After #60, the CI report this warning:
```
rdb.c: In function 'rdbSaveToReplicasSockets':
rdb.c:3661:28: error: 'safe_to_exit_pipe' may be used uninitialized [-Werror=maybe-uninitialized]
3661 | if (!dual_channel) close(safe_to_exit_pipe);
| ^~~~~~~~~~~~~~~~~~~~~~~~
rdb.c:3512:37: note: 'safe_to_exit_pipe' was declared here
3512 | int pipefds[2], rdb_pipe_write, safe_to_exit_pipe;
| ^~~~~~~~~~~~~~~~~
rdb.c:3654:17: error: 'rdb_pipe_write' may be used uninitialized [-Werror=maybe-uninitialized]
3654 | close(rdb_pipe_write); /* close write in parent so that it can detect the close on the child. */
| ^~~~~~~~~~~~~~~~~~~~~
rdb.c:3512:21: note: 'rdb_pipe_write' was declared here
3512 | int pipefds[2], rdb_pipe_write, safe_to_exit_pipe;
| ^~~~~~~~~~~~~~
cc1: all warnings being treated as errors
```
Signed-off-by: Binbin <binloveplay1314@qq.com>
In this PR we introduce the main benefit of dual channel replication by
continuously steaming the COB (client output buffers) in parallel to the
RDB and thus keeping the primary's side COB small AND accelerating the
overall sync process. By streaming the replication data to the replica
during the full sync, we reduce
1. Memory load from the primary's node.
2. CPU load from the primary's main process. [Latest performance
tests](#data)
## Motivation
* Reduce primary memory load. We do that by moving the COB tracking to
the replica side. This also decrease the chance for COB overruns. Note
that primary's input buffer limits at the replica side are less
restricted then primary's COB as the replica plays less critical part in
the replication group. While increasing the primary’s COB may end up
with primary reaching swap and clients suffering, at replica side we’re
more at ease with it. Larger COB means better chance to sync
successfully.
* Reduce primary main process CPU load. By opening a new, dedicated
connection for the RDB transfer, child processes can have direct access
to the new connection. Due to TLS connection restrictions, this was not
possible using one main connection. We eliminate the need for the child
process to use the primary's child-proc -> main-proc pipeline, thus
freeing up the main process to process clients queries.
## Dual Channel Replication high level interface design
- Dual channel replication begins when the replica sends a `REPLCONF
CAPA DUALCHANNEL` to the primary during initial
handshake. This is used to state that the replica is capable of dual
channel sync and that this is the replica's main channel, which is not
used for snapshot transfer.
- When replica lacks sufficient data for PSYNC, the primary will send
`-FULLSYNCNEEDED` response instead
of RDB data. As a next step, the replica creates a new connection
(rdb-channel) and configures it against
the primary with the appropriate capabilities and requirements. The
replica then requests a sync
using the RDB channel.
- Prior to forking, the primary sends the replica the snapshot's end
repl-offset, and attaches the replica
to the replication backlog to keep repl data until the replica requests
psync. The replica uses the main
channel to request a PSYNC starting at the snapshot end offset.
- The primary main threads sends incremental changes via the main
channel, while the bgsave process
sends the RDB directly to the replica via the rdb-channel. As for the
replica, the incremental
changes are stored on a local buffer, while the RDB is loaded into
memory.
- Once the replica completes loading the rdb, it drops the
rdb-connection and streams the accumulated incremental
changes into memory. Repl steady state continues normally.
## New replica state machine
## Data <a name="data"></a>
## Explanation
These graphs demonstrate performance improvements during full sync
sessions using rdb-channel + streaming rdb directly from the background
process to the replica.
First graph- with at most 50 clients and light weight commands, we saw
5%-7.5% improvement in write latency during sync session.
Two graphs below- full sync was tested during heavy read commands from
the primary (such as sdiff, sunion on large sets). In that case, the
child process writes to the replica without sharing CPU with the loaded
main process. As a result, this not only improves client response time,
but may also shorten sync time by about 50%. The shorter sync time
results in less memory being used to store replication diffs (>60% in
some of the tested cases).
## Test setup
Both primary and replica in the performance tests ran on the same
machine. RDB size in all tests is 3.7gb. I generated write load using
valkey-benchmark ` ./valkey-benchmark -r 100000 -n 6000000 lpush my_list
__rand_int__`.
---------
Signed-off-by: naglera <anagler123@gmail.com>
Signed-off-by: naglera <58042354+naglera@users.noreply.github.com>
Co-authored-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
Co-authored-by: Ping Xie <pingxie@outlook.com>
Co-authored-by: Madelyn Olson <madelyneolson@gmail.com>
This PR is 1 of 3 PRs intended to achieve the goal of 1 million requests
per second, as detailed by [dan touitou](https://github.com/touitou-dan)
in https://github.com/valkey-io/valkey/issues/22. This PR modifies the
IO threads to be fully asynchronous, which is a first and necessary step
to allow more work offloading and better utilization of the IO threads.
### Current IO threads state:
Valkey IO threads were introduced in Redis 6.0 to allow better
utilization of multi-core machines. Before this, Redis was
single-threaded and could only use one CPU core for network and command
processing. The introduction of IO threads helps in offloading the IO
operations to multiple threads.
