redict/tests/unit/aofrw.tcl
sundb 2168ccc661
Add listpack encoding for list (#11303)
Improve memory efficiency of list keys

## Description of the feature
The new listpack encoding uses the old `list-max-listpack-size` config
to perform the conversion, which we can think it of as a node inside a
quicklist, but without 80 bytes overhead (internal fragmentation included)
of quicklist and quicklistNode structs.
For example, a list key with 5 items of 10 chars each, now takes 128 bytes
instead of 208 it used to take.

## Conversion rules
* Convert listpack to quicklist
  When the listpack length or size reaches the `list-max-listpack-size` limit,
  it will be converted to a quicklist.
* Convert quicklist to listpack
  When a quicklist has only one node, and its length or size is reduced to half
  of the `list-max-listpack-size` limit, it will be converted to a listpack.
  This is done to avoid frequent conversions when we add or remove at the bounding size or length.
    
## Interface changes
1. add list entry param to listTypeSetIteratorDirection
    When list encoding is listpack, `listTypeIterator->lpi` points to the next entry of current entry,
    so when changing the direction, we need to use the current node (listTypeEntry->p) to 
    update `listTypeIterator->lpi` to the next node in the reverse direction.

## Benchmark
### Listpack VS Quicklist with one node
* LPUSH - roughly 0.3% improvement
* LRANGE - roughly 13% improvement

### Both are quicklist
* LRANGE - roughly 3% improvement
* LRANGE without pipeline - roughly 3% improvement

From the benchmark, as we can see from the results
1. When list is quicklist encoding, LRANGE improves performance by <5%.
2. When list is listpack encoding, LRANGE improves performance by ~13%,
   the main enhancement is brought by `addListListpackRangeReply()`.

## Memory usage
1M lists(key:0~key:1000000) with 5 items of 10 chars ("hellohello") each.
shows memory usage down by 35.49%, from 214MB to 138MB.

## Note
1. Add conversion callback to support doing some work before conversion
    Since the quicklist iterator decompresses the current node when it is released, we can 
    no longer decompress the quicklist after we convert the list.
2022-11-16 20:29:46 +02:00

