def _apply(
self,
fn: Any,
remote_args: dict,
block_list: BlockList,
clear_input_blocks: bool,
) -> BlockList:
context = DatasetContext.get_current()
# Handle empty datasets.
if block_list.initial_num_blocks() == 0:
return block_list
blocks = block_list.get_blocks_with_metadata()
map_bar = ProgressBar("Map Progress", total=len(blocks))
if context.block_splitting_enabled:
map_block = cached_remote_fn(_map_block_split).options(**remote_args)
refs = [map_block.remote(b, fn, m.input_files) for b, m in blocks]
else:
map_block = cached_remote_fn(_map_block_nosplit).options(
**dict(remote_args, num_returns=2)
)
all_refs = [map_block.remote(b, fn, m.input_files) for b, m in blocks]
data_refs = [r[0] for r in all_refs]
refs = [r[1] for r in all_refs]
# Release input block references.
if clear_input_blocks:
del blocks
block_list.clear()
# Common wait for non-data refs.
try:
results = map_bar.fetch_until_complete(refs)
except (ray.exceptions.RayTaskError, KeyboardInterrupt) as e:
# One or more mapper tasks failed, or we received a SIGINT signal
# while waiting; either way, we cancel all map tasks.
for ref in refs:
ray.cancel(ref)
# Wait until all tasks have failed or been cancelled.
for ref in refs:
try:
ray.get(ref)
except (ray.exceptions.RayTaskError, ray.exceptions.TaskCancelledError):
pass
# Reraise the original task failure exception.
raise e from None
new_blocks, new_metadata = [], []
if context.block_splitting_enabled:
for result in results:
for block, metadata in result:
new_blocks.append(block)
new_metadata.append(metadata)
else:
for block, metadata in zip(data_refs, results):
new_blocks.append(block)
new_metadata.append(metadata)
return BlockList(list(new_blocks), list(new_metadata))
def apply(self, fn: Any, remote_args: dict,
blocks: BlockList) -> BlockList:
# Handle empty datasets.
if blocks.initial_num_blocks() == 0:
return blocks
blocks = list(blocks.iter_blocks_with_metadata())
map_bar = ProgressBar("Map Progress", total=len(blocks))
map_block = cached_remote_fn(_map_block)
refs = [
map_block.options(**remote_args).remote(b, fn, m.input_files)
for b, m in blocks
]
try:
results = map_bar.fetch_until_complete(refs)
except (ray.exceptions.RayTaskError, KeyboardInterrupt) as e:
# One or more mapper tasks failed, or we received a SIGINT signal
# while waiting; either way, we cancel all map tasks.
for ref in refs:
ray.cancel(ref)
# Wait until all tasks have failed or been cancelled.
for ref in refs:
try:
ray.get(ref)
except (ray.exceptions.RayTaskError,
ray.exceptions.TaskCancelledError):
pass
# Reraise the original task failure exception.
raise e from None
new_blocks, new_metadata = [], []
for result in results:
for block, metadata in result:
new_blocks.append(block)
new_metadata.append(metadata)
return BlockList(list(new_blocks), list(new_metadata))