netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ido Schimmel <idosch@idosch.org>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, nhorman@tuxdriver.com, dsahern@gmail.com,
	roopa@cumulusnetworks.com, nikolay@cumulusnetworks.com,
	jakub.kicinski@netronome.com, toke@redhat.com,
	andy@greyhouse.net, f.fainelli@gmail.com, andrew@lunn.ch,
	vivien.didelot@gmail.com, mlxsw@mellanox.com,
	Ido Schimmel <idosch@mellanox.com>
Subject: [RFC PATCH net-next 00/12] drop_monitor: Capture dropped packets and metadata
Date: Mon, 22 Jul 2019 21:31:22 +0300	[thread overview]
Message-ID: <20190722183134.14516-1-idosch@idosch.org> (raw)

From: Ido Schimmel <idosch@mellanox.com>

So far drop monitor supported only one mode of operation in which a
summary of recent packet drops is periodically sent to user space as a
netlink event. The event only includes the drop location (program
counter) and number of drops in the last interval.

While this mode of operation allows one to understand if the system is
dropping packets, it is not sufficient if a more detailed analysis is
required. Both the packet itself and related metadata are missing.

This patchset extends drop monitor with another mode of operation where
the packet - potentially truncated - and metadata (e.g., drop location,
timestamp, netdev) are sent to user space as a netlink event. Thanks to
the extensible nature of netlink, more metadata can be added in the
future.

To avoid performing expensive operations in the context in which
kfree_skb() is called, the dropped skbs are cloned and queued on per-CPU
skb drop list. The list is then processed in process context (using a
workqueue), where the netlink messages are allocated, prepared and
finally sent to user space.

As a follow-up, I plan to integrate drop monitor with devlink and allow
the latter to call into drop monitor to report hardware drops. In the
future, XDP drops can be added as well, thereby making drop monitor the
go-to netlink channel for diagnosing all packet drops.

Example usage with patched dropwatch [1] can be found here [2]. Example
dissection of drop monitor netlink events with patched wireshark [3] can
be found here [4]. I will submit both changes upstream after the kernel
changes are accepted.

Patches #1-#6 are just cleanups with no functional changes intended.

Patches #7-#8 perform small refactoring before the actual changes are
introduced in the last four patches.

[1] https://github.com/idosch/dropwatch/tree/packet-mode
[2] https://gist.github.com/idosch/7391b77da0b16182406189561fdfa1ef#file-gistfile1-txt
[3] https://github.com/idosch/wireshark/tree/drop-monitor
[4] https://gist.github.com/idosch/7391b77da0b16182406189561fdfa1ef#file-gistfile2-txt

Ido Schimmel (12):
  drop_monitor: Use correct error code
  drop_monitor: Rename and document scope of mutex
  drop_monitor: Document scope of spinlock
  drop_monitor: Avoid multiple blank lines
  drop_monitor: Add extack support
  drop_monitor: Use pre_doit / post_doit hooks
  drop_monitor: Split tracing enable / disable to different functions
  drop_monitor: Initialize timer and work item upon tracing enable
  drop_monitor: Require CAP_NET_ADMIN for drop monitor configuration
  drop_monitor: Add packet alert mode
  drop_monitor: Allow truncation of dropped packets
  drop_monitor: Add a command to query current configuration

 include/uapi/linux/net_dropmon.h |  33 +++
 net/core/drop_monitor.c          | 492 ++++++++++++++++++++++++++++---
 2 files changed, 478 insertions(+), 47 deletions(-)

-- 
2.21.0


             reply	other threads:[~2019-07-22 18:33 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-22 18:31 Ido Schimmel [this message]
2019-07-22 18:31 ` [RFC PATCH net-next 01/12] drop_monitor: Use correct error code Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 02/12] drop_monitor: Rename and document scope of mutex Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 03/12] drop_monitor: Document scope of spinlock Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 04/12] drop_monitor: Avoid multiple blank lines Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 05/12] drop_monitor: Add extack support Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 06/12] drop_monitor: Use pre_doit / post_doit hooks Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 07/12] drop_monitor: Split tracing enable / disable to different functions Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 08/12] drop_monitor: Initialize timer and work item upon tracing enable Ido Schimmel
2019-07-24  9:01   ` Jiri Pirko
2019-07-24 17:02     ` Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 09/12] drop_monitor: Require CAP_NET_ADMIN for drop monitor configuration Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 10/12] drop_monitor: Add packet alert mode Ido Schimmel
2019-07-23 12:43   ` Neil Horman
2019-07-23 14:16     ` Ido Schimmel
2019-07-23 15:14       ` Neil Horman
2019-07-24  7:10         ` Ido Schimmel
2019-07-24 12:53   ` Jiri Pirko
2019-07-24 16:57     ` Ido Schimmel
2019-07-29  9:52   ` [drop_monitor] 98ffbd6cd2: will-it-scale.per_thread_ops -17.5% regression kernel test robot
2019-08-05 11:56     ` Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 11/12] drop_monitor: Allow truncation of dropped packets Ido Schimmel
     [not found]   ` <20190724125537.GC2225@nanopsycho>
2019-07-24 16:49     ` Ido Schimmel
2019-07-22 18:31 ` [RFC PATCH net-next 12/12] drop_monitor: Add a command to query current configuration Ido Schimmel
2019-07-22 19:43 ` [RFC PATCH net-next 00/12] drop_monitor: Capture dropped packets and metadata Toke Høiland-Jørgensen
2019-07-23  6:46   ` Ido Schimmel
2019-07-23 12:17     ` Toke Høiland-Jørgensen
2019-07-23 15:14       ` Ido Schimmel
2019-07-23 15:47         ` David Ahern
2019-07-24  7:57           ` Ido Schimmel
2019-07-23 16:08         ` Toke Høiland-Jørgensen
2019-07-24  8:10           ` Ido Schimmel
2019-07-24  9:51             ` Toke Høiland-Jørgensen
2019-07-24 12:58         ` Jiri Pirko
2019-07-24 16:48           ` Ido Schimmel
2019-07-24 22:48   ` David Miller
2019-07-24 15:15 ` Jiri Pirko

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=20190722183134.14516-1-idosch@idosch.org \
    --to=idosch@idosch.org \
    --cc=andrew@lunn.ch \
    --cc=andy@greyhouse.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@gmail.com \
    --cc=f.fainelli@gmail.com \
    --cc=idosch@mellanox.com \
    --cc=jakub.kicinski@netronome.com \
    --cc=mlxsw@mellanox.com \
    --cc=netdev@vger.kernel.org \
    --cc=nhorman@tuxdriver.com \
    --cc=nikolay@cumulusnetworks.com \
    --cc=roopa@cumulusnetworks.com \
    --cc=toke@redhat.com \
    --cc=vivien.didelot@gmail.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).