Re: [RFC v3] net/af_packet: make stats reset reliable

2024-10-04 Thread Stephen Hemminger
On Sun, 26 May 2024 09:21:55 +0200 Mattias Rönnblom wrote: > On 2024-05-08 17:23, Stephen Hemminger wrote: > > On Wed, 8 May 2024 09:19:02 +0200 > > Mattias Rönnblom wrote: > > > >> On 2024-05-04 00:00, Stephen Hemminger wrote: > >>> On Fri, 3 May 2024 16:45:47 +0100 > >>> Ferruh Yigit wro

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-26 Thread Mattias Rönnblom
On 2024-05-08 17:23, Stephen Hemminger wrote: On Wed, 8 May 2024 09:19:02 +0200 Mattias Rönnblom wrote: On 2024-05-04 00:00, Stephen Hemminger wrote: On Fri, 3 May 2024 16:45:47 +0100 Ferruh Yigit wrote: For stats reset, use an offset instead of zeroing out actual stats values, get_stat

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-26 Thread Mattias Rönnblom
On 2024-05-10 11:14, Morten Brørup wrote: From: Stephen Hemminger [mailto:step...@networkplumber.org] Sent: Friday, 10 May 2024 06.56 On Thu, 9 May 2024 16:19:08 +0200 Morten Brørup wrote: From: Morten Brørup [mailto:m...@smartsharesystems.com] Sent: Thursday, 9 May 2024 13.37 From: Bruce R

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-26 Thread Mattias Rönnblom
On 2024-05-09 16:19, Morten Brørup wrote: From: Morten Brørup [mailto:m...@smartsharesystems.com] Sent: Thursday, 9 May 2024 13.37 From: Bruce Richardson [mailto:bruce.richard...@intel.com] Sent: Thursday, 9 May 2024 11.30 On Thu, May 09, 2024 at 09:43:16AM +0200, Morten Brørup wrote: From: S

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-26 Thread Mattias Rönnblom
On 2024-05-09 13:37, Morten Brørup wrote: From: Bruce Richardson [mailto:bruce.richard...@intel.com] Sent: Thursday, 9 May 2024 11.30 On Thu, May 09, 2024 at 09:43:16AM +0200, Morten Brørup wrote: From: Stephen Hemminger [mailto:step...@networkplumber.org] Sent: Wednesday, 8 May 2024 22.54 On

RE: [RFC v3] net/af_packet: make stats reset reliable

2024-05-10 Thread Morten Brørup
> From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Friday, 10 May 2024 06.56 > > On Thu, 9 May 2024 16:19:08 +0200 > Morten Brørup wrote: > > > > From: Morten Brørup [mailto:m...@smartsharesystems.com] > > > Sent: Thursday, 9 May 2024 13.37 > > > > > > > From: Bruce Richardson

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-09 Thread Stephen Hemminger
On Thu, 9 May 2024 16:19:08 +0200 Morten Brørup wrote: > > From: Morten Brørup [mailto:m...@smartsharesystems.com] > > Sent: Thursday, 9 May 2024 13.37 > > > > > From: Bruce Richardson [mailto:bruce.richard...@intel.com] > > > Sent: Thursday, 9 May 2024 11.30 > > > > > > On Thu, May 09, 2024 a

RE: [RFC v3] net/af_packet: make stats reset reliable

2024-05-09 Thread Morten Brørup
> From: Morten Brørup [mailto:m...@smartsharesystems.com] > Sent: Thursday, 9 May 2024 13.37 > > > From: Bruce Richardson [mailto:bruce.richard...@intel.com] > > Sent: Thursday, 9 May 2024 11.30 > > > > On Thu, May 09, 2024 at 09:43:16AM +0200, Morten Brørup wrote: > > > > From: Stephen Hemminger

RE: [RFC v3] net/af_packet: make stats reset reliable

2024-05-09 Thread Morten Brørup
> From: Bruce Richardson [mailto:bruce.richard...@intel.com] > Sent: Thursday, 9 May 2024 11.30 > > On Thu, May 09, 2024 at 09:43:16AM +0200, Morten Brørup wrote: > > > From: Stephen Hemminger [mailto:step...@networkplumber.org] > > > Sent: Wednesday, 8 May 2024 22.54 > > > > > > On Wed, 8 May 202

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-09 Thread Bruce Richardson
On Thu, May 09, 2024 at 09:43:16AM +0200, Morten Brørup wrote: > > From: Stephen Hemminger [mailto:step...@networkplumber.org] > > Sent: Wednesday, 8 May 2024 22.54 > > > > On Wed, 8 May 2024 20:48:06 +0100 > > Ferruh Yigit wrote: > > > > > > > > > > The idea of load tearing is crazy talk of int

