From: Duy Nguyen <pclouds@gmail.com>
To: Elijah Newren <newren@gmail.com>
Cc: Git Mailing List <git@vger.kernel.org>, Jeff King <peff@peff.net>
Subject: Re: 2.18.0 Regression: packing performance and effectiveness
Date: Thu, 19 Jul 2018 17:16:42 +0200 [thread overview]
Message-ID: <20180719151640.GA24997@duynguyen.home> (raw)
In-Reply-To: <CACsJy8BNGboUb0F5NRR9tKj_P24j2ZgB48SCuLEphSHQAU2EUA@mail.gmail.com>
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.
-- 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
next prev parent reply other threads:[~2018-07-19 15:16 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-18 22:51 2.18.0 Regression: packing performance and effectiveness Elijah Newren
2018-07-18 22:51 ` [RFC PATCH] fix-v1: revert "pack-objects: shrink delta_size field in struct object_entry" Elijah Newren
2018-07-18 22:51 ` [RFC PATCH] fix-v2: make OE_DELTA_SIZE_BITS a bit bigger Elijah Newren
2018-07-19 5:41 ` 2.18.0 Regression: packing performance and effectiveness Duy Nguyen
2018-07-19 5:49 ` Jeff King
2018-07-19 15:27 ` Elijah Newren
2018-07-19 15:43 ` Duy Nguyen
2018-07-19 5:44 ` Jeff King
2018-07-19 5:57 ` Duy Nguyen
2018-07-19 15:16 ` Duy Nguyen [this message]
2018-07-19 16:42 ` Elijah Newren
2018-07-19 17:23 ` Jeff King
2018-07-19 17:31 ` Duy Nguyen
2018-07-19 18:24 ` Duy Nguyen
2018-07-19 19:17 ` Jeff King
2018-07-19 23:11 ` Elijah Newren
2018-07-20 5:28 ` Jeff King
2018-07-20 5:30 ` Jeff King
2018-07-20 5:47 ` Duy Nguyen
2018-07-20 17:21 ` Elijah Newren
2018-07-19 17:04 ` Jeff King
2018-07-19 19:25 ` Junio C Hamano
2018-07-19 19:27 ` Junio C Hamano
2018-07-20 15:39 ` [PATCH] pack-objects: fix performance issues on packing large deltas Nguyễn Thái Ngọc Duy
2018-07-20 17:40 ` Jeff King
2018-07-21 4:23 ` Duy Nguyen
2018-07-23 21:37 ` Jeff King
2018-07-20 17:43 ` Elijah Newren
2018-07-20 23:52 ` Elijah Newren
2018-07-21 4:07 ` Duy Nguyen
2018-07-21 7:08 ` Duy Nguyen
2018-07-21 4:47 ` Duy Nguyen
2018-07-21 6:56 ` Elijah Newren
2018-07-21 7:14 ` Duy Nguyen
2018-07-22 6:22 ` Elijah Newren
2018-07-22 6:49 ` Duy Nguyen
2018-07-23 12:34 ` Elijah Newren
2018-07-23 15:50 ` Duy Nguyen
2018-07-22 8:04 ` [PATCH v2] " Nguyễn Thái Ngọc Duy
2018-07-23 18:04 ` Junio C Hamano
2018-07-23 18:38 ` Duy Nguyen
2018-07-23 18:49 ` Duy Nguyen
2018-07-23 21:30 ` Jeff King
2018-07-26 8:12 ` Johannes Sixt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180719151640.GA24997@duynguyen.home \
--to=pclouds@gmail.com \
--cc=git@vger.kernel.org \
--cc=newren@gmail.com \
--cc=peff@peff.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).