Re: [PATCH v3 6/9] bugreport: count loose objects

[Johannes Schindelin <Johannes.Schindelin@gmx.de>]

Hi Emily,

On Thu, 24 Oct 2019, Emily Shaffer wrote:

> The number of unpacked objects in a user's repository may help us
> understand the root of the problem they're seeing, especially if a
> command is running unusually slowly.
>
> Rather than directly invoking 'git-count-objects', which may sometimes
> fail unexpectedly on Git for Windows, manually count the contents of
> .git/objects. Additionally, since we may wish to inspect other
> directories' contents for bugreport in the future, put the directory
> listing into a helper function.

Thank you, much appreciated!

I guess the next step is to count the number of packs, and the number of
submodules ;-)

>
> Signed-off-by: Emily Shaffer <emilyshaffer@google.com>
> ---
>  bugreport.c         | 72 +++++++++++++++++++++++++++++++++++++++++++++
>  bugreport.h         |  6 ++++
>  builtin/bugreport.c |  4 +++
>  3 files changed, 82 insertions(+)
>
> diff --git a/bugreport.c b/bugreport.c
> index 9d7f44ff28..54e1d47103 100644
> --- a/bugreport.c
> +++ b/bugreport.c
> @@ -5,8 +5,11 @@
>  #include "exec-cmd.h"
>  #include "help.h"
>  #include "run-command.h"
> +#include "strbuf.h"

Why not append this to the end of the `#include` list, as is common in
Git's commit history?

>  #include "version.h"
>
> +#include "dirent.h"

This header (although with pointy brackets instead of double quotes) is
already included in `git-compat-util.h`

> +
>  /**
>   * A sorted list of config options which we will add to the bugreport. Managed
>   * by 'gather_whitelist(...)'.
> @@ -147,3 +150,72 @@ void get_populated_hooks(struct strbuf *hook_info)
>  		}
>  	}
>  }
> +
> +/**
> + * Fill 'contents' with the contents of the dir at 'dirpath'.

Since you start this comment in JavaDoc style, there should be an almost
empty line after this one ("almost" because it still contains the
asterisk, of course).

> + * If 'filter' is nonzero, the contents are filtered on d_type as 'type' - see
> + * 'man readdir'. opendir() doesn't take string length as an arg, so don't
> + * bother passing it in.
> + */
> +void list_contents_of_dir(struct string_list *contents, struct strbuf *dirpath,

Shouldn't this be `static`?

> +			  int filter, unsigned char type)
> +{
> +	struct dirent *dir = NULL;
> +	DIR *dh = NULL;
> +
> +	dh = opendir(dirpath->buf);
> +	while (dh && (dir = readdir(dh))) {
> +		if (!filter || type == dir->d_type) {
> +			string_list_append(contents, dir->d_name);
> +		}
> +	}
> +}
> +
> +
> +void get_object_counts(struct strbuf *obj_info)

Oops. This function is no longer used.

> +{
> +	struct child_process cp = CHILD_PROCESS_INIT;
> +	struct strbuf std_out = STRBUF_INIT;
> +
> +	argv_array_push(&cp.args, "count-objects");
> +	argv_array_push(&cp.args, "-vH");
> +	cp.git_cmd = 1;
> +	capture_command(&cp, &std_out, 0);
> +
> +	strbuf_reset(obj_info);
> +	strbuf_addstr(obj_info, "git-count-objects -vH:\n");
> +	strbuf_addbuf(obj_info, &std_out);
> +}
> +
> +void get_loose_object_summary(struct strbuf *obj_info)
> +{
> +	struct strbuf dirpath = STRBUF_INIT;
> +	struct string_list subdirs = STRING_LIST_INIT_DUP;
> +	struct string_list_item *subdir;
> +
> +	strbuf_reset(obj_info);
> +
> +	strbuf_addstr(&dirpath, get_object_directory());
> +	strbuf_complete(&dirpath, '/');
> +
> +	list_contents_of_dir(&subdirs, &dirpath, 1, DT_DIR);
> +
> +	for_each_string_list_item(subdir, &subdirs)
> +	{
> +		struct strbuf subdir_buf = STRBUF_INIT;
> +		struct string_list objects = STRING_LIST_INIT_DUP;
> +
> +		/*
> +		 * Only interested in loose objects - so dirs named with the
> +		 * first byte of the object ID
> +		 */
> +		if (strlen(subdir->string) != 2 || !strcmp(subdir->string, ".."))
> +			continue;
> +
> +		strbuf_addbuf(&subdir_buf, &dirpath);
> +		strbuf_addstr(&subdir_buf, subdir->string);
> +		list_contents_of_dir(&objects, &subdir_buf, 0, 0);
> +		strbuf_addf(obj_info, "%s: %d objects\n", subdir->string,
> +			    objects.nr);

Hmm. Not only does this leak `objects`, it also throws away the contents
that we so painfully constructed.

Wouldn't it make more sense to do something like this instead?

static int is_hex(const char *string, size_t count)
{
	for (; count; string++, count--)
		if (hexval(*string) < 0)
			return 0;
	return 1;
}

static ssize_t count_loose_objects(struct strbuf *objects_path)
{
	ssize_t ret = 0;
	size_t len;
	struct dirent *d;
	DIR *dir, *subdir;

	dir = opendir(objects_path->buf);
	if (!dir)
		return -1;

	strbuf_complete(objects_path, '/');
	len = objects_path->len;
	while ((d = readdir(dir))) {
		if (d->d_type != DT_DIR)
			continue;
		strbuf_setlen(objects_path, len);
		strbuf_addstr(objects_path, d->d_name);
		subdir = opendir(objects_path->buf);
		if (!subdir)
			continue;
		while ((d = readdir(subdir)))
			if (d->dt_type == DT_REG &&
			    is_hex(dir->d_name, the_repository->hash_algo->hexsz))
				ret++;
		closedir(subdir);
	}
	closedir(dir);
	strbuf_reset(objects_path, len);
	return ret;
}

Ciao,
Dscho

> +	}
> +}
> diff --git a/bugreport.h b/bugreport.h
> index 942a5436e3..09ad0c2599 100644
> --- a/bugreport.h
> +++ b/bugreport.h
> @@ -18,3 +18,9 @@ void get_whitelisted_config(struct strbuf *sys_info);
>   * contents of hook_info will be discarded.
>   */
>  void get_populated_hooks(struct strbuf *hook_info);
> +
> +/**
> + * Adds the output of `git count-object -vH`. The previous contents of hook_info
> + * will be discarded.
> + */
> +void get_loose_object_summary(struct strbuf *obj_info);
> diff --git a/builtin/bugreport.c b/builtin/bugreport.c
> index a0eefba498..b2ab194207 100644
> --- a/builtin/bugreport.c
> +++ b/builtin/bugreport.c
> @@ -64,6 +64,10 @@ int cmd_bugreport(int argc, const char **argv, const char *prefix)
>  	get_populated_hooks(&buffer);
>  	strbuf_write(&buffer, report);
>
> +	add_header(report, "Object Counts");
> +	get_loose_object_summary(&buffer);
> +	strbuf_write(&buffer, report);
> +
>  	fclose(report);
>
>  	launch_editor(report_path.buf, NULL, NULL);
> --
> 2.24.0.rc0.303.g954a862665-goog
>
>