mirror of
https://github.com/Stone-Red-Code/dvc.git
synced 2026-11-10 07:18:27 +01:00
experiments: add dvc exp gc (#4803)
* experiments: add `dvc exp gc` * tests: add exp gc tests * add exp gc command test * fix review issue
This commit is contained in:
@@ -8,6 +8,7 @@ from datetime import date, datetime
|
||||
from itertools import groupby
|
||||
from typing import Iterable, Optional
|
||||
|
||||
import dvc.prompt as prompt
|
||||
from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
|
||||
from dvc.command.metrics import DEFAULT_PRECISION
|
||||
from dvc.command.repro import CmdRepro
|
||||
@@ -477,6 +478,61 @@ class CmdExperimentsRun(CmdRepro):
|
||||
return ret
|
||||
|
||||
|
||||
class CmdExperimentsGC(CmdRepro):
|
||||
def run(self):
|
||||
from dvc.repo.gc import _raise_error_if_all_disabled
|
||||
|
||||
if not self.repo.experiments:
|
||||
return 0
|
||||
|
||||
_raise_error_if_all_disabled(
|
||||
all_branches=self.args.all_branches,
|
||||
all_tags=self.args.all_tags,
|
||||
all_commits=self.args.all_commits,
|
||||
workspace=self.args.workspace,
|
||||
)
|
||||
|
||||
msg = "This will remove all experiments except those derived from "
|
||||
|
||||
msg += "the workspace"
|
||||
if self.args.all_commits:
|
||||
msg += " and all git commits"
|
||||
elif self.args.all_branches and self.args.all_tags:
|
||||
msg += " and all git branches and tags"
|
||||
elif self.args.all_branches:
|
||||
msg += " and all git branches"
|
||||
elif self.args.all_tags:
|
||||
msg += " and all git tags"
|
||||
msg += " of the current repo."
|
||||
if self.args.queued:
|
||||
msg += " Run queued experiments will be preserved."
|
||||
if self.args.queued:
|
||||
msg += " Run queued experiments will be removed."
|
||||
|
||||
logger.warning(msg)
|
||||
|
||||
msg = "Are you sure you want to proceed?"
|
||||
if not self.args.force and not prompt.confirm(msg):
|
||||
return 1
|
||||
|
||||
removed = self.repo.experiments.gc(
|
||||
all_branches=self.args.all_branches,
|
||||
all_tags=self.args.all_tags,
|
||||
all_commits=self.args.all_commits,
|
||||
workspace=self.args.workspace,
|
||||
queued=self.args.queued,
|
||||
)
|
||||
|
||||
if removed:
|
||||
logger.info(
|
||||
f"Removed {removed} experiments. To remove unused cache files "
|
||||
"use 'dvc gc'."
|
||||
)
|
||||
else:
|
||||
logger.info("No experiments to remove.")
|
||||
return 0
|
||||
|
||||
|
||||
def add_parser(subparsers, parent_parser):
|
||||
EXPERIMENTS_HELP = "Commands to display and compare experiments."
|
||||
|
||||
@@ -741,3 +797,62 @@ def add_parser(subparsers, parent_parser):
|
||||
),
|
||||
)
|
||||
experiments_run_parser.set_defaults(func=CmdExperimentsRun)
|
||||
|
||||
EXPERIMENTS_GC_HELP = "Garbage collect unneeded experiments."
|
||||
EXPERIMENTS_GC_DESCRIPTION = (
|
||||
"Removes all experiments which are not derived from the specified"
|
||||
"Git revisions."