**Current IO Threads flow:**
1. Initialization: When Redis starts, it initializes a specified number
of IO threads. These threads are in addition to the main thread, each
thread starts with an empty list, the main thread will populate that
list in each event-loop with pending-read-clients or
pending-write-clients.
2. Read Phase: The main thread accepts incoming connections and reads
requests from clients. The reading of requests are offloaded to IO
threads. The main thread puts the clients ready-to-read in a list and
set the global io_threads_op to IO_THREADS_OP_READ, the IO threads pick
the clients up, perform the read operation and parse the first incoming
command.
3. Command Processing: After reading the requests, command processing is
still single-threaded and handled by the main thread.
4. Write Phase: Similar to the read phase, the write phase is also be
offloaded to IO threads. The main thread prepares the response in the
clients’ output buffer then the main thread puts the client in the list,
and sets the global io_threads_op to the IO_THREADS_OP_WRITE. The IO
threads then pick the clients up and perform the write operation to send
the responses back to clients.
5. Synchronization: The main-thread communicate with the threads on how
many jobs left per each thread with atomic counter. The main-thread
doesn’t access the clients while being handled by the IO threads.
**Issues with current implementation:**
* Underutilized Cores: The current implementation of IO-threads leads to
the underutilization of CPU cores.
* The main thread remains responsible for a significant portion of
IO-related tasks that could be offloaded to IO-threads.
* When the main-thread is processing client’s commands, the IO threads
are idle for a considerable amount of time.
* Notably, the main thread's performance during the IO-related tasks is
constrained by the speed of the slowest IO-thread.
* Limited Offloading: Currently, Since the Main-threads waits
synchronously for the IO threads, the Threads perform only read-parse,
and write operations, with parsing done only for the first command. If
the threads can do work asynchronously we may offload more work to the
threads reducing the load from the main-thread.
* TLS: Currently, we don't support IO threads with TLS (where offloading
IO would be more beneficial) since TLS read/write operations are not
thread-safe with the current implementation.
### Suggested change
Non-blocking main thread - The main thread and IO threads will operate
in parallel to maximize efficiency. The main thread will not be blocked
by IO operations. It will continue to process commands independently of
the IO thread's activities.
**Implementation details**
**Inter-thread communication.**
* We use a static, lock-free ring buffer of fixed size (2048 jobs) for
the main thread to send jobs and for the IO to receive them. If the ring
buffer fills up, the main thread will handle the task itself, acting as
back pressure (in case IO operations are more expensive than command
processing). A static ring buffer is a better candidate than a dynamic
job queue as it eliminates the need for allocation/freeing per job.
* An IO job will be in the format: ` [void* function-call-back | void
*data] `where data is either a client to read/write from and the
function-ptr is the function to be called with the data for example
readQueryFromClient using this format we can use it later to offload
other types of works to the IO threads.
* The Ring buffer is one way from the main-thread to the IO thread, Upon
read/write event the main thread will send a read/write job then in
before sleep it will iterate over the pending read/write clients to
checking for each client if the IO threads has already finished handling
it. The IO thread signals it has finished handling a client read/write
by toggling an atomic flag read_state / write_state on the client
struct.
**Thread Safety**
As suggested in this solution, the IO threads are reading from and
writing to the clients' buffers while the main thread may access those
clients.
We must ensure no race conditions or unsafe access occurs while keeping
the Valkey code simple and lock free.
Minimal Action in the IO Threads
The main change is to limit the IO thread operations to the bare
minimum. The IO thread will access only the client's struct and only the
necessary fields in this struct.
The IO threads will be responsible for the following:
* Read Operation: The IO thread will only read and parse a single
command. It will not update the server stats, handle read errors, or
parsing errors. These tasks will be taken care of by the main thread.
* Write Operation: The IO thread will only write the available data. It
will not free the client's replies, handle write errors, or update the
server statistics.
To achieve this without code duplication, the read/write code has been
refactored into smaller, independent components:
* Functions that perform only the read/parse/write calls.
* Functions that handle the read/parse/write results.
This refactor accounts for the majority of the modifications in this PR.
**Client Struct Safe Access**
As we ensure that the IO threads access memory only within the client
struct, we need to ensure thread safety only for the client's struct's
shared fields.
* Query Buffer
* Command parsing - The main thread will not try to parse a command from
the query buffer when a client is offloaded to the IO thread.
* Client's memory checks in client-cron - The main thread will not
access the client query buffer if it is offloaded and will handle the
querybuf grow/shrink when the client is back.
* CLIENT LIST command - The main thread will busy-wait for the IO thread
to finish handling the client, falling back to the current behavior
where the main thread waits for the IO thread to finish their
processing.
* Output Buffer
* The IO thread will not change the client's bufpos and won't free the
client's reply lists. These actions will be done by the main thread on
the client's return from the IO thread.
* bufpos / block→used: As the main thread may change the bufpos, the
reply-block→used, or add/delete blocks to the reply list while the IO
thread writes, we add two fields to the client struct: io_last_bufpos
and io_last_reply_block. The IO thread will write until the
io_last_bufpos, which was set by the main-thread before sending the
client to the IO thread. If more data has been added to the cob in
between, it will be written in the next write-job. In addition, the main
thread will not trim or merge reply blocks while the client is
offloaded.
