hgext/fsmonitor/__init__.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Mon, 02 Nov 2020 11:03:56 +0100
changeset 45892 06b64fabf91c
parent 45557 2c86b9587740
child 45942 89a2afe31e82
permissions -rw-r--r--
copies: cache the ancestor checking call when tracing copy A good share of the time spent in this function is spent doing ancestors checking. To avoid spending time in duplicated call, we cache the result of calls. In the slower case, this provide a quite significant performance boost. Below are the result for a set of selected pairs (many of them pathological): (And further down is another table that summarize the current state of filelog based vs changeset base copy tracing) The benchmark have been configured to be killed after 6 minutes of runtime, which mean that any detect slower than 2 minutes will be marked as "killed". This drop some useful information about how much slower these case are… but also prevent 99% of the benchmark time to be spent on case that can be labelled "very slow" anyway. Repo Case Source-Rev Dest-Rev Old-Time New-Time Difference Factor ------------------------------------------------------------------------------------------------------------------------------------ mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 0.000044 s, 0.000044 s, +0.000000 s, × 1.0000 mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 0.000138 s, 0.000138 s, +0.000000 s, × 1.0000 mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 0.005067 s, 0.005052 s, -0.000015 s, × 0.9970 pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 0.000218 s, 0.000219 s, +0.000001 s, × 1.0046 pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 0.000053 s, 0.000055 s, +0.000002 s, × 1.0377 pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 0.000125 s, 0.000128 s, +0.000003 s, × 1.0240 pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 0.001098 s, 0.001089 s, -0.000009 s, × 0.9918 pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 0.017546 s, 0.017407 s, -0.000139 s, × 0.9921 pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 0.096723 s, 0.094175 s, -0.002548 s, × 0.9737 pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 0.271796 s, 0.238009 s, -0.033787 s, × 0.8757 pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 0.128602 s, 0.125876 s, -0.002726 s, × 0.9788 pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 7.086742 s, 3.581556 s, -3.505186 s, × 0.5054 pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 0.016634 s, 0.016721 s, +0.000087 s, × 1.0052 pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 0.254225 s, 0.242367 s, -0.011858 s, × 0.9534 netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 0.000166 s, 0.000165 s, -0.000001 s, × 0.9940 netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 0.000118 s, 0.000114 s, -0.000004 s, × 0.9661 netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 0.000296 s, 0.000296 s, +0.000000 s, × 1.0000 netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 0.001137 s, 0.001124 s, -0.000013 s, × 0.9886 netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 0.014133 s, 0.013060 s, -0.001073 s, × 0.9241 netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 0.016988 s, 0.017112 s, +0.000124 s, × 1.0073 netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 0.676361 s, 0.660350 s, -0.016011 s, × 0.9763 netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 12.515149 s, 10.032499 s, -2.482650 s, × 0.8016 mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 0.000186 s, 0.000189 s, +0.000003 s, × 1.0161 mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 0.000459 s, 0.000462 s, +0.000003 s, × 1.0065 mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 0.000273 s, 0.000270 s, -0.000003 s, × 0.9890 mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 0.001503 s, 0.001474 s, -0.000029 s, × 0.9807 mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 0.004862 s, 0.004806 s, -0.000056 s, × 0.9885 mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.088291 s, 0.085150 s, -0.003141 s, × 0.9644 mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.007113 s, 0.007064 s, -0.000049 s, × 0.9931 mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.004687 s, 0.004741 s, +0.000054 s, × 1.0115 mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 0.198710 s, 0.190133 s, -0.008577 s, × 0.9568 mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.036068 s, 0.035651 s, -0.000417 s, × 0.9884 mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 0.465362 s, 0.440694 s, -0.024668 s, × 0.9470 mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 24.519684 s, 18.454163 s, -6.065521 s, × 0.7526 mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 42.711897 s, 31.562719 s, -11.149178 s, × 0.7390 mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 0.001201 s, 0.001189 s, -0.000012 s, × 0.9900 mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 0.001216 s, 0.001204 s, -0.000012 s, × 0.9901 mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 0.000595 s, 0.000586 s, -0.000009 s, × 0.9849 mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 0.001856 s, 0.001845 s, -0.000011 s, × 0.9941 mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 0.064936 s, 0.063822 s, -0.001114 s, × 0.9828 mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.090601 s, 0.088038 s, -0.002563 s, × 0.9717 mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.007510 s, 0.007389 s, -0.000121 s, × 0.9839 mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.004911 s, 0.004868 s, -0.000043 s, × 0.9912 mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 0.233231 s, 0.222450 s, -0.010781 s, × 0.9538 mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 0.419989 s, 0.370675 s, -0.049314 s, × 0.8826 mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 0.401521 s, 0.358020 s, -0.043501 s, × 0.8917 mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 0.179555 s, 0.145235 s, -0.034320 s, × 0.8089 mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.038004 s, 0.037606 s, -0.000398 s, × 0.9895 mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 52.838482 s, 7.382439 s, -45.456043 s, × 0.1397 mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 8.705874 s, 7.273506 s, -1.432368 s, × 0.8355 mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 1.126708 s, 1.074593 s, -0.052115 s, × 0.9537 mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 83.854020 s, 27.746195 s, -56.107825 s, × 0.3309 Below is a table comparing the runtime of the current "filelog centric" algorithm, with