Adds two new metrics for per-slot statistics, network-bytes-in and
network-bytes-out. The network bytes are inclusive of replication bytes
but exclude other types of network traffic such as clusterbus traffic.
#### network-bytes-in
The metric tracks network ingress bytes under per-slot context, by
reverse calculation of `c->argv_len_sum` and `c->argc`, stored under a
newly introduced field `c->net_input_bytes_curr_cmd`.
#### network-bytes-out
The metric tracks network egress bytes under per-slot context, by
hooking onto COB buffer mutations.
#### sample response
Both metrics are reported under the `CLUSTER SLOT-STATS` command.
```
127.0.0.1:6379> cluster slot-stats slotsrange 0 0
1) 1) (integer) 0
2) 1) "key-count"
2) (integer) 0
3) "cpu-usec"
4) (integer) 0
5) "network-bytes-in"
6) (integer) 0
7) "network-bytes-out"
8) (integer) 0
```
---------
Signed-off-by: Kyle Kim <kimkyle@amazon.com>
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
Co-authored-by: Madelyn Olson <madelyneolson@gmail.com>
In some cases, like read more than write scenario, the replication
offset of the replicas are the same. When the primary fails, the
replicas have the same rankings (rank == 0). They issue the election
at the same time (although we have a random 500), the simultaneous
elections may lead to the failure of the election due to quorum.
In clusterGetReplicaRank, when we calculates the rank, if the offsets
are the same, the one with the smaller node name will have a better
rank to avoid this situation.
---------
Signed-off-by: Binbin <binloveplay1314@qq.com>
The metric tracks cpu time in micro-seconds, sharing the same value as
`INFO COMMANDSTATS`, aggregated under per-slot context.
---------
Signed-off-by: Kyle Kim <kimkyle@amazon.com>
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
Co-authored-by: Madelyn Olson <madelyneolson@gmail.com>
When executing the script, the client passed in is a fake
client, and its woff is always 0.
This results in woff always being 0 when executing wait/waitaof
in the script, and the command returns a wrong number.
---------
Signed-off-by: Binbin <binloveplay1314@qq.com>
We will not reset failover_auth_time after setting it, this is used
to check auth_timeout and auth_retry_time, but we should at least
reset it after a successful failover.
Let's assume the following scenario:
1. Two replicas initiate an election.
2. Replica 1 is elected as the primary node, and replica 2 does not have
enough votes.
3. Replica 1 is down, ie the new primary node down again in a short
time.
4. Replica 2 know that the new primary node is down and wants to
initiate
a failover, but because the failover_auth_time of the previous round
has not been reset, it needs to wait for it to time out and then wait
for the next retry time, which will take cluster-node-timeout * 4 times,
this adds a lot of delay.
There is another problem. Like we will set additional random time for
failover_auth_time, such as random 500ms and replicas ranking 1s. If
replica 2 receives PONG from the new primary node before sending the
FAILOVER_AUTH_REQUEST, that is, before the failover_auth_time, it will
change itself to a replica. If the new primary node goes down again at
this time, replica 2 will use the previous failover_auth_time to
initiate
an election instead of going through the logic of random 500ms and
replicas ranking 1s again, which may lead to unexpected consequences
(for example, a low-ranking replica initiates an election and becomes
the new primary node).
That is, we need to reset failover_auth_time at the appropriate time.
When the replica switches to a new primary, we reset it, because the
existing failover_auth_time is already out of date in this case.
---------
Signed-off-by: Binbin <binloveplay1314@qq.com>
Fix#784
Prior to the change, `CLUSTER SHARDS` command processing might pick a
failed primary node which won't have the slot coverage information and
the slots `output` in turn would be empty. This change finds an
appropriate node which has the slot coverage information served by a
given shard and correctly displays it as part of `CLUSTER SHARDS`
output.
Before:
```
1) 1) "slots"
2) (empty array)
3) "nodes"
4) 1) 1) "id"
2) "2936f22a490095a0a851b7956b0a88f2b67a5d44"
...