* Parsing Fields
* Client's cmd, argc, argv, reqtype, etc., are set during parsing.
* The main thread will indicate to the IO thread not to parse a cmd if
the client is not reset. In this case, the IO thread will only read from
the network and won't attempt to parse a new command.
* The main thread won't access the c→cmd/c→argv in the CLIENT LIST
command as stated before it will busy wait for the IO threads.
* Client Flags
* c→flags, which may be changed by the main thread in multiple places,
won't be accessed by the IO thread. Instead, the main thread will set
the c→io_flags with the information necessary for the IO thread to know
the client's state.
* Client Close
* On freeClient, the main thread will busy wait for the IO thread to
finish processing the client's read/write before proceeding to free the
client.
* Client's Memory Limits
* The IO thread won't handle the qb/cob limits. In case a client crosses
the qb limit, the IO thread will stop reading for it, letting the main
thread know that the client crossed the limit.
**TLS**
TLS is currently not supported with IO threads for the following
reasons:
1. Pending reads - If SSL has pending data that has already been read
from the socket, there is a risk of not calling the read handler again.
To handle this, a list is used to hold the pending clients. With IO
threads, multiple threads can access the list concurrently.
2. Event loop modification - Currently, the TLS code
registers/unregisters the file descriptor from the event loop depending
on the read/write results. With IO threads, multiple threads can modify
the event loop struct simultaneously.
3. The same client can be sent to 2 different threads concurrently
(https://github.com/redis/redis/issues/12540).
Those issues were handled in the current PR:
1. The IO thread only performs the read operation. The main thread will
check for pending reads after the client returns from the IO thread and
will be the only one to access the pending list.
2. The registering/unregistering of events will be similarly postponed
and handled by the main thread only.
3. Each client is being sent to the same dedicated thread (c→id %
num_of_threads).
**Sending Replies Immediately with IO threads.**
Currently, after processing a command, we add the client to the
pending_writes_list. Only after processing all the clients do we send
all the replies. Since the IO threads are now working asynchronously, we
can send the reply immediately after processing the client’s requests,
reducing the command latency. However, if we are using AOF=always, we
must wait for the AOF buffer to be written, in which case we revert to
the current behavior.
**IO threads dynamic adjustment**
Currently, we use an all-or-nothing approach when activating the IO
threads. The current logic is as follows: if the number of pending write
clients is greater than twice the number of threads (including the main
thread), we enable all threads; otherwise, we enable none. For example,
if 8 IO threads are defined, we enable all 8 threads if there are 16
pending clients; else, we enable none.
It makes more sense to enable partial activation of the IO threads. If
we have 10 pending clients, we will enable 5 threads, and so on. This
approach allows for a more granular and efficient allocation of
resources based on the current workload.
In addition, the user will now be able to change the number of I/O
threads at runtime. For example, when decreasing the number of threads
from 4 to 2, threads 3 and 4 will be closed after flushing their job
queues.
**Tests**
Currently, we run the io-threads tests with 4 IO threads
(443d80f168/.github/workflows/daily.yml (L353)).
This means that we will not activate the IO threads unless there are 8
(threads * 2) pending write clients per single loop, which is unlikely
to happened in most of tests, meaning the IO threads are not currently
being tested.
To enforce the main thread to always offload work to the IO threads,
regardless of the number of pending events, we add an
events-per-io-thread configuration with a default value of 2. When set
to 0, this configuration will force the main thread to always offload
work to the IO threads.
When we offload every single read/write operation to the IO threads, the
IO-threads are running with 100% CPU when running multiple tests
concurrently some tests fail as a result of larger than expected command
latencies. To address this issue, we have to add some after or wait_for
calls to some of the tests to ensure they pass with IO threads as well.
Signed-off-by: Uri Yagelnik <uriy@amazon.com>
This PR incorporates changes related to key embedding described in the
https://github.com/redis/redis/issues/12216
With this change there will be no `key` pointer and embedded the key
within the `dictEntry`. 1 byte is used for additional bookkeeping.
Overall the saving would be 7 bytes on average.
Key changes:
New dict entry type introduced, which is now used as an entry for the
main dictionary:
```c
typedef struct {
union {
void *val;
uint64_t u64;
int64_t s64;
double d;
} v;
struct dictEntry *next; /* Next entry in the same hash bucket. */
uint8_t key_header_size; /* offset into key_buf where the key is located at. */
unsigned char key_buf[]; /* buffer with embedded key. */
} embeddedDictEntry;
```
One new function has been added to the dictType:
```c
size_t (*embedKey)(unsigned char *buf, size_t buf_len, const void *key, unsigned char *header_size);
```
Change is opt-in per dict type, hence sets, hashes and other types that
are using dictionary are not impacted.
With this change main dictionary now owns the data, so copy on insert in
dbAdd is no longer needed.
### Benchmarking results
TLDR; Around 9-10% memory usage reduction in overall memory usage for
scenario with key of 16 bytes and value of 8 bytes and 16 bytes. The
throughput per second varies but is similar or greater in most of the
run(s) with the changes against unstable (ae2d421).