the "changeset centric" one, we just modified. The changeset centric algorithm is a significant win in many scenario, but they are still various cases where it is quite slower. When many revision has to be considered the cost of retrieving the copy information, creating new dictionaries, merging dictionaries and checking if revision are ancestors of each other can slow things down. The rest of this series, will introduce a rust version of the copy tracing code to deal with most of theses issues. Repo Case Source-Rev Dest-Rev filelog sidedata Difference Factor --------------------------------------------------------------------------------------------------------------------------------------- mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 0.000914 s, 0.000044 s, - 0.000870 s, × 0.048140 mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 0.001812 s, 0.000138 s, - 0.001674 s, × 0.076159 mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 0.017954 s, 0.005052 s, - 0.012902 s, × 0.281386 pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 0.001509 s, 0.000219 s, - 0.001290 s, × 0.145129 pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 0.206881 s, 0.000055 s, - 0.206826 s, × 0.000266 pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 0.016951 s, 0.000128 s, - 0.016823 s, × 0.007551 pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 0.019096 s, 0.001089 s, - 0.018007 s, × 0.057028 pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 0.762506 s, 0.017407 s, - 0.745099 s, × 0.022829 pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 1.179211 s, 0.094175 s, - 1.085036 s, × 0.079863 pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 1.249058 s, 0.238009 s, - 1.011049 s, × 0.190551 pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 1.614107 s, 0.125876 s, - 1.488231 s, × 0.077985 pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 0.001064 s, 3.581556 s, + 3.580492 s, × 3366.124060 pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 1.061275 s, 0.016721 s, - 1.044554 s, × 0.015756 pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 1.341119 s, 0.242367 s, - 1.098752 s, × 0.180720 netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 0.027803 s, 0.000165 s, - 0.027638 s, × 0.005935 netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 0.130014 s, 0.000114 s, - 0.129900 s, × 0.000877 netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 0.024990 s, 0.000296 s, - 0.024694 s, × 0.011845 netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 0.052201 s, 0.001124 s, - 0.051077 s, × 0.021532 netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 0.037642 s, 0.013060 s, - 0.024582 s, × 0.346953 netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 0.197086 s, 0.017112 s, - 0.179974 s, × 0.086825 netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 0.935148 s, 0.660350 s, - 0.274798 s, × 0.706145 netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 3.920674 s, 10.032499 s, + 6.111825 s, × 2.558871 mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 0.024232 s, 0.000189 s, - 0.024043 s, × 0.007800 mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 0.141483 s, 0.000462 s, - 0.141021 s, × 0.003265 mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 0.025775 s, 0.000270 s, - 0.025505 s, × 0.010475 mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 0.084922 s, 0.001474 s, - 0.083448 s, × 0.017357 mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 0.194784 s, 0.004806 s, - 0.189978 s, × 0.024673 mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 2.161103 s, 0.085150 s, - 2.075953 s, × 0.039401 mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.089347 s, 0.007064 s, - 0.082283 s, × 0.079063 mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.732171 s, 0.004741 s, - 0.727430 s, × 0.006475 mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 1.157287 s, 0.190133 s, - 0.967154 s, × 0.164292 mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 6.726568 s, 0.035651 s, - 6.690917 s, × 0.005300 mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 3.266229 s, 0.440694 s, - 2.825535 s, × 0.134924 mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 15.860534 s, 18.454163 s, + 2.593629 s, × 1.163527 mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 20.450475 s, 31.562719 s, +11.112244 s, × 1.543373 mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 0.080442 s, 0.001189 s, - 0.079253 s, × 0.014781 mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 0.497672 s, 0.001204 s, - 0.496468 s, × 0.002419 mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 0.021183 s, 0.000586 s, - 0.020597 s, × 0.027664 mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 0.230991 s, 0.001845 s, - 0.229146 s, × 0.007987 mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1.118461 s, 0.063822 s, - 1.054639 s, × 0.057062 mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 2.206083 s, 0.088038 s, - 2.118045 s, × 0.039907 mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.089404 s, 0.007389 s, - 0.082015 s, × 0.082647 mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.733043 s, 0.004868 s, - 0.728175 s, × 0.006641 mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 1.163367 s, 0.222450 s, - 0.940917 s, × 0.191212 mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 0.085456 s, 0.370675 s, + 0.285219 s, × 4.337612 mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 0.083601 s, 0.358020 s, + 0.274419 s, × 4.282485 mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 7.366614 s, 0.145235 s, - 7.221379 s, × 0.019715 mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 6.664464 s, 0.037606 s, - 6.626858 s, × 0.005643 mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 7.467836 s, 7.382439 s, - 0.085397 s, × 0.988565 mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 9.801294 s, 7.273506 s, - 2.527788 s, × 0.742097 mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 0.091886 s, killed mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 26.491140 s, 1.074593 s, -25.416547 s, × 0.040564 mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 0.092863 s, killed mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 0.226823 s, killed mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 18.914630 s, 27.746195 s, + 8.831565 s, × 1.466917 mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 21.198903 s, killed mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 24.952268 s, killed Differential Revision: https://phab.mercurial-scm.org/D9296

