Trace events to pstore


Pstore is a subsystem in the Linux kernel that is used to store kernel logs which can be retrieved after a machine warm-reboots. Currently, during ftrace tracing, ftrace events in the kernel are lost when a machine hard-locks up. There is a need for writing these events into the pstore so that after a lock up, the trace events that led to the crash can be retrieved from the Pstore after a warm reboot. This will help debug what happened before machine’s last breath. This has to be done in a scalable way so that tracing a live system does not impact the performance of the system -- ftrace is extremely fast. Introducing a scalable approach will open up more possibilities for crash analysis. The design and implementation of a solution for this need will have to face particular challenges that emerge from the integration of these two frameworks (pstore and ftrace). Manage at boot time the new interdependency between the two frameworks as well as how to handle the pages' ECC (where to store it and when it has to be calculated) are just examples of the issues that a solution would have to deal with.

Room 101
Sunday, March 8, 2020 - 13:30 to 14:30