netdev - RE: [PATCH NEXT 0/2] qlcnic: Add Qlogic 1/10Gb Ethernet driver for CNA devices

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: <7608421F3572AB4292BB2532AE89D5658B0B6E5012@AVEXMB1.qlogic.org>
Date:	Tue, 5 Jan 2010 20:27:24 -0800
From:	Dhananjay Phadke <dhananjay.phadke@...gic.com>
To:	David Miller <davem@...emloft.net>
CC:	"shemminger@...tta.com" <shemminger@...tta.com>,
	Amit Salecha <amit.salecha@...gic.com>,
	"netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: RE: [PATCH NEXT 0/2] qlcnic: Add Qlogic 1/10Gb Ethernet driver for
 CNA devices

> Ok, but you do realize that because GRO maintains enough state
> we can reconstitute packets across forwarding and bridging
> thus decreasing the per-packet costs in those situations as
> well right?
> 
> That's why hardware vendors should strive to align their hw
> LRO implementations with what GRO does, since it is truly
> generic and allows to optimize all cases not just local
> TCP streams.

Yes, GRO has better coverage but HW LRO allows better interrupt
mitigation since fewer buffers are cycled. While the size of
LRO buffer is debatable in terms of memory allocation (recall
discussion on subject "netxen: fix lro buffer allocation"),
it can cause fewer skb allocations.

May be some of this can be achieved with GRO + rx interrupt
coalesce thresholds, etc.

For now, we need to have option of HW LRO that can be turned
off based on use case (NAT etc) via ethtool or whatever.

Thanks,
Dhananjay
--
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