From: Mathieu Desnoyers via lttng-dev <lttng-dev@lists.lttng.org>
To: Mohammad Kavousi <kavousi@u.northwestern.edu>
Cc: lttng-dev <lttng-dev@lists.lttng.org>,
Yan Chen <ychen@northwestern.edu>,
Xutong Chen <XutongChen2021@u.northwestern.edu>
Subject: Re: [lttng-dev] LTTng Support for Network Namespace
Date: Mon, 8 Feb 2021 14:38:46 -0500 (EST) [thread overview]
Message-ID: <108657053.9981.1612813126291.JavaMail.zimbra@efficios.com> (raw)
In-Reply-To: <CAK7B4KcwnAK_u5t-F_ujjeG=mnEXBAtr4PfdcHuhqccrRmbo_Q@mail.gmail.com>
----- On Feb 8, 2021, at 1:04 PM, lttng-dev lttng-dev@lists.lttng.org wrote:
> Dear LTTng developers,
> I was wondering if LTTng currently (or in the future) supports network
> namespaces. For instance, an ambiguity in the logs would make problems for
> future system analysis.
Did you try the "net_ns" context ?
> Taking the "bind" system call, that would help us distinguish between different
> local IP addresses when two or more container instances are running on the
> host, given that the "umyaddr" field is an address inside the memory, how would
> we recover the local addresses after the trace has been collected?
> syscall_entry_bind: { cpu_id = 1 }, { mnt_ns = 4026532553, pid = 532, tid = 532,
> vtid = 532, vpid = 532 }, { fd = 14, umyaddr = 93827759199256, addrlen = 12 }
In lttng-modules, we'd need to implement a system call override for the bind system
call which fetches the umyaddr content from user-space. You can see the x86-64 override
code for the "connect" system call which fetches the uservaddr from user-space as an
inspiration.
Thanks,
Mathieu
> Thanks, we appreciate the help beforehand!
> Mohammad
> _______________________________________________
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> https://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
_______________________________________________
lttng-dev mailing list
lttng-dev@lists.lttng.org
https://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
prev parent reply other threads:[~2021-02-08 19:38 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-08 18:04 Mohammad Kavousi via lttng-dev
2021-02-08 19:38 ` Mathieu Desnoyers via lttng-dev [this message]
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=108657053.9981.1612813126291.JavaMail.zimbra@efficios.com \
--to=lttng-dev@lists.lttng.org \
--cc=XutongChen2021@u.northwestern.edu \
--cc=kavousi@u.northwestern.edu \
--cc=mathieu.desnoyers@efficios.com \
--cc=ychen@northwestern.edu \
/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