RE: rte_eth_stats_get seems slow

2025-04-29 Thread Morten Brørup
> From: Bruce Richardson [mailto:bruce.richard...@intel.com] > Sent: Tuesday, 29 April 2025 14.53 > > On Sun, Apr 27, 2025 at 09:00:31AM +0200, Morten Brørup wrote: > > > From: Stephen Hemminger [mailto:step...@networkplumber.org] > > > Sent: Saturday, 26 April 2025 17.24 > > > > > > On Fri, 25 Ap

Re: rte_eth_stats_get seems slow

2025-04-29 Thread Bruce Richardson
On Sun, Apr 27, 2025 at 09:00:31AM +0200, Morten Brørup wrote: > > From: Stephen Hemminger [mailto:step...@networkplumber.org] > > Sent: Saturday, 26 April 2025 17.24 > > > > On Fri, 25 Apr 2025 13:52:55 +0200 > > Morten Brørup wrote: > > > > > Bruce, > > > > > > rte_eth_stats_get() on Intel NIC

RE: rte_eth_stats_get seems slow

2025-04-27 Thread Morten Brørup
> From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Saturday, 26 April 2025 17.24 > > On Fri, 25 Apr 2025 13:52:55 +0200 > Morten Brørup wrote: > > > Bruce, > > > > rte_eth_stats_get() on Intel NICs seems slow to me. > > > > E.g. getting the stats on a single port takes ~132 us

Re: rte_eth_stats_get seems slow

2025-04-26 Thread Stephen Hemminger
On Fri, 25 Apr 2025 13:52:55 +0200 Morten Brørup wrote: > Bruce, > > rte_eth_stats_get() on Intel NICs seems slow to me. > > E.g. getting the stats on a single port takes ~132 us (~451,000 CPU cycles) > using the igb driver, and ~50 us using the i40e driver. > > Referring to the igb driver so

rte_eth_stats_get seems slow

2025-04-25 Thread Morten Brørup
Bruce, rte_eth_stats_get() on Intel NICs seems slow to me. E.g. getting the stats on a single port takes ~132 us (~451,000 CPU cycles) using the igb driver, and ~50 us using the i40e driver. Referring to the igb driver source code [1], it's 44 calls to E1000_READ_REG(), so the math says that e