not the complete set difference, because we look only at the tips of the command-line arguments, not all of their reachable commits. But it increases the set of boundary objects we consider, which is especially important for shallow fetches. So we are trading extra CPU time for a larger set of boundary objects, which can improve the resulting pack size for a --thin pack. This tradeoff probably makes sense in the context of pack-objects, where we have set revs->edge_hint to have the traversal feed us the set of boundary objects. For a regular rev-list, though, it is probably not a good tradeoff. It is true that it makes our list slightly closer to a true set difference, but it is a rare case where this is important. And because we do not have revs->edge_hint set, we do nothing useful with the larger set of boundary objects. This patch therefore ties the extra tree examination to the revs->edge_hint flag; it is the presence of that flag that makes the tradeoff worthwhile. Here is output from the p0001-rev-list showing the improvement in performance: Test HEAD^ HEAD ----------------------------------------------------------------------------------------- 0001.1: rev-list --all 0.69(0.65+0.02) 0.69(0.66+0.02) +0.0% 0001.2: rev-list --all --objects 3.22(3.19+0.03) 3.23(3.20+0.03) +0.3% 0001.4: rev-list $commit --not --all 0.04(0.04+0.00) 0.04(0.04+0.00) +0.0% 0001.5: rev-list --objects $commit --not --all 0.27(0.26+0.01) 0.04(0.04+0.00) -85.2% Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-01-21 03:25:40 +01:00
if (!(obj->flags & SHOWN)) {
obj->flags |= SHOWN;
show_edge(commit);
}
list-objects: mark more commits as edges in mark_edges_uninteresting The purpose of edge commits is to let pack-objects know what objects it can use as base, but does not need to include in the thin pack because the other side is supposed to already have them. So far we mark uninteresting parents of interesting commits as edges. But even an unrelated uninteresting commit (that the other side has) may become a good base for pack-objects and help produce more efficient packs. This is especially true for shallow clone, when the client issues a fetch with a depth smaller or equal to the number of commits the server is ahead of the client. For example, in this commit history the client has up to "A" and the server has up to "B": -------A---B have--^ ^ / want--+ If depth 1 is requested, the commit list to send to the client includes only B. The way m_e_u is working, it checks if parent commits of B are uninteresting, if so mark them as edges. Due to shallow effect, commit B is grafted to have no parents and the revision walker never sees A as the parent of B. In fact it marks no edges at all in this simple case and sends everything B has to the client even if it could have excluded what A and also the client already have. In a slightly different case where A is not a direct parent of B (iow there are commits in between A and B), marking A as an edge can still save some because B may still have stuff from the far ancestor A. There is another case from the earlier patch, when we deepen a ref from C->E to A->E: ---A---B C---D---E want--^ ^ ^ shallow-+ / have-------+ In this case we need to send A and B to the client, and C (i.e. the current shallow point that the client informs the server) is a very good base because it's closet to A and B. Normal m_e_u won't recognize C as an edge because it only looks back to parents (i.e. A<-B) not the opposite way B->C even if C is already marked as uninteresting commit by the previous patch. This patch includes all uninteresting commits from command line as edges and lets pack-objects decide what's best to do. The upside is we have better chance of producing better packs in certain cases. The downside is we may need to process some extra objects on the server side. For the shallow case on git.git, when the client is 5 commits behind and does "fetch --depth=3", the result pack is 99.26 KiB instead of 4.92 MiB. Reported-and-analyzed-by: Matthijs Kooijman <matthijs@stdin.nl> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-16 11:52:07 +02:00
}
}
}
process_{tree,blob}: show objects without buffering Here's a less trivial thing, and slightly more dubious one. I was looking at that "struct object_array objects", and wondering why we do that. I have honestly totally forgotten. Why not just call the "show()" function as we encounter the objects? Rather than add the objects to the object_array, and then at the very end going through the array and doing a 'show' on all, just do things more incrementally. Now, there are possible downsides to this: - the "buffer using object_array" _can_ in theory result in at least better I-cache usage (two tight loops rather than one more spread out one). I don't think this is a real issue, but in theory.. - this _does_ change the order of the objects printed. Instead of doing a "process_tree(revs, commit->tree, &objects, NULL, "");" in the loop over the commits (which puts all the root trees _first_ in the object list, this patch just adds them to the list of pending objects, and then we'll traverse them in that order (and thus show each root tree object together with the objects we discover under it) I _think_ the new ordering actually makes more sense, but the object ordering is actually a subtle thing when it comes to packing efficiency, so any change in order is going to have implications for packing. Good or bad, I dunno. - There may be some reason why we did it that odd way with the object array, that I have simply forgotten. Anyway, now that we don't buffer up the objects before showing them that may actually result in lower memory usage during that whole traverse_commit_list() phase. This is seriously not very deeply tested. It makes sense to me, it seems to pass all the tests, it looks ok, but... Does anybody remember why we did that "object_array" thing? It used to be an "object_list" a long long time ago, but got changed into the array due to better memory usage patterns (those linked lists of obejcts are horrible from a memory allocation standpoint). But I wonder why we didn't do this back then. Maybe there's a reason for it. Or maybe there _used_ to be a reason, and no longer is. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-04-11 02:27:58 +02:00
static void add_pending_tree(struct rev_info *revs, struct tree *tree)
{
add_pending_object(revs, &tree->object, "");
}
static void traverse_trees_and_blobs(struct traversal_context *ctx,