# __init__.py - fsmonitor initialization and overrides
#
# Copyright 2013-2016 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''Faster status operations with the Watchman file monitor (EXPERIMENTAL)

Integrates the file-watching program Watchman with Mercurial to produce faster
status results.

On a particular Linux system, for a real-world repository with over 400,000
files hosted on ext4, vanilla `hg status` takes 1.3 seconds. On the same
system, with fsmonitor it takes about 0.3 seconds.

fsmonitor requires no configuration -- it will tell Watchman about your
repository as necessary. You'll need to install Watchman from
https://facebook.github.io/watchman/ and make sure it is in your PATH.

fsmonitor is incompatible with the largefiles and eol extensions, and
will disable itself if any of those are active.

The following configuration options exist:

::

    [fsmonitor]
    mode = {off, on, paranoid}

When `mode = off`, fsmonitor will disable itself (similar to not loading the
extension at all). When `mode = on`, fsmonitor will be enabled (the default).
When `mode = paranoid`, fsmonitor will query both Watchman and the filesystem,
and ensure that the results are consistent.

::

    [fsmonitor]
    timeout = (float)

A value, in seconds, that determines how long fsmonitor will wait for Watchman
to return results. Defaults to `2.0`.

::

    [fsmonitor]
    blacklistusers = (list of userids)

A list of usernames for which fsmonitor will disable itself altogether.

::

    [fsmonitor]
    walk_on_invalidate = (boolean)

Whether or not to walk the whole repo ourselves when our cached state has been
invalidated, for example when Watchman has been restarted or .hgignore rules
have been changed. Walking the repo in that case can result in competing for
I/O with Watchman. For large repos it is recommended to set this value to
false. You may wish to set this to true if you have a very fast filesystem
that can outpace the IPC overhead of getting the result data for the full repo
from Watchman. Defaults to false.

::

    [fsmonitor]
    warn_when_unused = (boolean)

Whether to print a warning during certain operations when fsmonitor would be
beneficial to performance but isn't enabled.

::

    [fsmonitor]
    warn_update_file_count = (integer)
    # or when mercurial is built with rust support
    warn_update_file_count_rust = (integer)

If ``warn_when_unused`` is set and fsmonitor isn't enabled, a warning will
be printed during working directory updates if this many files will be
created.
'''

# Platforms Supported
# ===================
#
# **Linux:** *Stable*. Watchman and fsmonitor are both known to work reliably,
#   even under severe loads.
#
# **Mac OS X:** *Stable*. The Mercurial test suite passes with fsmonitor
#   turned on, on case-insensitive HFS+. There has been a reasonable amount of
#   user testing under normal loads.
#
# **Solaris, BSD:** *Alpha*. watchman and fsmonitor are believed to work, but
#   very little testing has been done.
#
# **Windows:** *Alpha*. Not in a release version of watchman or fsmonitor yet.
#
# Known Issues
# ============
#
# * fsmonitor will disable itself if any of the following extensions are
#   enabled: largefiles, inotify, eol; or if the repository has subrepos.
# * fsmonitor will produce incorrect results if nested repos that are not
#   subrepos exist. *Workaround*: add nested repo paths to your `.hgignore`.
#
# The issues related to nested repos and subrepos are probably not fundamental
# ones. Patches to fix them are welcome.

from __future__ import absolute_import

import codecs
import os
import stat
import sys
import tempfile
import weakref

from mercurial.i18n import _
from mercurial.node import hex
from mercurial.pycompat import open
from mercurial import (
    context,
    encoding,
    error,
    extensions,
    localrepo,
    merge,
    pathutil,
    pycompat,
    registrar,
    scmutil,
    util,
)
from mercurial import match as matchmod
from mercurial.utils import (
    hashutil,
    stringutil,
)

from . import (
    pywatchman,
    state,
    watchmanclient,
)

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'

configtable = {}
configitem = registrar.configitem(configtable)

configitem(
    b'fsmonitor', b'mode', default=b'on',
)
configitem(
    b'fsmonitor', b'walk_on_invalidate', default=False,
)
configitem(
    b'fsmonitor', b'timeout', default=b'2',
)
configitem(
    b'fsmonitor', b'blacklistusers', default=list,
)
configitem(
    b'fsmonitor', b'watchman_exe', default=b'watchman',
)
configitem(
    b'fsmonitor', b'verbose', default=True, experimental=True,
)
configitem(
    b'experimental', b'fsmonitor.transaction_notify', default=False,
)

