1919b39fc6
The apc->eth_stats.rx_cqes is one per NIC (vport), and it's on the
frequent and parallel code path of all queues. So, r/w into this
single shared variable by many threads on different CPUs creates a
lot caching and memory overhead, hence perf regression. And, it's
not accurate due to the high volume concurrent r/w.
For example, a workload is iperf with 128 threads, and with RPS
enabled. We saw perf regression of 25% with the previous patch
adding the counters. And this patch eliminates the regression.
Since the error path of mana_poll_rx_cq() already has warnings, so
keeping the counter and convert it to a per-queue variable is not
necessary. So, just remove this counter from this high frequency
code path.
Also, remove the tx_cqes counter for the same reason. We have
warnings & other counters for errors on that path, and don't need
to count every normal cqe processing.
Cc: stable@vger.kernel.org
Fixes:
|
||
|---|---|---|
| .. | ||
| appletalk | ||
| arcnet | ||
| bonding | ||
| caif | ||
| can | ||
| dsa | ||
| ethernet | ||
| fddi | ||
| fjes | ||
| hamradio | ||
| hippi | ||
| hyperv | ||
| ieee802154 | ||
| ipa | ||
| ipvlan | ||
| mctp | ||
| mdio | ||
| netdevsim | ||
| pcs | ||
| phy | ||
| plip | ||
| ppp | ||
| pse-pd | ||
| slip | ||
| team | ||
| thunderbolt | ||
| usb | ||
| vmxnet3 | ||
| vxlan | ||
| wan | ||
| wireguard | ||
| wireless | ||
| wwan | ||
| xen-netback | ||
| amt.c | ||
| bareudp.c | ||
| dummy.c | ||
| eql.c | ||
| geneve.c | ||
| gtp.c | ||
| ifb.c | ||
| Kconfig | ||
| LICENSE.SRC | ||
| loopback.c | ||
| macsec.c | ||
| macvlan.c | ||
| macvtap.c | ||
| Makefile | ||
| mdio.c | ||
| mhi_net.c | ||
| mii.c | ||
| net_failover.c | ||
| netconsole.c | ||
| nlmon.c | ||
| ntb_netdev.c | ||
| rionet.c | ||
| sb1000.c | ||
| Space.c | ||
| sungem_phy.c | ||
| tap.c | ||
| tun.c | ||
| veth.c | ||
| virtio_net.c | ||
| vrf.c | ||
| vsockmon.c | ||
| xen-netfront.c | ||