netdev - Re: Softirqs without captured packets

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]

Message-ID: <1361542281.3683.3.camel@edumazet-glaptop>
Date:	Fri, 22 Feb 2013 06:11:21 -0800
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Javier Domingo <javierdo1@...il.com>
Cc:	David Miller <davem@...emloft.net>, netdev@...r.kernel.org
Subject: Re: Softirqs without captured packets

On Fri, 2013-02-22 at 10:32 +0100, Javier Domingo wrote:
> Which is the reason for that in the poll function, not only some
> drivers have that tx completion (I suppose it is to free resources),
> but also to send packets in that routine?
> 
> In e1000e, I have found that it frees resources used in tx, with the
> e1000_clean_tx_irq, and also, although the tx completion is first, it
> executes the rx routine.
> 
> On the other hand, tg3 driver not only does the tx resources free but
> also sends packets in that time, and may return from the poll thought
> it might not have done rx work in the net_rx_action routine.
> 
> Why is this like that? I mean, why all the tx is done *before* the rx
> thread, thought it may not do any rx work (in tg3) ?

To free memory, so that rx handler gets more chance to be able to
allocate memory, and reuse memory already hot in cpu caches.



--
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