From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from localhost (localhost [127.0.0.1]) by turing.freelists.org (Avenir Technologies Mail Multiplex) with ESMTP id 4471E23F13 for ; Fri, 5 Jul 2019 18:43:43 -0400 (EDT) Received: from turing.freelists.org ([127.0.0.1]) by localhost (turing.freelists.org [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id YjbJDSRGFIgN for ; Fri, 5 Jul 2019 18:43:43 -0400 (EDT) Received: from smtp48.i.mail.ru (smtp48.i.mail.ru [94.100.177.108]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by turing.freelists.org (Avenir Technologies Mail Multiplex) with ESMTPS id F0A2B2325F for ; Fri, 5 Jul 2019 18:43:42 -0400 (EDT) Subject: [tarantool-patches] Re: [PATCH 0/5] SWIM loglog preparation From: Vladislav Shpilevoy References: Message-ID: <98e70beb-ae3f-c42b-ecc4-cffe8f63f247@tarantool.org> Date: Sat, 6 Jul 2019 00:44:52 +0200 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit Sender: tarantool-patches-bounce@freelists.org Errors-to: tarantool-patches-bounce@freelists.org Reply-To: tarantool-patches@freelists.org List-Help: List-Unsubscribe: List-software: Ecartis version 1.0.0 List-Id: tarantool-patches List-Subscribe: List-Owner: List-post: List-Archive: To: tarantool-patches@freelists.org Cc: kostja@tarantool.org Pushed to the master. On 04/07/2019 01:28, Vladislav Shpilevoy wrote: > The patchset prepares ground for a new SWIM's killer feature - > O(log(log(cluster_size))) full dissemination time. > > Most of the commits are quite obvious, see their commit messages. > > The last two ones could look strange. I've the final loglog commit on another > branch, and it slows down the SWIM tests in 2-3 times just spending much and > much more time on checking and decoding MessagePack in the padded out messages. > According to the profiler, most of the time is spent in mp_decode/check_uint, > when I use Debug build. > > The last two commits compensate that problem, making the tests perhaps even > faster than before the whole 4253. Especially the last one. See their messages > for details. > > Branch: http://github.com/tarantool/tarantool/tree/gerold103/gh-4253-loglog-preparation > Issue: https://github.com/tarantool/tarantool/issues/4253 > > Vladislav Shpilevoy (5): > swim: fix flaky 'indirect pings' test > swim: sadly remove cache > test: redo some swim tests using error injections > swim: speed-up tests > swim: speed-up empty payloads cluster bootstrap > > src/lib/core/errinj.h | 1 + > src/lib/swim/swim.c | 53 ++++------ > test/swim/errinj.result | 102 ++++++++++++++++++ > test/swim/errinj.test.lua | 41 ++++++++ > test/swim/suite.ini | 1 + > test/swim/swim.result | 55 ---------- > test/swim/swim.test.lua | 22 ---- > test/unit/CMakeLists.txt | 5 + > test/unit/suite.ini | 1 + > test/unit/swim.c | 197 ++-------------------------------- > test/unit/swim.result | 31 ++---- > test/unit/swim_errinj.c | 199 +++++++++++++++++++++++++++++++++++ > test/unit/swim_errinj.result | 18 ++++ > test/unit/swim_test_utils.c | 102 ++++++------------ > test/unit/swim_test_utils.h | 24 +++-- > 15 files changed, 456 insertions(+), 396 deletions(-) > create mode 100644 test/swim/errinj.result > create mode 100644 test/swim/errinj.test.lua > create mode 100644 test/unit/swim_errinj.c > create mode 100644 test/unit/swim_errinj.result >