From: Jakub Kicinski <kuba@kernel.org>
To: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
Keith Busch <kbusch@kernel.org>,
linux-nvme@lists.infradead.org,
Eric Dumazet <edumazet@google.com>,
Paolo Abeni <pabeni@redhat.com>,
netdev@vger.kernel.org, Boris Pismenny <boris.pismenny@gmail.com>
Subject: Re: [PATCH 6/6] net/tls: implement ->read_sock()
Date: Fri, 21 Jul 2023 07:50:13 -0700 [thread overview]
Message-ID: <20230721075013.0d71e21b@kernel.org> (raw)
In-Reply-To: <a3184117-751a-c582-6295-f45a26398deb@suse.de>
On Fri, 21 Jul 2023 15:53:05 +0200 Hannes Reinecke wrote:
> >> + err = tls_rx_one_record(sk, NULL, &darg);
> >> + if (err < 0) {
> >> + tls_err_abort(sk, -EBADMSG);
> >> + goto read_sock_end;
> >> + }
> >> +
> >> + sk_flush_backlog(sk);
> >
> > Hm, could be a bit often but okay.
> >
> When would you suggest to do it?
> (Do I need to do it at all?)
I picked every 128kB for the normal Rx path. I looked thru my old notes
and it seems I didn't measure smaller batches :( Only 128kB - 4MB.
Flush every 128kB was showing a 4% throughput hit, but much better TCP
behavior. Not sure how the perf hit would scale below 128kB, maybe
the lower the threshold the lower the overhead because statistically
only one of every 4 calls will have something to do? (GRO coalesces
to 64kB == 4 TLS records). Dunno. You'd have to measure.
But its not a blocker for me, FWIW, you can keep the flushing on every
record.
next prev parent reply other threads:[~2023-07-21 14:50 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-19 11:38 [RESENT PATCHv7 0/6] net/tls: fixes for NVMe-over-TLS Hannes Reinecke
2023-07-19 11:38 ` [PATCH 1/6] net/tls: handle MSG_EOR for tls_sw TX flow Hannes Reinecke
2023-07-19 11:38 ` [PATCH 2/6] net/tls: handle MSG_EOR for tls_device " Hannes Reinecke
2023-07-19 11:38 ` [PATCH 3/6] selftests/net/tls: add test for MSG_EOR Hannes Reinecke
2023-07-19 11:38 ` [PATCH 4/6] net/tls: Use tcp_read_sock() instead of ops->read_sock() Hannes Reinecke
2023-07-19 11:54 ` Sagi Grimberg
2023-07-19 11:38 ` [PATCH 5/6] net/tls: split tls_rx_reader_lock Hannes Reinecke
2023-07-19 11:55 ` Sagi Grimberg
2023-07-19 11:38 ` [PATCH 6/6] net/tls: implement ->read_sock() Hannes Reinecke
2023-07-19 11:55 ` Sagi Grimberg
2023-07-20 18:32 ` Simon Horman
2023-07-21 6:03 ` Hannes Reinecke
2023-07-21 3:02 ` Jakub Kicinski
2023-07-21 13:53 ` Hannes Reinecke
2023-07-21 14:50 ` Jakub Kicinski [this message]
-- strict thread matches above, loose matches on Subject: below --
2023-07-26 19:15 [PATCHv9 0/6] net/tls: fixes for NVMe-over-TLS Hannes Reinecke
2023-07-26 19:15 ` [PATCH 6/6] net/tls: implement ->read_sock() Hannes Reinecke
2023-07-21 14:35 [PATCHv8 0/6] net/tls: fixes for NVMe-over-TLS Hannes Reinecke
2023-07-21 14:35 ` [PATCH 6/6] net/tls: implement ->read_sock() Hannes Reinecke
2023-07-24 12:59 ` Sagi Grimberg
2023-07-24 13:47 ` Hannes Reinecke
[not found] <20230719111944.68544-1-hare@suse.de>
2023-07-19 11:19 ` Hannes Reinecke
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=20230721075013.0d71e21b@kernel.org \
--to=kuba@kernel.org \
--cc=boris.pismenny@gmail.com \
--cc=edumazet@google.com \
--cc=hare@suse.de \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=sagi@grimberg.me \
/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).