On 06/09/2019 03:22, Long Li wrote: [ ... ] > > Tracing shows that the CPU was in either hardirq or softirq all the > time before warnings. During tests, the system was unresponsive at > times. > > Ming's patch fixed this problem. The system was responsive throughout > tests. > > As for performance hit, both resulted in a small drop in peak IOPS. > With IRQ_TIME_ACCOUNTING I see a 3% drop. With Ming's patch it is 1% > drop. Do you mean IRQ_TIME_ACCOUNTING + irq threaded ? > For the tests, I used the following fio command on 10 NVMe disks: fio > --bs=4k --ioengine=libaio --iodepth=128 > --filename=/dev/nvme0n1:/dev/nvme1n1:/dev/nvme2n1:/dev/nvme3n1:/dev/nvme4n1:/dev/nvme5n1:/dev/nvme6n1:/dev/nvme7n1:/dev/nvme8n1:/dev/nvme9n1 > --direct=1 --runtime=12000 --numjobs=80 --rw=randread --name=test > --group_reporting --gtod_reduce=1 -- <http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs Follow Linaro: <http://www.facebook.com/pages/Linaro> Facebook | <http://twitter.com/#!/linaroorg> Twitter | <http://www.linaro.org/linaro-blog/> Blog
