# HG changeset patch # User Boris Feld # Date 2018-09-07 15:17:30 # Node ID 3ca144f1c8ddc99e9caae2d6b68ea07b781de661 # Parent a33f394b2bfd90da4bffa69a6bad624f49fd2446 snapshot: search for unrelated but reusable full-snapshot # New Strategy Step: Reusing Snapshot Outside Of Parents' Chain. If no suitable bases were found in the parent's chains, see if we could reuse a full snapshot not directly related to the current revision. Such search can be expensive, so we only search for snapshots appended to the revlog *after* the bases used by the parents of the current revision (the one we just tested). We assume the parent's bases were created because the previous snapshots were unsuitable, so there are low odds they would be useful now. This search gives a chance to reuse a delta chain unrelated to the current revision. Without this re-use, topological branches would keep reopening new full chains. Creating more and more snapshots as the repository grow. In repositories with many topological branches, the lack of delta reuse can create too many snapshots reducing overall compression to nothing. This results in a very large repository and other usability issues. For now, we still focus on creating level-1 snapshots. However, this principle will play a large part in how we avoid snapshot explosion once we have more snapshot levels. # Effects On The Test Repository In the test repository we created, we can see the beneficial effect of such reuse. We need very few level-0 snapshots and the overall revlog size has decreased. The `hg debugrevlog` call, show a "lvl-2" snapshot. It comes from the existing delta logic using the `prev` revision (revlog's tip) as the base. In this specific case, it turns out the tip was a level-1 snapshot. This is a coincidence that can be ignored. Finding and testing against all these unrelated snapshots can have a performance impact at write time. We currently focus on building good deltas chain we build. Performance concern will be dealt with later in another series. diff --git a/mercurial/revlogutils/deltas.py b/mercurial/revlogutils/deltas.py --- a/mercurial/revlogutils/deltas.py +++ b/mercurial/revlogutils/deltas.py @@ -9,6 +9,7 @@ from __future__ import absolute_import +import collections import heapq import struct @@ -607,8 +608,18 @@ def _candidategroups(revlog, textlen, p1 continue group.append(rev) if group: + # XXX: in the sparse revlog case, group can become large, + # impacting performances. Some bounding or slicing mecanism + # would help to reduce this impact. yield tuple(group) +def _findsnapshots(revlog, cache, start_rev): + """find snapshot from start_rev to tip""" + deltaparent = revlog.deltaparent + for rev in revlog.revs(start_rev): + if deltaparent(rev) == nullrev: + cache[nullrev].append(rev) + def _rawgroups(revlog, p1, p2, cachedelta): """Provides group of revision to be tested as delta base @@ -656,6 +667,18 @@ def _rawgroups(revlog, p1, p2, cachedelt for p in parents: bases.append(deltachain(p)[0]) yield tuple(sorted(bases)) + # No suitable base found in the parent chain, search if any full + # snapshots emitted since parent's base would be a suitable base for an + # intermediate snapshot. + # + # It give a chance to reuse a delta chain unrelated to the current + # revisions instead of starting our own. Without such re-use, + # topological branches would keep reopening new full chains. Creating + # more and more snapshot as the repository grow. + snapfloor = min(bases) + 1 + snapshots = collections.defaultdict(list) + _findsnapshots(revlog, snapshots, snapfloor) + yield tuple(snapshots[nullrev]) # other approach failed try against prev to hopefully save us a # fulltext. diff --git a/tests/test-sparse-revlog.t b/tests/test-sparse-revlog.t --- a/tests/test-sparse-revlog.t +++ b/tests/test-sparse-revlog.t @@ -77,7 +77,7 @@ repeatedly while some of it changes rare $ f -s .hg/store/data/*.d - .hg/store/data/_s_p_a_r_s_e-_r_e_v_l_o_g-_t_e_s_t-_f_i_l_e.d: size=72315280 + .hg/store/data/_s_p_a_r_s_e-_r_e_v_l_o_g-_t_e_s_t-_f_i_l_e.d: size=67810463 $ hg debugrevlog * format : 1 flags : generaldelta @@ -89,36 +89,39 @@ repeatedly while some of it changes rare empty : 0 ( 0.00%) text : 0 (100.00%) delta : 0 (100.00%) - snapshot : 145 ( 2.90%) - lvl-0 : 15 ( 0.30%) - lvl-1 : 130 ( 2.60%) - deltas : 4856 (97.10%) - revision size : 72315280 - snapshot : 18481085 (25.56%) - lvl-0 : 3016019 ( 4.17%) - lvl-1 : 15465066 (21.39%) - deltas : 53834195 (74.44%) + snapshot : 126 ( 2.52%) + lvl-0 : 4 ( 0.08%) + lvl-1 : 120 ( 2.40%) + lvl-2 : 2 ( 0.04%) + deltas : 4875 (97.48%) + revision size : 67810463 + snapshot : 14373347 (21.20%) + lvl-0 : 804235 ( 1.19%) + lvl-1 : 13535903 (19.96%) + lvl-2 : 33209 ( 0.05%) + deltas : 53437116 (78.80%) chunks : 5001 0x78 (x) : 5001 (100.00%) - chunks size : 72315280 - 0x78 (x) : 72315280 (100.00%) + chunks size : 67810463 + 0x78 (x) : 67810463 (100.00%) avg chain length : 18 max chain length : 45 - max chain reach : 32095083 - compression ratio : 23 + max chain reach : 25808240 + compression ratio : 25 uncompressed data size (min/max/avg) : 346468 / 346472 / 346471 - full revision size (min/max/avg) : 200990 / 201151 / 201067 - inter-snapshot size (min/max/avg) : 37202 / 173034 / 118962 - level-1 (min/max/avg) : 37202 / 173034 / 118962 - delta size (min/max/avg) : 10649 / 104791 / 11086 + full revision size (min/max/avg) : 201014 / 201116 / 201058 + inter-snapshot size (min/max/avg) : 11623 / 173150 / 111222 + level-1 (min/max/avg) : 11623 / 173150 / 112799 + level-2 (min/max/avg) : 14151 / 19058 / 16604 + delta size (min/max/avg) : 10649 / 101790 / 10961 - deltas against prev : 4185 (86.18%) - where prev = p1 : 4139 (98.90%) + deltas against prev : 4207 (86.30%) + where prev = p1 : 4164 (98.98%) where prev = p2 : 0 ( 0.00%) - other : 46 ( 1.10%) - deltas against p1 : 647 (13.32%) - deltas against p2 : 24 ( 0.49%) + other : 43 ( 1.02%) + deltas against p1 : 653 (13.39%) + deltas against p2 : 15 ( 0.31%) deltas against other : 0 ( 0.00%)