From: Joe Damato <jdamato@fastly.com>
To: netdev@vger.kernel.org
Cc: mkarsten@uwaterloo.ca, kuba@kernel.org, skhawaja@google.com,
sdf@fomichev.me, bjorn@rivosinc.com, amritha.nambiar@intel.com,
sridhar.samudrala@intel.com, Joe Damato <jdamato@fastly.com>,
Alexander Lobakin <aleksander.lobakin@intel.com>,
Breno Leitao <leitao@debian.org>,
Daniel Jurgens <danielj@nvidia.com>,
David Ahern <dsahern@kernel.org>,
"David S. Miller" <davem@davemloft.net>,
Donald Hunter <donald.hunter@gmail.com>,
Eric Dumazet <edumazet@google.com>,
Jesper Dangaard Brouer <hawk@kernel.org>,
Jiri Pirko <jiri@resnulli.us>,
Johannes Berg <johannes.berg@intel.com>,
Jonathan Corbet <corbet@lwn.net>,
Kory Maincent <kory.maincent@bootlin.com>,
Leon Romanovsky <leon@kernel.org>,
linux-doc@vger.kernel.org (open list:DOCUMENTATION),
linux-kernel@vger.kernel.org (open list),
linux-rdma@vger.kernel.org (open list:MELLANOX MLX4 core VPI
driver), Lorenzo Bianconi <lorenzo@kernel.org>,
Michael Chan <michael.chan@broadcom.com>,
Paolo Abeni <pabeni@redhat.com>,
Saeed Mahameed <saeedm@nvidia.com>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Tariq Toukan <tariqt@nvidia.com>,
Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Subject: [RFC net-next v3 0/9] Add support for per-NAPI config via netlink
Date: Thu, 12 Sep 2024 10:07:08 +0000 [thread overview]
Message-ID: <20240912100738.16567-1-jdamato@fastly.com> (raw)
Greetings:
Welcome to RFC v3.
This implementation allocates an array of "struct napi_config" in
net_device and each NAPI instance is assigned an index into the config
array.
Per-NAPI settings like:
- NAPI ID
- gro_flush_timeout
- defer_hard_irqs
are persisted in napi_config and restored on napi_disable/napi_enable
respectively.
To help illustrate how this would end up working, I've added patches for
3 drivers, of which I have access to only 1:
- mlx5 which is the basis of the examples below
- mlx4 which has TX only NAPIs, just to highlight that case. I have
only compile tested this patch; I don't have this hardware.
- bnxt which I have only compiled tested. I don't have this
hardware.
NOTE: I only tested this on mlx5; I have no access to the other hardware
for which I provided patches. Hopefully other folks can help test :)
This iteration seems to persist NAPI IDs and settings even when resizing
queues, see below, so I think maybe this is getting close to where we
want to land?
