lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Thu, 27 Jan 2022 09:51:48 +0100
From:   Jesper Dangaard Brouer <jbrouer@...hat.com>
To:     Joe Damato <jdamato@...tly.com>, netdev@...r.kernel.org
Cc:     brouer@...hat.com, kuba@...nel.org, davem@...emloft.net,
        ilias.apalodimas@...aro.org, hawk@...nel.org
Subject: Re: [PATCH net-next 0/6] net: page_pool: Add page_pool stat counters



On 26/01/2022 23.48, Joe Damato wrote:
> Greetings:
> 
> This series adds some stat counters for the page_pool allocation path which
> help to track:
> 
> 	- fast path allocations
> 	- slow path order-0 allocations
> 	- slow path high order allocations
> 	- refills which failed due to an empty ptr ring, forcing a slow
> 	  path allocation
> 	- allocations fulfilled via successful refill
> 	- pages which cannot be added to the cache because of numa mismatch
> 	  (i.e. waived)
> 
> Some static inline wrappers are provided for accessing these stats. The
> intention is that drivers which use the page_pool API can, if they choose,
> use this stats API.

You are adding (always on) counters to a critical fast-path, that 
drivers uses for the XDP_DROP use-case.

I want to see performance measurements as documentation, showing this is 
not causing a slow-down.

I have some performance tests here[1]:
  [1] 
https://github.com/netoptimizer/prototype-kernel/tree/master/kernel/lib

Look at:
  - bench_page_pool_simple.c and
  - bench_page_pool_cross_cpu.c

How to use + build this[2]:
  [2] 
https://prototype-kernel.readthedocs.io/en/latest/prototype-kernel/build-process.html

> It assumed that the API consumer will ensure the page_pool is not destroyed
> during calls to the stats API.
> 
> If this series is accepted, I'll submit a follow up patch which will export
> these stats per RX-ring via ethtool in a driver which uses the page_pool
> API.
> 
> Joe Damato (6):
>    net: page_pool: Add alloc stats and fast path stat
>    net: page_pool: Add a stat for the slow alloc path
>    net: page_pool: Add a high order alloc stat
>    net: page_pool: Add stat tracking empty ring
>    net: page_pool: Add stat tracking cache refills.
>    net: page_pool: Add a stat tracking waived pages.
> 
>   include/net/page_pool.h | 82 +++++++++++++++++++++++++++++++++++++++++++++++++
>   net/core/page_pool.c    | 15 +++++++--
>   2 files changed, 94 insertions(+), 3 deletions(-)
> 

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