# This extension is incompatible with the following blacklisted extensions
# and will disable itself when encountering one of these:
_blacklist = [b'largefiles', b'eol']


def debuginstall(ui, fm):
    fm.write(
        b"fsmonitor-watchman",
        _(b"fsmonitor checking for watchman binary... (%s)\n"),
        ui.configpath(b"fsmonitor", b"watchman_exe"),
    )
    root = tempfile.mkdtemp()
    c = watchmanclient.client(ui, root)
    err = None
    try:
        v = c.command(b"version")
        fm.write(
            b"fsmonitor-watchman-version",
            _(b" watchman binary version %s\n"),
            pycompat.bytestr(v["version"]),
        )
    except watchmanclient.Unavailable as e:
        err = stringutil.forcebytestr(e)
    fm.condwrite(
        err,
        b"fsmonitor-watchman-error",
        _(b" watchman binary missing or broken: %s\n"),
        err,
    )
    return 1 if err else 0


def _handleunavailable(ui, state, ex):
    """Exception handler for Watchman interaction exceptions"""
    if isinstance(ex, watchmanclient.Unavailable):
        # experimental config: fsmonitor.verbose
        if ex.warn and ui.configbool(b'fsmonitor', b'verbose'):
            if b'illegal_fstypes' not in stringutil.forcebytestr(ex):
                ui.warn(stringutil.forcebytestr(ex) + b'\n')
        if ex.invalidate:
            state.invalidate()
        # experimental config: fsmonitor.verbose
        if ui.configbool(b'fsmonitor', b'verbose'):
            ui.log(
                b'fsmonitor',
                b'Watchman unavailable: %s\n',
                stringutil.forcebytestr(ex.msg),
            )
    else:
        ui.log(
            b'fsmonitor',
            b'Watchman exception: %s\n',
            stringutil.forcebytestr(ex),
        )


def _hashignore(ignore):
    """Calculate hash for ignore patterns and filenames

    If this information changes between Mercurial invocations, we can't
    rely on Watchman information anymore and have to re-scan the working
    copy.

    """
    sha1 = hashutil.sha1()
    sha1.update(pycompat.byterepr(ignore))
    return pycompat.sysbytes(sha1.hexdigest())


_watchmanencoding = pywatchman.encoding.get_local_encoding()
_fsencoding = sys.getfilesystemencoding() or sys.getdefaultencoding()
_fixencoding = codecs.lookup(_watchmanencoding) != codecs.lookup(_fsencoding)


def _watchmantofsencoding(path):
    """Fix path to match watchman and local filesystem encoding

    watchman's paths encoding can differ from filesystem encoding. For example,
    on Windows, it's always utf-8.
    """
    try:
        decoded = path.decode(_watchmanencoding)
    except UnicodeDecodeError as e:
        raise error.Abort(
            stringutil.forcebytestr(e), hint=b'watchman encoding error'
        )

    try:
        encoded = decoded.encode(_fsencoding, 'strict')
    except UnicodeEncodeError as e:
        raise error.Abort(stringutil.forcebytestr(e))

    return encoded


def overridewalk(orig, self, match, subrepos, unknown, ignored, full=True):
    '''Replacement for dirstate.walk, hooking into Watchman.

    Whenever full is False, ignored is False, and the Watchman client is
    available, use Watchman combined with saved state to possibly return only a
    subset of files.'''

    def bail(reason):
        self._ui.debug(b'fsmonitor: fallback to core status, %s\n' % reason)
        return orig(match, subrepos, unknown, ignored, full=True)

    if full:
        return bail(b'full rewalk requested')
    if ignored:
        return bail(b'listing ignored files')
    if not self._watchmanclient.available():
        return bail(b'client unavailable')
    state = self._fsmonitorstate
    clock, ignorehash, notefiles = state.get()
    if not clock:
        if state.walk_on_invalidate:
            return bail(b'no clock')
        # Initial NULL clock value, see
        # https://facebook.github.io/watchman/docs/clockspec.html
        clock = b'c:0:0'
        notefiles = []

    ignore = self._ignore
    dirignore = self._dirignore
    if unknown:
        if _hashignore(ignore) != ignorehash and clock != b'c:0:0':
            # ignore list changed -- can't rely on Watchman state any more
            if state.walk_on_invalidate:
                return bail(b'ignore rules changed')
            notefiles = []
            clock = b'c:0:0'
    else:
        # always ignore
        ignore = util.always
        dirignore = util.always

    matchfn = match.matchfn
    matchalways = match.always()
    dmap = self._map
    if util.safehasattr(dmap, b'_map'):
        # for better performance, directly access the inner dirstate map if the
        # standard dirstate implementation is in use.
        dmap = dmap._map
    nonnormalset = self._map.nonnormalset

    copymap = self._map.copymap
    getkind = stat.S_IFMT
    dirkind = stat.S_IFDIR
    regkind = stat.S_IFREG
    lnkkind = stat.S_IFLNK
    join = self._join
    normcase = util.normcase
    fresh_instance = False

    exact = skipstep3 = False
    if match.isexact():  # match.exact
        exact = True
        dirignore = util.always  # skip step 2
    elif match.prefix():  # match.match, no patterns
        skipstep3 = True

    if not exact and self._checkcase:
        # note that even though we could receive directory entries, we're only
        # interested in checking if a file with the same name exists. So only
        # normalize files if possible.
        normalize = self._normalizefile
        skipstep3 = False
    else:
        normalize = None