---------
Signed-off-by: Harkrishn Patro <harkrisp@amazon.com>
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
Co-authored-by: Madelyn Olson <madelyneolson@gmail.com>
This PR makes our current RDB format compatible with the Redis 7.2.4 RDB
format. there are 2 changes introduced in this PR:
1. Move back the RDB version to 11
2. Make slot info section persist as AUX data instead of dedicated
section.
We have introduced slot-info as part of the work to replace cluster
metadata with slot specific dictionaries. This caused us to bump the RDB
version and thus we prevent downgrade (which is conceptualy O.K but
better be prevented). We do not require the slot-info section to exist,
so making it an AUX section will help suppport version downgrade from
Valkey 8.
fixes: [#645](https://github.com/valkey-io/valkey/issues/645)
NOTE: tested manually by:
1. connecting Redis 7.2.4 replica to a Valkey 8(RC)
2. upgrade/downgrade Redis 7.2.4 cluster and Valkey 8(RC) cluster
---------
Signed-off-by: ranshid <ranshid@amazon.com>
Co-authored-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
When we goto eoferr, we need to release the auxkey and auxval,
this is a cleanup, also explicitly check that decoder return
value is C_ERR.
Introduced in #586.
Signed-off-by: Binbin <binloveplay1314@qq.com>
More rebranding of
* Log messages (#252)
* The DENIED error reply
* Internal function names and comments, mainly Lua API
---------
Signed-off-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
- Replaces custom atomics logic with C11 default atomics logic.
- Drops "atomicvar_api" field from server info
Closes#485
---------
Signed-off-by: adetunjii <adetunjithomas1@outlook.com>
Signed-off-by: Samuel Adetunji <adetunjithomas1@outlook.com>
Co-authored-by: teej4y <samuel.adetunji@prunny.com>
I have validated that these settings closely match the existing coding
style with one major exception on `BreakBeforeBraces`, which will be
`Attach` going forward. The mixed `BreakBeforeBraces` styles in the
current codebase are hard to imitate and also very odd IMHO - see below
```
if (a == 1) { /*Attach */
}
```
```
if (a == 1 ||
b == 2)
{ /* Why? */
}
```
Please do NOT merge just yet. Will add the github action next once the
style is reviewed/approved.
---------
Signed-off-by: Ping Xie <pingxie@google.com>
If `valkey-server` was started with the `redis-server` symlink, the old
proc names are used, for backwards compatibility.
---------
Signed-off-by: Shivshankar-Reddy <shiva.sheri.github@gmail.com>
Updated strlcat function and macros name (redis_strlcat ->
valkey_strlcat).
I think the standard strcat function is not safe.
(https://codeql.github.com/codeql-query-help/cpp/cpp-unsafe-strcat/)
So, it would be better to keep it as a safe function.
Signed-off-by: NAM UK KIM <namuk2004@naver.com>
This includes comments used for module API documentation.
* Strategy for replacement: Regex search: `(//|/\*| \*|#).* ("|\()?(r|R)edis( |\.
|'|\n|,|-|\)|")(?!nor the names of its contributors)(?!Ltd.)(?!Labs)(?!Contributors.)`
* Don't edit copyright comments
* Replace "Redis version X.X" -> "Redis OSS version X.X" to distinguish
from newly licensed repository
* Replace "Redis Object" -> "Object"
* Exclude markdown for now
* Don't edit Lua scripting comments referring to redis.X API
* Replace "Redis Protocol" -> "RESP"
* Replace redis-benchmark, -cli, -server, -check-aof/rdb with "valkey-"
prefix
* Most other places, I use best judgement to either remove "Redis", or
replace with "the server" or "server"
Fixes#148
---------
Signed-off-by: Jacob Murphy <jkmurphy@google.com>
Signed-off-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
This commit updates the following fields:
1. server_version -> valkey_version in server info. Since we would like
to advertise specific compatibility, we are making the version specific
to valkey. servername will remain as an optional indicator, and other
valkey compatible stores might choose to advertise something else.
1. We dropped redis-ver from the API. This isn't related to API
compatibility, but we didn't want to "fake" that valkey was creating an
rdb from a Redis version.
1. Renamed server-ver -> valkey_version in rdb info. Same as point one,
we want to explicitly indicate this was created by a valkey server.
---------
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
Fix#146
Removed REDISMODULE_ prefixes from the core source code to align with
the new SERVERMODULE_ naming convention. Added a new 'redismodule.h'
header file to ensure full backward compatibility with existing modules.
This compatibility layer maps all legacy REDISMODULE_ prefixed
identifiers to their new SERVERMODULE_ equivalents, allowing existing
Redis modules to function without modification.
---------
Signed-off-by: Ping Xie <pingxie@google.com>
New info information to be used to determine the valkey versioning info.
Internally, introduce new define values for "SERVER_VERSION" which is
different from the Redis compatibility version, "REDIS_VERSION".
Add two new info fields:
`server_version`: The Valkey server version
`server_name`: Indicates that the server is valkey.
Add one new RDB field: `server_ver`, which indicates the valkey version
that produced the server.
Add 3 new LUA globals: `SERVER_VERSION_NUM`, `SERVER_VERSION`, and
`SERVER_NAME`. Which reflect the valkey version instead of the Redis
compatibility version.
Also clean up various places where Redis and configuration was being
used that is no longer necessary.
---------
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
Following the changes introduced by 8cd62f82c, the dbExpandExpires used
the db_size instead of expires_size.
Co-authored-by: YaacovHazan <yaacov.hazan@redislabs.com>
Following the changes introduced by 8cd62f82c, the kvstoreDictExpand for
the expires kvstore used the slot_size instead of expires_slot_size.
Co-authored-by: YaacovHazan <yaacov.hazan@redislabs.com>
We forgot to call quicklistSetOptions after createQuicklistObject,
in the sort store scenario, we will create a quicklist with default
fill or compress options.
This PR adds fill and depth parameters to createQuicklistObject to
specify that options need to be set after creating a quicklist.
This closes#12871.
release notes:
> Fix lists created by SORT STORE to respect list compression and
packing configs.
# Description
Gather most of the scattered `redisDb`-related code from the per-slot
dict PR (#11695) and turn it to a new data structure, `kvstore`. i.e.
it's a class that represents an array of dictionaries.
# Motivation
The main motivation is code cleanliness, the idea of using an array of
dictionaries is very well-suited to becoming a self-contained data
structure.
This allowed cleaning some ugly code, among others: loops that run twice
on the main dict and expires dict, and duplicate code for allocating and
releasing this data structure.
# Notes
1. This PR reverts the part of https://github.com/redis/redis/pull/12848
where the `rehashing` list is global (handling rehashing `dict`s is
under the responsibility of `kvstore`, and should not be managed by the
server)
2. This PR also replaces the type of `server.pubsubshard_channels` from
`dict**` to `kvstore` (original PR:
https://github.com/redis/redis/pull/12804). After that was done,
server.pubsub_channels was also chosen to be a `kvstore` (with only one
`dict`, which seems odd) just to make the code cleaner by making it the
same type as `server.pubsubshard_channels`, see
`pubsubtype.serverPubSubChannels`
3. the keys and expires kvstores are currenlty configured to allocate
the individual dicts only when the first key is added (unlike before, in
which they allocated them in advance), but they won't release them when
the last key is deleted.
Worth mentioning that due to the recent change the reply of DEBUG
HTSTATS changed, in case no keys were ever added to the db.
before:
```
127.0.0.1:6379> DEBUG htstats 9
[Dictionary HT]
Hash table 0 stats (main hash table):
No stats available for empty dictionaries
[Expires HT]
Hash table 0 stats (main hash table):
No stats available for empty dictionaries
```
after:
```
127.0.0.1:6379> DEBUG htstats 9
[Dictionary HT]
[Expires HT]
```
In Redis, rdb is produced in three scenarios mainly.
- backup, such as `bgsave` and `save` command
- full sync in replication
- aof rewrite if `aof-use-rdb-preamble` is yes
We also have some RDB flags to identify the purpose of rdb saving.
```C
/* flags on the purpose of rdb save or load */
#define RDBFLAGS_NONE 0 /* No special RDB loading. */
#define RDBFLAGS_AOF_PREAMBLE (1<<0) /* Load/save the RDB as AOF preamble. */
#define RDBFLAGS_REPLICATION (1<<1) /* Load/save for SYNC. */
```
But currently, it seems that these flags and purposes of rdb saving
don't exactly match. I find it in `rdbSaveRioWithEOFMark` which calls
`startSaving` with `RDBFLAGS_REPLICATION` but `rdbSaveRio` with
`RDBFLAGS_NONE`.
```C
int rdbSaveRioWithEOFMark(int req, rio *rdb, int *error, rdbSaveInfo *rsi) {
char eofmark[RDB_EOF_MARK_SIZE];
startSaving(RDBFLAGS_REPLICATION);
getRandomHexChars(eofmark,RDB_EOF_MARK_SIZE);
if (error) *error = 0;
if (rioWrite(rdb,"$EOF:",5) == 0) goto werr;
if (rioWrite(rdb,eofmark,RDB_EOF_MARK_SIZE) == 0) goto werr;
if (rioWrite(rdb,"\r\n",2) == 0) goto werr;
if (rdbSaveRio(req,rdb,error,RDBFLAGS_NONE,rsi) == C_ERR) goto werr;
if (rioWrite(rdb,eofmark,RDB_EOF_MARK_SIZE) == 0) goto werr;
stopSaving(1);
return C_OK;
werr: /* Write error. */
/* Set 'error' only if not already set by rdbSaveRio() call. */
if (error && *error == 0) *error = errno;
stopSaving(0);
return C_ERR;
}
```
In this PR, I refine the purpose of rdb saving with accurate flags.
The raxFind implementation uses a special pointer value (the address of
a static string) as the "not found" value. It works as long as actual
pointers were used. However we've seen usages where long long,
non-pointer values have been used. It creates a risk that one of the
long long value precisely is the address of the special "not found"
value. This commit changes raxFind to return 1 or 0 to indicate
elementhood, and take in a new void **value to optionally return the
associated value.