struct strbuf *base)
{
int i;
assert(base->len == 0);
for (i = 0; i < ctx->revs->pending.nr; i++) {
struct object_array_entry *pending = ctx->revs->pending.objects + i;
struct object *obj = pending->item;
const char *name = pending->name;
traverse_commit_list: support pending blobs/trees with paths When we call traverse_commit_list, we may have trees and blobs in the pending array. As we process these, we pass the "name" field from the pending entry as the path of the object within the tree (which then becomes the root path if we recurse into subtrees). When we set up the traversal in prepare_revision_walk, though, the "name" field of any pending trees and blobs is likely to be the ref at which we found the object. We would not want to make this part of the path (e.g., doing so would make "git rev-list --objects v2.6.11-tree" in linux.git show paths like "v2.6.11-tree/Makefile", which is nonsensical). Therefore prepare_revision_walk sets the name field of each pending tree and blobs to the empty string. However, this leaves no room for a caller who does know the correct path of a pending object to propagate that information to the revision walker. We can fix this by making two related changes: 1. Use the "path" field as the path instead of the "name" field in traverse_commit_list. If the path is not set, default to "" (which is what we always ended up with in the current code, because of prepare_revision_walk). 2. In prepare_revision_walk, make a complete copy of the entry. This makes the path field available to the walker (if there is one), solving our problem. Leaving the name field intact is now OK, as we do not use it as a path due to point (1) above (and we can use it to make more meaningful error messages if we want). We also make the original "mode" field available to the walker, though it does not actually use it. Note that we still re-add the pending objects and free the old ones (so we may strdup the path and name only to free the old ones). This could be made more efficient by simply copying the object_array entries that we are keeping. However, that would require more restructuring of the code, and is not done here. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-10-16 00:43:19 +02:00
const char *path = pending->path;
if (obj->flags & (UNINTERESTING | SEEN))
continue;
if (obj->type == OBJ_TAG) {
obj->flags |= SEEN;
ctx->show_object(obj, name, ctx->show_data);
continue;
}
traverse_commit_list: support pending blobs/trees with paths When we call traverse_commit_list, we may have trees and blobs in the pending array. As we process these, we pass the "name" field from the pending entry as the path of the object within the tree (which then becomes the root path if we recurse into subtrees). When we set up the traversal in prepare_revision_walk, though, the "name" field of any pending trees and blobs is likely to be the ref at which we found the object. We would not want to make this part of the path (e.g., doing so would make "git rev-list --objects v2.6.11-tree" in linux.git show paths like "v2.6.11-tree/Makefile", which is nonsensical). Therefore prepare_revision_walk sets the name field of each pending tree and blobs to the empty string. However, this leaves no room for a caller who does know the correct path of a pending object to propagate that information to the revision walker. We can fix this by making two related changes: 1. Use the "path" field as the path instead of the "name" field in traverse_commit_list. If the path is not set, default to "" (which is what we always ended up with in the current code, because of prepare_revision_walk). 2. In prepare_revision_walk, make a complete copy of the entry. This makes the path field available to the walker (if there is one), solving our problem. Leaving the name field intact is now OK, as we do not use it as a path due to point (1) above (and we can use it to make more meaningful error messages if we want). We also make the original "mode" field available to the walker, though it does not actually use it. Note that we still re-add the pending objects and free the old ones (so we may strdup the path and name only to free the old ones). This could be made more efficient by simply copying the object_array entries that we are keeping. However, that would require more restructuring of the code, and is not done here. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-10-16 00:43:19 +02:00
if (!path)
path = "";
if (obj->type == OBJ_TREE) {
process_tree(ctx, (struct tree *)obj, base, path);
continue;
}
if (obj->type == OBJ_BLOB) {
process_blob(ctx, (struct blob *)obj, base, path);
continue;
}
die("unknown pending object %s (%s)",
oid_to_hex(&obj->oid), name);
}
object_array_clear(&ctx->revs->pending);
}
static void do_traverse(struct traversal_context *ctx)
{
struct commit *commit;
struct strbuf csp; /* callee's scratch pad */
strbuf_init(&csp, PATH_MAX);
while ((commit = get_revision(ctx->revs)) != NULL) {
/*
* an uninteresting boundary commit may not have its tree
* parsed yet, but we are not going to show them anyway
*/
if (get_commit_tree(commit)) {
struct tree *tree = get_commit_tree(commit);
tree->object.flags |= NOT_USER_GIVEN;
add_pending_tree(ctx->revs, tree);
}
ctx->show_commit(commit, ctx->show_data);
if (ctx->revs->tree_blobs_in_commit_order)
/*
* NEEDSWORK: Adding the tree and then flushing it here
* needs a reallocation for each commit. Can we pass the
* tree directory without allocation churn?
*/
traverse_trees_and_blobs(ctx, &csp);
}
traverse_trees_and_blobs(ctx, &csp);
strbuf_release(&csp);
}
void traverse_commit_list(struct rev_info *revs,
show_commit_fn show_commit,
show_object_fn show_object,
void *show_data)
{
struct traversal_context ctx;
ctx.revs = revs;
ctx.show_commit = show_commit;
ctx.show_object = show_object;
ctx.show_data = show_data;
ctx.filter_fn = NULL;
ctx.filter_data = NULL;
do_traverse(&ctx);
}
void traverse_commit_list_filtered(
struct list_objects_filter_options *filter_options,
struct rev_info *revs,
show_commit_fn show_commit,
show_object_fn show_object,
void *show_data,
struct oidset *omitted)
{
struct traversal_context ctx;
filter_free_fn filter_free_fn = NULL;
ctx.revs = revs;
ctx.show_object = show_object;
ctx.show_commit = show_commit;
ctx.show_data = show_data;
ctx.filter_fn = NULL;
ctx.filter_data = list_objects_filter__init(omitted, filter_options,
&ctx.filter_fn, &filter_free_fn);
do_traverse(&ctx);
if (ctx.filter_data && filter_free_fn)
filter_free_fn(ctx.filter_data);
}