From: Nicolas Pitre <nico@fluxnic.net>
To: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
Cc: git@vger.kernel.org, Junio C Hamano <gitster@pobox.com>
Subject: Re: [PATCH v2 3/4] pack-objects: refactor write_object()
Date: Fri, 18 May 2012 22:43:59 -0400 (EDT) [thread overview]
Message-ID: <alpine.LFD.2.02.1205182243180.13185@xanadu.home> (raw)
In-Reply-To: <1337169731-23416-3-git-send-email-pclouds@gmail.com>
[-- Attachment #1: Type: TEXT/PLAIN, Size: 12290 bytes --]
On Wed, 16 May 2012, Nguyễn Thái Ngọc Duy wrote:
> Move !to_reuse and to_reuse write code out into two separate functions
> and remove "goto no_reuse;" hack
>
> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
I like this very much.
Acked-by: Nicolas Pitre <nico@fluxnic.net>
> ---
> builtin/pack-objects.c | 322 ++++++++++++++++++++++++++----------------------
> 1 files changed, 172 insertions(+), 150 deletions(-)
>
> diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
> index b2e0940..ccfcbad 100644
> --- a/builtin/pack-objects.c
> +++ b/builtin/pack-objects.c
> @@ -200,22 +200,178 @@ static void copy_pack_data(struct sha1file *f,
> }
>
> /* Return 0 if we will bust the pack-size limit */
> -static unsigned long write_object(struct sha1file *f,
> - struct object_entry *entry,
> - off_t write_offset)
> +static unsigned long write_no_reuse_object(struct sha1file *f, struct object_entry *entry,
> + unsigned long limit, int usable_delta)
> {
> - unsigned long size, limit, datalen;
> - void *buf;
> + unsigned long size, datalen;
> unsigned char header[10], dheader[10];
> unsigned hdrlen;
> enum object_type type;
> + void *buf;
> +
> + if (!usable_delta) {
> + buf = read_sha1_file(entry->idx.sha1, &type, &size);
> + if (!buf)
> + die("unable to read %s", sha1_to_hex(entry->idx.sha1));
> + /*
> + * make sure no cached delta data remains from a
> + * previous attempt before a pack split occurred.
> + */
> + free(entry->delta_data);
> + entry->delta_data = NULL;
> + entry->z_delta_size = 0;
> + } else if (entry->delta_data) {
> + size = entry->delta_size;
> + buf = entry->delta_data;
> + entry->delta_data = NULL;
> + type = (allow_ofs_delta && entry->delta->idx.offset) ?
> + OBJ_OFS_DELTA : OBJ_REF_DELTA;
> + } else {
> + buf = get_delta(entry);
> + size = entry->delta_size;
> + type = (allow_ofs_delta && entry->delta->idx.offset) ?
> + OBJ_OFS_DELTA : OBJ_REF_DELTA;
> + }
> +
> + if (entry->z_delta_size)
> + datalen = entry->z_delta_size;
> + else
> + datalen = do_compress(&buf, size);
> +
> + /*
> + * The object header is a byte of 'type' followed by zero or
> + * more bytes of length.
> + */
> + hdrlen = encode_in_pack_object_header(type, size, header);
> +
> + if (type == OBJ_OFS_DELTA) {
> + /*
> + * Deltas with relative base contain an additional
> + * encoding of the relative offset for the delta
> + * base from this object's position in the pack.
> + */
> + off_t ofs = entry->idx.offset - entry->delta->idx.offset;
> + unsigned pos = sizeof(dheader) - 1;
> + dheader[pos] = ofs & 127;
> + while (ofs >>= 7)
> + dheader[--pos] = 128 | (--ofs & 127);
> + if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
> + free(buf);
> + return 0;
> + }
> + sha1write(f, header, hdrlen);
> + sha1write(f, dheader + pos, sizeof(dheader) - pos);
> + hdrlen += sizeof(dheader) - pos;
> + } else if (type == OBJ_REF_DELTA) {
> + /*
> + * Deltas with a base reference contain
> + * an additional 20 bytes for the base sha1.
