[Tarantool-patches] [PATCH 2/2] test: stabilize quorum test conditions

[Vladislav Shpilevoy]

Hm. So you are not going to fix the flaky error I mentioned
in the previous thread about this commit?

Seems like it is also about 'conditions which need time to be
satisfied'.

On 20/11/2019 23:47, Ilya Kosarev wrote:
> There were some pass conditions in quorum test which could take some
> time to be satisfied. Now they are wrapped using test_run:wait_cond to
> make the test stable.
> 
> Part of #4586
> ---
>  test/replication/quorum.result   | 30 +++++++++++++++++-------------
>  test/replication/quorum.test.lua | 18 +++++++++---------
>  2 files changed, 26 insertions(+), 22 deletions(-)
> 
> diff --git a/test/replication/quorum.result b/test/replication/quorum.result
> index ff5fa0150..12604c8de 100644
> --- a/test/replication/quorum.result
> +++ b/test/replication/quorum.result
> @@ -115,15 +115,15 @@ box.info.status -- running
>  - running
>  ...
>  -- Check that the replica follows all masters.
> -box.info.id == 1 or box.info.replication[1].upstream.status == 'follow'
> +box.info.id == 1 or test_run:wait_cond(function() return box.info.replication[1].upstream.status == 'follow' end, 20)
>  ---
>  - true
>  ...
> -box.info.id == 2 or box.info.replication[2].upstream.status == 'follow'
> +box.info.id == 2 or test_run:wait_cond(function() return box.info.replication[2].upstream.status == 'follow' end, 20)
>  ---
>  - true
>  ...
> -box.info.id == 3 or box.info.replication[3].upstream.status == 'follow'
> +box.info.id == 3 or test_run:wait_cond(function() return box.info.replication[3].upstream.status == 'follow' end, 20)
>  ---
>  - true
>  ...
> @@ -149,6 +149,10 @@ test_run:cmd('stop server quorum1')
>  ---
>  - true
>  ...
> +test_run:wait_cond(function() return box.space.test.index.primary ~= nil end, 20)
> +---
> +- true
> +...
>  for i = 1, 100 do box.space.test:insert{i} end
>  ---
>  ...
> @@ -166,9 +170,9 @@ test_run:cmd('switch quorum1')
>  ---
>  - true
>  ...
> -box.space.test:count() -- 100
> +test_run:wait_cond(function() return box.space.test:count() == 100 end, 20)
>  ---
> -- 100
> +- true
>  ...
>  -- Rebootstrap one node of the cluster and check that others follow.
>  -- Note, due to ERRINJ_RELAY_TIMEOUT there is a substantial delay
> @@ -197,9 +201,9 @@ test_run:cmd('switch quorum1')
>  - true
>  ...
>  test_run:cmd('restart server quorum1 with cleanup=1, args="0.1 0.5"')
> -box.space.test:count() -- 100
> +test_run:wait_cond(function() return box.space.test:count() == 100 end, 20)
>  ---
> -- 100
> +- true
>  ...
>  -- The rebootstrapped replica will be assigned id = 4,
>  -- because ids 1..3 are busy.
> @@ -207,11 +211,9 @@ test_run:cmd('switch quorum2')
>  ---
>  - true
>  ...
> -fiber = require('fiber')
> ----
> -...
> -while box.info.replication[4].upstream.status ~= 'follow' do fiber.sleep(0.001) end
> +test_run:wait_cond(function() return box.info.replication[4].upstream.status == 'follow' end, 20)
>  ---
> +- true
>  ...
>  box.info.replication[4].upstream.status
>  ---
> @@ -221,11 +223,13 @@ test_run:cmd('switch quorum3')
>  ---
>  - true
>  ...
> -fiber = require('fiber')
> +test_run:wait_cond(function() return box.info.replication ~= nil end, 20)
>  ---
> +- true
>  ...
> -while box.info.replication[4].upstream.status ~= 'follow' do fiber.sleep(0.001) end
> +test_run:wait_cond(function() return box.info.replication[4].upstream.status == 'follow' end, 20)
>  ---
> +- true
>  ...
>  box.info.replication[4].upstream.status
>  ---
> diff --git a/test/replication/quorum.test.lua b/test/replication/quorum.test.lua
> index 98febb367..be23200d3 100644
> --- a/test/replication/quorum.test.lua
> +++ b/test/replication/quorum.test.lua
> @@ -47,9 +47,9 @@ box.info.ro -- false
>  box.info.status -- running
>  
>  -- Check that the replica follows all masters.
> -box.info.id == 1 or box.info.replication[1].upstream.status == 'follow'
> -box.info.id == 2 or box.info.replication[2].upstream.status == 'follow'
> -box.info.id == 3 or box.info.replication[3].upstream.status == 'follow'
> +box.info.id == 1 or test_run:wait_cond(function() return box.info.replication[1].upstream.status == 'follow' end, 20)
> +box.info.id == 2 or test_run:wait_cond(function() return box.info.replication[2].upstream.status == 'follow' end, 20)
> +box.info.id == 3 or test_run:wait_cond(function() return box.info.replication[3].upstream.status == 'follow' end, 20)
>  
>  -- Check that box.cfg() doesn't return until the instance
>  -- catches up with all configured replicas.
> @@ -59,13 +59,14 @@ test_run:cmd('switch quorum2')
>  box.error.injection.set("ERRINJ_RELAY_TIMEOUT", 0.001)
>  test_run:cmd('stop server quorum1')
>  
> +test_run:wait_cond(function() return box.space.test.index.primary ~= nil end, 20)
>  for i = 1, 100 do box.space.test:insert{i} end
>  fiber = require('fiber')
>  fiber.sleep(0.1)
>  
>  test_run:cmd('start server quorum1 with args="0.1  0.5"')
>  test_run:cmd('switch quorum1')
> -box.space.test:count() -- 100
> +test_run:wait_cond(function() return box.space.test:count() == 100 end, 20)
>  
>  -- Rebootstrap one node of the cluster and check that others follow.
>  -- Note, due to ERRINJ_RELAY_TIMEOUT there is a substantial delay
> @@ -81,17 +82,16 @@ box.snapshot()
>  test_run:cmd('switch quorum1')
>  test_run:cmd('restart server quorum1 with cleanup=1, args="0.1 0.5"')
>  
> -box.space.test:count() -- 100
> +test_run:wait_cond(function() return box.space.test:count() == 100 end, 20)
>  
>  -- The rebootstrapped replica will be assigned id = 4,
>  -- because ids 1..3 are busy.
>  test_run:cmd('switch quorum2')
> -fiber = require('fiber')
> -while box.info.replication[4].upstream.status ~= 'follow' do fiber.sleep(0.001) end
> +test_run:wait_cond(function() return box.info.replication[4].upstream.status == 'follow' end, 20)
>  box.info.replication[4].upstream.status
>  test_run:cmd('switch quorum3')
> -fiber = require('fiber')
> -while box.info.replication[4].upstream.status ~= 'follow' do fiber.sleep(0.001) end
> +test_run:wait_cond(function() return box.info.replication ~= nil end, 20)
> +test_run:wait_cond(function() return box.info.replication[4].upstream.status == 'follow' end, 20)
>  box.info.replication[4].upstream.status
>  
>  -- Cleanup.
>