netdev - RE: [RFC net-next (v2) 11/14] igb: set maximal number of default RSS queues

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1340648402.2486.28.camel@lb-tlvb-eilong.il.broadcom.com>
Date:	Mon, 25 Jun 2012 21:20:02 +0300
From:	"Eilon Greenstein" <eilong@...adcom.com>
To:	"Vick, Matthew" <matthew.vick@...el.com>
cc:	"Yuval Mintz" <yuvalmin@...adcom.com>,
	"davem@...emloft.net" <davem@...emloft.net>,
	"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
	"Kirsher, Jeffrey T" <jeffrey.t.kirsher@...el.com>
Subject: RE: [RFC net-next (v2) 11/14] igb: set maximal number of
 default RSS queues

On Mon, 2012-06-25 at 17:31 +0000, Vick, Matthew wrote:
> > -----Original Message-----
> > From: netdev-owner@...r.kernel.org [mailto:netdev-
> > owner@...r.kernel.org] On Behalf Of Yuval Mintz
> > Sent: Monday, June 25, 2012 4:46 AM
> > To: davem@...emloft.net; netdev@...r.kernel.org
> > Cc: eilong@...adcom.com; Yuval Mintz; Kirsher, Jeffrey T
> > Subject: [RFC net-next (v2) 11/14] igb: set maximal number of default
> > RSS queues
> > 
> > Signed-off-by: Yuval Mintz <yuvalmin@...adcom.com>
> > Signed-off-by: Eilon Greenstein <eilong@...adcom.com>
> > 
> > Cc: Jeff Kirsher <jeffrey.t.kirsher@...el.com>
> > ---
> >  drivers/net/ethernet/intel/igb/igb_main.c |    3 ++-
> >  1 files changed, 2 insertions(+), 1 deletions(-)
> > 
> > diff --git a/drivers/net/ethernet/intel/igb/igb_main.c
> > b/drivers/net/ethernet/intel/igb/igb_main.c
> > index 01ced68..b11ee60 100644
> > --- a/drivers/net/ethernet/intel/igb/igb_main.c
> > +++ b/drivers/net/ethernet/intel/igb/igb_main.c
> > @@ -2465,7 +2465,8 @@ static int __devinit igb_sw_init(struct
> > igb_adapter *adapter)
> >  		break;
> >  	}
> > 
> > -	adapter->rss_queues = min_t(u32, max_rss_queues,
> > num_online_cpus());
> > +	adapter->rss_queues = min_t(u32, max_rss_queues,
> > +				    netif_get_num_default_rss_queues());
> > 
> >  	/* Determine if we need to pair queues. */
> >  	switch (hw->mac.type) {
> > --
> > 1.7.9.rc2
> 
> Since igb supports a maximum of 8 RSS queues anyway, it's generally unaffected by this change. That being said, I'm confused about what you're trying to accomplish--is it to standardize the number of RSS queues or limit the number of interrupts by default? Or is it the former with a hope that it will trickle down to the latter?
> 
> For example, if you take an igb device that supports 8 RSS queues (say, I350) and you change the default to 4 RSS queues, you will end up with the same number of interrupt vectors being requested as we will disable queue pairing and request separate vectors for Rx/Tx queues. I haven't looked at the other drivers affected by this RFC, but it's possible other drivers behave the same way.

The main motivation is the Rx rings that consume significant amount of
memory. The MSI-X vectors are a nice byproduct, but the logic you
describe still sounds good for this kind of low numbers.



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html