> + */
> + if (limit && hdrlen + 20 + datalen + 20 >= limit) {
> + free(buf);
> + return 0;
> + }
> + sha1write(f, header, hdrlen);
> + sha1write(f, entry->delta->idx.sha1, 20);
> + hdrlen += 20;
> + } else {
> + if (limit && hdrlen + datalen + 20 >= limit) {
> + free(buf);
> + return 0;
> + }
> + sha1write(f, header, hdrlen);
> + }
> + sha1write(f, buf, datalen);
> + free(buf);
> +
> + return hdrlen + datalen;
> +}
> +
> +/* Return 0 if we will bust the pack-size limit */
> +static unsigned long write_reuse_object(struct sha1file *f, struct object_entry *entry,
> + unsigned long limit, int usable_delta)
> +{
> + struct packed_git *p = entry->in_pack;
> + struct pack_window *w_curs = NULL;
> + struct revindex_entry *revidx;
> + off_t offset;
> + enum object_type type = entry->type;
> + unsigned long datalen;
> + unsigned char header[10], dheader[10];
> + unsigned hdrlen;
> +
> + if (entry->delta)
> + type = (allow_ofs_delta && entry->delta->idx.offset) ?
> + OBJ_OFS_DELTA : OBJ_REF_DELTA;
> + hdrlen = encode_in_pack_object_header(type, entry->size, header);
> +
> + offset = entry->in_pack_offset;
> + revidx = find_pack_revindex(p, offset);
> + datalen = revidx[1].offset - offset;
> + if (!pack_to_stdout && p->index_version > 1 &&
> + check_pack_crc(p, &w_curs, offset, datalen, revidx->nr)) {
> + error("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1));
> + unuse_pack(&w_curs);
> + return write_no_reuse_object(f, entry, limit, usable_delta);
> + }
> +
> + offset += entry->in_pack_header_size;
> + datalen -= entry->in_pack_header_size;
> +
> + if (!pack_to_stdout && p->index_version == 1 &&
> + check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) {
> + error("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1));
> + unuse_pack(&w_curs);
> + return write_no_reuse_object(f, entry, limit, usable_delta);
> + }
> +
> + if (type == OBJ_OFS_DELTA) {
> + off_t ofs = entry->idx.offset - entry->delta->idx.offset;
> + unsigned pos = sizeof(dheader) - 1;
> + dheader[pos] = ofs & 127;
> + while (ofs >>= 7)
> + dheader[--pos] = 128 | (--ofs & 127);
> + if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
> + unuse_pack(&w_curs);
> + return 0;
> + }
> + sha1write(f, header, hdrlen);
> + sha1write(f, dheader + pos, sizeof(dheader) - pos);
> + hdrlen += sizeof(dheader) - pos;
> + reused_delta++;
> + } else if (type == OBJ_REF_DELTA) {
> + if (limit && hdrlen + 20 + datalen + 20 >= limit) {
> + unuse_pack(&w_curs);
> + return 0;
> + }
> + sha1write(f, header, hdrlen);
> + sha1write(f, entry->delta->idx.sha1, 20);
> + hdrlen += 20;
> + reused_delta++;
> + } else {
> + if (limit && hdrlen + datalen + 20 >= limit) {
> + unuse_pack(&w_curs);
> + return 0;
> + }
> + sha1write(f, header, hdrlen);
> + }
> + copy_pack_data(f, p, &w_curs, offset, datalen);
> + unuse_pack(&w_curs);
> + reused++;
> + return hdrlen + datalen;
> +}
> +
> +/* Return 0 if we will bust the pack-size limit */
> +static unsigned long write_object(struct sha1file *f,
> + struct object_entry *entry,
> + off_t write_offset)
> +{
> + unsigned long limit, len;
> int usable_delta, to_reuse;
>
> if (!pack_to_stdout)
> crc32_begin(f);
>
> - type = entry->type;
> -
> /* apply size limit if limited packsize and not first object */
> if (!pack_size_limit || !nr_written)
> limit = 0;
> @@ -243,11 +399,11 @@ static unsigned long write_object(struct sha1file *f,
> to_reuse = 0; /* explicit */
> else if (!entry->in_pack)
> to_reuse = 0; /* can't reuse what we don't have */
> - else if (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA)
> + else if (entry->type == OBJ_REF_DELTA || entry->type == OBJ_OFS_DELTA)
> /* check_object() decided it for us ... */
> to_reuse = usable_delta;
> /* ... but pack split may override that */
> - else if (type != entry->in_pack_type)
> + else if (entry->type != entry->in_pack_type)
> to_reuse = 0; /* pack has delta which is unusable */
> else if (entry->delta)
> to_reuse = 0; /* we want to pack afresh */
> @@ -256,153 +412,19 @@ static unsigned long write_object(struct sha1file *f,
> * and we do not need to deltify it.
