Re: [PATCH] read-cache.c: index format v5 -- 30% smaller/faster than v4
- From
Junio C Hamano <gitster@pobox.com>
- Date
- Feb 13, 2019, 22:27 UTC
- Message-ID
- <xmqq1s4bb9y5.fsf@gitster-ct.c.googlers.com>
- In-Reply-To
- <20190213120807.25326-1-pclouds@gmail.com>
Nguyễn Thái Ngọc Duy <pclouds@gmail.com> writes:
Show 6 quoted lines
> @@ -1749,16 +1750,16 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool, > * number of bytes to be stripped from the end of the previous name, > * and the bytes to append to the result, to come up with its name. > */ > - int expand_name_field = version == 4; > + int expand_name_field = version >= 4;
The code can be lazy like this, insteasd of being more descriptive to say "version 4 or 5", because we won't accept version 6 or later anyway. Which is OK, I guess.
Show 9 quoted lines
> if (flags & CE_EXTENDED) {
> - struct ondisk_cache_entry_extended *ondisk2;
> + const struct ondisk_cache_entry_extended *ondisk2 = mmap;
> int extended_flags;
> - ondisk2 = (struct ondisk_cache_entry_extended *)ondisk;
> +
> extended_flags = get_be16(&ondisk2->flags2) << 16;
> /* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
> if (extended_flags & ~CE_EXTENDED_FLAGS)This part may be a good clean-up regardless.
Show 15 quoted lines
> @@ -1820,6 +1821,113 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
> return ce;
> }
>
> +enum same_value_bit {
> + DELTA_FORMAT = 1 << 0,
> + SAME_CTIME = 1 << 1, /* only covers sec, not nsec */
> + SAME_MTIME = 1 << 2, /* only covers sec, not nsec */
> + SAME_DEV = 1 << 3,
> + SAME_INO = 1 << 4,
> + SAME_MODE = 1 << 5,
> + SAME_UID = 1 << 6,
> + SAME_GID = 1 << 7,
> + SAME_FLAGS = 1 << 7
> +};Hmph, really?
Show 5 quoted lines
> +static struct cache_entry no_previous_ce;
> +
> +static uintmax_t decode_varoffset(const unsigned char **bufp, uintmax_t prev)
> +{
> + uintmax_t val = decode_varint(bufp);You'd need to make sure (1) !val, which indicates an overflow of the varint, and (2) bufp after decoding haven't over-read the mmapped index file. We may want to improve decode_varint() API so that we can detect truncated data (i.e. (2)) more reliably without first reading too much. Loose error checking like these would make good targets for fuzz tests, I suspect.
> + return val & 1 ? prev - (val >> 1) : prev + (val >> 1); > +}
So, the LSB is used for sign, and the magnitude is shifted by one? OK.
Show 11 quoted lines
> +static uintmax_t decode_varoffset_same(const unsigned char **bufp, uintmax_t prev,
> + int same_flag)
> +{
> + return same_flag ? prev : decode_varoffset(bufp, prev);
> +}
> +
> +static uintmax_t decode_varint_same(const unsigned char **bufp, uintmax_t prev,
> + int same_flag)
> +{
> + return same_flag ? prev : decode_varint(bufp);
> +}Likewise about two error conditions.
Show 19 quoted lines
> @@ -1967,12 +2075,18 @@ static unsigned long load_cache_entry_block(struct index_state *istate,
> unsigned long src_offset = start_offset;
>
> for (i = offset; i < offset + nr; i++) {
> - struct ondisk_cache_entry *disk_ce;
> struct cache_entry *ce;
> unsigned long consumed;
>
> - disk_ce = (struct ondisk_cache_entry *)(mmap + src_offset);
> - ce = create_from_disk(ce_mem_pool, istate->version, disk_ce, &consumed, previous_ce);
> + if (istate->version <= 4)
> + ce = create_from_disk(ce_mem_pool, istate->version,
> + mmap + src_offset, &consumed,
> + previous_ce);
> + else
> + ce = create_from_disk_v5(ce_mem_pool,
> + mmap + src_offset,
> + &consumed,
> + previous_ce);This goes directly against the spirit of "create_from_disk()" internal API, doesn't it? It takes istate->version because it is an implementation detail of that function how bytes at &mmap[src_offset] are consumed, possibly using previous_ce information.
IOW, I think the version dependent switch should go inside that function and not in this loop.
> +static int ce_write_varint(git_hash_ctx *c, int fd, uintmax_t value)
> +{
> + unsigned char varint[16];We may want to do something about these "16".
> +static int ce_write_varoffset(git_hash_ctx *c, int fd, uintmax_t next, uintmax_t prev)
> +{
> + unsigned char varint[16];