| Message ID | 1622258536-55776-1-git-send-email-tanhuazhong@huawei.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | ethtool: extend coalesce uAPI | expand |
Huazhong Tan wrote: > In order to support some configuration in coalesce uAPI, this RFC > extends coalesce uAPI and add support for CQE mode. > ... > 3. ethool(netlink with cqe mode) + kernel with cqe mode: > estuary:/$ ethtool -c eth0 > Coalesce parameters for eth0: > Adaptive RX: on TX: on > stats-block-usecs: n/a > sample-interval: n/a > pkt-rate-low: n/a > pkt-rate-high: n/a > > rx-usecs: 20 > rx-frames: 0 > rx-usecs-irq: n/a > rx-frames-irq: n/a > > tx-usecs: 20 > tx-frames: 0 > tx-usecs-irq: n/a > tx-frames-irq: n/a > > rx-usecs-low: n/a > rx-frame-low: n/a > tx-usecs-low: n/a > tx-frame-low: n/a > > rx-usecs-high: 0 > rx-frame-high: n/a > tx-usecs-high: 0 > tx-frame-high: n/a > > CQE mode RX: off TX: off BTW, thanks for working on something like this. I hope it's not just me, but I don't like the display of the new CQE line, at the very least, it's not consistent with what is there already in the output of this command, and at worst, it surprises the user and makes it hard to parse for any scripting tools. Can I suggest something like: rx-cqe: off tx-cqe: off rx-eqe: off tx-eqe: off Then, if hardware is in EQE mode it is clear that it's supported and ON/OFF, as well as for CQE mode. -Jesse
On Tue, 1 Jun 2021 11:14:36 -0700 Jesse Brandeburg wrote: > > 3. ethool(netlink with cqe mode) + kernel with cqe mode: > > estuary:/$ ethtool -c eth0 > > Coalesce parameters for eth0: > > Adaptive RX: on TX: on > > stats-block-usecs: n/a > > sample-interval: n/a > > pkt-rate-low: n/a > > pkt-rate-high: n/a > > > > rx-usecs: 20 > > rx-frames: 0 > > rx-usecs-irq: n/a > > rx-frames-irq: n/a > > > > tx-usecs: 20 > > tx-frames: 0 > > tx-usecs-irq: n/a > > tx-frames-irq: n/a > > > > rx-usecs-low: n/a > > rx-frame-low: n/a > > tx-usecs-low: n/a > > tx-frame-low: n/a > > > > rx-usecs-high: 0 > > rx-frame-high: n/a > > tx-usecs-high: 0 > > tx-frame-high: n/a > > > > CQE mode RX: off TX: off > > BTW, thanks for working on something like this. > I hope it's not just me, but I don't like the display of the new CQE > line, at the very least, it's not consistent with what is there already > in the output of this command, and at worst, it surprises the user and > makes it hard to parse for any scripting tools. Tools should parse JSON output ;) > Can I suggest something like: > > rx-cqe: off > tx-cqe: off > rx-eqe: off > tx-eqe: off > > Then, if hardware is in EQE mode it is clear that it's supported and > ON/OFF, as well as for CQE mode. This is how "Adaptive" is displayed, maybe we should move the line up so that it's closer to its inspiration? Having cqe/eqe both listed when only one can be "on" may not be 100% intuitive either (assuming my understanding that this feature is just about restarting the timer on new packet arrival is correct).