A "runtime guard" for the kernel
A "runtime guard" for the kernel
Posted Mar 24, 2018 1:39 UTC (Sat) by pi3 (guest, #123274)Parent article: A "runtime guard" for the kernel
At the beginning I'd like to thank the author for taking his time to analyze LKRG and write a fair review.
The only comment I'd like to add is that performance impact in the latest LKRG version (we're on the edge of releasing v0.2) has been greatly improved. We have introduced a new sysctl to control whether LKRG performs code integrity checks on random events (or only at regular intervals). This can be translated to the following performance impact scenarios:
-> Average cost of running a fully enabled LKRG => 2.5%
-> Average cost of running LKRG without the code integrity checks on random events (disabled with the new sysctl) => 0.7%
The only comment I'd like to add is that performance impact in the latest LKRG version (we're on the edge of releasing v0.2) has been greatly improved. We have introduced a new sysctl to control whether LKRG performs code integrity checks on random events (or only at regular intervals). This can be translated to the following performance impact scenarios:
-> Average cost of running a fully enabled LKRG => 2.5%
-> Average cost of running LKRG without the code integrity checks on random events (disabled with the new sysctl) => 0.7%