By extension, this also allow the RedisModule_DictSet/Replace operations
to also safely insert integers instead of just pointers.
when dbExpand is called from rdb.c with try_expand set to 0, it will
either panic panic on OOM, or be non-fatal (should not fail RDB loading)
At the same time, the log text has been slightly adjusted to make it
more unified.
Currently, during RDB loading, once a `dbExpand` is performed, the
`should_expand_db` flag is set to 0. This causes the remaining DBs
unable to do `dbExpand` when there are multiple DBs.
To fix this issue, we need to set `should_expand_db` back to 1 whenever
we encounter `RDB_OPCODE_RESIZEDB`. This ensures that each DB can
perform `dbExpand` correctly.
Additionally, the initial value of `should_expand_db` should also be set
to 0 to prevent invalid `dbExpand` in older versions of RDB where
`RDB_OPCODE_RESIZEDB` is not present.
problem introduced in #11695
`open()` can return any non-negative integer on success, including zero.
This change modifies the check from open()'s return value to also
include checking for a return value of zero (e.g., if stdin were closed
and then `open()` was called).
Fixes Coverity 404720
Can't happen in Redis. just a cleanup.
When using DB iterator, it will use dictInitSafeIterator to init a old safe
dict iterator. When dbIteratorNext is used, it will jump to the next slot db
dict when we are done a dict. During this process, we do not have any calls to
dictResumeRehashing, which causes the dict's pauserehash to always be > 0.
And at last, it will be returned directly in dictRehashMilliseconds, which causes
us to have slot dict in a state where rehash cannot be completed.
In the "expire scan should skip dictionaries with lot's of empty buckets" test,
adding a `keys *` can reproduce the problem stably. `keys *` will call dbIteratorNext
to trigger a traversal of all slot dicts.
Added dbReleaseIterator and dbIteratorInitNextSafeIterator methods to call dictResetIterator.
Issue was introduced in #11695.
This is an implementation of https://github.com/redis/redis/issues/10589 that eliminates 16 bytes per entry in cluster mode, that are currently used to create a linked list between entries in the same slot. Main idea is splitting main dictionary into 16k smaller dictionaries (one per slot), so we can perform all slot specific operations, such as iteration, without any additional info in the `dictEntry`. For Redis cluster, the expectation is that there will be a larger number of keys, so the fixed overhead of 16k dictionaries will be The expire dictionary is also split up so that each slot is logically decoupled, so that in subsequent revisions we will be able to atomically flush a slot of data.
## Important changes
* Incremental rehashing - one big change here is that it's not one, but rather up to 16k dictionaries that can be rehashing at the same time, in order to keep track of them, we introduce a separate queue for dictionaries that are rehashing. Also instead of rehashing a single dictionary, cron job will now try to rehash as many as it can in 1ms.
* getRandomKey - now needs to not only select a random key, from the random bucket, but also needs to select a random dictionary. Fairness is a major concern here, as it's possible that keys can be unevenly distributed across the slots. In order to address this search we introduced binary index tree). With that data structure we are able to efficiently find a random slot using binary search in O(log^2(slot count)) time.
* Iteration efficiency - when iterating dictionary with a lot of empty slots, we want to skip them efficiently. We can do this using same binary index that is used for random key selection, this index allows us to find a slot for a specific key index. For example if there are 10 keys in the slot 0, then we can quickly find a slot that contains 11th key using binary search on top of the binary index tree.
* scan API - in order to perform a scan across the entire DB, the cursor now needs to not only save position within the dictionary but also the slot id. In this change we append slot id into LSB of the cursor so it can be passed around between client and the server. This has interesting side effect, now you'll be able to start scanning specific slot by simply providing slot id as a cursor value. The plan is to not document this as defined behavior, however. It's also worth nothing the SCAN API is now technically incompatible with previous versions, although practically we don't believe it's an issue.
* Checksum calculation optimizations - During command execution, we know that all of the keys are from the same slot (outside of a few notable exceptions such as cross slot scripts and modules). We don't want to compute the checksum multiple multiple times, hence we are relying on cached slot id in the client during the command executions. All operations that access random keys, either should pass in the known slot or recompute the slot.
* Slot info in RDB - in order to resize individual dictionaries correctly, while loading RDB, it's not enough to know total number of keys (of course we could approximate number of keys per slot, but it won't be precise). To address this issue, we've added additional metadata into RDB that contains number of keys in each slot, which can be used as a hint during loading.
* DB size - besides `DBSIZE` API, we need to know size of the DB in many places want, in order to avoid scanning all dictionaries and summing up their sizes in a loop, we've introduced a new field into `redisDb` that keeps track of `key_count`. This way we can keep DBSIZE operation O(1). This is also kept for O(1) expires computation as well.
## Performance
This change improves SET performance in cluster mode by ~5%, most of the gains come from us not having to maintain linked lists for keys in slot, non-cluster mode has same performance. For workloads that rely on evictions, the performance is similar because of the extra overhead for finding keys to evict.
RDB loading performance is slightly reduced, as the slot of each key needs to be computed during the load.
## Interface changes
* Removed `overhead.hashtable.slot-to-keys` to `MEMORY STATS`
* Scan API will now require 64 bits to store the cursor, even on 32 bit systems, as the slot information will be stored.
