On Thu, Jul 19, 2018 at 8:16 AM, Duy Nguyen <pclouds@xxxxxxxxx> wrote:
> On Thu, Jul 19, 2018 at 07:57:37AM +0200, Duy Nguyen wrote:
>> I thought 2M was generous but I was obviously wrong. I'd like to see
>> the biggest delta size in this pack and whether it's still reasonable
>> to increase OE_DELTA_SIZE_BITS. But if it's very close to 4GB limit
>> then we could just store 64-bit delta size in a separate array.
>
> I realize now that these two options don't have to be mutually
> exclusive and I should provide a good fallback in terms of performance
> anyway.
>
> So Elijah, could you try this patch and see if performance and pack
> size go back to 1.7.0? I can write proper commit message and test
> support later if it proves a good improvement.
Thanks for the quick turnaround. Unfortunately, I have some bad news.
With this patch, I get the following:
$ /usr/bin/time -f 'MaxRSS:%M Time:%e' git gc --aggressive
Enumerating objects: 4460703, done.
Counting objects: 100% (4460703/4460703), done.
Delta compression using up to 40 threads.
Compressing objects: 100% (3807140/3807140), done.
Writing objects: 100% (4460703/4460703), done.
Total 4460703 (delta 2831383), reused 1587071 (delta 0)
error: failed to unpack compressed delta at offset 183854150 from
.git/objects/pack/pack-30d4f0b0e5a03dc91a658a0586f4e74cdf4a94d6.pack
fatal: packed object 20ce811e53dabbb8ef9368c108cbbdfa65639c03 (stored
in .git/objects/pack/pack-30d4f0b0e5a03dc91a658a0586f4e74cdf4a94d6.pack)
is corrupt
error: failed to run prune
MaxRSS:40025196 Time:2531.52
It looks like this comes after it deleted the old packs, so running
git fsck afterwards prints lots of errors. Just in case they're
helpful at all, there are 26 "error: failed to unpack compressed delta
at offset..." messages, 26 "error: cannot unpack ... from ... at
offset ..." messages, 17 "error: failed to read delta base object..."
messages, 7 "broken link from ... to ..." messages, four missing
blobs, and three missing trees.
(This was run on a copy of the repo, so no harm done; I can still use
the original.)
> -- 8< --
> diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
> index ebc8cefb53..7f3546057d 100644
> --- a/builtin/pack-objects.c
> +++ b/builtin/pack-objects.c
> @@ -2023,10 +2023,6 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
> delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size);
> if (!delta_buf)
> return 0;
> - if (delta_size >= (1U << OE_DELTA_SIZE_BITS)) {
> - free(delta_buf);
> - return 0;
> - }
>
> if (DELTA(trg_entry)) {
> /* Prefer only shallower same-sized deltas. */
> diff --git a/pack-objects.c b/pack-objects.c
> index 92708522e7..191ed45faf 100644
> --- a/pack-objects.c
> +++ b/pack-objects.c
> @@ -160,6 +160,8 @@ struct object_entry *packlist_alloc(struct packing_data *pdata,
>
> if (!pdata->in_pack_by_idx)
> REALLOC_ARRAY(pdata->in_pack, pdata->nr_alloc);
> + if (pdata->delta_size)
> + REALLOC_ARRAY(pdata->delta_size, pdata->nr_alloc);
> }
>
> new_entry = pdata->objects + pdata->nr_objects++;
> @@ -177,3 +179,17 @@ struct object_entry *packlist_alloc(struct packing_data *pdata,
>
> return new_entry;
> }
> +
> +void oe_prepare_delta_size_array(struct packing_data *pack)
> +{
> + int i;
> +
> + /*
> + * nr_alloc, not nr_objects to align with realloc() strategy in
> + * packlist_alloc()
> + */
> + ALLOC_ARRAY(pack->delta_size, pack->nr_alloc);
> +
> + for (i = 0; i < pack->nr_objects; i++)
> + pack->delta_size[i] = pack->objects[i].delta_size_;
> +}
> diff --git a/pack-objects.h b/pack-objects.h
> index edf74dabdd..978500e474 100644
> --- a/pack-objects.h
> +++ b/pack-objects.h
> @@ -14,7 +14,7 @@
> * above this limit. Don't lower it too much.
> */
> #define OE_SIZE_BITS 31
> -#define OE_DELTA_SIZE_BITS 20
> +#define OE_DELTA_SIZE_BITS 21
>
> /*
> * State flags for depth-first search used for analyzing delta cycles.
> @@ -93,7 +93,6 @@ 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 in_pack_idx:OE_IN_PACK_BITS; /* already in pack */
> unsigned z_delta_size:OE_Z_DELTA_BITS;
> unsigned type_valid:1;
> @@ -130,6 +129,7 @@ struct packing_data {
> uint32_t index_size;
>
> unsigned int *in_pack_pos;
> + unsigned long *delta_size;
>
> /*
> * Only one of these can be non-NULL and they have different
> @@ -330,20 +330,27 @@ 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)
> {
> - if (e->delta_size_valid)
> + if (!pack->delta_size)
> return e->delta_size_;
> - return oe_size(pack, e);
> + return pack->delta_size[e - pack->objects];
> }
>
> +void oe_prepare_delta_size_array(struct packing_data *pack);
> static inline void oe_set_delta_size(struct packing_data *pack,
> struct object_entry *e,
> unsigned long size)
> {
> e->delta_size_ = size;
> - e->delta_size_valid = e->delta_size_ == size;
> - if (!e->delta_size_valid && size != oe_size(pack, e))
> - BUG("this can only happen in check_object() "
> - "where delta size is the same as entry size");
> + if (!pack->delta_size && e->delta_size_ == size)
> + return;
> + /*
> + * 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)
> + oe_prepare_delta_size_array(pack);
> + pack->delta_size[e - pack->objects] = size;
> }
>
> #endif
> -- 8< --
>
>
> --
> Duy
