Tue, 03 Oct 2017 12:00:07 -0700 config: add a missing preparewrite() call
Jun Wu <quark@fb.com> [Tue, 03 Oct 2017 12:00:07 -0700] rev 34454
config: add a missing preparewrite() call Thanks Yuya for pointing this out in D808. Differential Revision: https://phab.mercurial-scm.org/D924
Tue, 03 Oct 2017 16:59:17 -0700 test-strip: make test compatible with chg
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 16:59:17 -0700] rev 34453
test-strip: make test compatible with chg The test was using reposetup which had the logic for stripping commits. This leads to a situation where if the reposetup was called twice for an extension (which can happen with chg running), the stripped node would not be found the second time. Therefore, this commit changes the test to put the stripping logic inside commands instead of the reposetup. This ensures that the stripping logic is invoked only when the command is invoked and thus, avoids any problems. Test Plan: Ran the test 'test-strip.t' with and without the '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D928
Tue, 03 Oct 2017 14:35:24 -0700 test-hook: make test compatible with chg
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 14:35:24 -0700] rev 34452
test-hook: make test compatible with chg The test uses the 'print' method instead of writing to stdout using 'ui.write' which leads to incompatibility with chg. This commit modifies the test to use 'ui' instead which fixes the problem. Test Plan: Ran the test 'test-hook.t' with and without '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D927
Tue, 03 Oct 2017 13:30:36 -0700 test-setdiscovery: make test compatible with chg
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 13:30:36 -0700] rev 34451
test-setdiscovery: make test compatible with chg The test checks the output of the blackbox extension which will contain logs corresponding to chg in case chg is running. Therefore, this commit modifies the test to take chg into consideration while working with the blackbox extension. Test Plan: Ran the test 'test-setdiscovery.t' with and without the '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D926
Tue, 03 Oct 2017 13:05:58 -0700 test-merge-subrepos: make test compatible with chg
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 13:05:58 -0700] rev 34450
test-merge-subrepos: make test compatible with chg The test checks the output of '.hg/blackbox.log' which will contain logs corresponding to chg in case chg is running. Therefore, this commit modifies the test to take chg into consideration while checking the blackbox.log contents. Test Plan: Ran the test 'test-merge-subrepos.t' with and without the '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D925
Tue, 03 Oct 2017 12:49:28 -0700 test-convert-cvs: make test compatible with chg
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 12:49:28 -0700] rev 34449
test-convert-cvs: make test compatible with chg The test uses the 'print' method instead of writing to stdout using 'ui.write' which leads to incompatibility with chg. This commit modifies the test to use the 'ui' object instead which fixes the problem. Test Plan: Ran the test 'test-convert-cvs.t' with and without '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D923
Tue, 03 Oct 2017 12:09:23 -0700 test-basic: make test compatible with chg
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 12:09:23 -0700] rev 34448
test-basic: make test compatible with chg The error codes returned when writing to /dev/full are different after the first failure with and without '--chg' option. Therefore, this commit conditionally handles the error codes as appropriate. Test Plan: Ran the test 'test-basic.t' with and without '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D922
Mon, 02 Oct 2017 20:23:25 -0700 zeroconf: do not crash if socket being read is closed by another thread
Jun Wu <quark@fb.com> [Mon, 02 Oct 2017 20:23:25 -0700] rev 34447
zeroconf: do not crash if socket being read is closed by another thread In zeroconf/__init__.py, there is: server = Zeroconf.Zeroconf(ip) l = listener() Zeroconf.ServiceBrowser(server, "_hg._tcp.local.", l) time.sleep(1) server.close() `server.close()` closes the underlying socket while the `ServiceBrowser` may still have a background thread reading the socket. There could be a race condition where the reading thread reads the closed socket, resulting in EBADF crash. This patch catches the exception. This makes test-paths.t pass with chg. Differential Revision: https://phab.mercurial-scm.org/D919
Mon, 02 Oct 2017 19:31:33 -0700 test-revlog-mmapindex: make it compatible with chg
Jun Wu <quark@fb.com> [Mon, 02 Oct 2017 19:31:33 -0700] rev 34446
test-revlog-mmapindex: make it compatible with chg The test misses an explicit flush(). Differential Revision: https://phab.mercurial-scm.org/D918
Mon, 02 Oct 2017 19:10:32 -0700 test-profile: gate chg-incompatible part with '#if chg'
Jun Wu <quark@fb.com> [Mon, 02 Oct 2017 19:10:32 -0700] rev 34445
test-profile: gate chg-incompatible part with '#if chg' chg has a different extension loading logic, which affects the profiler extension test case. Gate the block with '#if chg' so the test passes with chg. Differential Revision: https://phab.mercurial-scm.org/D916
(0) -30000 -10000 -3000 -1000 -300 -100 -10 +10 +100 +300 +1000 +3000 +10000 tip