Danian: Tail latency reduction of networking application through an O(1) scheduler Gustavo Pantuza, Lucas A. C. Bleme, Marcos Augusto M. Vieira, Luiz Filipe M. Vieira 26th IEEE Symposium on Computers and Communications Athens, Greece, September 5-8, 2021 IEEE ISCC 2021 

Agenda ■ Introduction ■ Thread scheduling ■ Caladan ■ Danian ■ Experiments ■ Results ■ Future work ■ Conclusion 

Introduction ■ Tail at scale (2013) ■ Shenango (2019) ■ Caladan (2020) ■ Danian (2021) p50 p95 p99 1ms 5ms 10ms Hypothetical Example 

Thread scheduling ■ Lottery (1994) ■ Scheduler Activation (1991) ■ Caladan (2020) 

Caladan ■ Schedule threads into CPUs ■ Run on top of DPDK ■ Reads control signals every 5 μs ■ Implemented inside Shenango 

Caladan Simplified version of Caladan architecture inspired by the Caladan original paper architecture description 

Danian “In the 5000 years between the events of the Arrakis Revolt and the time the Lost Ones returned from The Scattering, Caladan's name was shortened to Dan, and all things pertaining to Dan were known as Danian.” Fonte: https://dune.fandom.com/wiki/Caladan 

Danian Fonte: https://dune.fandom.com/wiki/Caladan ■ Works inside Caladan ksched ■ Adds a memoization array ■ Intercepts threads join/leave ■ Algorithm to assign CPU→thread ■ O(n) → O(1) 

Danian struct proc { pid_t pid; ... struct thread *last_run[NCPU]; ... } 

Danian static struct thread * sched_pick_last_kthread(struct proc *p, unsigned int core) { struct thread *th; th = p->last_run[core]; if (!th->active) { return th; } return list_tail(&p->idle_threads, struct thread, idle_link); } 

Experiments ■ CloudLab ■ Client/Server ■ Latency percentiles ■ Varying number of threads ■ CPU usage ■ Netperf 

Experiments 

Results 

Results 

Results 

Results 

Results 

Results 

Future work Fonte: https://dune.fandom.com/wiki/Caladan ■ NFVs with lthreads inside Caladan ■ SDN using Caladan as control plane 

Conclusion ■ Thread picking from O(n) to O(1) ■ Memoization using LRU policy ■ -5% on tail latency (p99) ■ -15% CPU usage 

Danian: Tail latency reduction of networking application through an O(1) scheduler Gustavo Pantuza, Lucas A. C. Bleme, Marcos Augusto M. Vieira, Luiz Filipe M. Vieira 26th IEEE Symposium on Computers and Communications Athens, Greece, September 5-8, 2021 IEEE ISCC 2021