|
||||
)
|
||||
experiments_gc_parser = experiments_subparsers.add_parser(
|
||||
"gc",
|
||||
parents=[parent_parser],
|
||||
description=append_doc_link(
|
||||
EXPERIMENTS_GC_DESCRIPTION, "experiments/gc"
|
||||
),
|
||||
help=EXPERIMENTS_GC_HELP,
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
)
|
||||
experiments_gc_parser.add_argument(
|
||||
"-w",
|
||||
"--workspace",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="Keep experiments derived from the current workspace.",
|
||||
)
|
||||
experiments_gc_parser.add_argument(
|
||||
"-a",
|
||||
"--all-branches",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="Keep experiments derived from the tips of all Git branches.",
|
||||
)
|
||||
experiments_gc_parser.add_argument(
|
||||
"-T",
|
||||
"--all-tags",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="Keep experiments derived from all Git tags.",
|
||||
)
|
||||
experiments_gc_parser.add_argument(
|
||||
"--all-commits",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="Keep experiments derived from all Git commits.",
|
||||
)
|
||||
experiments_gc_parser.add_argument(
|
||||
"--queued",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help=(
|
||||
"Keep queued experiments (experiments run queue will be cleared "
|
||||
"by default)."
|
||||
),
|
||||
)
|
||||
experiments_gc_parser.add_argument(
|
||||
"-f",
|
||||
"--force",
|
||||
action="store_true",
|
||||
default=False,
|
||||
help="Force garbage collection - automatically agree to all prompts.",
|
||||
)
|
||||
experiments_gc_parser.set_defaults(func=CmdExperimentsGC)
|
||||
|
||||
@@ -900,3 +900,8 @@ class Experiments:
|
||||
from dvc.repo.experiments.run import run
|
||||
|
||||
return run(self.repo, *args, **kwargs)
|
||||
|
||||
def gc(self, *args, **kwargs):
|
||||
from dvc.repo.experiments.gc import gc
|
||||
|
||||
return gc(self.repo, *args, **kwargs)
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
import logging
|
||||
from typing import Optional
|
||||
|
||||
from dvc.repo import locked
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@locked
|
||||
def gc(
|
||||
repo,
|
||||
all_branches: Optional[bool] = False,
|
||||
all_tags: Optional[bool] = False,
|
||||
all_commits: Optional[bool] = False,
|
||||
workspace: Optional[bool] = False,
|
||||
queued: Optional[bool] = False,
|
||||
):
|
||||
keep_revs = set(
|
||||
repo.brancher(
|
||||
all_branches=all_branches,
|
||||
all_tags=all_tags,
|
||||
all_commits=all_commits,
|
||||
sha_only=True,
|
||||
)
|
||||
)
|
||||
if workspace:
|
||||
keep_revs.add(repo.scm.get_rev())
|
||||
|
||||
if not keep_revs:
|
||||
return 0
|
||||
|
||||
delete_branches = []
|
||||
for exp_branch in repo.experiments.scm.list_branches():
|
||||
m = repo.experiments.BRANCH_RE.match(exp_branch)
|
||||
if m:
|
||||
rev = repo.scm.resolve_rev(m.group("baseline_rev"))
|
||||
if rev not in keep_revs:
|
||||
delete_branches.append(exp_branch)
|
||||
if delete_branches:
|
||||
repo.experiments.scm.repo.delete_head(*delete_branches, force=True)
|
||||
removed = len(delete_branches)
|
||||
|
||||
delete_stashes = []
|
||||
for _, entry in repo.experiments.stash_revs.items():