231 lines
7.8 KiB
Tcl

start_server {tags {"aofrw external:skip"}} {
# Enable the AOF
r config set appendonly yes
r config set auto-aof-rewrite-percentage 0 ; # Disable auto-rewrite.
waitForBgrewriteaof r
foreach rdbpre {yes no} {
r config set aof-use-rdb-preamble $rdbpre
test "AOF rewrite during write load: RDB preamble=$rdbpre" {
# Start a write load for 10 seconds
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
set load_handle0 [start_write_load $master_host $master_port 10]
set load_handle1 [start_write_load $master_host $master_port 10]
set load_handle2 [start_write_load $master_host $master_port 10]
set load_handle3 [start_write_load $master_host $master_port 10]
set load_handle4 [start_write_load $master_host $master_port 10]
# Make sure the instance is really receiving data
wait_for_condition 50 100 {
[r dbsize] > 0
} else {
fail "No write load detected."
}
# After 3 seconds, start a rewrite, while the write load is still
# active.
after 3000
r bgrewriteaof
waitForBgrewriteaof r
# Let it run a bit more so that we'll append some data to the new
# AOF.
after 1000
# Stop the processes generating the load if they are still active
stop_write_load $load_handle0
stop_write_load $load_handle1
stop_write_load $load_handle2
stop_write_load $load_handle3
stop_write_load $load_handle4
# Make sure no more commands processed, before taking debug digest
wait_load_handlers_disconnected
# Get the data set digest
set d1 [debug_digest]
# Load the AOF
r debug loadaof
set d2 [debug_digest]
# Make sure they are the same
assert {$d1 eq $d2}
}
}
}
start_server {tags {"aofrw external:skip"} overrides {aof-use-rdb-preamble no}} {
test {Turning off AOF kills the background writing child if any} {
r config set appendonly yes
waitForBgrewriteaof r
# start a slow AOFRW
r set k v
r config set rdb-key-save-delay 10000000
r bgrewriteaof
# disable AOF and wait for the child to be killed
r config set appendonly no
wait_for_condition 50 100 {
[string match {*Killing*AOF*child*} [exec tail -5 < [srv 0 stdout]]]
} else {
fail "Can't find 'Killing AOF child' into recent logs"
}
r config set rdb-key-save-delay 0
}
foreach d {string int} {
foreach e {listpack quicklist} {
test "AOF rewrite of list with $e encoding, $d data" {
r flushall
if {$e eq {listpack}} {
r config set list-max-listpack-size -2
set len 10
} else {
r config set list-max-listpack-size 10
set len 1000
}
for {set j 0} {$j < $len} {incr j} {
if {$d eq {string}} {
set data [randstring 0 16 alpha]
} else {
set data [randomInt 4000000000]
}
r lpush key $data
}
assert_equal [r object encoding key] $e
set d1 [debug_digest]
r bgrewriteaof
waitForBgrewriteaof r
r debug loadaof
set d2 [debug_digest]
if {$d1 ne $d2} {
error "assertion:$d1 is not equal to $d2"
}
}
}
}
foreach d {string int} {
foreach e {intset hashtable} {
test "AOF rewrite of set with $e encoding, $d data" {
r flushall
if {$e eq {intset}} {set len 10} else {set len 1000}
for {set j 0} {$j < $len} {incr j} {
if {$d eq {string}} {
set data [randstring 0 16 alpha]
} else {
set data [randomInt 4000000000]
}
r sadd key $data
}
if {$d ne {string}} {
assert_equal [r object encoding key] $e
}
set d1 [debug_digest]
r bgrewriteaof
waitForBgrewriteaof r
r debug loadaof
set d2 [debug_digest]
if {$d1 ne $d2} {
error "assertion:$d1 is not equal to $d2"
}
}
}
}
foreach d {string int} {
foreach e {listpack hashtable} {
test "AOF rewrite of hash with $e encoding, $d data" {
r flushall
if {$e eq {listpack}} {set len 10} else {set len 1000}
for {set j 0} {$j < $len} {incr j} {
if {$d eq {string}} {
set data [randstring 0 16 alpha]
} else {
set data [randomInt 4000000000]
}
r hset key $data $data
}
assert_equal [r object encoding key] $e
set d1 [debug_digest]
r bgrewriteaof
waitForBgrewriteaof r
r debug loadaof
set d2 [debug_digest]
if {$d1 ne $d2} {
error "assertion:$d1 is not equal to $d2"
}
}
}
}
foreach d {string int} {
foreach e {listpack skiplist} {
test "AOF rewrite of zset with $e encoding, $d data" {
r flushall
if {$e eq {listpack}} {set len 10} else {set len 1000}
for {set j 0} {$j < $len} {incr j} {
if {$d eq {string}} {
set data [randstring 0 16 alpha]
} else {
set data [randomInt 4000000000]
}
r zadd key [expr rand()] $data
}
assert_equal [r object encoding key] $e
set d1 [debug_digest]
r bgrewriteaof
waitForBgrewriteaof r
r debug loadaof
set d2 [debug_digest]
if {$d1 ne $d2} {
error "assertion:$d1 is not equal to $d2"
}
}
}
}
test "AOF rewrite functions" {
r flushall
r FUNCTION LOAD {#!lua name=test
redis.register_function('test', function() return 1 end)
}
r bgrewriteaof
waitForBgrewriteaof r
r function flush
r debug loadaof
assert_equal [r fcall test 0] 1
r FUNCTION LIST
} {{library_name test engine LUA functions {{name test description {} flags {}}}}}
test {BGREWRITEAOF is delayed if BGSAVE is in progress} {
r flushall
r set k v
r config set rdb-key-save-delay 10000000
r bgsave
assert_match {*scheduled*} [r bgrewriteaof]
assert_equal [s aof_rewrite_scheduled] 1
r config set rdb-key-save-delay 0
catch {exec kill -9 [get_child_pid 0]}
while {[s aof_rewrite_scheduled] eq 1} {
after 100
}
}
test {BGREWRITEAOF is refused if already in progress} {
r config set aof-use-rdb-preamble yes
r config set rdb-key-save-delay 10000000
catch {
r bgrewriteaof
r bgrewriteaof
} e
assert_match {*ERR*already*} $e
r config set rdb-key-save-delay 0
catch {exec kill -9 [get_child_pid 0]}
}
}