Ceph » RADOS

This error occurs in Mar 6th, the osd.37 was down and out with bellow log info(ceph-osd.37.log-20210306):

2021-03-06 01:40:59.179419 7f41c8aab700 4 rocksdb: EVENT_LOG_v1 {"time_micros": 1614966059179414, "job": 108081, "event": "table_file_deletion", "file_number": 258350}
2021-03-06 01:46:23.818275 7f41d6a8b700 -1 ** Caught signal (Segmentation fault) *
in thread 7f41d6a8b700 thread_name:msgr-worker-2

ceph version 12.2.12-6-g6adf7f4 (6adf7f43aa4d9fc8b5f7c72ca5962bf005b13e6c) luminous (stable)
 1: (()+0xa65a21) [0x55f3a139ba21]
 2: (()+0xf5e0) [0x7f41db5775e0]
 3: (tcmalloc::DLL_Remove(tcmalloc::Span*)+0x14) [0x7f41dcff7e64]
 4: (tcmalloc::PageHeap::Carve(tcmalloc::Span*, unsigned long)+0x1c) [0x7f41dcff6a4c]
 5: (tcmalloc::PageHeap::New(unsigned long)+0x11) [0x7f41dcff7591]
 6: (()+0x16462) [0x7f41dcfe8462]
 7: (posix_memalign()+0x40) [0x7f41dd009010]
 8: (ceph::buffer::create_aligned_in_mempool(unsigned int, unsigned int, int)+0xf4) [0x55f3a13a2774]
 9: (AsyncConnection::process()+0x346e) [0x55f3a16a5ace]
 10: (EventCenter::process_events(int, std::chrono::duration<unsigned long, std::ratio<1l, 1000000000l> >*)+0x359) [0x55f3a14775e9]
 11: (()+0xb441ae) [0x55f3a147a1ae]
 12: (()+0xb52b0) [0x7f41daefb2b0]
 13: (()+0x7e25) [0x7f41db56fe25]
 14: (clone()+0x6d) [0x7f41da66334d]
 NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this.

--- begin dump of recent events ---

Then restart the osd service with command "systemctl restart ceph-osd@37.service", the osd works well.
I have upload the detail log file, please check the attachment. Please check if it is a bug.
If any environment info that can help figure out the root cause, I can provider later.