view tests/test-remotefilelog-gc.t @ 51977:42a116f1cdc1

branchmap-v3: introduce a "stop_rev" argument to `headsrevs` The `headsrevs` method of the revlog already have a `revs` argument to compute the headrevs of a limited set of heads. However, it disable the use of the native compiled code to compute the heads, which slows down the branchmap v3 code a lot. The branchmap v3 usage is actually quite constrained as we will always only ignores a part at the top of the graph. So we could be significantly faster. We start by making small change to the python side to improve the situation and introduce the new API. More collaboration with the native code are coming later. This massively speedup operation and close most of the remaining gaps between branchmap-v3 and branchmap-v2. especially on repository with many revs like mozilla-try. A small overhead remains mostly because the `headrevs` logic currently has some inefficiently. We will look into them from there. ### benchmark.name = hg.command.unbundle # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.resource-usage = default # benchmark.variants.reuse-external-delta-parent = yes # benchmark.variants.revs = any-1-extra-rev # benchmark.variants.source = unbundle # benchmark.variants.validate = default # benchmark.variants.verbosity = quiet ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.233711 ~~~~~ branch-v3 before: 0.368769 (+57.79%, +0.14) branch-v3 after: 0.239857 (+2.63%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.235230 ~~~~~ branch-v3 before: 0.372460 (+58.34%, +0.14) branch-v3 after: 0.240972 (+2.44%, +0.01) ## data-env-vars.name = netbeans-2018-08-01-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.255586 ~~~~~ branch-v3 before: 0.318907 (+24.78%, +0.06) branch-v3 after: 0.268560 (+5.08%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.339010 ~~~~~ branch-v3 before: 0.349752 (+3.17%, +0.01) branch-v3 after: 0.349389 (+3.06%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.346525 ~~~~~ branch-v3 before: 0.354300 (+2.24%, +0.01) branch-v3 after: 0.355661 (+2.64%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.380202 ~~~~~ branch-v3 before: 0.396293 (+4.23%, +0.02) branch-v3 after: 0.408851 (+7.54%, +0.03) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.412165 ~~~~~ branch-v3 before: 0.424769 (+3.06%, +0.01) branch-v3 after: 0.427782 (+3.79%, +0.02) # bin-env-vars.hg.flavor = rust branch-v2: 0.412397 ~~~~~ branch-v3 before: 0.421796 (+2.28%, +0.01) branch-v3 after: 0.422354 (+2.41%, +0.01) ## data-env-vars.name = mozilla-unified-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.429501 ~~~~~ branch-v3 before: 0.443849 (+3.34%, +0.01) branch-v3 after: 0.443197 (+3.19%, +0.01) ## data-env-vars.name = mozilla-try-2024-03-26-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 3.403171 ~~~~~ branch-v3 before: 6.234055 (+83.18%, +2.83) branch-v3 after: 3.819477 (+12.23%, +0.42) # bin-env-vars.hg.flavor = rust branch-v2: 3.454876 ~~~~~ branch-v3 before: 6.307813 (+82.58%, +2.85) branch-v3 after: 3.590284 (+3.92%, +0.14) ## data-env-vars.name = mozilla-try-2024-03-26-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 3.465435 ~~~~~ branch-v3 before: 5.176076 (+49.36%, +1.71) branch-v3 after: 3.633278 (+4.84%, +0.17)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 03 Sep 2024 11:11:17 +0200
parents 051de900b240
children
line wrap: on
line source

#require no-windows

  $ . "$TESTDIR/remotefilelog-library.sh"

  $ hg init master
  $ cd master
  $ cat >> .hg/hgrc <<EOF
  > [remotefilelog]
  > server=True
  > serverexpiration=-1
  > EOF
  $ echo x > x
  $ hg commit -qAm x
  $ cd ..

  $ hgcloneshallow ssh://user@dummy/master shallow -q
  1 files fetched over 1 fetches - (1 misses, 0.00% hit ratio) over *s (glob)

# Set the prefetchdays config to zero so that all commits are prefetched
# no matter what their creation date is.
  $ cd shallow
  $ cat >> .hg/hgrc <<EOF
  > [remotefilelog]
  > prefetchdays=0
  > EOF
  $ cd ..

# commit a new version of x so we can gc the old one

  $ cd master
  $ echo y > x
  $ hg commit -qAm y
  $ cd ..

