hgext/git/index.py | 24 +++++++++++++++---------
1 files changed, 15 insertions(+), 9 deletions(-)
# HG changeset patch
# User Josef 'Jeff' Sipek <jef...@josefsipek.net>
# Date 1727895686 14400
# Wed Oct 02 15:01:26 2024 -0400
# Node ID c904a51a704b9f241252dbdd0bacaa3a71c135d9
# Parent 4b50801797ddbbf4cd87849a1506a6073a76e028
git: speed up possible head processing during indexing by ~100x
Benchmarking of 50 iterations of indexing (see below) shows that there is
essentially no difference for small repos (<1k commits), similarly medium
repos (~12k commits) see some benefit but other overheads completely
overwhelm it, but for large repos (~122k commits) the 80-100x speedup is
clearly visible to the user.
All of the numbers are in seconds and were measured with time.time() calls
placed in _index_repo(). The times exclude the time taken by changedfiles
processing.
Small repo (guilt, 553 commits, 1 head):
Min. 1st Qu. Median Mean 3rd Qu. Max.
0.0008781 0.0009274 0.0009800 0.0012285 0.0014637 0.0024107 (before)
0.0003092 0.0003281 0.0003519 0.0003777 0.0003927 0.0006843 (after)
Medium repo (hamlib, 12k commits, 53 heads):
Min. 1st Qu. Median Mean 3rd Qu. Max.
0.04881 0.05135 0.07632 0.06672 0.08042 0.09415 (before)
0.004249 0.004420 0.004799 0.004809 0.005051 0.006416 (after)
Large repo (qemu, 122k commits, 50 heads):
Min. 1st Qu. Median Mean 3rd Qu. Max.
4.274 4.595 4.832 6.578 8.397 9.721 (before)
0.05180 0.05643 0.05865 0.06130 0.06712 0.06872 (after)
diff --git a/hgext/git/index.py b/hgext/git/index.py
--- a/hgext/git/index.py
+++ b/hgext/git/index.py
@@ -18,7 +18,7 @@ from . import gitutil
pygit2 = gitutil.get_pygit2()
-_CURRENT_SCHEMA_VERSION = 1
+_CURRENT_SCHEMA_VERSION = 2
_SCHEMA = (
"""
CREATE TABLE refs (
@@ -35,6 +35,8 @@ CREATE TABLE possible_heads (
node TEXT NOT NULL
);
+CREATE UNIQUE INDEX possible_heads_idx ON possible_heads(node);
+
-- The topological heads of the changelog, which hg depends on.
CREATE TABLE heads (
node TEXT NOT NULL
@@ -331,14 +333,18 @@ def _index_repo(
)
db.execute('DELETE FROM heads')
db.execute('DELETE FROM possible_heads')
- for hid in possible_heads:
- h = hid.hex
- db.execute('INSERT INTO possible_heads (node) VALUES(?)', (h,))
- haschild = db.execute(
- 'SELECT COUNT(*) FROM changelog WHERE p1 = ? OR p2 = ?', (h, h)
- ).fetchone()[0]
- if not haschild:
- db.execute('INSERT INTO heads (node) VALUES(?)', (h,))
+ db.executemany('INSERT INTO possible_heads (node) VALUES(?)',
+ [ (hid.hex,) for hid in possible_heads ]
+ )
+ db.execute('''
+ INSERT INTO heads (node)
+ SELECT node FROM possible_heads WHERE
+ node NOT IN (
+ SELECT DISTINCT possible_heads.node FROM changelog,
possible_heads WHERE
+ changelog.p1 = possible_heads.node OR
+ changelog.p2 = possible_heads.node
+ )
+ ''')
db.commit()
if prog is not None:
_______________________________________________
Mercurial-devel mailing list
Mercurial-devel@lists.mercurial-scm.org
https://lists.mercurial-scm.org/mailman/listinfo/mercurial-devel
