Hi Thomas > -----Original Message----- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Tuesday, October 28, 2014 8:13 PM > To: Zhang, Helin > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v2 04/13] ethdev: support of multiple sizes of > redirection table > > 2014-10-28 12:00, Zhang, Helin: > > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > > > 2014-10-28 00:33, Zhang, Helin: > > > > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > > > > > 2014-09-25 16:40, Helin Zhang: > > > > > > /* Definitions used for redirection table entry size */ > > > > > > -#define ETH_RSS_RETA_NUM_ENTRIES 128 > > > > > > -#define ETH_RSS_RETA_MAX_QUEUE 16 > > > > > > +#define ETH_RSS_RETA_SIZE_64 64 #define > > > > > > +ETH_RSS_RETA_SIZE_128 128 #define ETH_RSS_RETA_SIZE_512 512 > [...] > > > By the way, why only these values are allowed? > > > > It depends on hardware, 1G/10G hardware supports 128 reta size only, > > 40G hardware supports 512 or 128 depends on hardware configuration, > > 40G VF hardware supports 64. If more is introduced in the future, more > > values can be added later. It will return with errors if reta size is not > > supported > for specific hardware. > > So maybe it should be the responsibility of the driver to use the right > value. This > kind of hardware differences should be abstracted for the application. > If the application need to know the size, a "get" function could be provided. Yes, the size can be gotten by ops of 'dev_infos_get'. But if end users know the size of a specific port, he can just use these macros directly without getting it from somewhere.
> > -- > Thomas Regards, Helin