  $ cd shallow
  $ hg pull -q
  $ hg update -q
  1 files fetched over 1 fetches - (1 misses, 0.00% hit ratio) over *s (glob)
  $ cd ..

# gc client cache

  $ lastweek=`"$PYTHON" -c 'import datetime,time; print(datetime.datetime.fromtimestamp(time.time() - (86400 * 7)).strftime("%y%m%d%H%M"))'`
  $ find $CACHEDIR -type f -exec touch -t $lastweek {} \;

  $ find $CACHEDIR -type f | sort
  $TESTTMP/hgcache/master/11/f6ad8ec52a2984abaafd7c3b516503785c2072/1406e74118627694268417491f018a4a883152f0 (glob)
  $TESTTMP/hgcache/master/11/f6ad8ec52a2984abaafd7c3b516503785c2072/48023ec064c1d522f0d792a5a912bb1bf7859a4a (glob)
  $TESTTMP/hgcache/repos (glob)
  $ hg gc
  finished: removed 1 of 2 files (0.00 GB to 0.00 GB)
  $ find $CACHEDIR -type f | sort
  $TESTTMP/hgcache/master/11/f6ad8ec52a2984abaafd7c3b516503785c2072/48023ec064c1d522f0d792a5a912bb1bf7859a4a (glob)
  $TESTTMP/hgcache/repos

# gc server cache

  $ find master/.hg/remotefilelogcache -type f | sort
  master/.hg/remotefilelogcache/x/1406e74118627694268417491f018a4a883152f0 (glob)
  master/.hg/remotefilelogcache/x/48023ec064c1d522f0d792a5a912bb1bf7859a4a (glob)
  $ hg gc master
  finished: removed 0 of 1 files (0.00 GB to 0.00 GB)
  $ find master/.hg/remotefilelogcache -type f | sort
  master/.hg/remotefilelogcache/x/48023ec064c1d522f0d792a5a912bb1bf7859a4a (glob)

# Test that GC keepset includes pullprefetch revset if it is configured

  $ cd shallow
  $ cat >> .hg/hgrc <<EOF
  > [remotefilelog]
  > pullprefetch=all()
  > EOF
  $ hg prefetch
  1 files fetched over 1 fetches - (1 misses, 0.00% hit ratio) over *s (glob)

  $ cd ..
  $ hg gc
  finished: removed 0 of 2 files (0.00 GB to 0.00 GB)

# Ensure that there are 2 versions of the file in cache
  $ find $CACHEDIR -type f | sort
  $TESTTMP/hgcache/master/11/f6ad8ec52a2984abaafd7c3b516503785c2072/1406e74118627694268417491f018a4a883152f0 (glob)
  $TESTTMP/hgcache/master/11/f6ad8ec52a2984abaafd7c3b516503785c2072/48023ec064c1d522f0d792a5a912bb1bf7859a4a (glob)
  $TESTTMP/hgcache/repos (glob)

# Test that if garbage collection on repack and repack on hg gc flags are set then incremental repack with garbage collector is run

  $ hg gc --config remotefilelog.gcrepack=True --config remotefilelog.repackonhggc=True

# Ensure that loose files are repacked
  $ find $CACHEDIR -type f | sort
  $TESTTMP/hgcache/master/packs/320dab99b7e3f60512b97f347689625263d22cf5.dataidx
  $TESTTMP/hgcache/master/packs/320dab99b7e3f60512b97f347689625263d22cf5.datapack
  $TESTTMP/hgcache/master/packs/837b83c1ef6485a336eb4421ac5973c0ec130fbb.histidx
  $TESTTMP/hgcache/master/packs/837b83c1ef6485a336eb4421ac5973c0ec130fbb.histpack
  $TESTTMP/hgcache/repos

# Test that warning is displayed when there are no valid repos in repofile

  $ cp $CACHEDIR/repos $CACHEDIR/repos.bak
  $ echo " " > $CACHEDIR/repos
  $ hg gc
  warning: no valid repos in repofile
  $ mv $CACHEDIR/repos.bak $CACHEDIR/repos

# Test that warning is displayed when the repo path is malformed

  $ printf "asdas\0das" >> $CACHEDIR/repos
  $ hg gc
  abort: invalid path asdas\x00da: .*(null|NULL).* (re)
  [255]