O Title: Rearchitecting Linux Storage Stack for Remote SSD access

O Date: 2023년 02월 10 일 금요일 

O Start Time: 오후 1시 30분 

O Venue: 온라인 (https://kaist.zoom.us/j/82053120262?pwd=M1poSFY0OEZMVEU5UnZFbWo5SEdXUT09)

O Abstract:

There is a widespread belief in the community that it is not possible to achieve high throughput and µs-scale tail latency when using the Linux kernel stack.

Two most frequently cited arguments are (1) Linux has high CPU overheads; and (2) the resource multiplexing principle is so firmly entrenched in Linux that its performance stumbles when
multiple applications compete for host resources.

I will demonstrate that the above belief may be misplaced, at least for remote storage (SSD) access. In particular, I will present a new Linux storage stack architecture that achieves (1) high throughput comparable to NVMe-over-RDMA and (2) µs-scale latency, even when tens of applications compete for host resources while performing operations at throughput close to hardware capacity. Such a performance can be achieved without any modification in applications, network hardware, kernel CPU schedulers and/or kernel network stack.