From: Leon Romanovsky <leon@kernel.org>
To: Jason Gunthorpe <jgg@nvidia.com>
Cc: Michael Margolin <mrgolin@amazon.com>,
Gal Pressman <gal.pressman@linux.dev>,
Tom Sela <tomsela@amazon.com>,
linux-rdma@vger.kernel.org, sleybo@amazon.com, matua@amazon.com,
Yonatan Nachum <ynachum@amazon.com>
Subject: Re: [PATCH for-next] RDMA/efa: Add AH usage counter with sysfs exposure
Date: Wed, 18 Feb 2026 11:15:59 +0200 [thread overview]
Message-ID: <20260218091559.GF10368@unreal> (raw)
In-Reply-To: <20260218001408.GB723117@nvidia.com>
On Tue, Feb 17, 2026 at 08:14:08PM -0400, Jason Gunthorpe wrote:
> On Tue, Feb 17, 2026 at 02:54:26PM +0000, Michael Margolin wrote:
> > to monitor AH usage in production. Resource usage and traffic counters
> > are usually collected periodically (every 1-5 seconds) by dedicated
> > collectors (e.g., Prometheus node exporter).
>
> Can you just have two simple stats
> '# HW AHs created'
> '# HW AHs destroyed'
>
> and the value you want is the simple difference?
Which can be collected from FW through FWCTL?
I don't super excited to see slow, unique sysfs UAPI field in RDMA
subsystem. They are interested to get FW information, let's use
interfaces which are intended for it.
Thanks
>
> Jason
next prev parent reply other threads:[~2026-02-18 9:16 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-11 13:10 [PATCH for-next] RDMA/efa: Add AH usage counter with sysfs exposure Tom Sela
2026-02-11 13:13 ` Jason Gunthorpe
2026-02-12 6:52 ` Gal Pressman
2026-02-12 16:36 ` Leon Romanovsky
2026-02-15 13:41 ` Michael Margolin
2026-02-15 17:15 ` Leon Romanovsky
2026-02-15 17:23 ` Gal Pressman
2026-02-15 17:57 ` Leon Romanovsky
2026-02-16 11:08 ` Michael Margolin
2026-02-16 11:22 ` Leon Romanovsky
2026-02-17 14:54 ` Michael Margolin
2026-02-18 0:14 ` Jason Gunthorpe
2026-02-18 9:15 ` Leon Romanovsky [this message]
2026-02-18 17:27 ` Michael Margolin
2026-02-16 8:48 ` Michael Margolin
2026-02-16 9:41 ` Leon Romanovsky
2026-02-11 18:48 ` yanjun.zhu
2026-02-12 6:52 ` Gal Pressman
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=20260218091559.GF10368@unreal \
--to=leon@kernel.org \
--cc=gal.pressman@linux.dev \
--cc=jgg@nvidia.com \
--cc=linux-rdma@vger.kernel.org \
--cc=matua@amazon.com \
--cc=mrgolin@amazon.com \
--cc=sleybo@amazon.com \
--cc=tomsela@amazon.com \
--cc=ynachum@amazon.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.