RE: [RFC v3] net/af_packet: make stats reset reliable

2024-05-09 Thread Morten Brørup
> From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Wednesday, 8 May 2024 22.54 > > On Wed, 8 May 2024 20:48:06 +0100 > Ferruh Yigit wrote: > > > > > > > The idea of load tearing is crazy talk of integral types. It would > break so many things. > > > It is the kind of stupid co

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-08 Thread Stephen Hemminger
On Wed, 8 May 2024 20:48:06 +0100 Ferruh Yigit wrote: > > > > The idea of load tearing is crazy talk of integral types. It would break so > > many things. > > It is the kind of stupid compiler thing that would send Linus on a rant and > > get > > the GCC compiler writers in trouble. > > > >

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-08 Thread Ferruh Yigit
On 5/8/2024 4:23 PM, Stephen Hemminger wrote: > On Wed, 8 May 2024 09:19:02 +0200 > Mattias Rönnblom wrote: > >> On 2024-05-04 00:00, Stephen Hemminger wrote: >>> On Fri, 3 May 2024 16:45:47 +0100 >>> Ferruh Yigit wrote: >>> For stats reset, use an offset instead of zeroing out actual st

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-08 Thread Stephen Hemminger
On Wed, 8 May 2024 09:19:02 +0200 Mattias Rönnblom wrote: > On 2024-05-04 00:00, Stephen Hemminger wrote: > > On Fri, 3 May 2024 16:45:47 +0100 > > Ferruh Yigit wrote: > > > >> For stats reset, use an offset instead of zeroing out actual stats values, > >> get_stats() displays diff between st

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-08 Thread Mattias Rönnblom
On 2024-05-04 00:00, Stephen Hemminger wrote: On Fri, 3 May 2024 16:45:47 +0100 Ferruh Yigit wrote: For stats reset, use an offset instead of zeroing out actual stats values, get_stats() displays diff between stats and offset. This way stats only updated in datapath and offset only updated in

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-07 Thread Ferruh Yigit
On 5/7/2024 4:27 PM, Morten Brørup wrote: >> From: Ferruh Yigit [mailto:ferruh.yi...@amd.com] >> Sent: Friday, 3 May 2024 17.46 >> >> For stats reset, use an offset instead of zeroing out actual stats values, >> get_stats() displays diff between stats and offset. >> This way stats only updated in d

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-07 Thread Ferruh Yigit
On 5/7/2024 3:52 PM, Stephen Hemminger wrote: > On Tue, 7 May 2024 14:48:51 +0100 > Ferruh Yigit wrote: > >> On 5/3/2024 11:00 PM, Stephen Hemminger wrote: >>> On Fri, 3 May 2024 16:45:47 +0100 >>> Ferruh Yigit wrote: >>> For stats reset, use an offset instead of zeroing out actual stats

RE: [RFC v3] net/af_packet: make stats reset reliable

2024-05-07 Thread Morten Brørup
> From: Ferruh Yigit [mailto:ferruh.yi...@amd.com] > Sent: Friday, 3 May 2024 17.46 > > For stats reset, use an offset instead of zeroing out actual stats values, > get_stats() displays diff between stats and offset. > This way stats only updated in datapath and offset only updated in stats > rese

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-07 Thread Stephen Hemminger
On Tue, 7 May 2024 14:48:51 +0100 Ferruh Yigit wrote: > On 5/3/2024 11:00 PM, Stephen Hemminger wrote: > > On Fri, 3 May 2024 16:45:47 +0100 > > Ferruh Yigit wrote: > > > >> For stats reset, use an offset instead of zeroing out actual stats values, > >> get_stats() displays diff between stats

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-07 Thread Ferruh Yigit
On 5/3/2024 11:00 PM, Stephen Hemminger wrote: > On Fri, 3 May 2024 16:45:47 +0100 > Ferruh Yigit wrote: > >> For stats reset, use an offset instead of zeroing out actual stats values, >> get_stats() displays diff between stats and offset. >> This way stats only updated in datapath and offset onl

Re: [RFC v3] net/af_packet: make stats reset reliable

2024-05-03 Thread Stephen Hemminger
On Fri, 3 May 2024 16:45:47 +0100 Ferruh Yigit wrote: > For stats reset, use an offset instead of zeroing out actual stats values, > get_stats() displays diff between stats and offset. > This way stats only updated in datapath and offset only updated in stats > reset function. This makes stats re

[RFC v3] net/af_packet: make stats reset reliable

2024-05-03 Thread Ferruh Yigit
For stats reset, use an offset instead of zeroing out actual stats values, get_stats() displays diff between stats and offset. This way stats only updated in datapath and offset only updated in stats reset function. This makes stats reset function more reliable. As stats only written by single thr