summaryrefslogtreecommitdiff
path: root/builtin/receive-pack.c
diff options
context:
space:
mode:
authorJeff King <peff@peff.net>2017-02-08 20:53:10 (GMT)
committerJunio C Hamano <gitster@pobox.com>2017-02-08 23:39:55 (GMT)
commitab6eea6f7b9a5289d72c05476da19ab2bb457fd3 (patch)
tree70640ab6aea899442df3e67d3d5cf32e24ca7758 /builtin/receive-pack.c
parent29c2bd5fa8cb97eedcd463d49cfc7e753feb3145 (diff)
downloadgit-ab6eea6f7b9a5289d72c05476da19ab2bb457fd3.zip
git-ab6eea6f7b9a5289d72c05476da19ab2bb457fd3.tar.gz
git-ab6eea6f7b9a5289d72c05476da19ab2bb457fd3.tar.bz2
receive-pack: use oidset to de-duplicate .have lines
If you have an alternate object store with a very large number of refs, the peak memory usage of the sha1_array can grow high, even if most of them are duplicates that end up not being printed at all. The similar for_each_alternate_ref() code-paths in fetch-pack solve this by using flags in "struct object" to de-duplicate (and so are relying on obj_hash at the core). But we don't have a "struct object" at all in this case. We could call lookup_unknown_object() to get one, but if our goal is reducing memory footprint, it's not great: - an unknown object is as large as the largest object type (a commit), which is bigger than an oidset entry - we can free the memory after our ref advertisement, but "struct object" entries persist forever (and the receive-pack may hang around for a long time, as the bottleneck is often client upload bandwidth). So let's use an oidset. Note that unlike a sha1-array it doesn't sort the output as a side effect. However, our output is at least stable, because for_each_alternate_ref() will give us the sha1s in ref-sorted order. In one particularly pathological case with an alternate that has 60,000 unique refs out of 80 million total, this reduced the peak heap usage of "git receive-pack . </dev/null" from 13GB to 14MB. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'builtin/receive-pack.c')
-rw-r--r--builtin/receive-pack.c26
1 files changed, 12 insertions, 14 deletions
diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c
index d21332d..a4926fc 100644
--- a/builtin/receive-pack.c
+++ b/builtin/receive-pack.c
@@ -21,6 +21,7 @@
#include "sigchain.h"
#include "fsck.h"
#include "tmp-objdir.h"
+#include "oidset.h"
static const char * const receive_pack_usage[] = {
N_("git receive-pack <git-dir>"),
@@ -271,27 +272,24 @@ static int show_ref_cb(const char *path_full, const struct object_id *oid,
return 0;
}
-static int show_one_alternate_sha1(const unsigned char sha1[20], void *unused)
+static void show_one_alternate_ref(const char *refname,
+ const struct object_id *oid,
+ void *data)
{
- show_ref(".have", sha1);
- return 0;
-}
+ struct oidset *seen = data;
-static void collect_one_alternate_ref(const char *refname,
- const struct object_id *oid,
- void *data)
-{
- struct sha1_array *sa = data;
- sha1_array_append(sa, oid->hash);
+ if (oidset_insert(seen, oid))
+ return;
+
+ show_ref(".have", oid->hash);
}
static void write_head_info(void)
{
- struct sha1_array sa = SHA1_ARRAY_INIT;
+ static struct oidset seen = OIDSET_INIT;
- for_each_alternate_ref(collect_one_alternate_ref, &sa);
- sha1_array_for_each_unique(&sa, show_one_alternate_sha1, NULL);
- sha1_array_clear(&sa);
+ for_each_alternate_ref(show_one_alternate_ref, &seen);
+ oidset_clear(&seen);
for_each_ref(show_ref_cb, NULL);
if (!sent_capabilities)
show_ref("capabilities^{}", null_sha1);