git/t/helper/test-cache-tree.c

70 lines
2 KiB
C
Raw Normal View History

#define USE_THE_INDEX_VARIABLE
cache-tree: add perf test comparing update and prime Add a performance test comparing the execution times of 'prime_cache_tree()' and 'cache_tree_update(_, WRITE_TREE_SILENT | WRITE_TREE_REPAIR)'. The goal of comparing these two is to identify which is the faster method for rebuilding an invalid cache tree, ultimately to remove one when both are (reundantly) called in immediate succession. Both methods are fast, so the new tests in 'p0090-cache-tree.sh' must call each tested function multiple times to ensure the reported times (to 0.01s resolution) convey the differences between them. The tests compare the timing of a 'test-tool cache-tree' run as a no-op (to capture a baseline for the overhead associated with running the tool), 'cache_tree_update()', and 'prime_cache_tree()' on four scenarios: - A completely valid cache tree - A cache tree with 2 invalid paths - A cache tree with 50 invalid paths - A completely empty cache tree Example results: Test this tree ----------------------------------------------------------- 0090.2: no-op, clean 1.27(0.48+0.52) 0090.3: prime_cache_tree, clean 2.02(0.83+0.85) 0090.4: cache_tree_update, clean 1.30(0.49+0.54) 0090.5: no-op, invalidate 2 1.29(0.48+0.54) 0090.6: prime_cache_tree, invalidate 2 1.98(0.81+0.83) 0090.7: cache_tree_update, invalidate 2 2.12(0.94+0.86) 0090.8: no-op, invalidate 50 1.32(0.50+0.55) 0090.9: prime_cache_tree, invalidate 50 2.10(0.86+0.89) 0090.10: cache_tree_update, invalidate 50 2.35(1.14+0.90) 0090.11: no-op, empty 1.33(0.50+0.54) 0090.12: prime_cache_tree, empty 2.04(0.84+0.87) 0090.13: cache_tree_update, empty 2.51(1.27+0.92) These timings show that, while 'cache_tree_update()' is faster when the cache tree is completely valid, it is equal to or slower than 'prime_cache_tree()' when there are any invalid paths. Since the redundant calls are mostly in scenarios where the cache tree will be at least partially invalid (e.g., 'git reset --hard'), 'prime_cache_tree()' will likely perform better than 'cache_tree_update()' in typical cases. Helped-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Victoria Dye <vdye@github.com> Signed-off-by: Taylor Blau <me@ttaylorr.com>
2022-11-10 19:06:01 +00:00
#include "test-tool.h"
#include "gettext.h"
#include "hex.h"
cache-tree: add perf test comparing update and prime Add a performance test comparing the execution times of 'prime_cache_tree()' and 'cache_tree_update(_, WRITE_TREE_SILENT | WRITE_TREE_REPAIR)'. The goal of comparing these two is to identify which is the faster method for rebuilding an invalid cache tree, ultimately to remove one when both are (reundantly) called in immediate succession. Both methods are fast, so the new tests in 'p0090-cache-tree.sh' must call each tested function multiple times to ensure the reported times (to 0.01s resolution) convey the differences between them. The tests compare the timing of a 'test-tool cache-tree' run as a no-op (to capture a baseline for the overhead associated with running the tool), 'cache_tree_update()', and 'prime_cache_tree()' on four scenarios: - A completely valid cache tree - A cache tree with 2 invalid paths - A cache tree with 50 invalid paths - A completely empty cache tree Example results: Test this tree ----------------------------------------------------------- 0090.2: no-op, clean 1.27(0.48+0.52) 0090.3: prime_cache_tree, clean 2.02(0.83+0.85) 0090.4: cache_tree_update, clean 1.30(0.49+0.54) 0090.5: no-op, invalidate 2 1.29(0.48+0.54) 0090.6: prime_cache_tree, invalidate 