Here's an example of how it works on my mlx5:
# start with 2 queues
$ ethtool -l eth4 | grep Combined | tail -1
Combined: 2
First, output the current NAPI settings:
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[{'defer-hard-irqs': 0,
'gro-flush-timeout': 0,
'id': 345,
'ifindex': 7,
'irq': 527},
{'defer-hard-irqs': 0,
'gro-flush-timeout': 0,
'id': 344,
'ifindex': 7,
'irq': 327}]
Now, set the global sysfs parameters:
$ sudo bash -c 'echo 20000 >/sys/class/net/eth4/gro_flush_timeout'
$ sudo bash -c 'echo 100 >/sys/class/net/eth4/napi_defer_hard_irqs'
Output current NAPI settings again:
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 345,
'ifindex': 7,
'irq': 527},
{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 344,
'ifindex': 7,
'irq': 327}]
Now set NAPI ID 345, via its NAPI ID to specific values:
$ sudo ./tools/net/ynl/cli.py \
--spec Documentation/netlink/specs/netdev.yaml \
--do napi-set \
--json='{"id": 345,
"defer-hard-irqs": 111,
"gro-flush-timeout": 11111}'
None
Now output current NAPI settings again to ensure only NAPI ID 345
changed:
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[{'defer-hard-irqs': 111,
'gro-flush-timeout': 11111,
'id': 345,
'ifindex': 7,
'irq': 527},
{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 344,
'ifindex': 7,
'irq': 327}]
Now, increase gro-flush-timeout only:
$ sudo ./tools/net/ynl/cli.py \
--spec Documentation/netlink/specs/netdev.yaml \
--do napi-set --json='{"id": 345,
"gro-flush-timeout": 44444}'
None
Now output the current NAPI settings once more:
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[{'defer-hard-irqs': 111,
'gro-flush-timeout': 44444,
'id': 345,
'ifindex': 7,
'irq': 527},
{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 344,
'ifindex': 7,
'irq': 327}]
Now set NAPI ID 345 to have gro_flush_timeout of 0:
$ sudo ./tools/net/ynl/cli.py \
--spec Documentation/netlink/specs/netdev.yaml \
--do napi-set --json='{"id": 345,
"gro-flush-timeout": 0}'
None
Check that NAPI ID 345 has a value of 0:
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[{'defer-hard-irqs': 111,
'gro-flush-timeout': 0,
'id': 345,
'ifindex': 7,
'irq': 527},
{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 344,
'ifindex': 7,
'irq': 327}]
Change the queue count, ensuring that NAPI ID 345 retains its settings:
$ sudo ethtool -L eth4 combined 4
Check that the new queues have the system wide settings but that NAPI ID
345 remains unchanged:
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 347,
'ifindex': 7,
'irq': 529},
{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 346,
'ifindex': 7,
'irq': 528},
{'defer-hard-irqs': 111,
'gro-flush-timeout': 0,
'id': 345,
'ifindex': 7,
'irq': 527},
{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 344,
'ifindex': 7,
'irq': 327}]
Now reduce the queue count below where NAPI ID 345 is indexed:
$ sudo ethtool -L eth4 combined 1
Check the output:
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 344,
'ifindex': 7,
'irq': 327}]
Re-increase the queue count to ensure NAPI ID 345 is re-assigned the same
values:
$ sudo ethtool -L eth4 combined 2
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[{'defer-hard-irqs': 111,
'gro-flush-timeout': 0,
'id': 345,
'ifindex': 7,
'irq': 527},
{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 344,
'ifindex': 7,
'irq': 327}]
Create new queues to ensure the sysfs globals are used for the new NAPIs
but that NAPI ID 345 is unchanged:
$ sudo ethtool -L eth4 comabined 8
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[...]
{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 346,
'ifindex': 7,
'irq': 528},
{'defer-hard-irqs': 111,
'gro-flush-timeout': 0,
'id': 345,
'ifindex': 7,
'irq': 527},
{'defer-hard-irqs': 100,
'gro-flush-timeout': 20000,
'id': 344,
'ifindex': 7,
'irq': 327}]
Last, but not least, let's try writing the sysfs parameters to ensure
all NAPIs are rewritten:
$ sudo bash -c 'echo 33333 >/sys/class/net/eth4/gro_flush_timeout'
$ sudo bash -c 'echo 222 >/sys/class/net/eth4/napi_defer_hard_irqs'
Check that worked:
$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump napi-get --json='{"ifindex": 7}'
[...]
