Mercurial > hg
changeset 51090:de6a8cc24de3
revlog: move the splitting-inline-revlog logic inside the inner object
This is another large IO block that we need to move within the inner object if
we want's it to be self sufficient.
| author | Pierre-Yves David <pierre-yves.david@octobus.net> |
|---|---|
| date | Mon, 23 Oct 2023 14:27:07 +0200 |
| parents | c2c24b6b97f5 |
| children | a82704902db8 |
| files | mercurial/revlog.py |
| diffstat | 1 files changed, 74 insertions(+), 62 deletions(-) [+] |
line wrap: on
line diff
--- a/mercurial/revlog.py Wed Oct 25 01:02:47 2023 +0200 +++ b/mercurial/revlog.py Mon Oct 23 14:27:07 2023 +0200 @@ -518,6 +518,64 @@ atomictemp=True, ) + def split_inline(self, tr, header, new_index_file_path=None): + """split the data of an inline revlog into an index and a data file""" + existing_handles = False + if self._writinghandles is not None: + existing_handles = True + fp = self._writinghandles[0] + fp.flush() + fp.close() + # We can't use the cached file handle after close(). So prevent + # its usage. + self._writinghandles = None + self._segmentfile.writing_handle = None + # No need to deal with sidedata writing handle as it is only + # relevant with revlog-v2 which is never inline, not reaching + # this code + + new_dfh = self.opener(self.data_file, mode=b"w+") + new_dfh.truncate(0) # drop any potentially existing data + try: + with self.reading(): + for r in range(len(self.index)): + new_dfh.write(self.get_segment_for_revs(r, r)[1]) + new_dfh.flush() + + if new_index_file_path is not None: + self.index_file = new_index_file_path + with self.__index_new_fp() as fp: + self.inline = False + for i in range(len(self.index)): + e = self.index.entry_binary(i) + if i == 0: + packed_header = self.index.pack_header(header) + e = packed_header + e + fp.write(e) + + # If we don't use side-write, the temp file replace the real + # index when we exit the context manager + + self._segmentfile = randomaccessfile.randomaccessfile( + self.opener, + self.data_file, + self.data_config.chunk_cache_size, + ) + + if existing_handles: + # switched from inline to conventional reopen the index + ifh = self.__index_write_fp() + self._writinghandles = (ifh, new_dfh, None) + self._segmentfile.writing_handle = new_dfh + new_dfh = None + # No need to deal with sidedata writing handle as it is only + # relevant with revlog-v2 which is never inline, not reaching + # this code + finally: + if new_dfh is not None: + new_dfh.close() + return self.index_file + def get_segment_for_revs(self, startrev, endrev): """Obtain a segment of raw data corresponding to a range of revisions. @@ -2586,26 +2644,15 @@ tr.addbackup(self._indexfile, for_offset=True) tr.add(self._datafile, 0) - existing_handles = False - if self._inner._writinghandles is not None: - existing_handles = True - fp = self._inner._writinghandles[0] - fp.flush() - fp.close() - # We can't use the cached file handle after close(). So prevent - # its usage. - self._inner._writinghandles = None - self._inner._segmentfile.writing_handle = None - # No need to deal with sidedata writing handle as it is only - # relevant with revlog-v2 which is never inline, not reaching - # this code + new_index_file_path = None if side_write: old_index_file_path = self._indexfile new_index_file_path = self._split_index_file opener = self.opener weak_self = weakref.ref(self) - # the "split" index replace the real index when the transaction is finalized + # the "split" index replace the real index when the transaction is + # finalized def finalize_callback(tr): opener.rename( new_index_file_path, @@ -2621,6 +2668,7 @@ maybe_self = weak_self() if maybe_self is not None: maybe_self._indexfile = old_index_file_path + maybe_self._inner.inline = True maybe_self._inner.index_file = old_index_file_path tr.registertmp(new_index_file_path) @@ -2631,54 +2679,18 @@ tr.addfinalize(callback_id, finalize_callback) tr.addabort(callback_id, abort_callback) - new_dfh = self._datafp(b'w+') - new_dfh.truncate(0) # drop any potentially existing data - try: - with self.reading(): - for r in self: - new_dfh.write(self._inner.get_segment_for_revs(r, r)[1]) - new_dfh.flush() - - if side_write: - self._indexfile = new_index_file_path - self._inner.index_file = self._indexfile - with self._inner._InnerRevlog__index_new_fp() as fp: - self._format_flags &= ~FLAG_INLINE_DATA - self._inline = False - self._inner.inline = False - for i in self: - e = self.index.entry_binary(i) - if i == 0: - header = self._format_flags | self._format_version - header = self.index.pack_header(header) - e = header + e - fp.write(e) - - # If we don't use side-write, the temp file replace the real - # index when we exit the context manager - - nodemaputil.setup_persistent_nodemap(tr, self) - self._inner._segmentfile = randomaccessfile.randomaccessfile( - self.opener, - self._datafile, - self.data_config.chunk_cache_size, - ) - - if existing_handles: - # switched from inline to conventional reopen the index - index_end = None - ifh = self._inner._InnerRevlog__index_write_fp( - index_end=index_end - ) - self._inner._writinghandles = (ifh, new_dfh, None) - self._inner._segmentfile.writing_handle = new_dfh - new_dfh = None - # No need to deal with sidedata writing handle as it is only - # relevant with revlog-v2 which is never inline, not reaching - # this code - finally: - if new_dfh is not None: - new_dfh.close() + self._format_flags &= ~FLAG_INLINE_DATA + self._inner.split_inline( + tr, + self._format_flags | self._format_version, + new_index_file_path=new_index_file_path, + ) + + self._inline = False + if new_index_file_path is not None: + self._indexfile = new_index_file_path + + nodemaputil.setup_persistent_nodemap(tr, self) def _nodeduplicatecallback(self, transaction, node): """called when trying to add a node already stored."""