2 1.98(0.81+0.83) 0090.7: cache_tree_update, invalidate 2 2.12(0.94+0.86) 0090.8: no-op, invalidate 50 1.32(0.50+0.55) 0090.9: prime_cache_tree, invalidate 50 2.10(0.86+0.89) 0090.10: cache_tree_update, invalidate 50 2.35(1.14+0.90) 0090.11: no-op, empty 1.33(0.50+0.54) 0090.12: prime_cache_tree, empty 2.04(0.84+0.87) 0090.13: cache_tree_update, empty 2.51(1.27+0.92) These timings show that, while 'cache_tree_update()' is faster when the cache tree is completely valid, it is equal to or slower than 'prime_cache_tree()' when there are any invalid paths. Since the redundant calls are mostly in scenarios where the cache tree will be at least partially invalid (e.g., 'git reset --hard'), 'prime_cache_tree()' will likely perform better than 'cache_tree_update()' in typical cases. Helped-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Victoria Dye <vdye@github.com> Signed-off-by: Taylor Blau <me@ttaylorr.com>
2022-11-10 19:06:01 +00:00
#include "tree.h"
#include "cache-tree.h"
#include "parse-options.h"
#include "read-cache-ll.h"
#include "repository.h"
#include "setup.h"
cache-tree: add perf test comparing update and prime Add a performance test comparing the execution times of 'prime_cache_tree()' and 'cache_tree_update(_, WRITE_TREE_SILENT | WRITE_TREE_REPAIR)'. The goal of comparing these two is to identify which is the faster method for rebuilding an invalid cache tree, ultimately to remove one when both are (reundantly) called in immediate succession. Both methods are fast, so the new tests in 'p0090-cache-tree.sh' must call each tested function multiple times to ensure the reported times (to 0.01s resolution) convey the differences between them. The tests compare the timing of a 'test-tool cache-tree' run as a no-op (to capture a baseline for the overhead associated with running the tool), 'cache_tree_update()', and 'prime_cache_tree()' on four scenarios: - A completely valid cache tree - A cache tree with 2 invalid paths - A cache tree with 50 invalid paths - A completely empty cache tree Example results: Test this tree ----------------------------------------------------------- 0090.2: no-op, clean 1.27(0.48+0.52) 0090.3: prime_cache_tree, clean 2.02(0.83+0.85) 0090.4: cache_tree_update, clean 1.30(0.49+0.54) 0090.5: no-op, invalidate 2 1.29(0.48+0.54) 0090.6: prime_cache_tree, invalidate 2 1.98(0.81+0.83) 0090.7: cache_tree_update, invalidate 2 2.12(0.94+0.86) 0090.8: no-op, invalidate 50 1.32(0.50+0.55) 0090.9: prime_cache_tree, invalidate 50 2.10(0.86+0.89) 0090.10: cache_tree_update, invalidate 50 2.35(1.14+0.90) 0090.11: no-op, empty 1.33(0.50+0.54) 0090.12: prime_cache_tree, empty 2.04(0.84+0.87) 0090.13: cache_tree_update, empty 2.51(1.27+0.92) These timings show that, while 'cache_tree_update()' is faster when the cache tree is completely valid, it is equal to or slower than 'prime_cache_tree()' when there are any invalid paths. Since the redundant calls are mostly in scenarios where the cache tree will be at least partially invalid (e.g., 'git reset --hard'), 'prime_cache_tree()' will likely perform better than 'cache_tree_update()' in typical cases. Helped-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Victoria Dye <vdye@github.com> Signed-off-by: Taylor Blau <me@ttaylorr.com>
2022-11-10 19:06:01 +00:00
static char const * const test_cache_tree_usage[] = {
N_("test-tool cache-tree <options> (control|prime|update)"),
NULL
};
int cmd__cache_tree(int argc, const char **argv)
{
struct object_id oid;
struct tree *tree;
int empty = 0;
int invalidate_qty = 0;
int i;
struct option options[] = {
OPT_BOOL(0, "empty", &empty,
