From: Sagi Grimberg <sagi@grimberg.me>
To: Tal Gilboa <talgi@mellanox.com>, Or Gerlitz <gerlitz.or@gmail.com>
Cc: linux-block@vger.kernel.org,
RDMA mailing list <linux-rdma@vger.kernel.org>,
Jason Gunthorpe <jgg@ziepe.ca>, Christoph Hellwig <hch@lst.de>,
Jens Axboe <axboe@kernel.dk>, Idan Burstein <idanb@mellanox.com>,
Bart Van Assche <bart.vanassche@wdc.com>
Subject: Re: [PATCH rfc 0/5] generic adaptive IRQ moderation library for I/O devices
Date: Tue, 6 Feb 2018 11:34:04 +0200 [thread overview]
Message-ID: <73df42b8-106d-0c06-45e2-49285ed01ab5@grimberg.me> (raw)
In-Reply-To: <4c8a45cb-bd4b-8dce-b8d2-2d26c471ef7b@mellanox.com>
Hi Tal,
>> I think Tal has idea/s on how the existing library can be changed to
>> support more modes/models
>>
> What I was thinking is allowing DIM algorithm to disregard data which is
> 0. Currently if bytes == 0 we return "SAME" immediately. We can change
> it to simply move to the packets check (which may be renamed to
> "completions"). This way you could use DIM while only optimizing to (P1)
> high packet rate and (P2) low interrupt rate.
That was exactly where I started from. But unfortunately it did not work
well :(
From my experiments, the moderation was all over the place failing to
converge. At least the workloads that I've tested with, it was more
successful to have a stricter step policy and pulling towards latency
if we are consistently catching single completion per event.
I'm not an expert here at all, but at this point, based on my attempts
so far, I'm not convinced the current net_dim scheme could work.
next prev parent reply other threads:[~2018-02-06 9:34 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-05 22:03 [PATCH rfc 0/5] generic adaptive IRQ moderation library for I/O devices Sagi Grimberg
2018-02-05 22:03 ` [PATCH rfc 5/5] IB/cq: wire up adaptive moderation to workqueue based completion queues Sagi Grimberg
[not found] ` <20180205220316.30236-1-sagi-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2018-02-05 22:03 ` [PATCH rfc 1/5] irq-am: Introduce library implementing generic adaptive moderation Sagi Grimberg
[not found] ` <20180205220316.30236-2-sagi-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2018-02-06 7:43 ` Or Gerlitz
2018-02-05 22:03 ` [PATCH rfc 2/5] irq-am: add some debugfs exposure on tuning state Sagi Grimberg
2018-02-06 16:04 ` kbuild test robot
2018-02-06 17:38 ` kbuild test robot
2018-02-08 1:24 ` Bart Van Assche
2018-02-12 19:42 ` Sagi Grimberg
2018-02-05 22:03 ` [PATCH rfc 3/5] irq_poll: wire up irq_am Sagi Grimberg
[not found] ` <20180205220316.30236-4-sagi-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2018-02-08 1:28 ` Bart Van Assche
[not found] ` <1518053304.2870.95.camel-Sjgp3cTcYWE@public.gmane.org>
2018-02-12 19:40 ` Sagi Grimberg
2018-02-05 22:03 ` [PATCH rfc 4/5] IB/cq: add adaptive moderation support Sagi Grimberg
2018-02-06 6:56 ` [PATCH rfc 0/5] generic adaptive IRQ moderation library for I/O devices Or Gerlitz
2018-02-06 9:25 ` Sagi Grimberg
[not found] ` <08889344-db9d-cf46-6cfb-56764042f578-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2018-02-06 11:34 ` Or Gerlitz
2018-02-06 8:54 ` Or Gerlitz
[not found] ` <CAJ3xEMi0KzOMJt7d01ohHW-ZpmdwvfzZCLN0qA-LLFwROeVseQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-02-06 9:02 ` Tal Gilboa
2018-02-06 9:34 ` Sagi Grimberg [this message]
2018-02-06 9:45 ` Tal Gilboa
[not found] ` <a47a8012-c021-74c4-9161-eaff7374a0b2-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2018-02-13 9:30 ` Or Gerlitz
2018-02-13 21:46 ` Tal Gilboa
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=73df42b8-106d-0c06-45e2-49285ed01ab5@grimberg.me \
--to=sagi@grimberg.me \
--cc=axboe@kernel.dk \
--cc=bart.vanassche@wdc.com \
--cc=gerlitz.or@gmail.com \
--cc=hch@lst.de \
--cc=idanb@mellanox.com \
--cc=jgg@ziepe.ca \
--cc=linux-block@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=talgi@mellanox.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).