netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ido Schimmel <idosch@nvidia.com>
To: <netdev@vger.kernel.org>
Cc: <davem@davemloft.net>, <kuba@kernel.org>, <pabeni@redhat.com>,
	<edumazet@google.com>, <andrew+netdev@lunn.ch>,
	<horms@kernel.org>, <petrm@nvidia.com>, <razor@blackwall.org>,
	Ido Schimmel <idosch@nvidia.com>
Subject: [PATCH net-next 00/15] vxlan: Convert FDB table to rhashtable
Date: Tue, 15 Apr 2025 15:11:28 +0300	[thread overview]
Message-ID: <20250415121143.345227-1-idosch@nvidia.com> (raw)

The VXLAN driver currently stores FDB entries in a hash table with a
fixed number of buckets (256), resulting in reduced performance as the
number of entries grows. This patchset solves the issue by converting
the driver to use rhashtable which maintains a more or less constant
performance regardless of the number of entries.

Measured transmitted packets per second using a single pktgen thread
with varying number of entries when the transmitted packet always hits
the default entry (worst case):

Number of entries | Improvement
------------------|------------
1k                | +1.12%
4k                | +9.22%
16k               | +55%
64k               | +585%
256k              | +2460%

The first patches are preparations for the conversion in the last patch.
Specifically, the series is structured as follows:

Patch #1 adds RCU read-side critical sections in the Tx path when
accessing FDB entries. Targeting at net-next as I am not aware of any
issues due to this omission despite the code being structured that way
for a long time. Without it, traces will be generated when converting
FDB lookup to rhashtable_lookup().

Patch #2-#5 simplify the creation of the default FDB entry (all-zeroes).
Current code assumes that insertion into the hash table cannot fail,
which will no longer be true with rhashtable.

Patches #6-#10 add FDB entries to a linked list for entry traversal
instead of traversing over them using the fixed size hash table which is
removed in the last patch.

Patches #11-#12 add wrappers for FDB lookup that make it clear when each
should be used along with lockdep annotations. Needed as a preparation
for rhashtable_lookup() that must be called from an RCU read-side
critical section.

Patch #13 treats dst cache initialization errors as non-fatal. See more
info in the commit message. The current code happens to work because
insertion into the fixed size hash table is slow enough for the per-CPU
allocator to be able to create new chunks of per-CPU memory.

Patch #14 adds an FDB key structure that includes the MAC address and
source VNI. To be used as rhashtable key.

Patch #15 does the conversion to rhashtable.

Ido Schimmel (15):
  vxlan: Add RCU read-side critical sections in the Tx path
  vxlan: Simplify creation of default FDB entry
  vxlan: Insert FDB into hash table in vxlan_fdb_create()
  vxlan: Unsplit default FDB entry creation and notification
  vxlan: Relocate assignment of default remote device
  vxlan: Use a single lock to protect the FDB table
  vxlan: Add a linked list of FDB entries
  vxlan: Use linked list to traverse FDB entries
  vxlan: Convert FDB garbage collection to RCU
  vxlan: Convert FDB flushing to RCU
  vxlan: Rename FDB Tx lookup function
  vxlan: Create wrappers for FDB lookup
  vxlan: Do not treat dst cache initialization errors as fatal
  vxlan: Introduce FDB key structure
  vxlan: Convert FDB table to rhashtable

 drivers/net/vxlan/vxlan_core.c      | 542 ++++++++++++----------------
 drivers/net/vxlan/vxlan_private.h   |  11 +-
 drivers/net/vxlan/vxlan_vnifilter.c |   8 +-
 include/net/vxlan.h                 |   5 +-
 4 files changed, 248 insertions(+), 318 deletions(-)

-- 
2.49.0


             reply	other threads:[~2025-04-15 12:12 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-15 12:11 Ido Schimmel [this message]
2025-04-15 12:11 ` [PATCH net-next 01/15] vxlan: Add RCU read-side critical sections in the Tx path Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 02/15] vxlan: Simplify creation of default FDB entry Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 03/15] vxlan: Insert FDB into hash table in vxlan_fdb_create() Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 04/15] vxlan: Unsplit default FDB entry creation and notification Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 05/15] vxlan: Relocate assignment of default remote device Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 06/15] vxlan: Use a single lock to protect the FDB table Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 07/15] vxlan: Add a linked list of FDB entries Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 08/15] vxlan: Use linked list to traverse " Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 09/15] vxlan: Convert FDB garbage collection to RCU Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 10/15] vxlan: Convert FDB flushing " Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 11/15] vxlan: Rename FDB Tx lookup function Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 12/15] vxlan: Create wrappers for FDB lookup Ido Schimmel
2025-04-22  8:46   ` Paolo Abeni
2025-04-23 12:21     ` Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 13/15] vxlan: Do not treat dst cache initialization errors as fatal Ido Schimmel
2025-04-22  8:49   ` Paolo Abeni
2025-04-24  8:18     ` Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 14/15] vxlan: Introduce FDB key structure Ido Schimmel
2025-04-15 12:11 ` [PATCH net-next 15/15] vxlan: Convert FDB table to rhashtable Ido Schimmel
2025-04-15 14:15 ` [PATCH net-next 00/15] " Nikolay Aleksandrov
2025-04-22  9:38 ` patchwork-bot+netdevbpf

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=20250415121143.345227-1-idosch@nvidia.com \
    --to=idosch@nvidia.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=horms@kernel.org \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=petrm@nvidia.com \
    --cc=razor@blackwall.org \
    /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).