    # step 1: find all explicit files
    results, work, dirsnotfound = self._walkexplicit(match, subrepos)

    skipstep3 = skipstep3 and not (work or dirsnotfound)
    work = [d for d in work if not dirignore(d[0])]

    if not work and (exact or skipstep3):
        for s in subrepos:
            del results[s]
        del results[b'.hg']
        return results

    # step 2: query Watchman
    try:
        # Use the user-configured timeout for the query.
        # Add a little slack over the top of the user query to allow for
        # overheads while transferring the data
        self._watchmanclient.settimeout(state.timeout + 0.1)
        result = self._watchmanclient.command(
            b'query',
            {
                b'fields': [b'mode', b'mtime', b'size', b'exists', b'name'],
                b'since': clock,
                b'expression': [
                    b'not',
                    [
                        b'anyof',
                        [b'dirname', b'.hg'],
                        [b'name', b'.hg', b'wholename'],
                    ],
                ],
                b'sync_timeout': int(state.timeout * 1000),
                b'empty_on_fresh_instance': state.walk_on_invalidate,
            },
        )
    except Exception as ex:
        _handleunavailable(self._ui, state, ex)
        self._watchmanclient.clearconnection()
        return bail(b'exception during run')
    else:
        # We need to propagate the last observed clock up so that we
        # can use it for our next query
        state.setlastclock(pycompat.sysbytes(result[b'clock']))
        if result[b'is_fresh_instance']:
            if state.walk_on_invalidate:
                state.invalidate()
                return bail(b'fresh instance')
            fresh_instance = True
            # Ignore any prior noteable files from the state info
            notefiles = []

    # for file paths which require normalization and we encounter a case
    # collision, we store our own foldmap
    if normalize:
        foldmap = {normcase(k): k for k in results}

    switch_slashes = pycompat.ossep == b'\\'
    # The order of the results is, strictly speaking, undefined.
    # For case changes on a case insensitive filesystem we may receive
    # two entries, one with exists=True and another with exists=False.
    # The exists=True entries in the same response should be interpreted
    # as being happens-after the exists=False entries due to the way that
    # Watchman tracks files.  We use this property to reconcile deletes
    # for name case changes.
    for entry in result[b'files']:
        fname = entry[b'name']

        # Watchman always give us a str. Normalize to bytes on Python 3
        # using Watchman's encoding, if needed.
        if not isinstance(fname, bytes):
            fname = fname.encode(_watchmanencoding)

        if _fixencoding:
            fname = _watchmantofsencoding(fname)

        if switch_slashes:
            fname = fname.replace(b'\\', b'/')
        if normalize:
            normed = normcase(fname)
            fname = normalize(fname, True, True)
            foldmap[normed] = fname
        fmode = entry[b'mode']
        fexists = entry[b'exists']
        kind = getkind(fmode)

        if b'/.hg/' in fname or fname.endswith(b'/.hg'):
            return bail(b'nested-repo-detected')

        if not fexists:
            # if marked as deleted and we don't already have a change
            # record, mark it as deleted.  If we already have an entry
            # for fname then it was either part of walkexplicit or was
            # an earlier result that was a case change
            if (
                fname not in results
                and fname in dmap
                and (matchalways or matchfn(fname))
            ):
                results[fname] = None
        elif kind == dirkind:
            if fname in dmap and (matchalways or matchfn(fname)):
                results[fname] = None
        elif kind == regkind or kind == lnkkind:
            if fname in dmap:
                if matchalways or matchfn(fname):
                    results[fname] = entry
            elif (matchalways or matchfn(fname)) and not ignore(fname):
                results[fname] = entry
        elif fname in dmap and (matchalways or matchfn(fname)):
            results[fname] = None

