PaddlePaddle
diff --git a/‎cmake/external/jemalloc.cmake
+35 b/‎cmake/external/jemalloc.cmake
+35
diff --git a/‎cmake/external/rocksdb.cmake
+28-3 b/‎cmake/external/rocksdb.cmake
+28-3
diff --git a/‎cmake/third_party.cmake
+3 b/‎cmake/third_party.cmake
+3
diff --git a/‎paddle/fluid/distributed/common/afs_warpper.h
+12 b/‎paddle/fluid/distributed/common/afs_warpper.h
+12
diff --git a/‎paddle/fluid/distributed/ps/service/ps_client.h
+13-2 b/‎paddle/fluid/distributed/ps/service/ps_client.h
+13-2
diff --git a/‎paddle/fluid/distributed/ps/service/ps_local_client.cc
+28-2 b/‎paddle/fluid/distributed/ps/service/ps_local_client.cc
+28-2
diff --git a/‎paddle/fluid/distributed/ps/service/ps_local_client.h
+9-8 b/‎paddle/fluid/distributed/ps/service/ps_local_client.h
+9-8
diff --git a/‎paddle/fluid/distributed/ps/table/CMakeLists.txt
-11 b/‎paddle/fluid/distributed/ps/table/CMakeLists.txt
-11
diff --git a/‎paddle/fluid/distributed/ps/table/accessor.h
+13-1 b/‎paddle/fluid/distributed/ps/table/accessor.h
+13-1
@@ -0,0 +1,35 @@
+include(ExternalProject)
+
+set(JEMALLOC_PROJECT "extern_jemalloc")
+set(JEMALLOC_URL
+    https://github.com/jemalloc/jemalloc/releases/download/5.1.0/jemalloc-5.1.0.tar.bz2
+)
+set(JEMALLOC_BUILD ${THIRD_PARTY_PATH}/jemalloc/src/extern_jemalloc)
+set(JEMALLOC_SOURCE_DIR "${THIRD_PARTY_PATH}/jemalloc")
+set(JEMALLOC_INSTALL ${THIRD_PARTY_PATH}/install/jemalloc)
+set(JEMALLOC_INCLUDE_DIR ${JEMALLOC_INSTALL}/include)
+set(JEMALLOC_DOWNLOAD_DIR "${JEMALLOC_SOURCE_DIR}/src/${JEMALLOC_PROJECT}")
+
+set(JEMALLOC_STATIC_LIBRARIES
+    ${THIRD_PARTY_PATH}/install/jemalloc/lib/libjemalloc_pic.a)
+set(JEMALLOC_LIBRARIES
+    ${THIRD_PARTY_PATH}/install/jemalloc/lib/libjemalloc_pic.a)
+
+ExternalProject_Add(
+  extern_jemalloc
+  PREFIX ${JEMALLOC_SOURCE_DIR}
+  URL ${JEMALLOC_URL}
+  INSTALL_DIR ${JEMALLOC_INSTALL}
+  DOWNLOAD_DIR "${JEMALLOC_DOWNLOAD_DIR}"
+  BUILD_COMMAND $(MAKE)
+  BUILD_IN_SOURCE 1
+  INSTALL_COMMAND $(MAKE) install
+  CONFIGURE_COMMAND "${JEMALLOC_DOWNLOAD_DIR}/configure"
+                    --prefix=${JEMALLOC_INSTALL} --disable-initial-exec-tls)
+
+add_library(jemalloc STATIC IMPORTED GLOBAL)
+set_property(TARGET jemalloc PROPERTY IMPORTED_LOCATION
+                                      ${JEMALLOC_STATIC_LIBRARIES})
+
+include_directories(${JEMALLOC_INCLUDE_DIR})
+add_dependencies(jemalloc extern_jemalloc)
@@ -14,6 +14,13 @@
 
 include(ExternalProject)
 
