You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@doris.apache.org by mo...@apache.org on 2023/11/03 05:42:37 UTC

(doris) branch master updated: [Fix](multi-catalog) Filter _temporary dir which is generated by spark. (#26194)

This is an automated email from the ASF dual-hosted git repository.

morningman pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git


The following commit(s) were added to refs/heads/master by this push:
     new 9019a71770e [Fix](multi-catalog) Filter _temporary dir which is generated by spark. (#26194)
9019a71770e is described below

commit 9019a71770ea158b035159bb523a4501aee87b55
Author: Xiangyu Wang <du...@gmail.com>
AuthorDate: Fri Nov 3 13:42:29 2023 +0800

    [Fix](multi-catalog) Filter _temporary dir which is generated by spark. (#26194)
    
    Sometimes there are some temporary files which are generated by some spark jobs, we need filter these files.
    
    ```
    errCode = 2, detailMessage = (xxx.xxx.xxx.xxx.xxx)
    [CANCELLED][INTERNAL_ERROR]failed to init reader for file hdfs://xxx/user/hive/warehouse/xxx.db/xxx/_temporary/0/_temporary/attempt_202311010952379045223848154629697_0013_m_000442_3355/part-00442-3f97ac18-0583-4d2c-8995-8d21ceda56ec-c000.snappy.orc,
    err: [INTERNAL_ERROR]Init OrcReader failed. reason = Failed to parse the postscript from hdfs://xxx/user/hive/warehouse/xxx.db/xxx/_temporary/0/_temporary/attempt_202311010952379045223848154629697_0013_m_000442_3355/part-00442-3f97ac18-0583-4d2c-8995-8d21ceda56ec-c000.snappy.orc
    0.  @ 0x000000000bdbd89f
       doris::Status doris::Status::Error<6, true, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&>(std::basic_string_view<char, std::char_traits<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&)  /var/local/ldb-toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:173  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-36 [...]
       doris::vectorized::OrcReader::_create_file_reader()  /var/local/ldb-toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/basic_string.h:187  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  2.  @ 0x000000000ecceff9
       doris::vectorized::OrcReader::init_reader(std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const*, std::unordered_map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::variant<doris::ColumnValueRange<(doris::PrimitiveType)3>, doris::ColumnValueRange<(doris::PrimitiveType)4>, doris::ColumnValueRange<(doris: [...]
       doris::vectorized::VFileScanner::_get_next_reader()  /root/doris-master/be/src/vec/exec/scan/vfile_scanner.cpp:800  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  4.  @ 0x000000000ff4256f
       doris::vectorized::VFileScanner::_get_block_impl(doris::RuntimeState*, doris::vectorized::Block*, bool*)  /root/doris-master/be/src/common/status.h:448  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  5.  @ 0x000000000ffdb1aa
       doris::vectorized::VScanner::get_block(doris::RuntimeState*, doris::vectorized::Block*, bool*)  /root/doris-master/be/src/vec/exec/scan/vscanner.cpp:0  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  6.  @ 0x000000000ff3b379
       doris::vectorized::ScannerScheduler::_scanner_scan(doris::vectorized::ScannerScheduler*, doris::vectorized::ScannerContext*, std::shared_ptr<doris::vectorized::VScanner>)  /root/doris-master/be/src/common/status.h:346  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  7.  @ 0x000000000ff3ca11  std::_Function_handler<void (), doris::vectorized::ScannerSch [...]
       doris::ThreadPool::dispatch_thread()  /root/doris-master/be/src/util/threadpool.cpp:0  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  9.  @ 0x000000000c97c2ac
       doris::Thread::supervise_thread(void*)  /var/local/ldb-toolchain/bin/../usr/include/pthread.h:562  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  10. @ 0x0000000000007ea5  start_thread  in /usr/lib64/libpthread-2.17.so  11. @ 0x00000000000feb0d  __clone  in /usr/lib64/libc-2.17.so    0.  @ 0x000000000c647366
       doris::Status doris::Status::Error<6, true, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >(std::basic_string_view<char, std::char_traits<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&&)  /var/local/ldb-toolchain/bin/../lib/gcc/x86_6 [...]
       doris::vectorized::VFileScanner::_get_next_reader()  /var/local/ldb-toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/basic_string.h:187  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  2.  @ 0x000000000ff4256f
       doris::vectorized::VFileScanner::_get_block_impl(doris::RuntimeState*, doris::vectorized::Block*, bool*)  /root/doris-master/be/src/common/status.h:448  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  3.  @ 0x000000000ffdb1aa
       doris::vectorized::VScanner::get_block(doris::RuntimeState*, doris::vectorized::Block*, bool*)  /root/doris-master/be/src/vec/exec/scan/vscanner.cpp:0  in /hdpData10/yarn/localcache/usercache/hive/appcache/application_1696938614818_1832823/filecache/13/doris-be-360-master.tar.gz/apache-doris-be-360-master-bin-x86_64/lib/doris_be  4.  @ 0x000000000ff3b379
       doris::vectorized::ScannerScheduler::_scanner_scan(doris::vectorized::ScannerScheduler*, doris::vectorized::ScannerContext*, std::shared_ptr<doris::vectorized::VScanner>)  /root/doris-master/be/src/common/status.h:346  in /hdpData10/yarn/localcache/usercache/hive/appcache/a…
    ```
    Co-authored-by: wangxiangyu <wa...@360shuke.com>
---
 .../java/org/apache/doris/datasource/hive/HiveMetaStoreCache.java    | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fe/fe-core/src/main/java/org/apache/doris/datasource/hive/HiveMetaStoreCache.java b/fe/fe-core/src/main/java/org/apache/doris/datasource/hive/HiveMetaStoreCache.java
index 480edd60f2c..bac891eb920 100644
--- a/fe/fe-core/src/main/java/org/apache/doris/datasource/hive/HiveMetaStoreCache.java
+++ b/fe/fe-core/src/main/java/org/apache/doris/datasource/hive/HiveMetaStoreCache.java
@@ -1058,9 +1058,14 @@ public class HiveMetaStoreCache {
                 return false;
             }
             for (String name : path.toString().split("/")) {
+                // generated by hive
                 if (name.startsWith(".hive-staging")) {
                     return false;
                 }
+                // generated by spark
+                if ("_temporary".equals(name)) {
+                    return false;
+                }
             }
             return true;
         }


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org