{'defer-hard-irqs': 222,
'gro-flush-timeout': 33333,
'id': 346,
'ifindex': 7,
'irq': 528},
{'defer-hard-irqs': 222,
'gro-flush-timeout': 33333,
'id': 345,
'ifindex': 7,
'irq': 527},
{'defer-hard-irqs': 222,
'gro-flush-timeout': 33333,
'id': 344,
'ifindex': 7,
'irq': 327}]
Thanks,
Joe
rfcv3:
- Renamed napi_storage to napi_config
- Reordered patches
- Added defer_hard_irqs and gro_flush_timeout to napi_struct
- Attempt to save and restore settings on napi_disable/napi_enable
- Removed weight as a parameter to netif_napi_add_storage
- Updated driver patches to no longer pass in weight
rfcv2:
- Almost total rewrite from v1
Joe Damato (9):
net: napi: Make napi_defer_hard_irqs per-NAPI
netdev-genl: Dump napi_defer_hard_irqs
net: napi: Make gro_flush_timeout per-NAPI
netdev-genl: Dump gro_flush_timeout
net: napi: Add napi_config
netdev-genl: Support setting per-NAPI config values
bnxt: Add support for napi storage
mlx5: Add support for napi storage
mlx4: Add support for napi storage to RX CQs
Documentation/netlink/specs/netdev.yaml | 25 ++++++
.../networking/net_cachelines/net_device.rst | 5 +-
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +-
drivers/net/ethernet/mellanox/mlx4/en_cq.c | 3 +-
.../net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
include/linux/netdevice.h | 40 ++++++++-
include/uapi/linux/netdev.h | 3 +
net/core/dev.c | 90 +++++++++++++++----
net/core/dev.h | 87 ++++++++++++++++++
net/core/net-sysfs.c | 4 +-
net/core/netdev-genl-gen.c | 14 +++
net/core/netdev-genl-gen.h | 1 +
net/core/netdev-genl.c | 55 ++++++++++++
tools/include/uapi/linux/netdev.h | 3 +
14 files changed, 310 insertions(+), 25 deletions(-)
--
2.25.1
next reply other threads:[~2024-09-12 10:08 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-12 10:07 Joe Damato [this message]
2024-09-12 10:07 ` [RFC net-next v3 1/9] net: napi: Make napi_defer_hard_irqs per-NAPI Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 2/9] netdev-genl: Dump napi_defer_hard_irqs Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 3/9] net: napi: Make gro_flush_timeout per-NAPI Joe Damato
2024-09-15 5:30 ` kernel test robot
2024-09-12 10:07 ` [RFC net-next v3 4/9] netdev-genl: Dump gro_flush_timeout Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 5/9] net: napi: Add napi_config Joe Damato
2024-09-12 15:03 ` Joe Damato
2024-09-13 21:44 ` Willem de Bruijn
2024-09-13 22:10 ` Joe Damato
2024-09-13 17:42 ` Stanislav Fomichev
2024-09-13 18:55 ` Joe Damato
2024-09-13 19:39 ` Joe Damato
2024-09-14 13:00 ` Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 6/9] netdev-genl: Support setting per-NAPI config values Joe Damato
2024-09-12 10:38 ` Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 7/9] bnxt: Add support for napi storage Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 8/9] mlx5: " Joe Damato
2024-09-12 10:07 ` [RFC net-next v3 9/9] mlx4: Add support for napi storage to RX CQs Joe Damato
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=20240912100738.16567-1-jdamato@fastly.com \
--to=jdamato@fastly.com \
--cc=aleksander.lobakin@intel.com \
--cc=amritha.nambiar@intel.com \
--cc=bigeasy@linutronix.de \
--cc=bjorn@rivosinc.com \
--cc=corbet@lwn.net \
--cc=danielj@nvidia.com \
--cc=davem@davemloft.net \
--cc=donald.hunter@gmail.com \
--cc=dsahern@kernel.org \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=jiri@resnulli.us \
--cc=johannes.berg@intel.com \
--cc=kory.maincent@bootlin.com \
--cc=kuba@kernel.org \
--cc=leitao@debian.org \
--cc=leon@kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=lorenzo@kernel.org \
--cc=michael.chan@broadcom.com \
--cc=mkarsten@uwaterloo.ca \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=saeedm@nvidia.com \
--cc=sdf@fomichev.me \
--cc=skhawaja@google.com \
--cc=sridhar.samudrala@intel.com \
--cc=tariqt@nvidia.com \
--cc=xuanzhuo@linux.alibaba.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.