netdev - Definition of the term rx/tx/combined channel

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-next>] [day] [month] [year] [list]

Message-ID: <52B6FFE7.6080906@mellanox.com>
Date:	Sun, 22 Dec 2013 17:06:15 +0200
From:	Amir Vadai <amirv@...lanox.com>
To:	Ben Hutchings <bhutchings@...arflare.com>
CC:	Eugenia Emantayev <eugenia@...lanox.com>,
	netdev <netdev@...r.kernel.org>
Subject: Definition of the term rx/tx/combined channel

Hi Ben,

I'm trying to understand the exact definition of the term channel.

According to ethtool: A channel is an IRQ and the set of queues that can
trigger that IRQ.

In our driver (Mellanox's Connect-X), we have an IRQ's, rx rings and tx
rings.

Usually we have one IRQ per rx ring, but if system resources are
limited, those numbers could be different.
tx rings are sharing the same IRQ's assigned by rx rings (for
completions), but many tx rings could share the same IRQ.

Is the rx channels == number of rx rings, and same for tx?
How is this related to the number of IRQ's?
Should we show other IRQ's we use for async events from the HW, as 'other'?

Thanks,
Amir

--
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