The bug is introduced by #9323. (released in 7.0 RC1)
The define of `REDISMODULE_OPTIONS_HANDLE_IO_ERRORS` and `REDISMODULE_OPTION_NO_IMPLICIT_SIGNAL_MODIFIED` have the same value.
This will result in skipping `signalModifiedKey()` after `RM_CloseKey()` if the module has set
`REDISMODULE_OPTIONS_HANDLE_REPL_ASYNC_LOAD` option.
The implication is missing WATCH and client side tracking invalidations.
Other changes:
- add `no-implicit-signal-modified` to the options in INFO modules
Co-authored-by: Oran Agra <oran@redislabs.com>
In #9323, when `repl-diskless-load` is enabled and set to `swapdb`,
if the master replication ID hasn't changed, we can load data-set
asynchronously, and serving read commands during the full resync.
In `diskless loading short read` test, after a loading successfully,
we will wait for the loading to stop and continue the for loop.
After the introduction of `async_loading`, we also need to check it.
Otherwise the next loop will start too soon, may trigger a timing issue.
In both tests, "diskless loading short read" and "diskless loading short read with module",
the timeout of waiting for the replica to respond to a short read and log it, is too short.
Also, add --dump-logs in runtest-moduleapi for valgrind runs.
For diskless replication in swapdb mode, considering we already spend replica memory
having a backup of current db to restore in case of failure, we can have the following benefits
by instead swapping database only in case we succeeded in transferring db from master:
- Avoid `LOADING` response during failed and successful synchronization for cases where the
replica is already up and running with data.
- Faster total time of diskless replication, because now we're moving from Transfer + Flush + Load
time to Transfer + Load only. Flushing the tempDb is done asynchronously after swapping.
- This could be implemented also for disk replication with similar benefits if consumers are willing
to spend the extra memory usage.
General notes:
- The concept of `backupDb` becomes `tempDb` for clarity.
- Async loading mode will only kick in if the replica is syncing from a master that has the same
repl-id the one it had before. i.e. the data it's getting belongs to a different time of the same timeline.
- New property in INFO: `async_loading` to differentiate from the blocking loading
- Slot to Key mapping is now a field of `redisDb` as it's more natural to access it from both server.db
and the tempDb that is passed around.
- Because this is affecting replicas only, we assume that if they are not readonly and write commands
during replication, they are lost after SYNC same way as before, but we're still denying CONFIG SET
here anyways to avoid complications.
Considerations for review:
- We have many cases where server.loading flag is used and even though I tried my best, there may
be cases where async_loading should be checked as well and cases where it shouldn't (would require
very good understanding of whole code)
- Several places that had different behavior depending on the loading flag where actually meant to just
handle commands coming from the AOF client differently than ones coming from real clients, changed
to check CLIENT_ID_AOF instead.
**Additional for Release Notes**
- Bugfix - server.dirty was not incremented for any kind of diskless replication, as effect it wouldn't
contribute on triggering next database SAVE
- New flag for RM_GetContextFlags module API: REDISMODULE_CTX_FLAGS_ASYNC_LOADING
- Deprecated RedisModuleEvent_ReplBackup. Starting from Redis 7.0, we don't fire this event.
Instead, we have the new RedisModuleEvent_ReplAsyncLoad holding 3 sub-events: STARTED,
ABORTED and COMPLETED.
- New module flag REDISMODULE_OPTIONS_HANDLE_REPL_ASYNC_LOAD for RedisModule_SetModuleOptions
to allow modules to declare they support the diskless replication with async loading (when absent, we fall
back to disk-based loading).
Co-authored-by: Eduardo Semprebon <edus@saxobank.com>
Co-authored-by: Oran Agra <oran@redislabs.com>
## 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.
Diskless master has some inherent latencies.
1) fork starts with delay from cron rather than immediately
2) replica is put online only after an ACK. but the ACK
was sent only once a second.
3) but even if it would arrive immediately, it will not
register in case cron didn't yet detect that the fork is done.
Besides that, when a replica disconnects, it doesn't immediately
attempts to re-connect, it waits for replication cron (one per second).
in case it was already online, it may be important to try to re-connect
as soon as possible, so that the backlog at the master doesn't vanish.
In case it disconnected during rdb transfer, one can argue that it's
not very important to re-connect immediately, but this is needed for the
"diskless loading short read" test to be able to run 100 iterations in 5
seconds, rather than 3 (waiting for replication cron re-connection)
changes in this commit:
1) sync command starts a fork immediately if no sync_delay is configured
2) replica sends REPLCONF ACK when done reading the rdb (rather than on 1s cron)
3) when a replica unexpectedly disconnets, it immediately tries to
re-connect rather than waiting 1s
4) when when a child exits, if there is another replica waiting, we spawn a new
one right away, instead of waiting for 1s replicationCron.
5) added a call to connectWithMaster from replicationSetMaster. which is called
from the REPLICAOF command but also in 3 places in cluster.c, in all of
these the connection attempt will now be immediate instead of delayed by 1
second.
side note:
we can add a call to rdbPipeReadHandler in replconfCommand when getting
a REPLCONF ACK from the replica to solve a race where the replica got
the entire rdb and EOF marker before we detected that the pipe was
closed.
in the test i did see this race happens in one about of some 300 runs,
but i concluded that this race is unlikely in real life (where the
replica is on another host and we're more likely to first detect the
pipe was closed.
the test runs 100 iterations in 3 seconds, so in some cases it'll take 4
seconds instead (waiting for another REPLCONF ACK).
Removing unneeded startBgsaveForReplication from updateSlavesWaitingForBgsave
Now that CheckChildrenDone is calling the new replicationStartPendingFork
(extracted from serverCron) there's actually no need to call
startBgsaveForReplication from updateSlavesWaitingForBgsave anymore,
since as soon as updateSlavesWaitingForBgsave returns, CheckChildrenDone is
calling replicationStartPendingFork that handles that anyway.
The code in updateSlavesWaitingForBgsave had a bug in which it ignored
repl-diskless-sync-delay, but removing that code shows that this bug was
hiding another bug, which is that the max_idle should have used >= and
not >, this one second delay has a big impact on my new test.
- the test now waits for specific set of log messages rather than wait for
timeout looking for just one message.
- we don't wanna sample the current length of the log after an action, due
to a race, we need to start the search from the line number of the last
message we where waiting for.
- when attempting to trigger a full sync, use multi-exec to avoid a race
where the replica manages to re-connect before we completed the set of
actions that should force a full sync.
- fix verify_log_message which was broken and unused
tests were sensitive to additional log lines appearing in the log
causing the search to come empty handed.
instead of just looking for the n last log lines, capture the log lines
before performing the action, and then search from that offset.
