From: Laurent Vivier <lvivier@redhat.com>
To: David Gibson <david@gibson.dropbear.id.au>
Cc: passt-dev@passt.top
Subject: Re: [PATCH v4 4/7] tcp, flow: Replace per-connection in_epoll flag with threadnb in flow_common
Date: Tue, 21 Oct 2025 14:14:02 +0200 [thread overview]
Message-ID: <bb556e2f-b974-4e04-8605-1a5a46b7fa9b@redhat.com> (raw)
In-Reply-To: <aPWRsQD_hLaE5DXU@zatzit>
On 20/10/2025 03:34, David Gibson wrote:
>> @@ -570,7 +572,8 @@ static void tcp_timer_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
>> }
>> conn->timer = fd;
>>
>> - if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, conn->timer, &ev)) {
>> + if (epoll_ctl(flow_epollfd(&conn->f), EPOLL_CTL_ADD,
>> + conn->timer, &ev)) {
> Possibly a question for an earlier patch, but is there a reason we
> can't use epoll_add() here?
>
Yes, the fd we use in epoll_ctl() and the fd stored in ref are not the same.
The fd in ref is conn->sock (epoll_add() takes fd from ref) but in epoll_ctl() we add
conn->timer (the fd from timerfd_create()).
Thanks,
Laurent
next prev parent reply other threads:[~2025-10-21 12:14 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-17 10:31 [PATCH v4 0/7] Refactor epoll handling in preparation for multithreading Laurent Vivier
2025-10-17 10:31 ` [PATCH v4 1/7] util: Simplify epoll_del() interface to take epollfd directly Laurent Vivier
2025-10-17 10:31 ` [PATCH v4 2/7] epoll_ctl: Extract epoll operations Laurent Vivier
2025-10-17 11:48 ` Stefano Brivio
2025-10-17 12:21 ` Laurent Vivier
2025-10-17 13:05 ` Stefano Brivio
2025-10-20 1:20 ` David Gibson
2025-10-21 11:52 ` Laurent Vivier
2025-10-22 0:58 ` David Gibson
2025-10-17 10:31 ` [PATCH v4 3/7] util: Move epoll registration out of sock_l4_sa() Laurent Vivier
2025-10-17 10:31 ` [PATCH v4 4/7] tcp, flow: Replace per-connection in_epoll flag with threadnb in flow_common Laurent Vivier
2025-10-17 17:43 ` Stefano Brivio
2025-10-21 13:13 ` Laurent Vivier
2025-10-20 1:34 ` David Gibson
2025-10-21 12:14 ` Laurent Vivier [this message]
2025-10-22 1:00 ` David Gibson
2025-10-17 10:31 ` [PATCH v4 5/7] icmp: Use thread-based epoll management for ICMP flows Laurent Vivier
2025-10-20 1:35 ` David Gibson
2025-10-17 10:31 ` [PATCH v4 6/7] udp: Use thread-based epoll management for UDP flows Laurent Vivier
2025-10-20 1:39 ` David Gibson
2025-10-17 10:31 ` [PATCH v4 7/7] passt: Move main event loop processing into passt_worker() Laurent Vivier
2025-10-17 17:43 ` Stefano Brivio
2025-10-20 1:43 ` David Gibson
2025-10-21 8:00 ` Laurent Vivier
2025-10-22 0:53 ` David Gibson
2025-10-22 6:49 ` Laurent Vivier
2025-10-23 1:24 ` David Gibson
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=bb556e2f-b974-4e04-8605-1a5a46b7fa9b@redhat.com \
--to=lvivier@redhat.com \
--cc=david@gibson.dropbear.id.au \
--cc=passt-dev@passt.top \
/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.
Code repositories for project(s) associated with this public inbox
https://passt.top/passt
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 IMAP folder(s).