[PATCH v5] git-p4: improve performance when importing huge files by reducing the number of string concatenations while constraining memory usage.
Signed-off-by: Sam Hocevar <sam@zoy.org>
---
This is a properly formatted version of the previous patch.
contrib/fast-import/git-p4 | 13 ++++++++++++-
1 files changed, 12 insertions(+), 1 deletions(-)
diff --git a/contrib/fast-import/git-p4 b/contrib/fast-import/git-p4
index 3832f60..db0ea0a 100755
--- a/contrib/fast-import/git-p4
+++ b/contrib/fast-import/git-p4
@@ -984,11 +984,22 @@ class P4Sync(Command):
while j < len(filedata):
stat = filedata[j]
j += 1
+ data = []
text = ''
+ # Append data every 8192 chunks to 1) ensure decent performance
+ # by not making too many string concatenations and 2) avoid
+ # excessive memory usage by purging "data" often enough. p4
+ # sends 4k chunks, so we should not use more than 32 MiB of
+ # additional memory while rebuilding the file data.
while j < len(filedata) and filedata[j]['code'] in ('text', 'unicode', 'binary'):
- text += filedata[j]['data']
+ data.append(filedata[j]['data'])
del filedata[j]['data']
+ if len(data) > 8192:
+ text += ''.join(data)
+ data = []
j += 1
+ text += ''.join(data)
+ data = None
if not stat.has_key('depotFile'):
sys.stderr.write("p4 print fails with: %s\n" % repr(stat))
--
1.6.1.3
Sam Hocevar <sam@zoy.org>