Devel

devel@lists.kronosnet.org

47 discussions

compression plugin compress level validation

by Fabio M. Di Nitto

Hey guys, original discussion started here (for reference): https://github.com/kronosnet/kronosnet/pull/128 int knet_handle_compress(knet_handle_t knet_h, struct knet_handle_compress_cfg *knet_handle_compress_cfg); Where knet_handle_compress_cfg contains int compress_level. As you can see from libknet.h and relative code, we try (too hard) to validate the values for compress_level. Feri had a proper concern about applying incorrect filtering and I agree that it is already becoming complex to maintain a matrix of valid values, per plugin, per plugin-version, and whatever combination. AFAIR all plugins accept an int value for compress_level so from that perspective it shouldn´t be too much of a problem (aka no API/ABI changes). Historically, the reason why I added the validation was lzo2, that presents a rather unusual compress configuration vs all other plugins (as you can see). I think Feri´s suggestion to drop the filter completely might be too much, instead, after thinking a bit, it might be perfectly reason to change the internals of val_level to try and compress a small buffer to test that the value is good. The val_level is used only at configuration time, so it´s not too expensive to compress one small data chunk for validation and it would remove the whole hardcoded filter of different compress_levels. For special plugins like lzo2, I think it´s important we improve the logging at configuration time to make sure users at least warned of supported values (as you can see each values map to a specific lzo2 API call to compress). wdyt? Fabio

6 years, 2 months

stable1 backporting process

by Fabio M. Di Nitto

All, experimenting a bit here. As you build PR for master, please do NOT create a new PR for stable1. Indicate if the commit qualifies for stable1 and if we all agree it should be backported, you can or we will cherry-pick the fix in stable1-proposed branched. there is a PR open to merge stable1-proposed that will keep running CI on each cherry-pick backport for now, and we feel the time is ready to cut 1.1, we will just merge that PR at once. Cheers Fabio

6 years, 3 months

kronosnet v1.0 released

by Fabio M. Di Nitto

All, We are pleased to announce the general availability of kronosnet v1.0 kronosnet (or knet for short) is the new underlying network protocol for Linux HA components (corosync), that features ability to use multiple links between nodes, active/active and active/passive link failover policies, automatic link recovery, FIPS compliant encryption (nss and/or openssl), automatic PMTUd and in general better performances compared to the old network protocol. The source tarballs can be downloaded here: https://www.kronosnet.org/releases/ Upstream resources and contacts: https://kronosnet.org/ https://github.com/kronosnet/kronosnet/ https://ci.kronosnet.org/ https://trello.com/kronosnet (TODO list and activities tracking) https://goo.gl/9ZvkLS (google shared drive with presentations and diagrams) IRC: #kronosnet on Freenode https://lists.kronosnet.org/mailman/listinfo/users https://lists.kronosnet.org/mailman/listinfo/devel https://lists.kronosnet.org/mailman/listinfo/commits Known issues in this release: * Knet will fail to work on Fedora 26 arm when built with clang. This is a known issue with clang compiler that is fixed in more recent versions of clang. * Knet will fail to build with clang on rhel7 + epel version of clang. This is a known issue with clang compiler that is fixed in more recent versions of clang. * Running the knet test suite with valgrind (make check-memcheck) will fail with Debian Experimental glibc due to a known bug in valgrind. * Running the knet test suite with valgrind on FreeBSD is no longer supported. The valgrind version on FreeBSD is too old and generates too many false positives. Also, please refer to build-aux/check.mk on how to use valgrind in combination with knet. Some platforms requires extra options to work properly. * If you are planning to develop plugins, please be aware of this issue: https://github.com/kronosnet/kronosnet/issues/107 . It affects only development environments. Cheers, The knet developer team

6 years, 3 months

kronosnet v0.9 (aka 1.0 Release Candidate 1) released

by Fabio M. Di Nitto

All, We are pleased to announce the second public release candidate of kronosnet v1.0 - which we are calling v0.9 kronosnet (or knet for short) is the new underlying network protocol for Linux HA components (corosync), that features ability to use multiple links between nodes, active/active and active/passive link failover policies, automatic link recovery, FIPS compliant encryption (nss and/or openssl), automatic PMTUd and in general better performances compared to the old network protocol. The source tarballs can be downloaded here: https://www.kronosnet.org/releases/ Upstream resources and contacts: https://kronosnet.org/ https://github.com/kronosnet/kronosnet/ https://ci.kronosnet.org/ https://trello.com/kronosnet (TODO list and activities tracking) https://goo.gl/9ZvkLS (google shared drive with presentations and diagrams) IRC: #kronosnet on Freenode https://lists.kronosnet.org/mailman/listinfo/users https://lists.kronosnet.org/mailman/listinfo/devel https://lists.kronosnet.org/mailman/listinfo/commits Known issues in this release: * Knet will fail to work on Fedora 26 arm when built with clang. This is a known issue with clang compiler that is fixed in more recent versions of clang. * Knet will fail to build with clang on rhel7 + epel version of clang. This is a known issue with clang compiler that is fixed in more recent versions of clang. * Applications performing configuration changes might experience a long waiting time when calling into the knet API. This is a known interaction issue between the PMTUd thread inside knet and external API locking. https://trello.com/c/uPMjKRYy/847-fix-pmtud-locking-with-external-api * Running the knet test suite with valgrind (make check-memcheck) will fail with Debian Experimental glibc due to a known bug in valgrind. * Running the knet test suite with valgrind on FreeBSD is no longer supported. The valgrind version on FreeBSD is too old and generates too many false positives. Also, please refer to build-aux/check.mk on how to use valgrind in combination with knet. Some platforms requires extra options to work properly. Cheers, The knet developer team

