mirror of
https://codeberg.org/redict/redict.git
synced 2025-01-22 16:18:28 -05:00
c1718f9d86
## Background
For redis master, one replica uses one copy of replication buffer, that is a big waste of memory,
more replicas more waste, and allocate/free memory for every reply list also cost much.
If we set client-output-buffer-limit small and write traffic is heavy, master may disconnect with
replicas and can't finish synchronization with replica. If we set client-output-buffer-limit big,
master may be OOM when there are many replicas that separately keep much memory.
Because replication buffers of different replica client are the same, one simple idea is that
all replicas only use one replication buffer, that will effectively save memory.
Since replication backlog content is the same as replicas' output buffer, now we
can discard replication backlog memory and use global shared replication buffer
to implement replication backlog mechanism.
## Implementation
I create one global "replication buffer" which contains content of replication stream.
The structure of "replication buffer" is similar to the reply list that exists in every client.
But the node of list is `replBufBlock`, which has `id, repl_offset, refcount` fields.
```c
/* Replication buffer blocks is the list of replBufBlock.
*
* +--------------+ +--------------+ +--------------+
* | refcount = 1 | ... | refcount = 0 | ... | refcount = 2 |
* +--------------+ +--------------+ +--------------+
* | / \
* | / \
* | / \
* Repl Backlog Replia_A Replia_B
*
* Each replica or replication backlog increments only the refcount of the
* 'ref_repl_buf_node' which it points to. So when replica walks to the next
* node, it should first increase the next node's refcount, and when we trim
* the replication buffer nodes, we remove node always from the head node which
* refcount is 0. If the refcount of the head node is not 0, we must stop
* trimming and never iterate the next node. */
/* Similar with 'clientReplyBlock', it is used for shared buffers between
* all replica clients and replication backlog. */
typedef struct replBufBlock {
int refcount; /* Number of replicas or repl backlog using. */
long long id; /* The unique incremental number. */
long long repl_offset; /* Start replication offset of the block. */
size_t size, used;
char buf[];
} replBufBlock;
```
So now when we feed replication stream into replication backlog and all replicas, we only need
to feed stream into replication buffer `feedReplicationBuffer`. In this function, we set some fields of
replication backlog and replicas to references of the global replication buffer blocks. And we also
need to check replicas' output buffer limit to free if exceeding `client-output-buffer-limit`, and trim
replication backlog if exceeding `repl-backlog-size`.
When sending reply to replicas, we also need to iterate replication buffer blocks and send its
content, when totally sending one block for replica, we decrease current node count and
increase the next current node count, and then free the block which reference is 0 from the
head of replication buffer blocks.
Since now we use linked list to manage replication backlog, it may cost much time for iterating
all linked list nodes to find corresponding replication buffer node. So we create a rax tree to
store some nodes for index, but to avoid rax tree occupying too much memory, i record
one per 64 nodes for index.
Currently, to make partial resynchronization as possible as much, we always let replication
backlog as the last reference of replication buffer blocks, backlog size may exceeds our setting
if slow replicas that reference vast replication buffer blocks, and this method doesn't increase
memory usage since they share replication buffer. To avoid freezing server for freeing unreferenced
replication buffer blocks when we need to trim backlog for exceeding backlog size setting,
we trim backlog incrementally (free 64 blocks per call now), and make it faster in
`beforeSleep` (free 640 blocks).
### Other changes
- `mem_total_replication_buffers`: we add this field in INFO command, it means the total
memory of replication buffers used.
- `mem_clients_slaves`: now even replica is slow to replicate, and its output buffer memory
is not 0, but it still may be 0, since replication backlog and replicas share one global replication
buffer, only if replication buffer memory is more than the repl backlog setting size, we consider
the excess as replicas' memory. Otherwise, we think replication buffer memory is the consumption
of repl backlog.
- Key eviction
Since all replicas and replication backlog share global replication buffer, we think only the
part of exceeding backlog size the extra separate consumption of replicas.
