[ICRDMA] Chunk reclamation feature for slot mem pool. Change limit. EXT-1782 (#31708)

The original implementation of slot mem pool has no ability to reuse chunk for slots size X if it was split for slots size Y. It may cause the situation when we have no ability to allocate memory if all chunks was split for workset with different sizes.

The proposed change track usage of chunk and allows to reuse it for any slot size if use count for the chunk becomes 0.

This commit also changes limit so allocate object up to 32MB are allowed.

Two improvement should be implemented in a future work:

* Priority to allocate slots by use count of underlying chunk. This heuristic increases probability of success reclaimation
* Varied chunk size. No need to use 32Mb chunk to split it in to 4K slots. It also increases probability of success reclaimation and improve performance of it

Author: dcherednik

ydb/library/actors/interconnect/rdma/mem_pool.cpp

@@ -14,16 +14,20 @@ namespace NMonitoring {
     struct TDynamicCounters;
 }
 
+struct TMemRegCompare;
 namespace NInterconnect::NRdma {
 
     class IMemPool;
     class TMemRegion;
     class TChunk;
     class TMemPoolImpl;
+    class TSlotMemPool;
 
     using TChunkPtr = TIntrusivePtr<TChunk>;
 
     class TMemRegion: public NNonCopyable::TMoveOnly, public IContiguousChunk {
+        friend struct ::TMemRegCompare;
+        friend class TSlotMemPool;
     public:
         TMemRegion(TChunkPtr chunk, uint32_t offset, uint32_t size) noexcept;
         TMemRegion(TMemRegion&& other) noexcept = default;
@@ -35,16 +39,16 @@ namespace NInterconnect::NRdma {
         uint32_t GetLKey(size_t deviceIndex) const;
         uint32_t GetRKey(size_t deviceIndex) const;
 
-        void Resize(uint32_t newSize) noexcept;
-
     public: // IContiguousChunk
         TContiguousSpan GetData() const override;
         TMutableContiguousSpan UnsafeGetDataMut() override;
         size_t GetOccupiedMemorySize() const override;
         EInnerType GetInnerType() const noexcept override;
         IContiguousChunk::TPtr Clone() noexcept override;
     protected:
+        void Resize(uint32_t newSize) noexcept;
         TChunkPtr Chunk;
+        ui64 Generation = 0;
         const uint32_t Offset;
         uint32_t Size;
         const uint32_t OrigSize;
@@ -97,9 +101,9 @@ namespace NInterconnect::NRdma {
         virtual TString GetName() const noexcept = 0;
 
     protected:
-        virtual TMemRegion* AllocImpl(int size, ui32 flags) noexcept = 0;
+        virtual TMemRegionPtr AllocImpl(int size, ui32 flags) noexcept = 0;
         virtual void Free(TMemRegion&& mr, TChunk& chunk) noexcept = 0;
-        virtual void DealocateMr(std::vector<ibv_mr*>& mrs) noexcept = 0;
+        virtual void DealocateMr(TChunk*) noexcept = 0;
     private:
         virtual void Tick(NMonotonic::TMonotonic time) noexcept = 0;
     };