Mas p401 coverage (#404)

* refactor leveled_sst from gen_fsm to gen_statem

* format_status/2 takes State and State Data
but this function is deprecated... put in for backward compatibility

* refactor leveled_cdb from gen_fsm to gen_statem

* disable irrelevant warning ignorer

* Remove unnecessary code paths

Only support messages, especially info messages, where they are possible.

* Mas i1820 offlinedeserialisation cbo (#403)

* Log report GC Info by manifest level

* Hibernate on range query

If Block Index Cache is not full, and we're not yielding

* Spawn to deserialise blocks offline

Hypothesis is that the growth in the heap necessary due to continual term_to_binary calls to deserialise blocks is wasting memory - so do this memory-intensive task in a short-lived process.

* Start with hibernate_after option

* Always build BIC

Testing indicates that the BIC itself is not a primary memory issue - the primary issue is due to a lack of garbage collection and a growing heap.

This change enhances the patch to offline serialisation so that:
- get_sqn & get_kv are standardised to build the BIC, and hibernate when it is built.
- the offline PId is linked to crash this process on failure (as would happen now).

* Standardise spawning for check_block/3

Now deserialise in both parts of the code.

* Only spawn for check_block if cache not full

* Update following review

* Standardise formatting

Make test more reliable.  Show no new compaction after third compaction.

* Update comments

---------

Co-authored-by: Thomas Arts <thomas.arts@quviq.com>
This commit is contained in:
Martin Sumner 2023-03-13 11:46:08 +00:00 committed by GitHub
parent e06d2a538f
commit 3d3d284805
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 1255 additions and 1253 deletions

View file

@ -266,11 +266,16 @@ remove_manifest(RootPath, GC_SQN) ->
end.
-spec report_manifest_level(manifest(), non_neg_integer()) ->
{non_neg_integer(),
non_neg_integer(),
{string(), pid(), non_neg_integer()} |
undefined}.
-spec report_manifest_level(
manifest(), non_neg_integer()) ->
{non_neg_integer(),
non_neg_integer(),
{string(), pid(), non_neg_integer()} |
undefined,
non_neg_integer(),
non_neg_integer(),
non_neg_integer(),
non_neg_integer()}.
%% @doc
%% Report on a level in the manifest
%% - How many files in the level
@ -287,7 +292,7 @@ report_manifest_level(Manifest, LevelIdx) ->
{leveled_tree:tsize(Level), leveled_tree:to_list(Level)}
end,
AccMemFun =
fun(MaybeME, {MemAcc, Max}) ->
fun(MaybeME, {MemAcc, Max, HBSAcc, HSAcc, LHSAcc, BVHSAcc}) ->
ME = get_manifest_entry(MaybeME),
P = ME#manifest_entry.owner,
{memory, PM} = process_info(P, memory),
@ -298,15 +303,26 @@ report_manifest_level(Manifest, LevelIdx) ->
_ ->
{ME#manifest_entry.filename, P, PM}
end,
{MemAcc + PM, UpdMax}
{garbage_collection_info, GCI} =
process_info(P, garbage_collection_info),
HBS = proplists:get_value(heap_block_size, GCI),
HS = proplists:get_value(heap_size, GCI),
LHS = proplists:get_value(recent_size, GCI),
BVHS = proplists:get_value(bin_vheap_size, GCI),
{MemAcc + PM, UpdMax,
HBSAcc + HBS, HSAcc + HS, LHSAcc + LHS, BVHSAcc + BVHS}
end,
case LevelSize of
0 ->
{0, 0, undefined};
{0, 0, undefined, 0, 0, 0, 0};
_ ->
{TotalMem, BiggestMem} =
lists:foldl(AccMemFun, {0, undefined}, LevelList),
{LevelSize, TotalMem div LevelSize, BiggestMem}
{TotalMem, BiggestMem, TotalHBS, TotalHS, TotalLHS, TotalBVBS} =
lists:foldl(AccMemFun, {0, undefined, 0, 0, 0, 0}, LevelList),
{LevelSize, TotalMem div LevelSize, BiggestMem,
TotalHBS div LevelSize,
TotalHS div LevelSize,
TotalLHS div LevelSize,
TotalBVBS div LevelSize}
end.