    # step 3: query notable files we don't already know about
    # XXX try not to iterate over the entire dmap
    if normalize:
        # any notable files that have changed case will already be handled
        # above, so just check membership in the foldmap
        notefiles = {
            normalize(f, True, True)
            for f in notefiles
            if normcase(f) not in foldmap
        }
    visit = {
        f
        for f in notefiles
        if (f not in results and matchfn(f) and (f in dmap or not ignore(f)))
    }

    if not fresh_instance:
        if matchalways:
            visit.update(f for f in nonnormalset if f not in results)
            visit.update(f for f in copymap if f not in results)
        else:
            visit.update(
                f for f in nonnormalset if f not in results and matchfn(f)
            )
            visit.update(f for f in copymap if f not in results and matchfn(f))
    else:
        if matchalways:
            visit.update(
                f for f, st in pycompat.iteritems(dmap) if f not in results
            )
            visit.update(f for f in copymap if f not in results)
        else:
            visit.update(
                f
                for f, st in pycompat.iteritems(dmap)
                if f not in results and matchfn(f)
            )
            visit.update(f for f in copymap if f not in results and matchfn(f))

    audit = pathutil.pathauditor(self._root, cached=True).check
    auditpass = [f for f in visit if audit(f)]
    auditpass.sort()
    auditfail = visit.difference(auditpass)
    for f in auditfail:
        results[f] = None

    nf = iter(auditpass)
    for st in util.statfiles([join(f) for f in auditpass]):
        f = next(nf)
        if st or f in dmap:
            results[f] = st

    for s in subrepos:
        del results[s]
    del results[b'.hg']
    return results


def overridestatus(
    orig,
    self,
    node1=b'.',
    node2=None,
    match=None,
    ignored=False,
    clean=False,
    unknown=False,
    listsubrepos=False,
):
    listignored = ignored
    listclean = clean
    listunknown = unknown

    def _cmpsets(l1, l2):
        try:
            if b'FSMONITOR_LOG_FILE' in encoding.environ:
                fn = encoding.environ[b'FSMONITOR_LOG_FILE']
                f = open(fn, b'wb')
            else:
                fn = b'fsmonitorfail.log'
                f = self.vfs.open(fn, b'wb')
        except (IOError, OSError):
            self.ui.warn(_(b'warning: unable to write to %s\n') % fn)
            return

        try:
            for i, (s1, s2) in enumerate(zip(l1, l2)):
                if set(s1) != set(s2):
                    f.write(b'sets at position %d are unequal\n' % i)
                    f.write(b'watchman returned: %s\n' % s1)
                    f.write(b'stat returned: %s\n' % s2)
        finally:
            f.close()

    if isinstance(node1, context.changectx):
        ctx1 = node1
    else:
        ctx1 = self[node1]
    if isinstance(node2, context.changectx):
        ctx2 = node2
    else:
        ctx2 = self[node2]

    working = ctx2.rev() is None
    parentworking = working and ctx1 == self[b'.']
    match = match or matchmod.always()

    # Maybe we can use this opportunity to update Watchman's state.
    # Mercurial uses workingcommitctx and/or memctx to represent the part of
    # the workingctx that is to be committed. So don't update the state in
    # that case.
    # HG_PENDING is set in the environment when the dirstate is being updated
    # in the middle of a transaction; we must not update our state in that
    # case, or we risk forgetting about changes in the working copy.
    updatestate = (
        parentworking
        and match.always()
        and not isinstance(ctx2, (context.workingcommitctx, context.memctx))
        and b'HG_PENDING' not in encoding.environ
    )

    try:
        if self._fsmonitorstate.walk_on_invalidate:
            # Use a short timeout to query the current clock.  If that
            # takes too long then we assume that the service will be slow
            # to answer our query.
            # walk_on_invalidate indicates that we prefer to walk the
            # tree ourselves because we can ignore portions that Watchman
            # cannot and we tend to be faster in the warmer buffer cache
            # cases.
            self._watchmanclient.settimeout(0.1)
        else:
            # Give Watchman more time to potentially complete its walk
            # and return the initial clock.  In this mode we assume that
            # the filesystem will be slower than parsing a potentially
            # very large Watchman result set.
            self._watchmanclient.settimeout(self._fsmonitorstate.timeout + 0.1)
        startclock = self._watchmanclient.getcurrentclock()
    except Exception as ex:
        self._watchmanclient.clearconnection()
        _handleunavailable(self.ui, self._fsmonitorstate, ex)
        # boo, Watchman failed. bail
        return orig(
            node1,
            node2,
            match,
            listignored,
            listclean,
            listunknown,
            listsubrepos,
        )

    if updatestate:
        # We need info about unknown files. This may make things slower the
        # first time, but whatever.
        stateunknown = True
    else:
        stateunknown = listunknown

    if updatestate:
        ps = poststatus(startclock)
        self.addpostdsstatus(ps)

    r = orig(
        node1, node2, match, listignored, listclean, stateunknown, listsubrepos
    )
    modified, added, removed, deleted, unknown, ignored, clean = r

    if not listunknown:
        unknown = []

    # don't do paranoid checks if we're not going to query Watchman anyway
    full = listclean or match.traversedir is not None
    if self._fsmonitorstate.mode == b'paranoid' and not full:
        # run status again and fall back to the old walk this time
        self.dirstate._fsmonitordisable = True

        # shut the UI up
        quiet = self.ui.quiet
        self.ui.quiet = True
        fout, ferr = self.ui.fout, self.ui.ferr
        self.ui.fout = self.ui.ferr = open(os.devnull, b'wb')

        try:
            rv2 = orig(
                node1,
                node2,
                match,
                listignored,
                listclean,
                listunknown,
                listsubrepos,
            )
        finally:
            self.dirstate._fsmonitordisable = False
            self.ui.quiet = quiet
            self.ui.fout, self.ui.ferr = fout, ferr

