linux-kernel - Re: [PATCH] Add support for multiple MSI on x86

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] [day] [month] [year] [list]

Date:	Thu, 10 Mar 2011 16:33:48 +0100
From:	Clemens Ladisch <clemens@...isch.de>
To:	Roland Dreier <roland@...estorage.com>
CC:	"H. Peter Anvin" <hpa@...or.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	Micha Nelissen <micha@...i.hopto.org>,
	Jesse Barnes <jbarnes@...tuousgeek.org>,
	Ingo Molnar <mingo@...hat.com>, x86@...nel.org,
	"Venkatesh Pallipadi (Venki)" <venki@...gle.com>,
	linux-kernel@...r.kernel.org, linux-pci@...r.kernel.org,
	Matthew Wilcox <matthew@....cx>
Subject: Re: [PATCH] Add support for multiple MSI on x86

Roland Dreier wrote:
> > Yes, but there are MSI devices in the field...
> 
> But do any of them benefit from having multiple interrupt vectors available?
> 
> If I recall correct, willy was motivated by AHCI performance to try this out,
> and in the end things didn't go any faster using multiple MSI.
> 
> The big win with multiple interrupt vectors is when you have independent
> queues that you can point different CPUs at, and give each CPU its own
> interrupt.

And this is how AHCI is designed, but libahci.c currently wraps its
interrupt handler in a device-wide lock.  I don't know if that test also
reorganized the driver code.


Regards,
Clemens
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/