SortManager found maxMerges too small

IUUU

On our test cluster running 9.0.0, we continuously see in the vertica logfile messages saying:
2017-12-20 03:09:29.961 DistCall Dispatch:7fb530e3f700-a0000000013b07 [EE] SortManager found maxMerges 7 too small(39 MB Assigned).
2017-12-20 03:09:29.961 DistCall Dispatch:7fb530e3f700-a0000000013b07 [EE] After disabling optimization, maxMerges becomes 7.
2017-12-20 03:09:29.971 DistCall Dispatch:7fb530e3f700-a0000000013b07 [EE] SortManager found maxMerges 7 too small(39 MB Assigned).
2017-12-20 03:09:29.971 DistCall Dispatch:7fb530e3f700-a0000000013b07 [EE] After disabling optimization, maxMerges becomes 7.
2017-12-20 03:09:29.972 DistCall Dispatch:7fb530e3f700-a0000000013b07 [EE] SortManager found maxMerges 7 too small(39 MB Assigned).
2017-12-20 03:09:29.972 DistCall Dispatch:7fb530e3f700-a0000000013b07 [EE] After disabling optimization, maxMerges becomes 7.
2017-12-20 03:09:29.972 DistCall Dispatch:7fb530e3f700-a0000000013b07 [EE]
We have sqls that execute every 5 minutes,and almost after half of the day ,the vertica.log have message like this:
File Name: /home/dbadmin/event_track/v_event_track_node0001_data/775/0272b160f02cda9772c3545f4e4b938400b000000000b107_0.gt
File Offset: 54836643
Compressed size in file: 33519
Memory Address of Read Buffer: (nil)
Pointer to Compressed Data: 0x7fb51954c2b0
I fixed it by deleting the wrong data , restart the database by -F,and everything goes well,but the next day,the same problem came out again and again ,
so ,what is the problem and what should i do ?