使用Hibernate/Spring数据批量插入Postgres数据库:60K行需要2分钟,这是不可接受的
我需要使用Hibernate/Spring数据将60K行插入Java/Spring应用程序中的Postgres DB中 插入的数据是(1)用户,(2)相关的新用户也必须在研究参与者中。这两个都是针对每个60K记录的 下面的操作正常,但性能很差:60K需要2分钟。请注意,我正在填写Hibernate实体,然后根据大小为1000的列表执行使用Hibernate/Spring数据批量插入Postgres数据库:60K行需要2分钟,这是不可接受的,spring,postgresql,hibernate,jpa,batch-insert,Spring,Postgresql,Hibernate,Jpa,Batch Insert,我需要使用Hibernate/Spring数据将60K行插入Java/Spring应用程序中的Postgres DB中 插入的数据是(1)用户,(2)相关的新用户也必须在研究参与者中。这两个都是针对每个60K记录的 下面的操作正常,但性能很差:60K需要2分钟。请注意,我正在填写Hibernate实体,然后根据大小为1000的列表执行saveAll UsersT user = new UsersT(); user.setUsername(study.getAbbr
saveAll
UsersT user = new UsersT();
user.setUsername(study.getAbbreviation().toUpperCase()+subjectId);
user.setRoleTypeId(new LookupT(150));
user.setCreatedDate(new Date());
//...
List<StudyParticipantsT> participants = new ArrayList<StudyParticipantsT>();
StudyParticipantsT sp = new StudyParticipantsT();
sp.setStudyT(study);
sp.setUsersT(user);
sp.setSubjectId(subjectId);
sp.setLocked("N");
participants.add(sp);
user.setStudyParticipantsTs(participants);
// Add to Batch-Insert List; if list size ready for batch-insert, or if at the end of all subjectIds, do Batch-Insert saveAll() and clear the list
batchInsertUsers.add(user);
if (batchInsertUsers.size() == 1000 || i == subjectIds.size() - 1) {
// Log this Batch-Insert
if(log.isDebugEnabled()){
log.debug("createParticipantsAccounts() Batch-Insert: Saving " + batchInsertUsers.size() + " records");
}
userDAO.saveAll(batchInsertUsers);
// Reset list
batchInsertUsers.clear();
}
UsersT user=new UsersT();
user.setUsername(study.get缩写().toUpperCase()+subjectId);
setRoleTypeId(新LookupT(150));
setCreatedDate(新日期());
//...
列表参与者=新建ArrayList();
StudyParticipantsT sp=新的StudyParticipantsT();
sp.setStudyT(研究);
sp.setUsersT(用户);
sp.setsubjected(主语);
sp.setLocked(“N”);
参与者。添加(sp);
user.setStudyParticipantsTs(参与者);
//添加到批量插入列表;如果列表大小已准备好批量插入,或者如果在所有主题的末尾,请执行batch insert saveAll()并清除列表
batchInsertUsers.add(用户);
if(batchInsertUsers.size()==1000 | | i==subjectIds.size()-1){
//记录此批插入
if(log.isDebugEnabled()){
log.debug(“createParticipantsAccounts()批插入:保存“+batchInsertUsers.size()+”记录”);
}
userDAO.saveAll(batchInsertUsers);
//重置列表
batchInsertUsers.clear();
}
我找到了一个线程,其中有人遇到了相同的问题,他们找到的唯一解决方案是为每个1000块编写一个自定义的本机SQLINSERT(…),(…),(…)
字符串,然后手动运行,完全删除ORM/Hibernate层:
但是我的插入涉及一些连接的表。我可以自己花时间将所有这些实体语句重写为自定义SQL,但这并不简单
还有其他解决办法吗?我正在使用
-弹簧5.0.2
-Hibernate5.2.12我们通过使用SpringJDBC的
jdbcTemplate.batchUpdate
(无Hibernate)并提前为任何外键保留一个序列范围来提高性能
我们没有降低到实际N个重复的INSERT
语句的水平,而上面提到的另一张海报做到了这一点;我们仍然使用框架方法(JDBCTemplate),但至少我们不再使用Hibernate/ORM。这种方法速度很快,但没有N repeatedINSERT
s那么快,但现在可以接受了
实际的SpringJDBC批插入是通过jdbcTemplate.batchUpdate(sqlInsert,new BatchPreparedStatementSetter(){..}
,我们实际上自己分割了批次--BatchPreparedStatementSetter
不会自动为我们分割任何内容,它只会以预定大小提交特定批次
/**
* The following method performs a Native-SQL Batch-Insert of Participant accounts (using JdbcTemplate) to improve performance.
