Re: [PATCH] cat-file: speed up default format
On 6/15/26 7:06 PM, Jeff King wrote:
Show 17 quoted lines
> On Mon, Jun 15, 2026 at 12:53:26PM -0400, Jeff King wrote:
>
>> It uses per-atom callback functions which is nice and clean, though we
>> might be able to do even better with a big ugly switch() statement.
>
> Being the curious sort, I swapped it out for a big switch statement.
> Patch below, but it does not seem to be any faster.
>
> So the bottom line is I think you could gain a little bit of performance
> by pre-parsing (versus strbuf_expand() on each object). Around 3% for
> something that actually looks at the objects, though more like 15% if
> for just dumping the objectnames.
>
> IMHO that is probably not worth it for a custom parsing system just for
> cat-file. But if we were to finally unify ref-filter and cat-file (and
> even --pretty=format) then it would probably worth doing this kind of
> pre-parsing.
It could be worth it for cat-file alone if we find the right balance, as it already does do a separate parsing step, but that is awkward with its mark_query checks all over the place and remembers only object property requirements and no other format string details.
Making the opcodes small should be beneficial. We need only a handful of them, so a byte each should suffice. We can use a strbuf for that.
We can also store literal characters in there. An opcode plus with a payload char incurs an overhead of 50%, which sounds high, but at least the default format only has two of them and it's much better than storing pointer plus size for an overhead of more than 90% in case of a single char.
That gets us closer to native speed, at least on an Apple M1:
Benchmark 1: ./git_fp cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
Time (mean ± σ): 992.7 ms ± 3.2 ms [User: 967.5 ms, System: 23.8 ms]
Range (min … max): 990.1 ms … 1000.7 ms 10 runs
Benchmark 2: ./git_switch cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
Time (mean ± σ): 991.8 ms ± 1.6 ms [User: 967.0 ms, System: 23.3 ms]
Range (min … max): 989.3 ms … 994.4 ms 10 runs
Benchmark 3: ./git cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
Time (mean ± σ): 985.8 ms ± 2.9 ms [User: 960.5 ms, System: 23.6 ms]
Range (min … max): 982.9 ms … 993.0 ms 10 runs
Benchmark 4: ./git cat-file --batch-all-objects --batch-check='%(objectname) %(objecttype) %(objectsize)'
Time (mean ± σ): 982.1 ms ± 3.2 ms [User: 956.7 ms, System: 23.6 ms]
Range (min … max): 979.2 ms … 989.2 ms 10 runs
Summary
./git cat-file --batch-all-objects --batch-check='%(objectname) %(objecttype) %(objectsize)' ran
1.00 ± 0.00 times faster than ./git cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
1.01 ± 0.00 times faster than ./git_switch cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
1.01 ± 0.00 times faster than ./git_fp cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'A Ryzen laptop gives me noisy numbers that seem to suggest your switch-based code already won, but the more compact representation is at least not worse:
Benchmark 1: ./git_fp cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
Time (mean ± σ): 397.5 ms ± 8.0 ms [User: 326.9 ms, System: 39.4 ms]
Range (min … max): 388.1 ms … 410.0 ms 10 runs
Benchmark 2: ./git_switch cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
Time (mean ± σ): 388.2 ms ± 4.2 ms [User: 318.2 ms, System: 39.2 ms]
Range (min … max): 382.8 ms … 395.7 ms 10 runs