* New RDB version to support the new op code for SLOT information.
---------
Co-authored-by: Vitaly Arbuzov <arvit@amazon.com>
Co-authored-by: Harkrishn Patro <harkrisp@amazon.com>
Co-authored-by: Roshan Khatri <rvkhatri@amazon.com>
Co-authored-by: Madelyn Olson <madelyneolson@gmail.com>
Co-authored-by: Oran Agra <oran@redislabs.com>
Currently rdbSaveMillisecondTime, rdbSaveDoubleValue api's return type is
int but they return the value directly from rdbWriteRaw function which has the
return type of ssize_t. As this may cause overflow to int so changed to ssize_t.
When loading a function from either RDB/AOF or a replica, it is essential not to
fail on timeout errors. The loading time may vary due to various factors, such as
hardware specifications or the system's workload during the loading process.
Once a function has been successfully loaded, it should be allowed to load from
persistence or on replicas without encountering a timeout failure.
To maintain a clear separation between the engine and Redis internals, the
implementation refrains from directly checking the state of Redis within the
engine itself. Instead, the engine receives the desired timeout as part of the
library creation and duly respects this timeout value. If Redis wishes to disable
any timeout, it can simply send a value of 0.
A value of type long long is always less than 21 bytes when convert to a
string, so always meets the conditions for using embedded string object
which can always get memory reduction and performance gain (less calls
to the heap allocator).
Additionally, for the conversion of longlong type to sds, we also use a faster
algorithm (the one in util.c instead of the one that used to be in sds.c).
For the DECR command on 32-bit Redis, we get about a 5.7% performance
improvement. There will also be some performance gains for some commands
that heavily use sdscatfmt to convert numbers, such as INFO.
Co-authored-by: Oran Agra <oran@redislabs.com>
The nightly tests showed that the recent PR #12022 caused random failures
in aof.tcl on checking RDB preamble inside an AOF file.
Root cause:
When checking RDB preamble in an AOF file, what's passed into redis_check_rdb is
aof_filename, not aof_filepath. The newly introduced isFifo function does not check return
status of the stat call and hence uses the uninitailized stat_p object.
Fix:
1. Fix isFifo by checking stat call's return code.
2. Pass aof_filepath instead of aof_filename to redis_check_rdb.
3. move the FIFO check to rdb.c since the limitation is the re-opening of the file, and not
anything specific about redis-check-rdb.
Add `RM_RdbLoad()` and `RM_RdbSave()` to load/save RDB files from the module API.
In our use case, we have our clustering implementation as a module. As part of this
implementation, the module needs to trigger RDB save operation at specific points.
Also, this module delivers RDB files to other nodes (not using Redis' replication).
When a node receives an RDB file, it should be able to load the RDB. Currently,
there is no module API to save/load RDB files.
This PR adds four new APIs:
```c
RedisModuleRdbStream *RM_RdbStreamCreateFromFile(const char *filename);
void RM_RdbStreamFree(RedisModuleRdbStream *stream);
int RM_RdbLoad(RedisModuleCtx *ctx, RedisModuleRdbStream *stream, int flags);
int RM_RdbSave(RedisModuleCtx *ctx, RedisModuleRdbStream *stream, int flags);
```
The first step is to create a `RedisModuleRdbStream` object. This PR provides a function to
create RedisModuleRdbStream from the filename. (You can load/save RDB with the filename).
In the future, this API can be extended if needed:
e.g., `RM_RdbStreamCreateFromFd()`, `RM_RdbStreamCreateFromSocket()` to save/load
RDB from an `fd` or a `socket`.
Usage:
```c
/* Save RDB */
RedisModuleRdbStream *stream = RedisModule_RdbStreamCreateFromFile("example.rdb");
RedisModule_RdbSave(ctx, stream, 0);
RedisModule_RdbStreamFree(stream);
/* Load RDB */
RedisModuleRdbStream *stream = RedisModule_RdbStreamCreateFromFile("example.rdb");
RedisModule_RdbLoad(ctx, stream, 0);
RedisModule_RdbStreamFree(stream);
```
We have cases where we print information (might be important but by
no means an error indicator) with the LL_WARNING level.
Demoting these to LL_NOTICE:
- oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo
- User requested shutdown...
This is also true for cases that we encounter a rare but normal situation.
Demoting to LL_NOTICE. Examples:
- AOF was enabled but there is already another background operation. An AOF background was scheduled to start when possible.
- Connection with master lost.
base on yoav-steinberg's https://github.com/redis/redis/pull/10650#issuecomment-1112280554
and yossigo's https://github.com/redis/redis/pull/10650#pullrequestreview-967677676
# Background
The RDB file is usually generated and used once and seldom used again, but the content would reside in page cache until OS evicts it. A potential problem is that once the free memory exhausts, the OS have to reclaim some memory from page cache or swap anonymous page out, which may result in a jitters to the Redis service.
Supposing an exact scenario, a high-capacity machine hosts many redis instances, and we're upgrading the Redis together. The page cache in host machine increases as RDBs are generated. Once the free memory drop into low watermark(which is more likely to happen in older Linux kernel like 3.10, before [watermark_scale_factor](https://lore.kernel.org/lkml/1455813719-2395-1-git-send-email-hannes@cmpxchg.org/) is introduced, the `low watermark` is linear to `min watermark`, and there'is not too much buffer space for `kswapd` to be wake up to reclaim memory), a `direct reclaim` happens, which means the process would stall to wait for memory allocation.