N_("clear the cache tree before each iteration")),
OPT_INTEGER_F(0, "invalidate", &invalidate_qty,
N_("number of entries in the cache tree to invalidate (default 0)"),
PARSE_OPT_NONEG),
OPT_END()
};
setup_git_directory();
argc = parse_options(argc, argv, NULL, options, test_cache_tree_usage, 0);
if (repo_read_index(the_repository) < 0)
cache-tree: add perf test comparing update and prime Add a performance test comparing the execution times of 'prime_cache_tree()' and 'cache_tree_update(_, WRITE_TREE_SILENT | WRITE_TREE_REPAIR)'. The goal of comparing these two is to identify which is the faster method for rebuilding an invalid cache tree, ultimately to remove one when both are (reundantly) called in immediate succession. Both methods are fast, so the new tests in 'p0090-cache-tree.sh' must call each tested function multiple times to ensure the reported times (to 0.01s resolution) convey the differences between them. The tests compare the timing of a 'test-tool cache-tree' run as a no-op (to capture a baseline for the overhead associated with running the tool), 'cache_tree_update()', and 'prime_cache_tree()' on four scenarios: - A completely valid cache tree - A cache tree with 2 invalid paths - A cache tree with 50 invalid paths - A completely empty cache tree Example results: Test this tree ----------------------------------------------------------- 0090.2: no-op, clean 1.27(0.48+0.52) 0090.3: prime_cache_tree, clean 2.02(0.83+0.85) 0090.4: cache_tree_update, clean 1.30(0.49+0.54) 0090.5: no-op, invalidate 2 1.29(0.48+0.54) 0090.6: prime_cache_tree, invalidate 2 1.98(0.81+0.83) 0090.7: cache_tree_update, invalidate 2 2.12(0.94+0.86) 0090.8: no-op, invalidate 50 1.32(0.50+0.55) 0090.9: prime_cache_tree, invalidate 50 2.10(0.86+0.89) 0090.10: cache_tree_update, invalidate 50 2.35(1.14+0.90) 0090.11: no-op, empty 1.33(0.50+0.54) 0090.12: prime_cache_tree, empty 2.04(0.84+0.87) 0090.13: cache_tree_update, empty 2.51(1.27+0.92) These timings show that, while 'cache_tree_update()' is faster when the cache tree is completely valid, it is equal to or slower than 'prime_cache_tree()' when there are any invalid paths. Since the redundant calls are mostly in scenarios where the cache tree will be at least partially invalid (e.g., 'git reset --hard'), 'prime_cache_tree()' will likely perform better than 'cache_tree_update()' in typical cases. Helped-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Victoria Dye <vdye@github.com> Signed-off-by: Taylor Blau <me@ttaylorr.com>
2022-11-10 19:06:01 +00:00
die(_("unable to read index file"));
oidcpy(&oid, &the_index.cache_tree->oid);
tree = parse_tree_indirect(&oid);
if (!tree)
die(_("not a tree object: %s"), oid_to_hex(&oid));
if (empty) {
/* clear the cache tree & allocate a new one */
cache_tree_free(&the_index.cache_tree);
the_index.cache_tree = cache_tree();
} else if (invalidate_qty) {
/* invalidate the specified number of unique paths */
float f_interval = (float)the_index.cache_nr / invalidate_qty;
int interval = f_interval < 1.0 ? 1 : (int)f_interval;
for (i = 0; i < invalidate_qty && i * interval < the_index.cache_nr; i++)
cache_tree_invalidate_path(&the_index, the_index.cache[i * interval]->name);
}
if (argc != 1)
usage_with_options(test_cache_tree_usage, options);
else if (!strcmp(argv[0], "prime"))
prime_cache_tree(the_repository, &the_index, tree);
else if (!strcmp(argv[0], "update"))
cache_tree_update(&the_index, WRITE_TREE_SILENT | WRITE_TREE_REPAIR);
/* use "control" subcommand to specify no-op */
else if (!!strcmp(argv[0], "control"))
die(_("Unhandled subcommand '%s'"), argv[0]);
return 0;
}