        # clean isn't tested since it's set to True above
        with self.wlock():
            _cmpsets(
                [modified, added, removed, deleted, unknown, ignored, clean],
                rv2,
            )
        modified, added, removed, deleted, unknown, ignored, clean = rv2

    return scmutil.status(
        modified, added, removed, deleted, unknown, ignored, clean
    )


class poststatus(object):
    def __init__(self, startclock):
        self._startclock = pycompat.sysbytes(startclock)

    def __call__(self, wctx, status):
        clock = wctx.repo()._fsmonitorstate.getlastclock() or self._startclock
        hashignore = _hashignore(wctx.repo().dirstate._ignore)
        notefiles = (
            status.modified
            + status.added
            + status.removed
            + status.deleted
            + status.unknown
        )
        wctx.repo()._fsmonitorstate.set(clock, hashignore, notefiles)


def makedirstate(repo, dirstate):
    class fsmonitordirstate(dirstate.__class__):
        def _fsmonitorinit(self, repo):
            # _fsmonitordisable is used in paranoid mode
            self._fsmonitordisable = False
            self._fsmonitorstate = repo._fsmonitorstate
            self._watchmanclient = repo._watchmanclient
            self._repo = weakref.proxy(repo)

        def walk(self, *args, **kwargs):
            orig = super(fsmonitordirstate, self).walk
            if self._fsmonitordisable:
                return orig(*args, **kwargs)
            return overridewalk(orig, self, *args, **kwargs)

        def rebuild(self, *args, **kwargs):
            self._fsmonitorstate.invalidate()
            return super(fsmonitordirstate, self).rebuild(*args, **kwargs)

        def invalidate(self, *args, **kwargs):
            self._fsmonitorstate.invalidate()
            return super(fsmonitordirstate, self).invalidate(*args, **kwargs)

    dirstate.__class__ = fsmonitordirstate
    dirstate._fsmonitorinit(repo)


def wrapdirstate(orig, self):
    ds = orig(self)
    # only override the dirstate when Watchman is available for the repo
    if util.safehasattr(self, b'_fsmonitorstate'):
        makedirstate(self, ds)
    return ds


def extsetup(ui):
    extensions.wrapfilecache(
        localrepo.localrepository, b'dirstate', wrapdirstate
    )
    if pycompat.isdarwin:
        # An assist for avoiding the dangling-symlink fsevents bug
        extensions.wrapfunction(os, b'symlink', wrapsymlink)

    extensions.wrapfunction(merge, b'_update', wrapupdate)


def wrapsymlink(orig, source, link_name):
    ''' if we create a dangling symlink, also touch the parent dir
    to encourage fsevents notifications to work more correctly '''
    try:
        return orig(source, link_name)
    finally:
        try:
            os.utime(os.path.dirname(link_name), None)
        except OSError:
            pass


class state_update(object):
    ''' This context manager is responsible for dispatching the state-enter
        and state-leave signals to the watchman service. The enter and leave
        methods can be invoked manually (for scenarios where context manager
        semantics are not possible). If parameters oldnode and newnode are None,
        they will be populated based on current working copy in enter and
        leave, respectively. Similarly, if the distance is none, it will be
        calculated based on the oldnode and newnode in the leave method.'''

    def __init__(
        self,
        repo,
        name,
        oldnode=None,
        newnode=None,
        distance=None,
        partial=False,
    ):
        self.repo = repo.unfiltered()
        self.name = name
        self.oldnode = oldnode
        self.newnode = newnode
        self.distance = distance
        self.partial = partial
        self._lock = None
        self.need_leave = False

    def __enter__(self):
        self.enter()

    def enter(self):
        # Make sure we have a wlock prior to sending notifications to watchman.
        # We don't want to race with other actors. In the update case,
        # merge.update is going to take the wlock almost immediately. We are
        # effectively extending the lock around several short sanity checks.
        if self.oldnode is None:
            self.oldnode = self.repo[b'.'].node()

        if self.repo.currentwlock() is None:
            if util.safehasattr(self.repo, b'wlocknostateupdate'):
                self._lock = self.repo.wlocknostateupdate()
            else:
                self._lock = self.repo.wlock()
        self.need_leave = self._state(b'state-enter', hex(self.oldnode))
        return self

    def __exit__(self, type_, value, tb):
        abort = True if type_ else False
        self.exit(abort=abort)

    def exit(self, abort=False):
        try:
            if self.need_leave:
                status = b'failed' if abort else b'ok'
                if self.newnode is None:
                    self.newnode = self.repo[b'.'].node()
                if self.distance is None:
                    self.distance = calcdistance(
                        self.repo, self.oldnode, self.newnode
                    )
                self._state(b'state-leave', hex(self.newnode), status=status)
        finally:
            self.need_leave = False
            if self._lock:
                self._lock.release()

