Files
kv/tests/integration/psync2-master-restart.tcl
zeekay 5b2e5fe98e fix: revert the -X ours upstream merge, which left the tree uncompilable
`merge: upstream/unstable (-X ours, brand preserved)` resolved every conflicting
hunk in our favour. That is right for brand strings and wrong for code: it kept
our old server.h beside their new module.c, so module.c calls
commandResultSuccessListeners and reads from_call_argv off a struct that has
neither, and zslFreeLexRange lost the declarations it still has call sites for.
kvReaderFeed got a newer body calling kvReaderGetReadBuf/CommitRead grafted onto
older locals — an sds newbuf and an oom: label the new body never uses. Across
398 files nothing downstream noticed, because main has not compiled since.

That is what the Dockerfile was working around. Pulling valkey/valkey and copying
binaries out of it produced an image no matter what the source did, so a tree
that cannot build looked like a tree that builds. Now the image compiles this
source, so the build breaking is visible the moment it breaks.

src, deps and tests return to the last coherent commit. Carried forward on top:

  - Two identical rdbIsVersionAccepted definitions, differing only in a
    parameter name. The rename pass copied the function instead of editing it,
    so this never compiled either.
  - kv_strtod.h lost the #ifdef USE_FAST_FLOAT that separated its two
    implementations, leaving both definitions and a stray #endif.
  - extended-redis-compatibility is deleted, not defaulted off. It made the
    server answer HELLO with "redis" and name itself Redis in five error
    strings. A server that can be configured to lie about what it is has one
    setting too many. HELLO now reports kv unconditionally.
  - The redis-server and redis-cli install symlinks, on by default via
    USE_REDIS_SYMLINKS?=yes. This is why a running instance answered to
    redis-cli at all.
  - valkeymodule.h and redismodule.h, 3094 lines of adapters mapping old
    prefixes onto KVMODULE_*, included by nothing. kvmodule.h is the header.
  - deps/libvalkey, one documentation file the rename stranded.

Wire contract is untouched. INFO still reports redis_version, redis_git_sha1,
redis_git_dirty and redis_build_id, and the Lua sandbox still exports
REDIS_VERSION — clients parse those field names, so they are protocol, not
branding. What we choose is what the server calls itself, and it calls itself kv.

Verified: builds clean, and a live instance answers HELLO with "server kv",
reports server_name:kv, has no extended-redis-compatibility directive, and
serves strings and lists.
2026-07-26 15:04:44 -07:00