+# find_package(jemalloc REQUIRED)
+
+set(JEMALLOC_INCLUDE_DIR ${THIRD_PARTY_PATH}/install/jemalloc/include)
+set(JEMALLOC_LIBRARIES
+    ${THIRD_PARTY_PATH}/install/jemalloc/lib/libjemalloc_pic.a)
+message(STATUS "rocksdb jemalloc:" ${JEMALLOC_LIBRARIES})
+
 set(ROCKSDB_PREFIX_DIR ${THIRD_PARTY_PATH}/rocksdb)
 set(ROCKSDB_INSTALL_DIR ${THIRD_PARTY_PATH}/install/rocksdb)
 set(ROCKSDB_INCLUDE_DIR
@@ -22,21 +29,39 @@ set(ROCKSDB_INCLUDE_DIR
 set(ROCKSDB_LIBRARIES
     "${ROCKSDB_INSTALL_DIR}/lib/librocksdb.a"
     CACHE FILEPATH "rocksdb library." FORCE)
-set(ROCKSDB_CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fPIC")
+set(ROCKSDB_COMMON_FLAGS
+    "-g -pipe -O2 -W -Wall -Wno-unused-parameter -fPIC -fno-builtin-memcmp -fno-omit-frame-pointer"
+)
+set(ROCKSDB_FLAGS
+    "-DNDEBUG -DROCKSDB_JEMALLOC -DJEMALLOC_NO_DEMANGLE -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DOS_LINUX -DROCKSDB_FALLOCATE_PRESENT -DHAVE_SSE42 -DHAVE_PCLMUL -DZLIB -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_PTHREAD_ADAPTIVE_MUTEX -DROCKSDB_BACKTRACE -DROCKSDB_SUPPORT_THREAD_LOCAL -DROCKSDB_USE_RTTI -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_AUXV_GETAUXVAL_PRESENT"
+)
+set(ROCKSDB_CMAKE_CXX_FLAGS
+    "${ROCKSDB_COMMON_FLAGS} -DROCKSDB_LIBAIO_PRESENT -msse -msse4.2 -mpclmul ${ROCKSDB_FLAGS} -fPIC  -I${JEMALLOC_INCLUDE_DIR} -lz -ldl"
+)
+set(ROCKSDB_CMAKE_C_FLAGS
+    "${ROCKSDB_COMMON_FLAGS} ${ROCKSDB_FLAGS} -DROCKSDB_LIBAIO_PRESENT -fPIC  -I${JEMALLOC_INCLUDE_DIR}"
+)
 include_directories(${ROCKSDB_INCLUDE_DIR})
 
+set(CMAKE_CXX_LINK_EXECUTABLE
+    "${CMAKE_CXX_LINK_EXECUTABLE} -pthread -ldl -lrt -lz")
 ExternalProject_Add(
   extern_rocksdb
   ${EXTERNAL_PROJECT_LOG_ARGS}
   PREFIX ${ROCKSDB_PREFIX_DIR}
-  GIT_REPOSITORY "https://github.com/facebook/rocksdb"
-  GIT_TAG v6.10.1
+  GIT_REPOSITORY "https://github.com/Thunderbrook/rocksdb"
+  GIT_TAG 6.19.fb
   UPDATE_COMMAND ""
   CMAKE_ARGS -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
              -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
              -DWITH_BZ2=OFF
              -DPORTABLE=1
              -DWITH_GFLAGS=OFF
+             -DWITH_TESTS=OFF
+             -DWITH_JEMALLOC=ON
+             -DWITH_BENCHMARK_TOOLS=OFF
+             -DJeMalloc_LIBRARIES=${JEMALLOC_LIBRARIES}
+             -DJeMalloc_INCLUDE_DIRS=${JEMALLOC_INCLUDE_DIR}
              -DCMAKE_CXX_FLAGS=${ROCKSDB_CMAKE_CXX_FLAGS}
              -DCMAKE_C_FLAGS=${CMAKE_C_FLAGS}
   INSTALL_COMMAND
 
@@ -423,6 +423,9 @@ if(WITH_PSCORE)
 
   include(external/rocksdb) # download, build, install rocksdb
   list(APPEND third_party_deps extern_rocksdb)
+
+  include(external/jemalloc) # download, build, install jemalloc
+  list(APPEND third_party_deps extern_jemalloc)
 endif()
 
 if(WITH_RPC
 
@@ -66,6 +66,10 @@ class FsReadChannel {
     return 0;
   }
 
+  inline int read(char* data, size_t size) {
+    return fread(data, 1, size, _file.get());
+  }
+
  private:
   uint32_t _buffer_size;
   FsChannelConfig _config;
@@ -114,6 +118,14 @@ class FsWriteChannel {
     return write_line(data.c_str(), data.size());
   }
 
+  inline uint32_t write(const char* data, size_t size) {
+    size_t write_count = fwrite(data, 1, size, _file.get());
+    if (write_count != size) {
+      return -1;
+    }
+    return 0;
+  }
+
  private:
   uint32_t _buffer_size;
   FsChannelConfig _config;
 
@@ -148,10 +148,12 @@ class PSClient {
     return fut;
   }
 
-  virtual ::std::future<int32_t> PullSparsePtr(char **select_values,
+  virtual ::std::future<int32_t> PullSparsePtr(int shard_id,
+                                               char **select_values,
                                                size_t table_id,
                                                const uint64_t *keys,
-                                               size_t num) {
+                                               size_t num,
+                                               uint16_t pass_id) {
     VLOG(0) << "Did not implement";
     std::promise<int32_t> promise;
     std::future<int> fut = promise.get_future();
@@ -160,6 +162,15 @@ class PSClient {
   }
 
   virtual std::future<int32_t> PrintTableStat(uint32_t table_id) = 0;
+  virtual std::future<int32_t> SaveCacheTable(uint32_t table_id,
+                                              uint16_t pass_id,
+                                              size_t threshold) {
+    VLOG(0) << "Did not implement";
+    std::promise<int32_t> promise;
+    std::future<int> fut = promise.get_future();
+    promise.set_value(-1);
+    return fut;
+  }
 
   // 确保所有积攒中的请求都发起发送
   virtual std::future<int32_t> Flush() = 0;
 
@@ -260,10 +260,12 @@ ::std::future<int32_t> PsLocalClient::PushDense(const Region* regions,
 //  return done();
 //}
 