6 years, 4 months

PMTUd remaining issues

by Fabio M. Di Nitto

Hey Chrissie, I am still having issues with the latest pmtu code: 1) using crypto, just with knet_bench ping_data test, the MTU changes on each run (I think you mentioned that on IRC, but not sure it's the same problem). 2) there is a spurious link down event on MTU change. I can reproduce this one without crypto and with ping_data test (I set it at 10 secs interval to avoid waiting minutes). Start knet_bench on both nodes with standard MTU at 1500. At the end of each run, change MTU on the interfaces to: - 1400 (good). - 1500 (good). - 1600 (good, mtu doesn't change) - back to 1500 (link down event) from time to time, the first MTU after the down/up event is wrong the code is stable on heavy load, I haven't tested yet load + changing MTU at runtime. I'll do that once the basic tests are passing. Cheers Fabio

6 years, 4 months

0.9 RC - merge freeze

by Fabio M. Di Nitto

Hi guys, we have one PR open (plugins/modules) and one bug fix (PMTUd) pending. We will complete the merge of both and we will not accept any more changes for 0.9 RC. Between 0.9 and 1.0 we will only accept critical bug fixes. Any other change is 2.0/1.1 material. Cheers Fabio

6 years, 4 months

plugin future (after 1.0)

by Fabio M. Di Nitto

Hey Feri, what do you think for a 1.1 or 2.0 feature: https://trello.com/c/nJLaEOMw/735-consider-to-develop-a-more-dynamic-plugin… Also, if you have a trello account, I'd be happy to add you there to better track who is working on what. Cheers Fabio

6 years, 4 months

Re: [kronosnet/kronosnet] a2f08e: Switch over all plugins to the module system

by Fabio M. Di Nitto

Hey Feri, let me stop you a minute here. what is the end goal of this work? We originally didn´t implement the modules model because it has several downsides for little benefit, based on the experience we had with corosync modules in the past. I think it might be beneficial to have a chat about those major changes before you implement them :-) I *hate* for people to waste time on stuff that might not merge. Cheers Fabio On 11/28/2017 8:07 AM, GitHub wrote: > Branch: refs/heads/modules > Home: https://github.com/kronosnet/kronosnet > Commit: a2f08e189c0143381f9f3ac5031d6b5dd32f5432 > https://github.com/kronosnet/kronosnet/commit/a2f08e189c0143381f9f3ac5031d6… > Author: Ferenc Wágner <wferi(a)debian.org> > Date: 2017-11-28 (Tue, 28 Nov 2017) >

6 years, 4 months

kronosnet v0.8 (aka 1.0 Beta) released

by Fabio M. Di Nitto

All, We are pleased to announce the first public beta of kronosnet v1.0 - which we are calling v0.8 (to make distro packager life a bit easier :-)) kronosnet (or knet for short) is the new underlying network protocol for Linux HA components (corosync), that features ability to use multiple links between nodes, active/active and active/passive link failover policies, automatic link recovery, FIPS compliant encryption (nss and/or openssl), automatic PMTUd and in general better performances compared to the old network protocol. The source tarballs can be downloaded here: http://www.kronosnet.org/releases/ Upstream resources and contacts: http://www.kronosnet.org/ https://github.com/kronosnet/kronosnet/ https://ci.kronosnet.org/ https://trello.com/kronosnet (TODO list and activities tracking) https://goo.gl/9ZvkLS (google shared drive with presentations and diagrams) IRC: #kronosnet on Freenode http://lists.kronosnet.org/mailman/listinfo/users http://lists.kronosnet.org/mailman/listinfo/devel http://lists.kronosnet.org/mailman/listinfo/commits Known issues in this release: * FreeBSD port currently does not work https://trello.com/c/fJSU31Fa/122-fix-port-to-freebsd * Missing developer documentation / best practice and .3 man pages https://trello.com/c/HxL2JIFI/32-add-documentation https://trello.com/c/d5nk9rLS/30-add-3-man-pages Cheers, The knet developer team

6 years, 5 months

[HA Summit 2017] follow up on questions after knet upstream presentation

by Fabio M. Di Nitto

Hey guys, as $subject, the only pending question that I was not able to answer directly during the presentation was: "why are knet is not using vxlan encapsulation?" Tl;dr: the vxlan and knet don't share the same use cases and vxlan is not completely fit for the HA use case. I spent some time looking at vxlan and wrote a small doc: https://docs.google.com/document/d/1fmMiIPYg01s1d8WbnKC51x2DvaBCKQB9g6p8gAp… please feel free to comment in the doc. Thanks Fabio

6 years, 7 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

Devel