|
||||
if not queued or entry.baseline_rev not in keep_revs:
|
||||
delete_stashes.append(entry.index)
|
||||
for index in sorted(delete_stashes, reverse=True):
|
||||
repo.experiments.scm.repo.git.stash("drop", index)
|
||||
removed += len(delete_stashes)
|
||||
|
||||
return removed
|
||||
@@ -0,0 +1,120 @@
|
||||
import pytest
|
||||
from funcy import first
|
||||
|
||||
from tests.func.test_repro_multistage import COPY_SCRIPT
|
||||
|
||||
|
||||
@pytest.mark.parametrize("queued, expected", [(True, 0), (False, 1)])
|
||||
def test_workspace(tmp_dir, scm, dvc, queued, expected):
|
||||
tmp_dir.gen("copy.py", COPY_SCRIPT)
|
||||
tmp_dir.gen("params.yaml", "foo: 1")
|
||||
|
||||
stage = dvc.run(
|
||||
cmd="python copy.py params.yaml metrics.yaml",
|
||||
metrics_no_cache=["metrics.yaml"],
|
||||
params=["foo"],
|
||||
name="foo",
|
||||
)
|
||||
scm.add(["dvc.yaml", "dvc.lock", "copy.py", "params.yaml", "metrics.yaml"])
|
||||
scm.commit("v1")
|
||||
|
||||
dvc.experiments.run(stage.addressing, params=["foo=2"])
|
||||
dvc.experiments.run(stage.addressing, params=["foo=3"], queue=True)
|
||||
|
||||
removed = dvc.experiments.gc(workspace=True, queued=queued)
|
||||
assert removed == expected
|
||||
|
||||
|
||||
@pytest.mark.parametrize("queued, expected", [(True, 0), (False, 2)])
|
||||
def test_all_commits(tmp_dir, scm, dvc, queued, expected):
|
||||
tmp_dir.gen("copy.py", COPY_SCRIPT)
|
||||
tmp_dir.gen("params.yaml", "foo: 1")
|
||||
|
||||
stage = dvc.run(
|
||||
cmd="python copy.py params.yaml metrics.yaml",
|
||||
metrics_no_cache=["metrics.yaml"],
|
||||
params=["foo"],
|
||||
name="foo",
|
||||
)
|
||||
scm.add(["dvc.yaml", "dvc.lock", "copy.py", "params.yaml", "metrics.yaml"])
|
||||
scm.commit("v1")
|
||||
|
||||
results = dvc.experiments.run(stage.addressing, params=["foo=2"])
|
||||
exp_rev = first(results)
|
||||
dvc.experiments.run(stage.addressing, params=["foo=3"], queue=True)
|
||||
|
||||
dvc.experiments.checkout(exp_rev)
|
||||
scm.add(["dvc.yaml", "dvc.lock", "copy.py", "params.yaml", "metrics.yaml"])
|
||||
scm.commit("v2")
|
||||
|
||||
dvc.experiments.run(stage.addressing, params=["foo=4"])
|
||||
dvc.experiments.run(stage.addressing, params=["foo=5"], queue=True)
|
||||
|
||||
removed = dvc.experiments.gc(all_commits=True, queued=queued)
|
||||
assert removed == expected
|
||||
|
||||
|
||||
@pytest.mark.parametrize("queued, expected", [(True, 2), (False, 3)])
|
||||
def test_all_branches(tmp_dir, scm, dvc, queued, expected):
|
||||
tmp_dir.gen("copy.py", COPY_SCRIPT)
|
||||
tmp_dir.gen("params.yaml", "foo: 1")
|
||||
|
||||
stage = dvc.run(
|
||||
cmd="python copy.py params.yaml metrics.yaml",
|
||||
metrics_no_cache=["metrics.yaml"],
|
||||
params=["foo"],
|
||||
name="foo",
|
||||
)
|
||||
scm.add(["dvc.yaml", "dvc.lock", "copy.py", "params.yaml", "metrics.yaml"])
|
||||
scm.commit("v1")
|
||||
|
||||
results = dvc.experiments.run(stage.addressing, params=["foo=2"])
|
||||
exp_rev = first(results)
|
||||
dvc.experiments.run(stage.addressing, params=["foo=3"], queue=True)
|
||||
|
||||
dvc.experiments.checkout(exp_rev)
|
||||