9) "role"
10) "master"
...
13) "health"
14) "fail"
```
After:
```
1) 1) "slots"
2) 1) 0
2) 5461
3) "nodes"
4) 1) 1) "id"
2) "2936f22a490095a0a851b7956b0a88f2b67a5d44"
...
9) "role"
10) "master"
...
13) "health"
14) "fail"
```
---------
Signed-off-by: Harkrishn Patro <harkrisp@amazon.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>
Fixes a regression introduced in PR #445, which allowed a message from a
replica
to update the slot ownership of its primary. The regression results in a
`replicaof` cycle, causing server crashes due to the cycle detection
assert. The
fix restores the previous behavior where only primary senders can
trigger
`clusterUpdateSlotsConfigWith`.
Additional changes:
* Handling of primaries without slots is obsoleted by new handling of
when a
sender that was a replica announces that it is now a primary.
* Replication loop detection code is unchanged but shifted downwards.
* Some variables are renamed for better readability and some are
introduced to
avoid repeated memcmp() calls.
Fixes#753.
---------
Signed-off-by: Ping Xie <pingxie@google.com>
Implementing the change proposed here:
https://github.com/valkey-io/valkey/issues/487
In this PR, we prevent tracking new custom error messages (e.g. LUA) if
the number of error messages (in the errors RAX) is greater than 128.
Instead, we will track any additional custom error prefix in a new
counter: `errorstat_ERRORSTATS_OVERFLOW ` and if any non-custom flagged
errors (e.g. MOVED / CLUSTERDOWN) occur, they will continue to be
tracked as usual.
This will address the issue of spammed error messages / memory usage of
the errors RAX. Additionally, we will not have to execute `CONFIG
RESETSTAT` to restore error stats functionality because normal error
messages continue to be tracked.
Example:
```
# Errorstats
.
.
.
errorstat_127:count=2
errorstat_128:count=2
errorstat_ERR:count=1
errorstat_ERRORSTATS_OVERFLOW:count=2
```
---------
Signed-off-by: Karthik Subbarao <karthikrs2021@gmail.com>
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
The test fails because, in external, another test may have
enabled appendonly, causing acklocal to return 1.
We can add a CONFIG SET to disable the appendonly, but this
is not safe too unless we use multi. The test does not actually
rely on appendonly, so we can just * it.
Fixes#770.
Signed-off-by: Binbin <binloveplay1314@qq.com>
New configs:
* `cluster-announce-client-ipv4`
* `cluster-announce-client-ipv6`
New module API function:
* `ValkeyModule_GetClusterNodeInfoForClient`, takes a client id and is
otherwise just like its non-ForClient cousin.
If configured, one of these IP addresses are reported to each client in
CLUSTER SLOTS, CLUSTER SHARDS, CLUSTER NODES and redirects, replacing
the IP (`custer-announce-ip` or the auto-detected IP) of each node.
Which one is reported to the client depends on whether the client is
connected over IPv4 or IPv6.
Benefits:
* This allows clients using IPv4 to get the IPv4 addresses of all
cluster nodes and IPv6 clients to get the IPv6 clients.
* This allows the IPs visible to clients to be different to the IPs used
between the cluster nodes due to NAT'ing.
The information is propagated in the cluster bus using new Ping
extensions. (Old nodes without this feature ignore unknown Ping
extensions.)
This adds another dimension to CLUSTER SLOTS reply. It now depends on
the client's use of TLS, the IP address family and RESP version.
Refactoring: The cached connection type definition is moved from
connection.h (it actually has nothing to do with the connection
abstraction) to server.h and is changed to a bitmap, with one bit for
each of TLS, IPv6 and RESP3.
Fixes#337
---------
Signed-off-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
Test case "EVAL - Scripts do not block on waitaof" observed to fail in
e.g.
https://github.com/valkey-io/valkey/actions/runs/9860131487/job/27233756421?pr=688
It can happen that the local AOF has been written and 1 is returned here
where 0 is expected. Writing a key inside the EVAL script makes sure
there's no time to write the AOF.