* Each Participant account requires 2 INSERTs: (1) USERS_T, (2) STUDY_PARTICIPANTS_T (with an FK reference to USERS_T.ID).
* Since there is no easy way to track the Sequence IDs between the two Batch-Inserts, we reserve the ID range for both tables, and
* then manually calculate our own IDs for USERS_T and STUDY_PARTICIPANTS_T ourselves.
* Initially, domain objects are filled out; then they are added to the Batch List that we submit and clear ourselves.
* (Originally the Batch-Insert was implemented with Hibernate/HQL, but due to slow performance it was nativized with jdbcTemplate.)
*
* NOTE: The entire method is @Transactional and all data will be rolled back in case of any exceptions in this method (rollbackFor=Exception.class).
* The updated Sequence values (set during reservation) will not be rolled back in this case, but Sequence gaps are normal.
*/
@Override
@Transactional(readOnly = false, rollbackFor = Exception.class)
public void createParticipantsAccounts(long studyId, List<String> subjectIds) throws Exception {
int maxInsertParticipantsBatchSize = 1000; // Batch size is 1000
/*
We need to insert into 2 tables, USERS_T and STUDY_PARTICIPANTS_T.
The table STUDY_PARTICIPANTS_T has an FK dependency on USERS_T.ID.
Since there is no easy way to track the Sequence IDs between the two Batch-Inserts, we reserve the ID range for both tables,
and then manually calculate our own IDs for USERS_T and STUDY_PARTICIPANTS_T ourselves.
The Sequences are immediately updated to the calculated final values to reserve the range.
*/
// 1. Obtain current Sequence values
Integer currUsersTSeqVal = userDAO.getCurrentUsersTSeqVal();
Integer currStudyParticipantsTSeqVal = studyParticipantsDAO.getCurrentStudyParticipantsTSeqVal();
// 2. Immediately update the Sequences to the calculated final value (this reserves the ID range immediately)
// In Postgres, updating the Sequences is: SELECT setval('users_t_id_seq', :val)
userDAO.setCurrentUsersTSeqVal(currUsersTSeqVal + subjectIds.size());
studyParticipantsDAO.setCurrentStudyParticipantsTSeqVal(currStudyParticipantsTSeqVal + subjectIds.size());
// List for Batch-Inserts, maintained and submitted by ourselves in accordance with our batch size
List<UsersT> batchInsertUsers = new ArrayList<UsersT>();
for(int i = 0; i < subjectIds.size(); i++) {
String subjectId = subjectIds.get(i);
// Prepare domain object (UsersT with associated StudyParticipantsT) to be used in the Native-SQL jdbcTemplate batchUpdate
UsersT user = new UsersT();
user.setId(currUsersTSeqVal + 1 + i); // Set ID to calculated value
user.setUsername(study.getAbbreviation().toUpperCase()+subjectId);
user.setActiveFlag(true);
// etc., fill out object, then subobject:
List<StudyParticipantsT> participants = new ArrayList<StudyParticipantsT>();
StudyParticipantsT sp = new StudyParticipantsT();
sp.setId(currStudyParticipantsTSeqVal + 1 + i); // Set ID to caculated value
// ...etc.