-::std::future<int32_t> PsLocalClient::PullSparsePtr(char** select_values,
+::std::future<int32_t> PsLocalClient::PullSparsePtr(int shard_id,
+                                                    char** select_values,
                                                     size_t table_id,
                                                     const uint64_t* keys,
-                                                    size_t num) {
+                                                    size_t num,
+                                                    uint16_t pass_id) {
   // FIXME
   // auto timer =
   // std::make_shared<CostTimer>("pslib_downpour_client_pull_sparse");
@@ -278,13 +280,37 @@ ::std::future<int32_t> PsLocalClient::PullSparsePtr(char** select_values,
   table_context.pull_context.ptr_values = select_values;
   table_context.use_ptr = true;
   table_context.num = num;
+  table_context.shard_id = shard_id;
+  table_context.pass_id = pass_id;
 
   //  table_ptr->PullSparsePtr(select_values, keys, num);
   table_ptr->Pull(table_context);
 
   return done();
 }
 
+::std::future<int32_t> PsLocalClient::PrintTableStat(uint32_t table_id) {
+  auto* table_ptr = GetTable(table_id);
+  std::pair<int64_t, int64_t> ret = table_ptr->PrintTableStat();
+  VLOG(0) << "table id: " << table_id << ", feasign size: " << ret.first
+          << ", mf size: " << ret.second;
+  return done();
+}
+
+::std::future<int32_t> PsLocalClient::SaveCacheTable(uint32_t table_id,
+                                                     uint16_t pass_id,
+                                                     size_t threshold) {
+  auto* table_ptr = GetTable(table_id);
+  std::pair<int64_t, int64_t> ret = table_ptr->PrintTableStat();
+  VLOG(0) << "table id: " << table_id << ", feasign size: " << ret.first
+          << ", mf size: " << ret.second;
+  if (ret.first > (int64_t)threshold) {
+    VLOG(0) << "run cache table";
+    table_ptr->CacheTable(pass_id);
+  }
+  return done();
+}
+
 ::std::future<int32_t> PsLocalClient::PushSparseRawGradient(
     size_t table_id,
     const uint64_t* keys,
 
@@ -76,18 +76,19 @@ class PsLocalClient : public PSClient {
     return fut;
   }
 
-  virtual ::std::future<int32_t> PullSparsePtr(char** select_values,
+  virtual ::std::future<int32_t> PullSparsePtr(int shard_id,
+                                               char** select_values,
                                                size_t table_id,
                                                const uint64_t* keys,
-                                               size_t num);
+                                               size_t num,
+                                               uint16_t pass_id);
 
-  virtual ::std::future<int32_t> PrintTableStat(uint32_t table_id) {
-    std::promise<int32_t> prom;
-    std::future<int32_t> fut = prom.get_future();
-    prom.set_value(0);
+  virtual ::std::future<int32_t> PrintTableStat(uint32_t table_id);
+
+  virtual ::std::future<int32_t> SaveCacheTable(uint32_t table_id,
+                                                uint16_t pass_id,
+                                                size_t threshold);
 
-    return fut;
-  }
   virtual ::std::future<int32_t> PushSparse(size_t table_id,
                                             const uint64_t* keys,
                                             const float** update_values,
 
@@ -53,16 +53,6 @@ cc_library(
 set_source_files_properties(
   tensor_accessor.cc PROPERTIES COMPILE_FLAGS ${DISTRIBUTE_COMPILE_FLAGS})
 
-cc_library(
-  tensor_table
-  SRCS
-  DEPS eigen3
-       ps_framework_proto
-       executor
-       scope
-       device_context
-       tensor
-       ${TABLE_DEPS})
 set_source_files_properties(table.cc PROPERTIES COMPILE_FLAGS
                                                 ${DISTRIBUTE_COMPILE_FLAGS})
 
@@ -98,7 +88,6 @@ cc_library(
        table.cc
   DEPS ${TABLE_DEPS}
        common_table
-       tensor_table
        ps_framework_proto
        string_helper
        device_context
 
@@ -121,6 +121,9 @@ class ValueAccessor {
   virtual void UpdateStatAfterSave(float* value, int param) {}
   // 判断该value是否保存到ssd
   virtual bool SaveSSD(float* value) = 0;
+  // 判断热启时是否过滤slot对应的feasign
+  virtual bool FilterSlot(float* value) { return false; }
+
   //
   virtual bool SaveCache(float* value,
                          int param,
@@ -162,9 +165,18 @@ class ValueAccessor {
     return 0;
   }
 
+  virtual bool SaveMemCache(float* value,
+                            int param,
+                            double global_cache_threshold,
+                            uint16_t pass_id) {
+    return true;
+  }
+
+  virtual void UpdatePassId(float* value, uint16_t pass_id) {}
+
   virtual float GetField(float* value, const std::string& name) { return 0.0; }
 #define DEFINE_GET_INDEX(class, field) \
-  virtual int get_##field##_index() override { return class ::field##_index(); }
+  virtual int get_##field##_index() { return class ::field##_index(); }
 
  protected:
   size_t _value_size;