[unpackfs] Simplify progress reporting more

If there's thousands of files in a squashfs (e.g. 400000 like on
some ArcoLinux ISOs) then progress would be reported every
4000 files, which can take quite some time to write. Reduce
file_chunk_count to at most 500, so that progress is reported
more often even if that wouldn't lead to a visible change
in the percentage progress: instead we **do** get a change
in files-transferred numbers.

- The total weight is only needed by the UnpackOperation,
  not by each entry.
- Use a chunk size of 107 so that the number-complete seems busy:
  the whole larger-or-smaller chunk size doesn't really matter.
- The progress-report was missing the weight of the current
  module, so would report way too low if weight > 1. This affects
  ArcoLinux configurations where one entry is huge and one is a
  single file, so weights 50 and 1 are appropriate.
This commit is contained in:
Adriaan de Groot 2020-10-06 12:25:22 +02:00
parent bc591f9bc1
commit 57fa51ecd9

View File

@ -49,7 +49,7 @@ class UnpackEntry:
:param destination: :param destination:
""" """
__slots__ = ('source', 'sourcefs', 'destination', 'copied', 'total', 'exclude', 'excludeFile', __slots__ = ('source', 'sourcefs', 'destination', 'copied', 'total', 'exclude', 'excludeFile',
'mountPoint', 'weight', 'accumulated_weight') 'mountPoint', 'weight')
def __init__(self, source, sourcefs, destination): def __init__(self, source, sourcefs, destination):
""" """
@ -72,7 +72,6 @@ class UnpackEntry:
self.total = 0 self.total = 0
self.mountPoint = None self.mountPoint = None
self.weight = 1 self.weight = 1
self.accumulated_weight = 0 # That's weight **before** this entry
def is_file(self): def is_file(self):
return self.sourcefs == "file" return self.sourcefs == "file"
@ -193,11 +192,12 @@ def file_copy(source, entry, progress_cb):
stdout=subprocess.PIPE, close_fds=ON_POSIX stdout=subprocess.PIPE, close_fds=ON_POSIX
) )
# last_num_files_copied trails num_files_copied, and whenever at least 100 more # last_num_files_copied trails num_files_copied, and whenever at least 100 more
# files have been copied, progress is reported and last_num_files_copied is updated. # files (file_count_chunk) have been copied, progress is reported and
# last_num_files_copied is updated. Pick a chunk size that isn't "tidy"
# so that all the digits of the progress-reported number change.
#
last_num_files_copied = 0 last_num_files_copied = 0
file_count_chunk = entry.total / 100 file_count_chunk = 107
if file_count_chunk < 100:
file_count_chunk = 100
for line in iter(process.stdout.readline, b''): for line in iter(process.stdout.readline, b''):
# rsync outputs progress in parentheses. Each line will have an # rsync outputs progress in parentheses. Each line will have an
@ -262,7 +262,7 @@ class UnpackOperation:
def __init__(self, entries): def __init__(self, entries):
self.entries = entries self.entries = entries
self.entry_for_source = dict((x.source, x) for x in self.entries) self.entry_for_source = dict((x.source, x) for x in self.entries)
self.total_weight = entries[-1].accumulated_weight + entries[-1].weight self.total_weight = sum([e.weight for e in entries])
def report_progress(self): def report_progress(self):
""" """
@ -285,7 +285,7 @@ class UnpackOperation:
# There is at most *one* entry in-progress # There is at most *one* entry in-progress
current_total = entry.total current_total = entry.total
current_done = entry.copied current_done = entry.copied
complete_weight += ( 1.0 * current_done ) / current_total complete_weight += entry.weight * ( 1.0 * current_done ) / current_total
break break
if current_total > 0: if current_total > 0:
@ -482,15 +482,9 @@ def run():
if entry.get("excludeFile", None): if entry.get("excludeFile", None):
unpack[-1].excludeFile = entry["excludeFile"] unpack[-1].excludeFile = entry["excludeFile"]
unpack[-1].weight = extract_weight(entry) unpack[-1].weight = extract_weight(entry)
unpack[-1].accumulated_weight = sum([e.weight for e in unpack[:-1]])
is_first = False is_first = False
# Show the entry, weight and accumulated_weight before each entry,
# to allow tweaking the weights.
for e in unpack:
utils.debug(".. {!s} w={!s} aw={!s}".format(e.source, e.weight, e.accumulated_weight))
repair_root_permissions(root_mount_point) repair_root_permissions(root_mount_point)
try: try:
unpackop = UnpackOperation(unpack) unpackop = UnpackOperation(unpack)