summaryrefslogtreecommitdiff
path: root/builtin/name-rev.c
diff options
context:
space:
mode:
authorSZEDER Gábor <szeder.dev@gmail.com>2019-12-09 11:52:57 (GMT)
committerJunio C Hamano <gitster@pobox.com>2019-12-09 21:33:01 (GMT)
commit49f7a2fde98e375562c2f8f2e3e3effba70d0402 (patch)
tree231bec7df797870efd57d7458961c75b1c29f7f9 /builtin/name-rev.c
parentfee984bcab9f7331b319aa5a48824593e854b784 (diff)
downloadgit-49f7a2fde98e375562c2f8f2e3e3effba70d0402.zip
git-49f7a2fde98e375562c2f8f2e3e3effba70d0402.tar.gz
git-49f7a2fde98e375562c2f8f2e3e3effba70d0402.tar.bz2
name-rev: eliminate recursion in name_rev()
The name_rev() function calls itself recursively for each interesting parent of the commit it got as parameter, and, consequently, it can segfault when processing a deep history if it exhausts the available stack space. E.g. running 'git name-rev --all' and 'git name-rev HEAD~100000' in the gcc, gecko-dev, llvm, and WebKit repositories results in segfaults on my machine ('ulimit -s' reports 8192kB of stack size limit), and nowadays the former segfaults in the Linux repo as well (it reached the necessasry depth sometime between v5.3-rc4 and -rc5). Eliminate the recursion by inserting the interesting parents into a LIFO 'prio_queue' [1] and iterating until the queue becomes empty. Note that the parent commits must be added in reverse order to the LIFO 'prio_queue', so their relative order is preserved during processing, i.e. the first parent should come out first from the queue, because otherwise performance greatly suffers on mergy histories [2]. The stacksize-limited test 'name-rev works in a deep repo' in 't6120-describe.sh' demonstrated this issue and expected failure. Now the recursion is gone, so flip it to expect success. Also gone are the dmesg entries logging the segfault of that segfaulting 'git name-rev' process on every execution of the test suite. Note that this slightly changes the order of lines in the output of 'git name-rev --all', usually swapping two lines every 35 lines in git.git or every 150 lines in linux.git. This shouldn't matter in practice, because the output has always been unordered anyway. This patch is best viewed with '--ignore-all-space'. [1] Early versions of this patch used a 'commit_list', resulting in ~15% performance penalty for 'git name-rev --all' in 'linux.git', presumably because of the memory allocation and release for each insertion and removal. Using a LIFO 'prio_queue' has basically no effect on performance. [2] We prefer shorter names, i.e. 'v0.1~234' is preferred over 'v0.1^2~5', meaning that usually following the first parent of a merge results in the best name for its ancestors. So when later we follow the remaining parent(s) of a merge, and reach an already named commit, then we usually find that we can't give that commit a better name, and thus we don't have to visit any of its ancestors again. OTOH, if we were to follow the Nth parent of the merge first, then the name of all its ancestors would include a corresponding '^N'. Those are not the best names for those commits, so when later we reach an already named commit following the first parent of that merge, then we would have to update the name of that commit and the names of all of its ancestors as well. Consequently, we would have to visit many commits several times, resulting in a significant slowdown. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'builtin/name-rev.c')
-rw-r--r--builtin/name-rev.c102
1 files changed, 64 insertions, 38 deletions
diff --git a/builtin/name-rev.c b/builtin/name-rev.c
index 6c1e6e9..a3b796e 100644
--- a/builtin/name-rev.c
+++ b/builtin/name-rev.c
@@ -6,6 +6,7 @@
#include "tag.h"
#include "refs.h"
#include "parse-options.h"
+#include "prio-queue.h"
#include "sha1-lookup.h"
#include "commit-slab.h"
@@ -104,52 +105,77 @@ copy_data:
return NULL;
}
-static void name_rev(struct commit *commit,
+static void name_rev(struct commit *start_commit,
const char *tip_name, timestamp_t taggerdate,
int from_tag)
{
- struct rev_name *name = get_commit_rev_name(commit);
- struct commit_list *parents;
- int parent_number = 1;
-
- for (parents = commit->parents;
- parents;
- parents = parents->next, parent_number++) {
- struct commit *parent = parents->item;
- const char *new_name;
- int generation, distance;
-
- parse_commit(parent);
- if (parent->date < cutoff)
- continue;
+ struct prio_queue queue;
+ struct commit *commit;
+ struct commit **parents_to_queue = NULL;
+ size_t parents_to_queue_nr, parents_to_queue_alloc = 0;
+
+ memset(&queue, 0, sizeof(queue)); /* Use the prio_queue as LIFO */
+ prio_queue_put(&queue, start_commit);
+
+ while ((commit = prio_queue_get(&queue))) {
+ struct rev_name *name = get_commit_rev_name(commit);
+ struct commit_list *parents;
+ int parent_number = 1;
+
+ parents_to_queue_nr = 0;
+
+ for (parents = commit->parents;
+ parents;
+ parents = parents->next, parent_number++) {
+ struct commit *parent = parents->item;
+ const char *new_name;
+ int generation, distance;
+
+ parse_commit(parent);
+ if (parent->date < cutoff)
+ continue;
- if (parent_number > 1) {
- size_t len;
+ if (parent_number > 1) {
+ size_t len;
+
+ strip_suffix(name->tip_name, "^0", &len);
+ if (name->generation > 0)
+ new_name = xstrfmt("%.*s~%d^%d",
+ (int)len,
+ name->tip_name,
+ name->generation,
+ parent_number);
+ else
+ new_name = xstrfmt("%.*s^%d", (int)len,
+ name->tip_name,
+ parent_number);
+ generation = 0;
+ distance = name->distance + MERGE_TRAVERSAL_WEIGHT;
+ } else {
+ new_name = name->tip_name;
+ generation = name->generation + 1;
+ distance = name->distance + 1;
+ }
- strip_suffix(name->tip_name, "^0", &len);
- if (name->generation > 0)
- new_name = xstrfmt("%.*s~%d^%d",
- (int)len,
- name->tip_name,
- name->generation,
- parent_number);
- else
- new_name = xstrfmt("%.*s^%d", (int)len,
- name->tip_name,
- parent_number);
- generation = 0;
- distance = name->distance + MERGE_TRAVERSAL_WEIGHT;
- } else {
- new_name = name->tip_name;
- generation = name->generation + 1;
- distance = name->distance + 1;
+ if (create_or_update_name(parent, new_name, taggerdate,
+ generation, distance,
+ from_tag)) {
+ ALLOC_GROW(parents_to_queue,
+ parents_to_queue_nr + 1,
+ parents_to_queue_alloc);
+ parents_to_queue[parents_to_queue_nr] = parent;
+ parents_to_queue_nr++;
+ }
}
- if (create_or_update_name(parent, new_name, taggerdate,
- generation, distance,
- from_tag))
- name_rev(parent, new_name, taggerdate, from_tag);
+ /* The first parent must come out first from the prio_queue */
+ while (parents_to_queue_nr)
+ prio_queue_put(&queue,
+ parents_to_queue[--parents_to_queue_nr]);
}
+
+ clear_prio_queue(&queue);
+ free(parents_to_queue);
}
static int subpath_matches(const char *path, const char *filter)