# HG changeset patch # User Gregory Szorc # Date 1450401362 28800 # Node ID e240e914d2261788c3ba700401659c11ed820fe3 # Parent 00aa37c65e0a365230938aed51d1b38b7cace135 revlog: seek to end of file before writing (issue4943) Revlogs were recently refactored to open file handles in "a+" and use a persistent file handle for reading and writing. This drastically reduced the number of file handles being opened. Unfortunately, it appears that some versions of Solaris lose the file offset when performing a write after the handle has been seeked. The simplest workaround is to seek to EOF on files opened in a+ mode before writing to them, which is what this patch does. Ideally, this code would exist in the vfs layer. However, this would require creating a proxy class for file objects in order to provide a custom implementation of write(). This would add overhead. Since revlogs are the only files we open in a+ mode, the one-off workaround in revlog.py should be sufficient. This patch appears to have little to no impact on performance on my Linux machine. diff -r 00aa37c65e0a -r e240e914d226 mercurial/revlog.py --- a/mercurial/revlog.py Mon Nov 30 13:47:29 2015 -0600 +++ b/mercurial/revlog.py Thu Dec 17 17:16:02 2015 -0800 @@ -13,6 +13,7 @@ # import stuff from node for others to import from revlog import collections +import os from node import bin, hex, nullid, nullrev from i18n import _ import ancestor, mdiff, parsers, error, util, templatefilters @@ -1426,6 +1427,20 @@ return node def _writeentry(self, transaction, ifh, dfh, entry, data, link, offset): + # Files opened in a+ mode have inconsistent behavior on various + # platforms. Windows requires that a file positioning call be made + # when the file handle transitions between reads and writes. See + # 3686fa2b8eee and the mixedfilemodewrapper in windows.py. On other + # platforms, Python or the platform itself can be buggy. Some versions + # of Solaris have been observed to not append at the end of the file + # if the file was seeked to before the end. See issue4943 for more. + # + # We work around this issue by inserting a seek() before writing. + # Note: This is likely not necessary on Python 3. + ifh.seek(0, os.SEEK_END) + if dfh: + dfh.seek(0, os.SEEK_END) + curr = len(self) - 1 if not self._inline: transaction.add(self.datafile, offset)