-
Type:
Bug
-
Resolution: Done
-
Priority:
Major - P3
-
Affects Version/s: None
-
Component/s: None
-
Labels:None
Found that the wiredtiger-perf-log-append task was running for over 2 days. http://build.wiredtiger.com:8080/job/wiredtiger-perf-log-append/567/
Looking at the PMP traces we could see that there were 7 threads sleeping at all times and one thread working. Double-check with GDB confirmed that this was never the same one thread working and each of the threads could take their turn.
PMP Trace:
7 select,__wt_sleep,,__wt_row_search,__wt_btcur_insert,__curfile_insert,populate_thread,start_thread,clone
2
1 pwrite64,__wt_write,__wt_block_write,__wt_bt_write,__rec_split_write,__rec_split,__rec_row_leaf_insert,__rec_row_leaf,__wt_reconcile,__wt_evict,__wt_page_in_func,__wt_row_search,__wt_btcur_insert,__curfile_insert,populate_thread,start_thread,clone
1 pthread_cond_wait@@GLIBC_2.3.2,__wt_cond_wait,__ckpt_server,start_thread,clone
1 pthread_cond_timedwait@@GLIBC_2.3.2,__wt_cond_wait,__sweep_server,start_thread,clone
1 pthread_cond_timedwait@@GLIBC_2.3.2,__wt_cond_wait,__log_wrlsn_server,start_thread,clone
1 pthread_cond_timedwait@@GLIBC_2.3.2,__wt_cond_wait,__log_server,start_thread,clone
1 pthread_cond_timedwait@@GLIBC_2.3.2,__wt_cond_wait,__log_file_server,start_thread,clone
1 pthread_cond_timedwait@@GLIBC_2.3.2,__wt_cond_wait,__evict_server,start_thread,clone
1 nanosleep,usleep,start_run,main
Unfortunately, there were no debug symbols so line numbers were not available.
- is depended on by
-
SERVER-20060 WiredTiger changes for MongoDB 3.1.8
-
- Closed
-