# HG changeset patch # User Gregory Szorc # Date 1483386617 28800 # Node ID 4215dc1b708b775e37afd4c920cb23da9edc7a9f # Parent ada160a8cfd85bf7bbaf021e7066cf08101b062b revlog: make compressed size comparisons consistent revlog.compress() compares the compressed size to the input size and throws away the compressed data if it is larger than the input. This is the correct thing to do, as storing compressed data that is larger than the input takes up more storage space and makes reading slower. However, the comparison was implemented inconsistently. For the streaming compression mode, we threw away the result if it was greater than or equal to the input size. But for the one-shot compression, we threw away the compression only if it was greater than the input size! This patch changes the comparison for the simple case so it is consistent with the streaming case. As a few tests demonstrate, this adds 1 byte to some revlog entries. This is because of an added 'u' header on the chunk. It seems somewhat wrong to increase the revlog size here. However, IMO the cost of 1 byte in storage is insignificant compared to the performance gains of avoiding decompression. This patch should invite questions around the heuristic for throwing away compressed data. For example, I'd argue we should be more liberal about rejecting compressed data, additionally doing so where the number of bytes saved fails to reach a threshold. But we can have this discussion another time. diff -r ada160a8cfd8 -r 4215dc1b708b mercurial/revlog.py --- a/mercurial/revlog.py Sat Jan 07 20:43:49 2017 -0800 +++ b/mercurial/revlog.py Mon Jan 02 11:50:17 2017 -0800 @@ -1503,7 +1503,7 @@ bin = "".join(p) else: bin = _compress(text) - if bin is None or len(bin) > l: + if bin is None or len(bin) >= l: if text[0] == '\0': return ("", text) return ('u', text) diff -r ada160a8cfd8 -r 4215dc1b708b tests/test-bundle.t --- a/tests/test-bundle.t Sat Jan 07 20:43:49 2017 -0800 +++ b/tests/test-bundle.t Mon Jan 02 11:50:17 2017 -0800 @@ -268,13 +268,13 @@ packed1 is produced properly $ hg -R test debugcreatestreamclonebundle packed.hg - writing 2663 bytes for 6 files + writing 2664 bytes for 6 files bundle requirements: generaldelta, revlogv1 $ f -B 64 --size --sha1 --hexdump packed.hg - packed.hg: size=2826, sha1=e139f97692a142b19cdcff64a69697d5307ce6d4 + packed.hg: size=2827, sha1=9d14cb90c66a21462d915ab33656f38b9deed686 0000: 48 47 53 31 55 4e 00 00 00 00 00 00 00 06 00 00 |HGS1UN..........| - 0010: 00 00 00 00 0a 67 00 16 67 65 6e 65 72 61 6c 64 |.....g..generald| + 0010: 00 00 00 00 0a 68 00 16 67 65 6e 65 72 61 6c 64 |.....h..generald| 0020: 65 6c 74 61 2c 72 65 76 6c 6f 67 76 31 00 64 61 |elta,revlogv1.da| 0030: 74 61 2f 61 64 69 66 66 65 72 65 6e 74 66 69 6c |ta/adifferentfil| diff -r ada160a8cfd8 -r 4215dc1b708b tests/test-commit-amend.t --- a/tests/test-commit-amend.t Sat Jan 07 20:43:49 2017 -0800 +++ b/tests/test-commit-amend.t Mon Jan 02 11:50:17 2017 -0800 @@ -1147,7 +1147,7 @@ R olddirname/newfile.py $ hg debugindex newdirname/newfile.py rev offset length delta linkrev nodeid p1 p2 - 0 0 88 -1 3 34a4d536c0c0 000000000000 000000000000 + 0 0 89 -1 3 34a4d536c0c0 000000000000 000000000000 $ echo a >> newdirname/commonfile.py $ hg ci --amend -m bug @@ -1155,7 +1155,7 @@ newdirname/newfile.py renamed from olddirname/newfile.py:690b295714aed510803d3020da9c70fca8336def (glob) $ hg debugindex newdirname/newfile.py rev offset length delta linkrev nodeid p1 p2 - 0 0 88 -1 3 34a4d536c0c0 000000000000 000000000000 + 0 0 89 -1 3 34a4d536c0c0 000000000000 000000000000 #if execbit