Benchmark 3: ./git cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
Time (mean ± σ): 385.5 ms ± 5.7 ms [User: 311.2 ms, System: 43.2 ms]
Range (min … max): 377.0 ms … 392.9 ms 10 runs
Benchmark 4: ./git cat-file --batch-all-objects --batch-check='%(objectname) %(objecttype) %(objectsize)'
Time (mean ± σ): 397.5 ms ± 8.4 ms [User: 321.9 ms, System: 45.2 ms]
Range (min … max): 382.1 ms … 406.5 ms 10 runs
Summary
./git cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)' ran
1.01 ± 0.02 times faster than ./git_switch cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
1.03 ± 0.03 times faster than ./git_fp cat-file --batch-all-objects --batch-check='%(objectname)-%(objecttype)-%(objectsize)'
1.03 ± 0.03 times faster than ./git cat-file --batch-all-objects --batch-check='%(objectname) %(objecttype) %(objectsize)'René
Show changes to builtin/cat-file.c +37 −71
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 0d1998784c..5667a13e93 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -36,8 +36,6 @@ enum batch_mode {
BATCH_MODE_QUEUE_AND_DISPATCH,
};
-struct format_item;
-
struct batch_options {
struct list_objects_filter_options objects_filter;
int enabled;
@@ -50,7 +48,7 @@ struct batch_options {
char input_delim;
char output_delim;
const char *format;
- struct format_item *parsed_format;
+ struct strbuf parsed_format;
};
static const char *force_path;
@@ -320,30 +318,16 @@ struct expand_data {
};
#define EXPAND_DATA_INIT { .mode = S_IFINVALID }
-struct format_item {
- enum {
- FORMAT_TYPE_END = 0,
- FORMAT_TYPE_LITERAL,
- FORMAT_TYPE_OBJECTNAME,
- FORMAT_TYPE_OBJECTTYPE,
- FORMAT_TYPE_OBJECTSIZE,
- FORMAT_TYPE_OBJECTSIZE_DISK,
- FORMAT_TYPE_REST,
- FORMAT_TYPE_DELTABASE,
- FORMAT_TYPE_OBJECTMODE,
- } type;
- union {
- struct {
- const char *p;
- size_t len;
- } literal;
- } u;
- /*
- * We could make a true tree here with child/next pointers, which would
- * be necessary if we had recursive formats, like %(if). But for our
- * simple formats for now it is enough to have a linear set of items,
- * so we'll just allocate an array and terminate it with a NULL entry.
- */
+
+enum item_type {
+ FORMAT_TYPE_LITERAL,
+ FORMAT_TYPE_OBJECTNAME,
+ FORMAT_TYPE_OBJECTTYPE,
+ FORMAT_TYPE_OBJECTSIZE,
+ FORMAT_TYPE_OBJECTSIZE_DISK,
+ FORMAT_TYPE_REST,
+ FORMAT_TYPE_DELTABASE,
+ FORMAT_TYPE_OBJECTMODE,
};
static int is_atom(const char *atom, const char *s, int slen)
@@ -352,84 +336,66 @@ static int is_atom(const char *atom, const char *s, int slen)
return alen == slen && !memcmp(atom, s, alen);
}
-static int parse_atom(struct format_item *fmt, const char *atom, int len,
+static int parse_atom(struct strbuf *parsed_format, const char *atom, int len,
struct expand_data *data)
{
if (is_atom("objectname", atom, len)) {
- fmt->type = FORMAT_TYPE_OBJECTNAME;
+ strbuf_addch(parsed_format, FORMAT_TYPE_OBJECTNAME);
} else if (is_atom("objecttype", atom, len)) {
data->info.typep = &data->type;
- fmt->type = FORMAT_TYPE_OBJECTTYPE;
+ strbuf_addch(parsed_format, FORMAT_TYPE_OBJECTTYPE);
} else if (is_atom("objectsize", atom, len)) {
data->info.sizep = &data->size;
- fmt->type = FORMAT_TYPE_OBJECTSIZE;
+ strbuf_addch(parsed_format, FORMAT_TYPE_OBJECTSIZE);
} else if (is_atom("objectsize:disk", atom, len)) {
data->info.disk_sizep = &data->disk_size;
- fmt->type = FORMAT_TYPE_OBJECTSIZE_DISK;
+ strbuf_addch(parsed_format, FORMAT_TYPE_OBJECTSIZE_DISK);
} else if (is_atom("rest", atom, len)) {
