Avoid extra out-of-cache hash table deduplication for package names

We were de-duplicating package name strings in StoreString, but also
deduplicating most of them by them being in groups, so we had extra
hash table lookups that could be avoided in NewGroup().

To continue deduplicating names across binary packages and source
packages, insert groups for source packages as well. This is also
a good first step in allowing efficient lookup of packages by source
package - we can extend Group later by a list of SourceVersion objects,
or alternatively, simply add a by-source chain into pkgCache::Version.

This change improves performance by about 10% (913 to 814 ms), while
having no significant overhead on the cache size:

--- before
+++ after
@@ -1,7 +1,7 @@
-Total package names: 109536 (2.191 k)
-Total package structures: 118689 (4.748 k)
+Total package names: 119642 (2.393 k)
+Total package structures: 118687 (4.747 k)
   Normal packages: 83309
-  Pure virtual packages: 3365
+  Pure virtual packages: 3363
   Single virtual packages: 17811
   Mixed virtual packages: 1973
   Missing: 12231
@@ -10,21 +10,21 @@ Total distinct descriptions: 149291 (3.583 k)
 Total dependencies: 484135/156650 (12,2 M)
 Total ver/file relations: 57421 (1.378 k)
 Total Desc/File relations: 18219 (437 k)
-Total Provides mappings: 29963 (719 k)
+Total Provides mappings: 29959 (719 k)
 Total globbed strings: 226993 (5.332 k)
 Total slack space: 26,8 k
-Total space accounted for: 38,1 M
+Total space accounted for: 38,3 M
 Total buckets in PkgHashTable: 50503
-  Unused: 5727
-  Used: 44776
-  Utilization: 88.6601%
-  Average entries: 2.65073
+  Unused: 5728
+  Used: 44775
+  Utilization: 88.6581%
+  Average entries: 2.65074
   Longest: 60
   Shortest: 1
 Total buckets in GrpHashTable: 50503
-  Unused: 5727
-  Used: 44776
-  Utilization: 88.6601%
-  Average entries: 2.44631
-  Longest: 10
+  Unused: 4649
+  Used: 45854
+  Utilization: 90.7946%
+  Average entries: 2.60919
+  Longest: 11
   Shortest: 1

3 files changed, 8 insertions, 7 deletions

diff --git a/apt-pkg/deb/deblistparser.cc b/apt-pkg/deb/deblistparser.cc
index 75fc2d242..88b41ad30 100644
--- a/apt-pkg/deb/deblistparser.cc
+++ b/apt-pkg/deb/deblistparser.cc
@@ -211,9 +211,12 @@ bool debListParser::NewVersion(pkgCache::VerIterator &Ver)
 	 }
 	 if (V.end() == true)
 	 {
-	    map_stringitem_t const idx = StoreString(pkgCacheGenerator::PKGNAME, pkgname);
+	    pkgCache::GrpIterator SG;
+	    if (not NewGroup(SG, pkgname))
+	       return false;
+
 	    G = Ver.ParentPkg().Group();
-	    Ver->SourcePkgName = idx;
+	    Ver->SourcePkgName = SG->Name;
 	 }
       }
    }
diff --git a/apt-pkg/pkgcachegen.cc b/apt-pkg/pkgcachegen.cc
index 030f4df0a..183750acb 100644
--- a/apt-pkg/pkgcachegen.cc
+++ b/apt-pkg/pkgcachegen.cc
@@ -559,7 +559,7 @@ bool pkgCacheGenerator::NewGroup(pkgCache::GrpIterator &Grp, StringView Name)
       return false;
 
    Grp = pkgCache::GrpIterator(Cache, Cache.GrpP + Group);
-   map_stringitem_t const idxName = StoreString(PKGNAME, Name);
+   map_stringitem_t const idxName = WriteStringInMap(Name);
    if (unlikely(idxName == 0))
       return false;
    Grp->Name = idxName;
@@ -1336,7 +1336,6 @@ map_stringitem_t pkgCacheGenerator::StoreString(enum StringType const type, cons
    auto strings = &strMixed;
    switch(type) {
       case MIXED: strings = &strMixed; break;
-      case PKGNAME: strings = &strPkgNames; break;
       case VERSIONNUMBER: strings = &strVersions; break;
       case SECTION: strings = &strSections; break;
       default: _error->Fatal("Unknown enum type used for string storage of '%.*s'", Size, S); return 0;
diff --git a/apt-pkg/pkgcachegen.h b/apt-pkg/pkgcachegen.h
index 1f639c526..2db2237da 100644
--- a/apt-pkg/pkgcachegen.h
+++ b/apt-pkg/pkgcachegen.h
@@ -70,7 +70,6 @@ class APT_HIDDEN pkgCacheGenerator					/*{{{*/
    };
 
    std::unordered_set<string_pointer, hash> strMixed;
-   std::unordered_set<string_pointer, hash> strPkgNames;
    std::unordered_set<string_pointer, hash> strVersions;
    std::unordered_set<string_pointer, hash> strSections;
 #endif
@@ -124,7 +123,7 @@ class APT_HIDDEN pkgCacheGenerator					/*{{{*/
 
    public:
 
-   enum StringType { MIXED, PKGNAME, VERSIONNUMBER, SECTION };
+   enum StringType { MIXED, VERSIONNUMBER, SECTION };
    map_stringitem_t StoreString(StringType const type, const char * S, unsigned int const Size);
 
    inline map_stringitem_t StoreString(enum StringType const type, APT::StringView S) {return StoreString(type, S.data(),S.length());};
@@ -179,7 +178,7 @@ class APT_HIDDEN pkgCacheListParser
    void * const d;
 
    protected:
-
+   inline bool NewGroup(pkgCache::GrpIterator &Grp, APT::StringView Name) { return Owner->NewGroup(Grp, Name); }
    inline map_stringitem_t StoreString(pkgCacheGenerator::StringType const type, const char *S,unsigned int Size) {return Owner->StoreString(type, S, Size);};
    inline map_stringitem_t StoreString(pkgCacheGenerator::StringType const type, APT::StringView S) {return Owner->StoreString(type, S);};
    inline map_stringitem_t WriteString(APT::StringView S) {return Owner->WriteStringInMap(S.data(), S.size());};