scm.add(["dvc.yaml", "dvc.lock", "copy.py", "params.yaml", "metrics.yaml"])
|
||||
scm.commit("v2")
|
||||
|
||||
scm.branch("branch")
|
||||
|
||||
results = dvc.experiments.run(stage.addressing, params=["foo=4"])
|
||||
dvc.experiments.run(stage.addressing, params=["foo=5"], queue=True)
|
||||
exp_rev = first(results)
|
||||
|
||||
dvc.experiments.checkout(exp_rev)
|
||||
scm.add(["dvc.yaml", "dvc.lock", "copy.py", "params.yaml", "metrics.yaml"])
|
||||
scm.commit("v3")
|
||||
|
||||
removed = dvc.experiments.gc(all_branches=True, queued=queued)
|
||||
assert removed == expected
|
||||
|
||||
|
||||
@pytest.mark.parametrize("queued, expected", [(True, 2), (False, 3)])
|
||||
def test_all_tags(tmp_dir, scm, dvc, queued, expected):
|
||||
tmp_dir.gen("copy.py", COPY_SCRIPT)
|
||||
tmp_dir.gen("params.yaml", "foo: 1")
|
||||
|
||||
stage = dvc.run(
|
||||
cmd="python copy.py params.yaml metrics.yaml",
|
||||
metrics_no_cache=["metrics.yaml"],
|
||||
params=["foo"],
|
||||
name="foo",
|
||||
)
|
||||
scm.add(["dvc.yaml", "dvc.lock", "copy.py", "params.yaml", "metrics.yaml"])
|
||||
scm.commit("v1")
|
||||
|
||||
results = dvc.experiments.run(stage.addressing, params=["foo=2"])
|
||||
exp_rev = first(results)
|
||||
dvc.experiments.run(stage.addressing, params=["foo=3"], queue=True)
|
||||
|
||||
dvc.experiments.checkout(exp_rev)
|
||||
scm.add(["dvc.yaml", "dvc.lock", "copy.py", "params.yaml", "metrics.yaml"])
|
||||
scm.commit("v2")
|
||||
scm.tag("tag-v2")
|
||||
|
||||
dvc.experiments.run(stage.addressing, params=["foo=4"])
|
||||
dvc.experiments.run(stage.addressing, params=["foo=5"], queue=True)
|
||||
|
||||
removed = dvc.experiments.gc(all_tags=True, queued=queued)
|
||||
assert removed == expected
|
||||
@@ -1,10 +1,14 @@
|
||||
import pytest
|
||||
|
||||
from dvc.cli import parse_args
|
||||
from dvc.command.experiments import (
|
||||
CmdExperimentsDiff,
|
||||
CmdExperimentsGC,
|
||||
CmdExperimentsRun,
|
||||
CmdExperimentsShow,
|
||||
)
|
||||
from dvc.dvcfile import PIPELINE_FILE
|
||||
from dvc.exceptions import InvalidArgumentError
|
||||
|
||||
from .test_repro import default_arguments as repro_arguments
|
||||
|
||||
@@ -83,3 +87,38 @@ def test_experiments_run(dvc, mocker):
|
||||
cmd.repo.experiments.run.assert_called_with(
|
||||
PIPELINE_FILE, **default_arguments
|
||||
)
|
||||
|
||||
|
||||
def test_experiments_gc(dvc, mocker):
|
||||
cli_args = parse_args(
|
||||
[
|
||||
"exp",
|
||||
"gc",
|
||||
"--workspace",
|
||||
"--all-tags",
|
||||
"--all-branches",
|
||||
"--all-commits",
|
||||
"--queued",
|
||||
"--force",
|
||||
]
|
||||
)
|
||||
assert cli_args.func == CmdExperimentsGC
|
||||
|
||||
cmd = cli_args.func(cli_args)
|
||||
m = mocker.patch("dvc.repo.experiments.gc.gc", return_value={})
|
||||
|
||||
assert cmd.run() == 0
|
||||
|
||||
m.assert_called_once_with(
|
||||
cmd.repo,
|
||||
workspace=True,
|
||||
all_tags=True,
|
||||
all_branches=True,
|
||||
all_commits=True,
|
||||
queued=True,
|
||||
)
|
||||
|
||||
cli_args = parse_args(["exp", "gc"])
|
||||
cmd = cli_args.func(cli_args)
|
||||
with pytest.raises(InvalidArgumentError):
|
||||
cmd.run()
|
||||
|
||||
Reference in New Issue
Block a user