Because we trim backlog incrementally in the background, backlog size may exceeds our
setting if slow replicas that reference vast replication buffer blocks disconnect.
To avoid massive eviction loop, we don't count the delayed freed replication backlog into
used memory even if there are no replicas, i.e. we also regard this memory as replicas's memory.
- `client-output-buffer-limit` check for replica clients
It doesn't make sense to set the replica clients output buffer limit lower than the repl-backlog-size
config (partial sync will succeed and then replica will get disconnected). Such a configuration is
ignored (the size of repl-backlog-size will be used). This doesn't have memory consumption
implications since the replica client will share the backlog buffers memory.
- Drop replication backlog after loading data if needed
We always create replication backlog if server is a master, we need it because we put DELs in
it when loading expired keys in RDB, but if RDB doesn't have replication info or there is no rdb,
it is not possible to support partial resynchronization, to avoid extra memory of replication backlog,
we drop it.
- Multi IO threads
Since all replicas and replication backlog use global replication buffer, if I/O threads are enabled,
to guarantee data accessing thread safe, we must let main thread handle sending the output buffer
to all replicas. But before, other IO threads could handle sending output buffer of all replicas.
## Other optimizations
This solution resolve some other problem:
- When replicas disconnect with master since of out of output buffer limit, releasing the output
buffer of replicas may freeze server if we set big `client-output-buffer-limit` for replicas, but now,
it doesn't cause freezing.
- This implementation may mitigate reply list copy cost time(also freezes server) when one replication
has huge reply buffer and another replica can copy buffer for full synchronization. now, we just copy
reference info, it is very light.
- If we set replication backlog size big, it also may cost much time to copy replication backlog into
replica's output buffer. But this commit eliminates this problem.
- Resizing replication backlog size doesn't empty current replication backlog content.
136 lines
6.3 KiB
Tcl
136 lines
6.3 KiB
Tcl
set testmodule [file normalize tests/modules/testrdb.so]
|
|
|
|
tags "modules" {
|
|
test {modules are able to persist types} {
|
|
start_server [list overrides [list loadmodule "$testmodule"]] {
|
|
r testrdb.set.key key1 value1
|
|
assert_equal "value1" [r testrdb.get.key key1]
|
|
r debug reload
|
|
assert_equal "value1" [r testrdb.get.key key1]
|
|
}
|
|
}
|
|
|
|
test {modules global are lost without aux} {
|
|
set server_path [tmpdir "server.module-testrdb"]
|
|
start_server [list overrides [list loadmodule "$testmodule" "dir" $server_path] keep_persistence true] {
|
|
r testrdb.set.before global1
|
|
assert_equal "global1" [r testrdb.get.before]
|
|
}
|
|
start_server [list overrides [list loadmodule "$testmodule" "dir" $server_path]] {
|
|
assert_equal "" [r testrdb.get.before]
|
|
}
|
|
}
|
|
|
|
test {modules are able to persist globals before and after} {
|
|
set server_path [tmpdir "server.module-testrdb"]
|
|
start_server [list overrides [list loadmodule "$testmodule 2" "dir" $server_path] keep_persistence true] {
|
|
r testrdb.set.before global1
|
|
r testrdb.set.after global2
|
|
assert_equal "global1" [r testrdb.get.before]
|
|
assert_equal "global2" [r testrdb.get.after]
|
|
}
|
|
start_server [list overrides [list loadmodule "$testmodule 2" "dir" $server_path]] {
|
|
