Is this the last stable version you made and any plans to do some more development?Opened up the thread again - seems to be a lot of requests for my kernel so here ya go :
Is this the last stable version you made and any plans to do some more development?
Sent from my Redmi Note 9S using XDA Labs
- Minimal debugging and tracing - No messy upstreams / backports that might cause issues down the line - Latency focused - Anxiety I/O scheduler - Scheduler tweaks and hacks - CPU governor adjustments - ZERO in-kernel boosting while maintaining a smooth userspace
- Remove AVB checks - Disable SECCOMP (faster syscalls) - Disable Audit (expensive in Android) - Use non-blocking random pool - Target small cluster in Makefile - Disable IRQ debugging - Don't use high-priority workqueue for usb policy_engine - Disable profiling (kdrag0n) - Anxiety I/O scheduler (sync read priority) - Schedule last-woken task for better cache locality - Reduce cache pressure to keep cache valid for longer - Increase vmstat interval to reduce intermittent jitter - Adjust dirty ratios to writeback dirty pages later rather than sooner - Do not collect I/O stats from block subsystem - Don't dump oom_killed tasks - Do not use UFS for randomness - Disable ASLR fully by default (performance not benchmarked) - Disable JTAG debugging by default - Inform kcompact of fragmentation moreso than full RAM usage - Do not compile HIGHMEM (unused by our system) - Awaken kswapd at 1% (80mb free left) instead of 0.1% (8mb free left) - Do not compile watchdog (reduces jitter) - BFP JIT (better networking performance) - Force block requests to execute on their origin cpu (better cache locality) - Increase haptic strength - Allow GPU to sleep / nap - Do not compile zRAM (unnecessary for this kernels MM settings) - Do not perform readahead (proven to improve power and performance by 70%) - Align scheduler timeslices with jiffies - Overcommit memory for faster Android start times - Remove a bunch of debug and tracing that is unnecessary for the kernel - Remove schedutil hispeed boosting - Remove iowait boosting (saves a large amount of battery) - Do not expedite RCU - Halve round-robin timeslices - Expedite wakelock garbage collection - Lower I/O request limit for lower latency - More that I forgot