[Bug]: Rogue thread activity correlated with opportunistic sleep setting of rx_runner rte-worker threads
Open
@ShyamB97 is already working on this.
Since Nov 11, 2025.
bug
- Dominant language
- C++
- Stars
- 0
- Forks
- 1
- Avg merge
- 5h 38m
- Merged PRs (30d)
- 4
Description
Description
Modifying the opportunistic sleep for the rx_runner (link) has a direct impact on some other unnamed threads resource utilization.
Proof with disabled sleep:
On the picture above one see non DPDK rte-worker cores with 100% CPU utilization. Seemingly, one extra core per 100Gb interface.
Steps to reproduce
- Take any detector session with Readout applications.
- Modify the configuration parameter for the opportunistic sleep in the NICReader configuration.
- Boot and configure the system.
- Inspect
htopto discover the extra 100% polling PIDs.
Version and environment
fddaq-v5.4.3, using ProtoDUNE-VD (np02-session).
Impact
Small/Isolated
Anything else?
Investigate with VTune or other profilers via directly attaching to the particular PIDs to trace down what is executed there.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.