Wed, 22 Mar 2017 05:32:25 +0100 debugstablerange: minor code reformat
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 05:32:25 +0100] rev 2138
debugstablerange: minor code reformat The content of that list will become more complex as we drop the object so we make sure to have one value per line for clarity.
Wed, 22 Mar 2017 05:09:21 +0100 stablerange: move the subrangesclosure inside the module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 05:09:21 +0100] rev 2137
stablerange: move the subrangesclosure inside the module This seems more suitable and open the way to simple update of how we build things without too much impact outside the module. The debug command is still in the 'obsdiscovery' module because it also deal to obshash and I'm not sure of were this should live yet.
Sun, 19 Mar 2017 05:33:52 +0100 stablerange: compute subranges from parent when possible
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 05:33:52 +0100] rev 2136
stablerange: compute subranges from parent when possible Unless we are a merge, we can infer the standard subranges of a range by reusing the subranger of its parent. We update the implementation to do so. We still needs the "old way" for merge. We move that code in a dedicated function for the sake of simplicity.
Wed, 22 Mar 2017 04:27:42 +0100 stablerange: add an official warmup function
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 04:27:42 +0100] rev 2135
stablerange: add an official warmup function The function is responsible for making sure we have the necessary data for a sets of heads. For now this only warm the depth cache. More will follow soon. Such explicite warmup will be usefull for on disck caching as an early point of writing will be easier.
Sun, 19 Mar 2017 04:47:31 +0100 stablerange: remove now unnecessary setter
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 04:47:31 +0100] rev 2134
stablerange: remove now unnecessary setter The class is handling all computations and cache access by itself now. So we can drop this method.
Sun, 19 Mar 2017 04:45:28 +0100 stablerange: directly perform slicing in the getting method
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 04:45:28 +0100] rev 2133
stablerange: directly perform slicing in the getting method Now that all necessary functions are available, we simply apply the standard slicing on cache miss and proceed.
Sun, 19 Mar 2017 04:43:33 +0100 stablerange: move standard slice point definition in main class
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 04:43:33 +0100] rev 2132
stablerange: move standard slice point definition in main class More migration of code away from the doomed individual class.
Sun, 19 Mar 2017 04:39:00 +0100 stablerange: move the slicing method on the central class
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 04:39:00 +0100] rev 2131
stablerange: move the slicing method on the central class We migrate code away for the individual range class.
Sun, 19 Mar 2017 03:07:01 +0100 stablerange: move the range class in the new module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 03:07:01 +0100] rev 2130
stablerange: move the range class in the new module Our ultimate goal is to remove this class for performance reason. however for now, it contains most of the code we care about so we migrate it as a block first.
Sun, 19 Mar 2017 03:06:53 +0100 stablesort: move into the stablerange module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 03:06:53 +0100] rev 2129
stablesort: move into the stablerange module The stable range rely on the stable sort so it make senses to move it there. Will need direct access to it in the future.
Wed, 22 Mar 2017 03:49:40 +0100 subranges: migrate handling of single element range
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 03:49:40 +0100] rev 2128
subranges: migrate handling of single element range This is the simplest case by far, so we start with that one. We still use the rich object as an argument, but we'll do our best to not relying on that. This is important for performance reason.
Wed, 22 Mar 2017 03:47:28 +0100 stablerange: move the subrange cache into our new class
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 03:47:28 +0100] rev 2127
stablerange: move the subrange cache into our new class This is the first step toward having more logic in that class
Sun, 19 Mar 2017 00:44:31 +0100 depth: extract code dedicated to depth of a merge in its own function
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 00:44:31 +0100] rev 2126
depth: extract code dedicated to depth of a merge in its own function The merge case is more complicated than the regular one, we extract is for the sake of clarity.
Sat, 18 Mar 2017 22:48:26 +0100 stablerange: move 'depth' inside a new 'stablerange' module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sat, 18 Mar 2017 22:48:26 +0100] rev 2125
stablerange: move 'depth' inside a new 'stablerange' module The stablerange used for discovery requires significant amount of code. There is algorithme, cache, cache persistence, etc. So we create a dedicated module for it. The function is directly moved into a rich class handling cache (for now in memory) because we know we will need it.
(0) -1000 -300 -100 -14 +14 +100 +300 +1000 +3000 tip