Core dump occurs when YCSB is executed.

[yqekzb123]

Hello, I have been trying to use your system for testing recently. But when I test the YCSB load here, core dump always happens.
Here's a screenshot of Core Dump.
The command to test YCSB is ./ycsb_bench --dbid=mvcc --nthreads=1 --mode=C --time=10 –perf

In addition, I am using Centos7.5 and g++ version 10.2.0.
By core dump, the problem should be in the str.reserve() function with the value of the __tmp variable 0x0. But I'm not sure why this is the case.
Do you know why this is? How should I handle it?
Thank you very much!

[huangyihe]

The problem appears to be due to the lack of hugetlb pages. Use the ./mount_hugepages.sh script to mount the appropriate number of hugetlb pages (see comments in the script for suggestions) and this error should go away.

[yqekzb123]

Thanks for your reply, I tried to use./mount_hugepages.sh 65536. And TPCC for 1 Warehouse can be tested normally.
But when I test YCSB, the same core will still happen after a while.
Is it because The number of pages I set is not large enough?

[yqekzb123]

And can the system run with 8GB of ram? If so, where in the code do I need to change? Thank you very much.

[wqian94]

Sorry, just getting around to responding here. Yes, the system can run with 8GB of ram. Are you still encountering the same core dump as you were before?