From: Michal Jastrzebski <michalx.k.jastrzebski@intel.com>
To: dev@dpdk.org
Subject: [dpdk-dev] [PATCH v6 0/2] bond: mode 4 support
Date: Wed, 26 Nov 2014 11:17:21 +0000 [thread overview]
Message-ID: <1417000643-26885-1-git-send-email-michalx.k.jastrzebski@intel.com> (raw)
v6 changes
- add commit log description to link bondig mode 4
v5 changes
- fix compilation errors when CONFIG_RTE_LIBRTE_PMD_BOND=n
v4 changes:
- fix compilation error when building without mbuf refcnt
- testpmd: add slave state information in "show bonding config X" command
- change patch dependency to Declan Doherty v6
v3 changes:
This is a rework of previous patchset. Basic functionality is the same but
contain following changes:
- use one global array of slaves instead separate instance for every bonded
device (reduce memory usage). This also allow use of port id instead of
offsetting to current active slaves.
- make mode 4 immune to partner timings standard violation.
- fix possible buffer overflow in RX function if caller provide buffer
that is less than received packets (additional slow packets).
- change/fix promiscus mode and MAC management.
- fix compiling issues on gcc version less than 4.5
- bring API for tunig mode 4 parameters and expose mode 4 frames structure.
- prevent console flood with warning messages if mode 4 RX/TX buffers are full.
test-pmd:
- add mode 4 support (force periodic TX if no packets received during 100ms
period). Some forwardning modes (ex. rx only) does not allow mode 4 usage.
- 'port start X' - check if X is valid value
v2 changes:
New version handles race issues with setting/cancelin callbacks,
fixes promiscus mode setting in mode 4 and some other minor errors in mode 4
implementation.
changes not related to mode 4:
- fix memcpy() usage in bond_ethdev_tx_burst_balance() (OOM/undfined behaviour
if TX burst fail)
This patch set add support for dynamic link aggregation (mode 4) to the
librte_pmd_bond library. This mode provides auto negotiation/configuration
of peers and well as link status changes monitoring using out of band
LACP (link aggregation control protocol) messages. For further details of
LACP specification see the IEEE 802.3ad/802.1AX standards. It is also
described here
https://www.kernel.org/doc/Documentation/networking/bonding.txt.
In this implementation we have an array of mode 4 settings for each slave.
There is also assumption that for every port is one aggregator (it might
be unused if better is found).
Difference in this implementation vs Linux implementation:
- this implementation it is not directly based on state machines but current
state is calculated from actor and partner states (and other things too).
Some implementation details:
- during rx burst every packet Is checked if this is LACP or marker packet.
If it is LACP frame it is passed to mode 4 logic using slaves rx ring and
removed from rx buffer before it is returned
- in tx burst, packets from mode 4 (if any) are injected into each slave.
- there is a timer running in background to process/produce mode 4
frames form rx/to tx functions.
Some requirements for this mode:
- for LACP mode to work rx and tx burst functions must be invoked
at least in 100ms intervals (testpmd modified to satisfy this requirement)
- provided buffer to rx burst should be at least 2x slave count size. This is
not needed but might increase performance especially during initial
handshake.
Pawel Wodkowski (2):
bond: add mode 4 support v6
testpmd: add mode 4 support v6
app/test-pmd/cmdline.c | 28 +-
app/test-pmd/csumonly.c | 9 +
app/test-pmd/icmpecho.c | 21 +-
app/test-pmd/iofwd.c | 9 +
app/test-pmd/macfwd-retry.c | 9 +
app/test-pmd/macfwd.c | 9 +
app/test-pmd/macswap.c | 9 +
app/test-pmd/testpmd.c | 50 +-
app/test-pmd/testpmd.h | 11 +-
lib/librte_ether/rte_ether.h | 1 +
lib/librte_pmd_bond/Makefile | 2 +
lib/librte_pmd_bond/rte_eth_bond.h | 5 +
lib/librte_pmd_bond/rte_eth_bond_8023ad.c | 1216 +++++++++++++++++++++
lib/librte_pmd_bond/rte_eth_bond_8023ad.h | 214 ++++
lib/librte_pmd_bond/rte_eth_bond_8023ad_private.h | 308 ++++++
lib/librte_pmd_bond/rte_eth_bond_api.c | 91 +-
lib/librte_pmd_bond/rte_eth_bond_args.c | 1 +
lib/librte_pmd_bond/rte_eth_bond_pmd.c | 262 ++++-
lib/librte_pmd_bond/rte_eth_bond_private.h | 31 +-
19 files changed, 2227 insertions(+), 59 deletions(-)
create mode 100644 lib/librte_pmd_bond/rte_eth_bond_8023ad.c
create mode 100644 lib/librte_pmd_bond/rte_eth_bond_8023ad.h
create mode 100644 lib/librte_pmd_bond/rte_eth_bond_8023ad_private.h
--
1.7.9.5
next reply other threads:[~2014-11-26 11:06 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-11-26 11:17 Michal Jastrzebski [this message]
2014-11-26 11:17 ` [dpdk-dev] [PATCH v6 1/2] bond: add mode 4 support v6 Michal Jastrzebski
2014-11-26 11:17 ` [dpdk-dev] [PATCH v6 2/2] testpmd: " Michal Jastrzebski
2014-11-26 12:31 ` Thomas Monjalon
2014-11-26 13:00 ` Wodkowski, PawelX
2014-11-26 13:30 ` Thomas Monjalon
2014-11-26 14:05 ` Jastrzebski, MichalX K
2014-11-26 12:16 ` [dpdk-dev] [PATCH v6 0/2] bond: mode 4 support Thomas Monjalon
2014-11-26 12:24 ` Jastrzebski, MichalX K
2014-11-26 12:27 ` Thomas Monjalon
2014-11-26 13:29 ` Jastrzebski, MichalX K
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=1417000643-26885-1-git-send-email-michalx.k.jastrzebski@intel.com \
--to=michalx.k.jastrzebski@intel.com \
--cc=dev@dpdk.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).