redict/tests/integration/replication-2.tcl
Oran Agra 997fa41e99
Attempt to solve MacOS CI issues in GH Actions (#12013)
The MacOS CI in github actions often hangs without any logs. GH argues that
it's due to resource utilization, either running out of disk space, memory, or CPU
starvation, and thus the runner is terminated.

This PR contains multiple attempts to resolve this:
1. introducing pause_process instead of SIGSTOP, which waits for the process
  to stop before resuming the test, possibly resolving race conditions in some tests,
  this was a suspect since there was one test that could result in an infinite loop in that
 case, in practice this didn't help, but still a good idea to keep.
2. disable the `save` config in many tests that don't need it, specifically ones that use
  heavy writes and could create large files.
3. change the `populate` proc to use short pipeline rather than an infinite one.
4. use `--clients 1` in the macos CI so that we don't risk running multiple resource
  demanding tests in parallel.
5. enable `--verbose` to be repeated to elevate verbosity and print more info to stdout
  when a test or a server starts.
2023-04-12 09:19:21 +03:00

94 lines
3.3 KiB
Tcl

start_server {tags {"repl external:skip"}} {
start_server {} {
test {First server should have role slave after SLAVEOF} {
r -1 slaveof [srv 0 host] [srv 0 port]
wait_replica_online r
wait_for_condition 50 100 {
[s -1 master_link_status] eq {up}
} else {
fail "Replication not started."
}
}
test {If min-slaves-to-write is honored, write is accepted} {
r config set min-slaves-to-write 1
r config set min-slaves-max-lag 10
r set foo 12345
wait_for_condition 50 100 {
[r -1 get foo] eq {12345}
} else {
fail "Write did not reached replica"
}
}
test {No write if min-slaves-to-write is < attached slaves} {
r config set min-slaves-to-write 2
r config set min-slaves-max-lag 10
catch {r set foo 12345} err
set err
} {NOREPLICAS*}
test {If min-slaves-to-write is honored, write is accepted (again)} {
r config set min-slaves-to-write 1
r config set min-slaves-max-lag 10
r set foo 12345
wait_for_condition 50 100 {
[r -1 get foo] eq {12345}
} else {
fail "Write did not reached replica"
}
}
test {No write if min-slaves-max-lag is > of the slave lag} {
r config set min-slaves-to-write 1
r config set min-slaves-max-lag 2
pause_process [srv -1 pid]
assert {[r set foo 12345] eq {OK}}
wait_for_condition 100 100 {
[catch {r set foo 12345}] != 0
} else {
fail "Master didn't become readonly"
}
catch {r set foo 12345} err
assert_match {NOREPLICAS*} $err
}
resume_process [srv -1 pid]
test {min-slaves-to-write is ignored by slaves} {
r config set min-slaves-to-write 1
r config set min-slaves-max-lag 10
r -1 config set min-slaves-to-write 1
r -1 config set min-slaves-max-lag 10
r set foo aaabbb
wait_for_condition 50 100 {
[r -1 get foo] eq {aaabbb}
} else {
fail "Write did not reached replica"
}
}
# Fix parameters for the next test to work
r config set min-slaves-to-write 0
r -1 config set min-slaves-to-write 0
r flushall
test {MASTER and SLAVE dataset should be identical after complex ops} {
createComplexDataset r 10000
after 500
if {[r debug digest] ne [r -1 debug digest]} {
set csv1 [csvdump r]
set csv2 [csvdump {r -1}]
set fd [open /tmp/repldump1.txt w]
puts -nonewline $fd $csv1
close $fd
set fd [open /tmp/repldump2.txt w]
puts -nonewline $fd $csv2
close $fd
puts "Master - Replica inconsistency"
puts "Run diff -u against /tmp/repldump*.txt for more info"
}
assert_equal [r debug digest] [r -1 debug digest]
}
}
}