# What the PR does
The PR introduces a capability to reclaim the cache when the RDB is operated. Generally there're two cases, read and write the RDB. For read it's a little messy to address the incremental reclaim, so the reclaim is done in one go in background after the load is finished to avoid blocking the work thread. For write, incremental reclaim amortizes the work of reclaim so no need to put it into background, and the peak watermark of cache can be reduced in this way.
Two cases are addresses specially, replication and restart, for both of which the cache is leveraged to speed up the processing, so the reclaim is postponed to a right time. To do this, a flag is added to`rdbSave` and `rdbLoad` to control whether the cache need to be kept, with the default value false.
# Something deserve noting
1. Though `posix_fadvise` is the POSIX standard, but only few platform support it, e.g. Linux, FreeBSD 10.0.
2. In Linux `posix_fadvise` only take effect on writeback-ed pages, so a `sync`(or `fsync`, `fdatasync`) is needed to flush the dirty page before `posix_fadvise` if we reclaim write cache.
# About test
A unit test is added to verify the effect of `posix_fadvise`.
In integration test overall cache increase is checked, as well as the cache backed by RDB as a specific TCL test is executed in isolated Github action job.
In #11290, we added listpack encoding for SET object.
But forgot to support it in zuiFind, causes ZINTER, ZINTERSTORE,
ZINTERCARD, ZIDFF, ZDIFFSTORE to crash.
And forgot to support it in RM_ScanKey, causes it hang.
This PR add support SET listpack in zuiFind, and in RM_ScanKey.
And add tests for related commands to cover this case.
Other changes:
- There is no reason for zuiFind to go into the internals of the SET.
It can simply use setTypeIsMember and don't care about encoding.
- Remove the `#include "intset.h"` from server.h reduce the chance of
accidental intset API use.
- Move setTypeAddAux, setTypeRemoveAux and setTypeIsMemberAux
interfaces to the header.
- In scanGenericCommand, use setTypeInitIterator and setTypeNext
to handle OBJ_SET scan.
- In RM_ScanKey, improve hash scan mode, use lpGetValue like zset,
they can share code and better performance.
The zuiFind part fixes#11578
Co-authored-by: Oran Agra <oran@redislabs.com>
Co-authored-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
In most cases when a listpack or intset is converted to a dict, the conversion
is trigged when adding an element. The extra element is added after conversion
to dict (in all cases except when the conversion is triggered by
set-max-intset-entries being reached).
If set-max-listpack-entries is set to a power of two, let's say 128, when
adding the 129th element, the 128 element listpack is first converted to a dict
with a hashtable presized for 128 elements. After converting to dict, the 129th
element is added to the dict which immediately triggers incremental rehashing
to size 256.
This commit instead presizes the dict to one more element, with the assumption
that conversion to dict is followed by adding another element, so the dict
doesn't immediately need rehashing.
Co-authored-by: sundb <sundbcn@gmail.com>
Co-authored-by: Oran Agra <oran@redislabs.com>
1. "Fixed" the current code so that seen-time/idle actually refers to interaction
attempts (as documented; breaking change)
2. Added active-time/inactive to refer to successful interaction (what
seen-time/idle used to be)
At first, I tried to avoid changing the behavior of seen-time/idle but then realized
that, in this case, the odds are the people read the docs and implemented their
code based on the docs (which didn't match the behavior).
For the most part, that would work fine, except that issue #9996 was found.
I was working under the assumption that people relied on the docs, and for
the most part, it could have worked well enough. so instead of fixing the docs,
as I would usually do, I fixed the code to match the docs in this particular case.
Note that, in case the consumer has never read any entries, the values
for both "active-time" (XINFO FULL) and "inactive" (XINFO CONSUMERS) will
be -1, meaning here that the consumer was never active.
Note that seen/active time is only affected by XREADGROUP / X[AUTO]CLAIM, not
by XPENDING, XINFO, and other "read-only" stream CG commands (always has been,
even before this PR)
Other changes:
* Another behavioral change (arguably a bugfix) is that XREADGROUP and X[AUTO]CLAIM
create the consumer regardless of whether it was able to perform some reading/claiming
* RDB format change to save the `active_time`, and set it to the same value of `seen_time` in old rdb files.
The following example will create an empty set (listpack encoding):
```
> RESTORE key 0
"\x14\x25\x25\x00\x00\x00\x00\x00\x02\x01\x82\x5F\x37\x03\x06\x01\x82\x5F\x35\x03\x82\x5F\x33\x03\x00\x01\x82\x5F\x31\x03\x82\x5F\x39\x03\x04\xA9\x08\x01\xFF\x0B\x00\xA3\x26\x49\xB4\x86\xB0\x0F\x41"
OK
> SCARD key
(integer) 0
> SRANDMEMBER key
Error: Server closed the connection
```
In the spirit of #9297, skip empty set when loading RDB_TYPE_SET_LISTPACK.
Introduced in #11290
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.
