Mercurial > public > mercurial-scm > hg-stable

changeset 52940:7fc882f7fada

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
stream-clone-v2: disable buffering when writing the files Not going through python's buffer while writing chunk is not only faster, but it reduce the amount of operation that are needed under the GIL, increasing the benefit from the threads. ### benchmark.name = hg.perf.exchange.stream.consume # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.memory-target = default # benchmark.variants.num-writer = default # benchmark.variants.parallel-processing = yes # benchmark.variants.progress = no # benchmark.variants.read-from-memory = yes # benchmark.variants.version = v2 ## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog prev-change: 0.233780 ~~~~~ this-change: 0.217293 (-7.05%, -0.02) ## data-env-vars.name = netbeans-2019-11-07-zstd-sparse-revlog prev-change: 11.754377 ~~~~~ this-change: 11.222771 (-4.52%, -0.53) ## data-env-vars.name = netbsd-xsrc-all-2024-09-19-zstd-sparse-revlog prev-change: 4.735520 ~~~~~ this-change: 4.465113 (-5.71%, -0.27) ## data-env-vars.name = netbsd-xsrc-draft-2024-09-19-zstd-sparse-revlog prev-change: 4.728870 ~~~~~ this-change: 4.667360 (-1.30%, -0.06) ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog prev-change: 2.783987 ~~~~~ this-change: 2.559670 (-8.06%, -0.22) ## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog prev-change: 6.532561 ~~~~~ this-change: 6.123469 (-6.26%, -0.41) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog prev-change: 47.154728 ~~~~~ this-change: 44.781498 (-5.03%, -2.37) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog prev-change: 47.166569 ~~~~~ this-change: 44.396959 (-5.87%, -2.77) ## data-env-vars.name = mozilla-try-2024-03-26-zstd-sparse-revlog # benchmark.variants.read-from-memory = no prev-change: 113.696529 ~~~~~ this-change: 108.552706 (-4.52%, -5.14)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Mon, 20 Jan 2025 12:41:20 +0100
parents b6f24a92b399
children 5b8f6e198a6e
files mercurial/streamclone.py
diffstat 1 files changed, 9 insertions(+), 2 deletions(-) [+]
line wrap: on
line diff
--- a/mercurial/streamclone.py	Sat Nov 30 02:24:22 2024 +0100
+++ b/mercurial/streamclone.py	Mon Jan 20 12:41:20 2025 +0100
@@ -1541,9 +1541,16 @@
     """write files from parsed data"""
     for src, name, data in info:
         vfs = vfsmap[src]
-        with vfs(name, b'w') as ofp:
+        # we disable the internal Python buffering because the streamed data
+        # are assume to have been written with large enough block for it to not
+        # matters. So we only have more memory copy and GIL holding time to
+        # gain with the Python buffering.
+        with vfs(name, b'w', buffering=0) as ofp:
             for chunk in data:
-                ofp.write(chunk)
+                written = ofp.write(chunk)
+                # write missing pieces if the write was interrupted
+                while written < len(chunk):
+                    written += ofp.write(chunk[written:])
 
 
 def consumev3(repo, fp) -> None: