public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Jason Wang <jasowang@redhat•com>
To: "Michael S. Tsirkin" <mst@redhat•com>
Cc: Eric Dumazet <eric.dumazet@gmail•com>,
	davem@davemloft•net, hkchu@google•com,
	netdev <netdev@vger•kernel.org>,
	dwmw2@infradead•org
Subject: Re: [PATCH net-next] net: allow large number of tx queues
Date: Fri, 21 Jun 2013 14:41:48 +0800	[thread overview]
Message-ID: <51C3F5AC.2090008@redhat.com> (raw)
In-Reply-To: <20130620083530.GA23909@redhat.com>

On 06/20/2013 04:35 PM, Michael S. Tsirkin wrote:
> On Thu, Jun 20, 2013 at 01:15:51AM -0700, Eric Dumazet wrote:
>> From: Eric Dumazet <edumazet@google•com>
>>
>> On Wed, 2013-06-19 at 21:07 +0300, Michael S. Tsirkin wrote:
>>
>>> As we have explicit code to recover, maybe set __GFP_NOWARN?
>>> If we are out of memory, vzalloc will warn too, we don't
>>> need two warnings.
>> Yes, that's absolutely the right thing to do.
>>
>> Its yet not clear this patch is really needed, but here it is.
>>
>> Thanks
>>
>> [PATCH net-next] net: allow large number of tx queues
>>
>> netif_alloc_netdev_queues() uses kcalloc() to allocate memory
>> for the "struct netdev_queue *_tx" array.
>>
>> For large number of tx queues, kcalloc() might fail, so this
>> patch does a fallback to vzalloc().
>>
>> As vmalloc() adds overhead on a critical network path, add __GFP_REPEAT
>> to kzalloc() flags to do this fallback only when really needed.
>>
>> Signed-off-by: Eric Dumazet <edumazet@google•com>
> FWIW
>
> Acked-by: Michael S. Tsirkin <mst@redhat•com>
>
> This makes it possible to go up to 1K queues which should
> be enough, so we can revert the first chunk in
> edfb6a148ce62e5e19354a1dcd9a34e00815c2a1.

1K queues (about 80 pages) looks a little bit aggressive which means we
may always fall back to vmalloc()?
>
>
>> ---
>>  net/core/dev.c |   26 +++++++++++++++++++-------
>>  1 file changed, 19 insertions(+), 7 deletions(-)
>>
>> diff --git a/net/core/dev.c b/net/core/dev.c
>> index fa007db..722f633 100644
>> --- a/net/core/dev.c
>> +++ b/net/core/dev.c
>> @@ -130,6 +130,7 @@
>>  #include <linux/cpu_rmap.h>
>>  #include <linux/static_key.h>
>>  #include <linux/hashtable.h>
>> +#include <linux/vmalloc.h>
>>  
>>  #include "net-sysfs.h"
>>  
>> @@ -5253,17 +5254,28 @@ static void netdev_init_one_queue(struct net_device *dev,
>>  #endif
>>  }
>>  
>> +static void netif_free_tx_queues(struct net_device *dev)
>> +{
>> +	if (is_vmalloc_addr(dev->_tx))
>> +		vfree(dev->_tx);
>> +	else
>> +		kfree(dev->_tx);
>> +}
>> +
>>  static int netif_alloc_netdev_queues(struct net_device *dev)
>>  {
>>  	unsigned int count = dev->num_tx_queues;
>>  	struct netdev_queue *tx;
>> +	size_t sz = count * sizeof(*tx);
>>  
>> -	BUG_ON(count < 1);
>> -
>> -	tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
>> -	if (!tx)
>> -		return -ENOMEM;
>> +	BUG_ON(count < 1 || count > 0xffff);
>>  
>> +	tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
>> +	if (!tx) {
>> +		tx = vzalloc(sz);
>> +		if (!tx)
>> +			return -ENOMEM;
>> +	}
>>  	dev->_tx = tx;
>>  
>>  	netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
>> @@ -5811,7 +5823,7 @@ free_all:
>>  
>>  free_pcpu:
>>  	free_percpu(dev->pcpu_refcnt);
>> -	kfree(dev->_tx);
>> +	netif_free_tx_queues(dev);
>>  #ifdef CONFIG_RPS
>>  	kfree(dev->_rx);
>>  #endif
>> @@ -5836,7 +5848,7 @@ void free_netdev(struct net_device *dev)
>>  
>>  	release_net(dev_net(dev));
>>  
>> -	kfree(dev->_tx);
>> +	netif_free_tx_queues(dev);
>>  #ifdef CONFIG_RPS
>>  	kfree(dev->_rx);
>>  #endif
>>

  reply	other threads:[~2013-06-21  6:42 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-06-19  5:40 [net-next rfc 0/3] increase the limit of tuntap queues Jason Wang
2013-06-19  5:40 ` [net-next rfc 1/3] net: avoid high order memory allocation for queues by using flex array Jason Wang
2013-06-19  6:31   ` Eric Dumazet
2013-06-19  7:14     ` Jason Wang
2013-06-19  9:11     ` Michael S. Tsirkin
2013-06-19  9:56       ` Eric Dumazet
2013-06-19 12:22         ` Michael S. Tsirkin
2013-06-19 15:40         ` Michael S. Tsirkin
2013-06-19 15:58           ` Eric Dumazet
2013-06-19 16:06             ` David Laight
2013-06-19 16:28               ` Eric Dumazet
2013-06-19 18:07             ` Michael S. Tsirkin
2013-06-20  8:15               ` [PATCH net-next] net: allow large number of tx queues Eric Dumazet
2013-06-20  8:35                 ` Michael S. Tsirkin
2013-06-21  6:41                   ` Jason Wang [this message]
2013-06-21  7:12                     ` Eric Dumazet
2013-06-23 10:29                       ` Michael S. Tsirkin
2013-06-24  6:57                 ` David Miller
2013-06-20  5:14         ` [net-next rfc 1/3] net: avoid high order memory allocation for queues by using flex array Jason Wang
2013-06-20  6:05           ` Eric Dumazet
2013-06-19  5:40 ` [net-next rfc 2/3] tuntap: reduce the size of tun_struct " Jason Wang
2013-06-19  5:40 ` [net-next rfc 3/3] tuntap: increase the max queues to 16 Jason Wang
2013-06-19  6:34   ` Eric Dumazet
2013-06-19  7:15     ` Jason Wang
2013-06-19 19:16     ` Jerry Chu

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=51C3F5AC.2090008@redhat.com \
    --to=jasowang@redhat$(echo .)com \
    --cc=davem@davemloft$(echo .)net \
    --cc=dwmw2@infradead$(echo .)org \
    --cc=eric.dumazet@gmail$(echo .)com \
    --cc=hkchu@google$(echo .)com \
    --cc=mst@redhat$(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