> */
>
> - if (!to_reuse) {
> - no_reuse:
> - if (!usable_delta) {
> - buf = read_sha1_file(entry->idx.sha1, &type, &size);
> - if (!buf)
> - die("unable to read %s", sha1_to_hex(entry->idx.sha1));
> - /*
> - * make sure no cached delta data remains from a
> - * previous attempt before a pack split occurred.
> - */
> - free(entry->delta_data);
> - entry->delta_data = NULL;
> - entry->z_delta_size = 0;
> - } else if (entry->delta_data) {
> - size = entry->delta_size;
> - buf = entry->delta_data;
> - entry->delta_data = NULL;
> - type = (allow_ofs_delta && entry->delta->idx.offset) ?
> - OBJ_OFS_DELTA : OBJ_REF_DELTA;
> - } else {
> - buf = get_delta(entry);
> - size = entry->delta_size;
> - type = (allow_ofs_delta && entry->delta->idx.offset) ?
> - OBJ_OFS_DELTA : OBJ_REF_DELTA;
> - }
> -
> - if (entry->z_delta_size)
> - datalen = entry->z_delta_size;
> - else
> - datalen = do_compress(&buf, size);
> -
> - /*
> - * The object header is a byte of 'type' followed by zero or
> - * more bytes of length.
> - */
> - hdrlen = encode_in_pack_object_header(type, size, header);
> -
> - if (type == OBJ_OFS_DELTA) {
> - /*
> - * Deltas with relative base contain an additional
> - * encoding of the relative offset for the delta
> - * base from this object's position in the pack.
> - */
> - off_t ofs = entry->idx.offset - entry->delta->idx.offset;
> - unsigned pos = sizeof(dheader) - 1;
> - dheader[pos] = ofs & 127;
> - while (ofs >>= 7)
> - dheader[--pos] = 128 | (--ofs & 127);
> - if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
> - free(buf);
> - return 0;
> - }
> - sha1write(f, header, hdrlen);
> - sha1write(f, dheader + pos, sizeof(dheader) - pos);
> - hdrlen += sizeof(dheader) - pos;
> - } else if (type == OBJ_REF_DELTA) {
> - /*
> - * Deltas with a base reference contain
> - * an additional 20 bytes for the base sha1.
> - */
> - if (limit && hdrlen + 20 + datalen + 20 >= limit) {
> - free(buf);
> - return 0;
> - }
> - sha1write(f, header, hdrlen);
> - sha1write(f, entry->delta->idx.sha1, 20);
> - hdrlen += 20;
> - } else {
> - if (limit && hdrlen + datalen + 20 >= limit) {
> - free(buf);
> - return 0;
> - }
> - sha1write(f, header, hdrlen);
> - }
> - sha1write(f, buf, datalen);
> - free(buf);
> - }
> - else {
> - struct packed_git *p = entry->in_pack;
> - struct pack_window *w_curs = NULL;
> - struct revindex_entry *revidx;
> - off_t offset;
> -
> - if (entry->delta)
> - type = (allow_ofs_delta && entry->delta->idx.offset) ?
> - OBJ_OFS_DELTA : OBJ_REF_DELTA;
> - hdrlen = encode_in_pack_object_header(type, entry->size, header);
> -
> - offset = entry->in_pack_offset;
> - revidx = find_pack_revindex(p, offset);
> - datalen = revidx[1].offset - offset;
> - if (!pack_to_stdout && p->index_version > 1 &&
> - check_pack_crc(p, &w_curs, offset, datalen, revidx->nr)) {
> - error("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1));
> - unuse_pack(&w_curs);
> - goto no_reuse;
> - }
> -
> - offset += entry->in_pack_header_size;
> - datalen -= entry->in_pack_header_size;
> - if (!pack_to_stdout && p->index_version == 1 &&
> - check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) {
> - error("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1));
> - unuse_pack(&w_curs);
> - goto no_reuse;
> - }
> + if (!to_reuse)
> + len = write_no_reuse_object(f, entry, limit, usable_delta);
> + else
> + len = write_reuse_object(f, entry, limit, usable_delta);
> + if (!len)
> + return 0;
>
> - if (type == OBJ_OFS_DELTA) {
> - off_t ofs = entry->idx.offset - entry->delta->idx.offset;
> - unsigned pos = sizeof(dheader) - 1;
> - dheader[pos] = ofs & 127;
> - while (ofs >>= 7)
> - dheader[--pos] = 128 | (--ofs & 127);
> - if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
> - unuse_pack(&w_curs);
> - return 0;
> - }
> - sha1write(f, header, hdrlen);
> - sha1write(f, dheader + pos, sizeof(dheader) - pos);
> - hdrlen += sizeof(dheader) - pos;
> - reused_delta++;
> - } else if (type == OBJ_REF_DELTA) {
> - if (limit && hdrlen + 20 + datalen + 20 >= limit) {
> - unuse_pack(&w_curs);
> - return 0;
> - }
> - sha1write(f, header, hdrlen);
> - sha1write(f, entry->delta->idx.sha1, 20);
> - hdrlen += 20;
> - reused_delta++;
> - } else {
> - if (limit && hdrlen + datalen + 20 >= limit) {
> - unuse_pack(&w_curs);
> - return 0;
> - }
> - sha1write(f, header, hdrlen);
> - }
> - copy_pack_data(f, p, &w_curs, offset, datalen);
> - unuse_pack(&w_curs);
> - reused++;
> - }
> if (usable_delta)
> written_delta++;
> written++;
> if (!pack_to_stdout)
> entry->idx.crc32 = crc32_end(f);
> - return hdrlen + datalen;
> + return len;
> }
>
> enum write_one_status {
> --
> 1.7.8.36.g69ee2
>
next prev parent reply other threads:[~2012-05-19 2:44 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-12 10:26 [PATCH] pack-objects: use streaming interface for reading large loose blobs Nguyễn Thái Ngọc Duy
2012-05-12 16:51 ` Nicolas Pitre
2012-05-13 4:37 ` [PATCH v2] " Nguyễn Thái Ngọc Duy
2012-05-14 15:56 ` Junio C Hamano
2012-05-14 19:43 ` Junio C Hamano
2012-05-15 11:18 ` Nguyen Thai Ngoc Duy
2012-05-15 15:27 ` Junio C Hamano
2012-05-16 7:09 ` Nguyen Thai Ngoc Duy
2012-05-16 12:02 ` [PATCH v2 1/4] streaming: allow to call close_istream(NULL); Nguyễn Thái Ngọc Duy
2012-05-16 12:02 ` [PATCH v2 2/4] pack-objects, streaming: turn "xx >= big_file_threshold" to ".. > .." Nguyễn Thái Ngọc Duy
2012-05-18 21:05 ` Junio C Hamano
2012-05-16 12:02 ` [PATCH v2 3/4] pack-objects: refactor write_object() Nguyễn Thái Ngọc Duy
2012-05-18 21:16 ` Junio C Hamano
2012-05-19 2:43 ` Nicolas Pitre [this message]
2012-05-16 12:02 ` [PATCH v2 4/4] pack-objects: use streaming interface for reading large loose blobs Nguyễn Thái Ngọc Duy
2012-05-18 21:02 ` [PATCH v2 1/4] streaming: allow to call close_istream(NULL); Junio C Hamano
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=alpine.LFD.2.02.1205182243180.13185@xanadu.home \
--to=nico@fluxnic.net \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=pclouds@gmail.com \
/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).