    def _state(self, cmd, commithash, status=b'ok'):
        if not util.safehasattr(self.repo, b'_watchmanclient'):
            return False
        try:
            self.repo._watchmanclient.command(
                cmd,
                {
                    b'name': self.name,
                    b'metadata': {
                        # the target revision
                        b'rev': commithash,
                        # approximate number of commits between current and target
                        b'distance': self.distance if self.distance else 0,
                        # success/failure (only really meaningful for state-leave)
                        b'status': status,
                        # whether the working copy parent is changing
                        b'partial': self.partial,
                    },
                },
            )
            return True
        except Exception as e:
            # Swallow any errors; fire and forget
            self.repo.ui.log(
                b'watchman', b'Exception %s while running %s\n', e, cmd
            )
            return False


# Estimate the distance between two nodes
def calcdistance(repo, oldnode, newnode):
    anc = repo.changelog.ancestor(oldnode, newnode)
    ancrev = repo[anc].rev()
    distance = abs(repo[oldnode].rev() - ancrev) + abs(
        repo[newnode].rev() - ancrev
    )
    return distance


# Bracket working copy updates with calls to the watchman state-enter
# and state-leave commands.  This allows clients to perform more intelligent
# settling during bulk file change scenarios
# https://facebook.github.io/watchman/docs/cmd/subscribe.html#advanced-settling
def wrapupdate(
    orig,
    repo,
    node,
    branchmerge,
    force,
    ancestor=None,
    mergeancestor=False,
    labels=None,
    matcher=None,
    **kwargs
):

    distance = 0
    partial = True
    oldnode = repo[b'.'].node()
    newnode = repo[node].node()
    if matcher is None or matcher.always():
        partial = False
        distance = calcdistance(repo.unfiltered(), oldnode, newnode)

    with state_update(
        repo,
        name=b"hg.update",
        oldnode=oldnode,
        newnode=newnode,
        distance=distance,
        partial=partial,
    ):
        return orig(
            repo,
            node,
            branchmerge,
            force,
            ancestor,
            mergeancestor,
            labels,
            matcher,
            **kwargs
        )


def repo_has_depth_one_nested_repo(repo):
    for f in repo.wvfs.listdir():
        if os.path.isdir(os.path.join(repo.root, f, b'.hg')):
            msg = b'fsmonitor: sub-repository %r detected, fsmonitor disabled\n'
            repo.ui.debug(msg % f)
            return True
    return False


def reposetup(ui, repo):
    # We don't work with largefiles or inotify
    exts = extensions.enabled()
    for ext in _blacklist:
        if ext in exts:
            ui.warn(
                _(
                    b'The fsmonitor extension is incompatible with the %s '
                    b'extension and has been disabled.\n'
                )
                % ext
            )
            return

    if repo.local():
        # We don't work with subrepos either.
        #
        # if repo[None].substate can cause a dirstate parse, which is too
        # slow. Instead, look for a file called hgsubstate,
        if repo.wvfs.exists(b'.hgsubstate') or repo.wvfs.exists(b'.hgsub'):
            return

        if repo_has_depth_one_nested_repo(repo):
            return

        fsmonitorstate = state.state(repo)
        if fsmonitorstate.mode == b'off':
            return

        try:
            client = watchmanclient.client(repo.ui, repo.root)
        except Exception as ex:
            _handleunavailable(ui, fsmonitorstate, ex)
            return

        repo._fsmonitorstate = fsmonitorstate
        repo._watchmanclient = client

        dirstate, cached = localrepo.isfilecached(repo, b'dirstate')
        if cached:
            # at this point since fsmonitorstate wasn't present,
            # repo.dirstate is not a fsmonitordirstate
            makedirstate(repo, dirstate)

        class fsmonitorrepo(repo.__class__):
            def status(self, *args, **kwargs):
                orig = super(fsmonitorrepo, self).status
                return overridestatus(orig, self, *args, **kwargs)

            def wlocknostateupdate(self, *args, **kwargs):
                return super(fsmonitorrepo, self).wlock(*args, **kwargs)

            def wlock(self, *args, **kwargs):
                l = super(fsmonitorrepo, self).wlock(*args, **kwargs)
                if not ui.configbool(
                    b"experimental", b"fsmonitor.transaction_notify"
                ):
                    return l
                if l.held != 1:
                    return l
                origrelease = l.releasefn

                def staterelease():
                    if origrelease:
                        origrelease()
                    if l.stateupdate:
                        l.stateupdate.exit()
                        l.stateupdate = None

                try:
                    l.stateupdate = None
                    l.stateupdate = state_update(self, name=b"hg.transaction")
                    l.stateupdate.enter()
                    l.releasefn = staterelease
                except Exception as e:
                    # Swallow any errors; fire and forget
                    self.ui.log(
                        b'watchman', b'Exception in state update %s\n', e
                    )
                return l

        repo.__class__ = fsmonitorrepo