public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: "Yuval Mintz" <yuvalmin@broadcom•com>
To: "Greg Rose" <gregory.v.rose@intel•com>
Cc: eilong@broadcom•com,
	"Alexander Duyck" <alexander.h.duyck@intel•com>,
	netdev@vger•kernel.org, davem@davemloft•net,
	"Jeff Kirsher" <jeffrey.t.kirsher@intel•com>
Subject: Re: [RFC net-next 05/14] Fix intel/ixgbevf
Date: Mon, 25 Jun 2012 14:23:08 +0300	[thread overview]
Message-ID: <4FE84A1C.90901@broadcom.com> (raw)
In-Reply-To: <20120619110704.000045b2@unknown>

>>>>  	 * It's easy to be greedy for MSI-X vectors, but it

>>>> really @@ -2022,8 +2022,9 @@ static int
>>>> ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter)
>>>>  	 * than CPU's.  So let's be conservative and only ask for
>>>>  	 * (roughly) twice the number of vectors as there are
>>>> CPU's. */
>>>> +	ncpu = min_t(int, num_online_cpus(),
>>>> DEFAULT_MAX_NUM_RSS_QUEUES); v_budget =
>>>> min(adapter->num_rx_queues + adapter->num_tx_queues,
>>>> -		       (int)(num_online_cpus() * 2)) +
>>>> NON_Q_VECTORS;
>>>> +		       ncpu * 2) + NON_Q_VECTORS;
>>>>  
>>>>  	/* A failure in MSI-X entry allocation isn't fatal, but
>>>> it does
>>>>  	 * mean we disable MSI-X capabilities of the adapter. */
>>> This change is pointless on the ixgbevf driver.  The VF hardware can
>>> support at most 4 RSS queues.  As such num_rx_queues + num_tx_queues
>>> will never exceed 8 so you are essentially adding a necessary
>>> min(x,8).
>>
>> It is pointless with the current value, but if someone will edit the
>> kernel source code and replace the 8 with a 2, it will become
>> meaningful. The compiler will optimize this part, and I think that for
>> completion, it is best to keep this reference so a future default
>> number change will not be missed.
>>
>> Eilon
> 
> I don't feel there is any real point to making this change to the
> ixgbevf driver.  82599 virtual functions have 3 MSI-X vectors, one of
> which is for the mailbox and the other two can be shared with tx/rx
> queue pairs or assigned separately to tx or rx queues.  So this code is
> pointless no matter what value is set for DEFAULT_MAX_NUM_RSS_QUEUES.
> Perhaps the patches to the other drivers in your RFC will have some
> effect but this one looks like a no-op for the ixgbevf driver so there
> is no reason for it.
> 
> - Greg
> 

Hi Greg,

Since we're changing the RFC to use a new wrapper function which should
replace num_online_cpus (for these purpose), the next RFC version will still
change this driver (for uniformity, if nothing else).

Of course, if you would still have reservations for this change - send them.

Thanks,
Yuval

  parent reply	other threads:[~2012-06-25 11:25 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-06-19 15:13 [RFC net-next 00/14] default maximal number of RSS queues in mq drivers Yuval Mintz
2012-06-19 15:13 ` [RFC net-next 01/14] Add Default Yuval Mintz
2012-06-19 16:37   ` Alexander Duyck
2012-06-19 17:41     ` Eilon Greenstein
2012-06-19 19:01       ` Alexander Duyck
2012-06-19 19:53         ` Eilon Greenstein
2012-06-19 21:26         ` David Miller
2012-06-19 21:22     ` David Miller
2012-06-19 15:13 ` [RFC net-next 02/14] Fix mellanox/mlx4 Yuval Mintz
2012-06-19 15:13 ` [RFC net-next 03/14] fix neterion/vxge Yuval Mintz
2012-06-19 15:13 ` [RFC net-next 04/14] Fix qlogic/qlge Yuval Mintz
2012-06-19 15:13 ` [RFC net-next 05/14] Fix intel/ixgbevf Yuval Mintz
2012-06-19 15:39   ` Alexander Duyck
2012-06-19 16:06     ` Eilon Greenstein
2012-06-19 18:07       ` Greg Rose
2012-06-19 18:24         ` Eilon Greenstein
2012-06-25 11:23         ` Yuval Mintz [this message]
2012-06-19 15:14 ` [RFC net-next 06/14] Fix intel/igb Yuval Mintz
2012-06-19 15:42   ` Alexander Duyck
2012-06-19 16:07     ` Eilon Greenstein
2012-06-19 15:14 ` [RFC net-next 07/14] Fix intel/ixgbe Yuval Mintz
2012-06-19 15:54   ` Alexander Duyck
2012-06-19 16:11     ` Eilon Greenstein
2012-06-20  8:55     ` Eric Dumazet
2012-06-20 15:30       ` John Fastabend
2012-06-19 15:14 ` [RFC net-next 08/14] Fix chelsio/cxgb3 Yuval Mintz
2012-06-19 15:14 ` [RFC net-next 09/14] Fix chelsio/cxgb4 Yuval Mintz
2012-06-19 15:14 ` [RFC net-next 10/14] Fix myricom/myri10ge Yuval Mintz
2012-06-19 15:14 ` [RFC net-next 11/14] Fix emulex/benet Yuval Mintz
2012-06-19 22:55   ` Ajit.Khaparde
2012-06-21  6:42   ` Sathya.Perla
2012-06-19 15:14 ` [RFC net-next 12/14] Fix broadcom/tg3 Yuval Mintz
2012-06-19 15:14 ` [RFC net-next 13/14] Fix broadcom/bnx2 Yuval Mintz
2012-06-19 15:14 ` [RFC net-next 14/14] Fix broadcom/bnx2x Yuval Mintz
2012-06-19 16:17 ` [RFC net-next 00/14] default maximal number of RSS queues in mq drivers Eilon Greenstein
2012-06-20 20:43 ` Ben Hutchings
2012-06-20 20:48   ` Ben Hutchings
2012-06-21  5:15     ` Yuval Mintz
2012-06-21  5:49       ` David Miller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4FE84A1C.90901@broadcom.com \
    --to=yuvalmin@broadcom$(echo .)com \
    --cc=alexander.h.duyck@intel$(echo .)com \
    --cc=davem@davemloft$(echo .)net \
    --cc=eilong@broadcom$(echo .)com \
    --cc=gregory.v.rose@intel$(echo .)com \
    --cc=jeffrey.t.kirsher@intel$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox