On Fri, Jul 20, 2018 at 10:43:25AM -0700, Elijah Newren wrote:
> > This patch provides a better fallback that is
> >
> > - cheaper in terms of cpu and io because we won't have to read
> > existing pack files as much
> >
> > - better in terms of pack size because the pack heuristics is back to
> > 2.17.0 time, we do not drop large deltas at all
> >
> > If we encounter any delta (on-disk or created during try_delta phase)
> > that is larger than the 2MB limit, we stop using delta_size_ field for
> > this because it can't contain such size anyway. A new array of delta
> > size is dynamically allocated and can hold all the deltas that 2.17.0
> > can [1]. All current delta sizes are migrated over.
> >
> > With this, we do not have to drop deltas in try_delta() anymore. Of
> > course the downside is we use slightly more memory, even compared to
> > 2.17.0. But since this is considered an uncommon case, a bit more
> > memory consumption should not be a problem.
>
> Out of curiosity, would it be possible to use the delta_size_ field
> for deltas that are small enough, and only use an external data
> structure (perhaps a hash rather than an array) for the few deltas
> that are large?
We could. And because repack time is still a bit higher in your
linux.git case. Let's try this. No locking in common case and very
small locked region when we hit large deltas
-- 8< --
diff --git a/pack-objects.c b/pack-objects.c
index eef344b7c1..e3c32bbfc2 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -88,23 +88,6 @@ struct object_entry *packlist_find(struct packing_data *pdata,
return &pdata->objects[pdata->index[i] - 1];
}
-uint32_t *new_delta_size_array(struct packing_data *pack)
-{
- uint32_t *delta_size;
- uint32_t i;
-
- /*
- * nr_alloc, not nr_objects to align with realloc() strategy in
- * packlist_alloc()
- */
- ALLOC_ARRAY(delta_size, pack->nr_alloc);
-
- for (i = 0; i < pack->nr_objects; i++)
- delta_size[i] = pack->objects[i].delta_size_;
-
- return delta_size;
-}
-
static void prepare_in_pack_by_idx(struct packing_data *pdata)
{
struct packed_git **mapping, *p;
diff --git a/pack-objects.h b/pack-objects.h
index 9f977ae800..11890e7217 100644
--- a/pack-objects.h
+++ b/pack-objects.h
@@ -15,7 +15,7 @@
* above this limit. Don't lower it too much.
*/
#define OE_SIZE_BITS 31
-#define OE_DELTA_SIZE_BITS 24
+#define OE_DELTA_SIZE_BITS 23
/*
* State flags for depth-first search used for analyzing delta cycles.
@@ -94,6 +94,7 @@ struct object_entry {
* uses the same base as me
*/
unsigned delta_size_:OE_DELTA_SIZE_BITS; /* delta data size (uncompressed) */
+ unsigned delta_size_valid:1;
unsigned char in_pack_header_size;
unsigned in_pack_idx:OE_IN_PACK_BITS; /* already in pack */
unsigned z_delta_size:OE_Z_DELTA_BITS;
@@ -353,37 +354,26 @@ static inline void oe_set_size(struct packing_data *pack,
static inline unsigned long oe_delta_size(struct packing_data *pack,
const struct object_entry *e)
{
- unsigned long size;
-
- packing_data_lock(pack);
- if (pack->delta_size)
- size = pack->delta_size[e - pack->objects];
+ if (e->delta_size_valid)
+ return e->delta_size_;
else
- size = e->delta_size_;
- packing_data_unlock(pack);
- return size;
+ return pack->delta_size[e - pack->objects];
}
-uint32_t *new_delta_size_array(struct packing_data *pdata);
static inline void oe_set_delta_size(struct packing_data *pack,
struct object_entry *e,
unsigned long size)
{
- packing_data_lock(pack);
- if (!pack->delta_size && size < pack->oe_delta_size_limit) {
- packing_data_unlock(pack);
+ if (size < pack->oe_delta_size_limit) {
e->delta_size_ = size;
- return;
+ e->delta_size_valid = 1;
+ } else {
+ packing_data_lock(pack);
+ if (!pack->delta_size)
+ ALLOC_ARRAY(pack->delta_size, pack->nr_alloc);
+ packing_data_unlock(pack);
+ pack->delta_size[e - pack->objects] = size;
}
- /*
- * We have had at least one delta size exceeding OE_DELTA_SIZE_BITS
- * limit. delta_size_ will not be used anymore. All delta sizes are
- * now from the delta_size[] array.
- */
- if (!pack->delta_size)
- pack->delta_size = new_delta_size_array(pack);
- pack->delta_size[e - pack->objects] = size;
- packing_data_unlock(pack);
}
#endif
-- 8< --
> > --
> > 2.18.0.rc2.476.g39500d3211
>
> Missing the 2.18.0 tag? ;-)
Hehe I was a bit busy lately and have not rebased my branch on the
latest and greatest version.
--
Duy