data->split_on_whitespace = 1;
- fmt->type = FORMAT_TYPE_REST;
+ strbuf_addch(parsed_format, FORMAT_TYPE_REST);
} else if (is_atom("deltabase", atom, len)) {
data->info.delta_base_oid = &data->delta_base_oid;
- fmt->type = FORMAT_TYPE_DELTABASE;
+ strbuf_addch(parsed_format, FORMAT_TYPE_DELTABASE);
} else if (is_atom("objectmode", atom, len)) {
- fmt->type = FORMAT_TYPE_OBJECTMODE;
+ strbuf_addch(parsed_format, FORMAT_TYPE_OBJECTMODE);
} else
return 0;
return 1;
}
-static struct format_item *parse_format(const char *start,
- struct expand_data *data)
+static void parse_format(struct strbuf *parsed_format,
+ const char *start, struct expand_data *data)
{
- struct format_item *ret = NULL;
- size_t nr = 0, alloc = 0;
-
while (1) {
- const char *percent = strchrnul(start, '%');
const char *end;
- if (percent != start) {
- ALLOC_GROW(ret, nr + 1, alloc);
- ret[nr].type = FORMAT_TYPE_LITERAL;
- ret[nr].u.literal.p = start;
- ret[nr].u.literal.len = percent - start;
- nr++;
+ while (*start && *start != '%') {
+ strbuf_addch(parsed_format, FORMAT_TYPE_LITERAL);
+ strbuf_addch(parsed_format, *start++);
}
- if (!*percent)
+ if (!*start)
break;
- start = percent + 1;
+ start++;
- ALLOC_GROW(ret, nr + 1, alloc);
if (skip_prefix(start, "%", &start) || *start != '(') {
- ret[nr].type = FORMAT_TYPE_LITERAL;
- ret[nr].u.literal.p = "%";
- ret[nr].u.literal.len = 1;
+ strbuf_addch(parsed_format, FORMAT_TYPE_LITERAL);
+ strbuf_addch(parsed_format, '%');
} else if ((end = strchr(start + 1, ')')) &&
- parse_atom(&ret[nr], start + 1, end - start - 1, data)) {
+ parse_atom(parsed_format, start + 1, end - start - 1, data)) {
start = end + 1;
} else {
strbuf_expand_bad_format(start, "cat-file");
}
- nr++;
}
-
- ALLOC_GROW(ret, nr + 1, alloc);
- ret[nr].type = FORMAT_TYPE_END;
-
- return ret;
}
-static void expand_format(struct strbuf *sb, struct format_item *fmt,
+static void expand_format(struct strbuf *sb, struct strbuf *parsed_format,
struct expand_data *data)
{
- for (; fmt->type; fmt++)
- switch (fmt->type) {
- case FORMAT_TYPE_END:
- BUG("we should have already left the loop!");
- break;
+ for (size_t i = 0; i < parsed_format->len; i++)
+ switch (parsed_format->buf[i]) {
case FORMAT_TYPE_OBJECTNAME:
strbuf_add_oid_hex(sb, &data->oid);
break;
@@ -453,7 +419,7 @@ static void expand_format(struct strbuf *sb, struct format_item *fmt,
strbuf_addf(sb, "%06o", data->mode);
break;
case FORMAT_TYPE_LITERAL:
- strbuf_add(sb, fmt->u.literal.p, fmt->u.literal.len);
+ strbuf_addch(sb, parsed_format->buf[++i]);
}
}
@@ -641,7 +607,7 @@ static void batch_object_write(const char *obj_name,
if (!opt->format) {
print_default_format(scratch, data, opt);
} else {
- expand_format(scratch, opt->parsed_format, data);
+ expand_format(scratch, &opt->parsed_format, data);
strbuf_addch(scratch, opt->output_delim);
}
@@ -1010,9 +976,8 @@ static int batch_objects(struct batch_options *opt)
int save_warning;
int retval = 0;
- opt->parsed_format = parse_format(opt->format ?
- opt->format : DEFAULT_FORMAT,
- &data);
+ parse_format(&opt->parsed_format,
+ opt->format ? opt->format : DEFAULT_FORMAT, &data);
if (opt->transform_mode)
data.split_on_whitespace = 1;
@@ -1152,6 +1117,7 @@ int cmd_cat_file(int argc,
const char *exp_type = NULL, *obj_name = NULL;
struct batch_options batch = {
.objects_filter = LIST_OBJECTS_FILTER_INIT,
+ .parsed_format = STRBUF_INIT,
};
int unknown_type = 0;
int input_nul_terminated = 0;