user.setStudyParticipantsTs(participants);
// Add to Batch-Insert List of Users
batchInsertUsers.add(user);
// If list size ready for Batch-Insert, or if at the end of all subjectIds, perform Batch Insert (both tables) and clear list
if (batchInsertUsers.size() == maxInsertParticipantsBatchSize || i == subjectIds.size() - 1) {
// Part 1: Insert batch into USERS_T
nativeBatchInsertUsers(jdbcTemplate, batchInsertUsers);
// Part 2: Insert batch into STUDY_PARTICIPANTS_T
nativeBatchInsertStudyParticipants(jdbcTemplate, batchInsertUsers);
// Reset list
batchInsertUsers.clear();
}
}
}
/**
*以下方法执行参与者帐户的本机SQL批插入(使用JdbcTemplate)以提高性能。
*每个参与者帐户需要2个插入项:(1)用户;(2)研究参与者(带有对用户ID的FK引用)。
*由于没有简单的方法跟踪两个批插入之间的序列ID,因此我们为两个表保留ID范围,并且
*然后为用户手动计算我们自己的ID,并自己研究参与者。
*首先填写域对象;然后将它们添加到我们提交的批处理列表中并自行清除。
*(批插入最初是用Hibernate/HQL实现的,但由于性能低下,它是用jdbcTemplate实现的。)
*
*注意:整个方法是@Transactional的,如果此方法中出现任何异常,所有数据都将回滚(rollboor=Exception.class)。
*在这种情况下,更新的序列值(在保留期间设置)将不会回滚,但序列间隔是正常的。
*/
@凌驾
@事务(readOnly=false,rollboor=Exception.class)
public void createParticipantsAccounts(长studyId,列表主体ID)引发异常{
int maxInsertParticipantsBatchSize=1000;//批大小为1000
/*
我们需要在两个表中插入用户和研究参与者。
表研究参与者对用户ID具有FK依赖性。
由于没有简单的方法跟踪两个批插入之间的序列ID,我们为两个表保留了ID范围,
然后为用户手动计算我们自己的ID,并自己研究参与者。
序列立即更新为计算的最终值以保留范围。
*/
//1.获取当前序列值
整数currUsersTSeqVal=userDAO.getCurrentUsersTSeqVal();
整数currStudyParticipantsTSeqVal=studyParticipantsDAO.getCurrentStudyParticipantsTSeqVal();
//2.立即将序列更新为计算的最终值(这将立即保留ID范围)
//在Postgres中,更新序列是:选择setval('users\t\u id\u seq',:val)
userDAO.setCurrentUsersTSeqVal(currUsersTSeqVal+subjectIds.size());
studyParticipantDao.setCurrentStudyParticipantsTSeqVal(currStudyParticipantsTSeqVal+subjectId.size());
//批次插入物清单,由我方根据我方批次大小进行维护和提交
列出batchInsertUsers=new ArrayList();
for(int i=0;i/**
* Native-SQL Batch-Insert into USERS_T for Participant Upload.
* NOTE: This method is part of its Parent's @Transactional. (Note also that we need "final" on the List param for Inner-Class access to this variable.)
*
* @param jdbcTemplate
* @param batchInsertUsers
*/
private void nativeBatchInsertUsers(JdbcTemplate jdbcTemplate, final List<UsersT> batchInsertUsers) {
String sqlInsert = "INSERT INTO PUBLIC.USERS_T (id, password, user_name, created_by, created_date, last_changed_by, last_changed_date, " +
"first_name, last_name, organization, phone, lockout_date, lockout_counter, last_login_date, " +
"password_last_changed_date, temporary_password, active_flag, uuid, " +
"role_type_id, ws_account_researcher_id) " +
"VALUES (?, ?, ?, ?, ?, ?, ?, " +
"?, ?, ?, ?, ?, ?, ?, " +
"?, ?, ?, ?, " +
"?, ?" +
") ";
jdbcTemplate.batchUpdate(sqlInsert, new BatchPreparedStatementSetter() {
@Override
public int getBatchSize() {
return batchInsertUsers.size();
}
@Override
public void setValues(PreparedStatement ps, int i) throws SQLException {
ps.setInt(1, batchInsertUsers.get(i).getId()); // ID (provided by ourselves)
// etc., set PS for each i-th object
}
});
}
/**
* Native-SQL Batch-Insert into STUDY_PARTICIPANTS_T for Participant Upload.
* NOTE: This method is part of its Parent's @Transactional. (Note also that we need "final" on the List param for Inner-Class access to this variable.)
*
* @param jdbcTemplate
* @param batchInsertUsers
*/
private void nativeBatchInsertStudyParticipants(JdbcTemplate jdbcTemplate, final List<UsersT> batchInsertUsers) {
String sqlInsert = "INSERT INTO PUBLIC.STUDY_PARTICIPANTS_T (id, study_id, subject_id, user_id, locked, " + "created_by, created_date, last_changed_by, last_changed_date) " +
"VALUES (?, ?, ?, ?, ?, " +
"?, ?, ?, ? " +
") ";
jdbcTemplate.batchUpdate(sqlInsert, new BatchPreparedStatementSetter() {
@Override
public int getBatchSize() {
return batchInsertUsers.size();
}
@Override
public void setValues(PreparedStatement ps, int i) throws SQLException {
ps.setInt(1, batchInsertUsers.get(i).getStudyParticipantsTs().get(0).getId()); // ID (provided by ourselves)
// etc.
}
});
}