assert_equal "global1" [r testrdb.get.before]
|
|
assert_equal "global2" [r testrdb.get.after]
|
|
}
|
|
|
|
}
|
|
|
|
test {modules are able to persist globals just after} {
|
|
set server_path [tmpdir "server.module-testrdb"]
|
|
start_server [list overrides [list loadmodule "$testmodule 1" "dir" $server_path] keep_persistence true] {
|
|
r testrdb.set.after global2
|
|
assert_equal "global2" [r testrdb.get.after]
|
|
}
|
|
start_server [list overrides [list loadmodule "$testmodule 1" "dir" $server_path]] {
|
|
assert_equal "global2" [r testrdb.get.after]
|
|
}
|
|
}
|
|
|
|
tags {repl} {
|
|
test {diskless loading short read with module} {
|
|
start_server [list overrides [list loadmodule "$testmodule"]] {
|
|
set replica [srv 0 client]
|
|
set replica_host [srv 0 host]
|
|
set replica_port [srv 0 port]
|
|
start_server [list overrides [list loadmodule "$testmodule"]] {
|
|
set master [srv 0 client]
|
|
set master_host [srv 0 host]
|
|
set master_port [srv 0 port]
|
|
|
|
# Set master and replica to use diskless replication
|
|
$master config set repl-diskless-sync yes
|
|
$master config set rdbcompression no
|
|
$replica config set repl-diskless-load swapdb
|
|
$master config set hz 500
|
|
$replica config set hz 500
|
|
$master config set dynamic-hz no
|
|
$replica config set dynamic-hz no
|
|
set start [clock clicks -milliseconds]
|
|
for {set k 0} {$k < 30} {incr k} {
|
|
r testrdb.set.key key$k [string repeat A [expr {int(rand()*1000000)}]]
|
|
}
|
|
|
|
if {$::verbose} {
|
|
set end [clock clicks -milliseconds]
|
|
set duration [expr $end - $start]
|
|
puts "filling took $duration ms (TODO: use pipeline)"
|
|
set start [clock clicks -milliseconds]
|
|
}
|
|
|
|
# Start the replication process...
|
|
set loglines [count_log_lines -1]
|
|
$master config set repl-diskless-sync-delay 0
|
|
$replica replicaof $master_host $master_port
|
|
|
|
# kill the replication at various points
|
|
set attempts 100
|
|
if {$::accurate} { set attempts 500 }
|
|
for {set i 0} {$i < $attempts} {incr i} {
|
|
# wait for the replica to start reading the rdb
|
|
# using the log file since the replica only responds to INFO once in 2mb
|
|
set res [wait_for_log_messages -1 {"*Loading DB in memory*"} $loglines 2000 1]
|
|
set loglines [lindex $res 1]
|
|
|
|
# add some additional random sleep so that we kill the master on a different place each time
|
|
after [expr {int(rand()*50)}]
|
|
|
|
# kill the replica connection on the master
|
|
set killed [$master client kill type replica]
|
|
|
|
set res [wait_for_log_messages -1 {"*Internal error in RDB*" "*Finished with success*" "*Successful partial resynchronization*"} $loglines 1000 1]
|
|
if {$::verbose} { puts $res }
|
|
set log_text [lindex $res 0]
|
|
set loglines [lindex $res 1]
|
|
if {![string match "*Internal error in RDB*" $log_text]} {
|
|
# force the replica to try another full sync
|
|
$master multi
|
|
$master client kill type replica
|
|
$master set asdf asdf
|
|
# fill replication backlog with new content
|
|
$master config set repl-backlog-size 16384
|
|
for {set keyid 0} {$keyid < 10} {incr keyid} {
|
|
$master set "$keyid string_$keyid" [string repeat A 16384]
|
|
}
|
|
$master exec
|
|
}
|
|
# wait for loading to stop (fail)
|
|
wait_for_condition 1000 1 {
|
|
[s -1 loading] eq 0
|
|
} else {
|
|
fail "Replica didn't disconnect"
|
|
}
|
|
}
|
|
if {$::verbose} {
|
|
set end [clock clicks -milliseconds]
|
|
set duration [expr $end - $start]
|
|
puts "test took $duration ms"
|
|
}
|
|
# enable fast shutdown
|
|
$master config set rdb-key-save-delay 0
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|