225 lines
8.6 KiB
Tcl

start_server {tags {"psync2 external:skip"}} {
start_server {} {
start_server {} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
set replica [srv -1 client]
set replica_host [srv -1 host]
set replica_port [srv -1 port]
set sub_replica [srv -2 client]
# Make sure the server saves an RDB on shutdown
$master config set save "3600 1"
# Because we will test partial resync later, we don't want a timeout to cause
# the master-replica disconnect, then the extra reconnections will break the
# sync_partial_ok stat test
$master config set repl-timeout 3600
$replica config set repl-timeout 3600
$sub_replica config set repl-timeout 3600
# Avoid PINGs
$master config set repl-ping-replica-period 3600
$master config rewrite
# Build replication chain
$replica replicaof $master_host $master_port
$sub_replica replicaof $replica_host $replica_port
wait_for_condition 50 100 {
[status $replica master_link_status] eq {up} &&
[status $sub_replica master_link_status] eq {up}
} else {
fail "Replication not started."
}
test "PSYNC2: Partial resync after Master restart using RDB aux fields when offset is 0" {
assert {[status $master master_repl_offset] == 0}
set replid [status $master master_replid]
$replica config resetstat
catch {
restart_server 0 true false true now
set master [srv 0 client]
}
wait_for_condition 50 1000 {
[status $replica master_link_status] eq {up} &&
[status $sub_replica master_link_status] eq {up}
} else {
fail "Replicas didn't sync after master restart"
}
# Make sure master restore replication info correctly
assert {[status $master master_replid] != $replid}
assert {[status $master master_repl_offset] == 0}
assert {[status $master master_replid2] eq $replid}
assert {[status $master second_repl_offset] == 1}
# Make sure master set replication backlog correctly
assert {[status $master repl_backlog_active] == 1}
assert {[status $master repl_backlog_first_byte_offset] == 1}
assert {[status $master repl_backlog_histlen] == 0}
# Partial resync after Master restart
assert {[status $master sync_partial_ok] == 1}
assert {[status $replica sync_partial_ok] == 1}
}
# Generate some data
createComplexDataset $master 1000
test "PSYNC2: Partial resync after Master restart using RDB aux fields with data" {
wait_for_condition 500 100 {
[status $master master_repl_offset] == [status $replica master_repl_offset] &&
[status $master master_repl_offset] == [status $sub_replica master_repl_offset]
} else {
fail "Replicas and master offsets were unable to match *exactly*."
}
set replid [status $master master_replid]
set offset [status $master master_repl_offset]
$replica config resetstat
catch {
# SHUTDOWN NOW ensures master doesn't send GETACK to replicas before
# shutting down which would affect the replication offset.
restart_server 0 true false true now
set master [srv 0 client]
}
wait_for_condition 50 1000 {
[status $replica master_link_status] eq {up} &&
[status $sub_replica master_link_status] eq {up}
} else {
fail "Replicas didn't sync after master restart"
}
# Make sure master restore replication info correctly
assert {[status $master master_replid] != $replid}
assert {[status $master master_repl_offset] == $offset}
assert {[status $master master_replid2] eq $replid}
assert {[status $master second_repl_offset] == [expr $offset+1]}
# Make sure master set replication backlog correctly
assert {[status $master repl_backlog_active] == 1}
assert {[status $master repl_backlog_first_byte_offset] == [expr $offset+1]}
assert {[status $master repl_backlog_histlen] == 0}
# Partial resync after Master restart
assert {[status $master sync_partial_ok] == 1}
assert {[status $replica sync_partial_ok] == 1}
}
test "PSYNC2: Partial resync after Master restart using RDB aux fields with expire" {
$master debug set-active-expire 0
for {set j 0} {$j < 1024} {incr j} {
$master select [expr $j%16]
$master set $j somevalue px 10
}
after 20
# Wait until master has received ACK from replica. If the master thinks
# that any replica is lagging when it shuts down, master would send
# GETACK to the replicas, affecting the replication offset.
set offset [status $master master_repl_offset]
wait_for_condition 500 100 {
[string match "*slave0:*,offset=$offset,*" [$master info replication]] &&
$offset == [status $replica master_repl_offset] &&
$offset == [status $sub_replica master_repl_offset]
} else {
show_cluster_status
fail "Replicas and master offsets were unable to match *exactly*."
}
set offset [status $master master_repl_offset]
$replica config resetstat
catch {
# Unlike the test above, here we use SIGTERM, which behaves
# differently compared to SHUTDOWN NOW if there are lagging
# replicas. This is just to increase coverage and let each test use
# a different shutdown approach. In this case there are no lagging
# replicas though.
restart_server 0 true false
set master [srv 0 client]
}
wait_for_condition 50 1000 {
[status $replica master_link_status] eq {up} &&
[status $sub_replica master_link_status] eq {up}
} else {
fail "Replicas didn't sync after master restart"
}
set expired_offset [status $master repl_backlog_histlen]
# Stale keys expired and master_repl_offset grows correctly
assert {[status $master rdb_last_load_keys_expired] == 1024}
assert {[status $master master_repl_offset] == [expr $offset+$expired_offset]}
# Partial resync after Master restart
assert {[status $master sync_partial_ok] == 1}
assert {[status $replica sync_partial_ok] == 1}
set digest [$master debug digest]
assert {$digest eq [$replica debug digest]}
assert {$digest eq [$sub_replica debug digest]}
}
test "PSYNC2: Full resync after Master restart when too many key expired" {
$master config set repl-backlog-size 16384
$master config rewrite
$master debug set-active-expire 0
# Make sure replication backlog is full and will be trimmed.
for {set j 0} {$j < 2048} {incr j} {
$master select [expr $j%16]
$master set $j somevalue px 10
}
after 20
wait_for_condition 500 100 {
[status $master master_repl_offset] == [status $replica master_repl_offset] &&
[status $master master_repl_offset] == [status $sub_replica master_repl_offset]
} else {
fail "Replicas and master offsets were unable to match *exactly*."
}
$replica config resetstat
catch {
# Unlike the test above, here we use SIGTERM. This is just to
# increase coverage and let each test use a different shutdown
# approach.
restart_server 0 true false
set master [srv 0 client]
}
wait_for_condition 50 1000 {
[status $replica master_link_status] eq {up} &&
[status $sub_replica master_link_status] eq {up}
} else {
fail "Replicas didn't sync after master restart"
}
set dualchannel [lindex [r config get dual-channel-replication-enabled] 1]
set psync_count 0
if {$dualchannel == "yes"} {
# Expect one fake psync
set psync_count 1
}
# Replication backlog is full
assert {[status $master repl_backlog_first_byte_offset] > [status $master second_repl_offset]}
assert {[status $master sync_partial_ok] == $psync_count}
assert {[status $master sync_full] == 1}
assert {[status $master rdb_last_load_keys_expired] == 2048}
assert {[status $replica sync_full] == 1}
set digest [$master debug digest]
assert {$digest eq [$replica debug digest]}
assert {$digest eq [$sub_replica debug digest]}
}
}}}