Signed-off-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
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>
Currently, for nested MULTI or executing WATCH in MULTI, we will return
an error but we will not abort the transaction.
```
127.0.0.1:6379> multi
OK
127.0.0.1:6379(TX)> multi
(error) ERR MULTI calls can not be nested
127.0.0.1:6379(TX)> set key value
QUEUED
127.0.0.1:6379(TX)> exec
1) OK
127.0.0.1:6379> multi
OK
127.0.0.1:6379(TX)> watch key
(error) ERR WATCH inside MULTI is not allowed
127.0.0.1:6379(TX)> set key value
QUEUED
127.0.0.1:6379(TX)> exec
1) OK
```
This is an unexpected behavior that should abort the transaction.
The number of elements returned by EXEC also doesn't match the number
of commands in MULTI.
Add the NO_MULTI flag to them so that they will
be rejected in processCommand and rejectCommand will abort the
transaction.
So there are two visible changes:
- Different words in the error messages. (Command not allowed inside a
transaction)
- Exec returns error.
Signed-off-by: Binbin <binloveplay1314@qq.com>
Module Authentication using a blocking implementation currently gets
rejected when the "cluster is down" from the client timeout cron job
(`clientsCronHandleTimeout`).
This PR exempts clients blocked on Module Authentication from being
rejected here.
---------
Signed-off-by: KarthikSubbarao <karthikrs2021@gmail.com>
cluster-slots test is tesing a very fragmented slots range of a
relatively large cluster. For this reason, when run under valgrind, some
of the nodes are timing out when cluster is attempting to converge and
propagate.
This pr sets the test's cluster-node-timeout to 90000 and
cluster-ping-interval to 1000.
Signed-off-by: ranshid <ranshid@amazon.com>
Test failed in my local:
```
*** [err]: CLUSTER SLOT-STATS ORDERBY LIMIT correct response pagination, where limit is less than number of assigned slots in tests/unit/cluster/slot-stats.tcl
Expected [dict exists 0 0 1 0 2 0 3 0 4 0 16383] (context: type source line 64 file /xxx/tests/unit/cluster/slot-stats.tcl cmd {assert {[dict exists $expected_slots $slot]}} proc ::assert_slot_visibility level 1)
```
It seems that when the stat is equal, that is, when the key-count is
equal,
the qsort performance will be different. When the stat is equal, we
compare
by slot (in ascending order).
Signed-off-by: Binbin <binloveplay1314@qq.com>
We did not set a default value for limit, but it will be used
in addReplyOrderBy later, the undefined behavior may crash the
server since the value could be negative and crash will happen
in addReplyArrayLen.
An interesting reproducible example (limit reuses the value of -1):
```
> cluster slot-stats orderby key-count desc limit -1
(error) ERR Limit has to lie in between 1 and 16384 (maximum number of slots).
> cluster slot-stats orderby key-count desc
Error: Server closed the connection
```
Set the default value of limit to 16384.
---------
Signed-off-by: Binbin <binloveplay1314@qq.com>
The command provides detailed slot usage statistics upon invocation,
with initial support for key-count metric. cpu-usec (approved) and
memory-bytes (pending-approval) metrics will soon follow after the
merger of this PR.
---------
Signed-off-by: Kyle Kim <kimkyle@amazon.com>
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
Co-authored-by: Madelyn Olson <madelyneolson@gmail.com>
In some scenarios, the business may not be able to find the
previously used Lua script and only have a SHA signature.
Or there are multiple identical evalsha's args in monitor/slowlog,
and admin is not able to distinguish the script body.
Add a new script subcommmand to show the contents of script
given the scripts sha1. Returns a NOSCRIPT error if the script
is not present in the cache.
Usage: `SCRIPT SHOW sha1`
Complexity: `O(1)`
Closes#604.
Doc PR: https://github.com/valkey-io/valkey-doc/pull/143
---------
Signed-off-by: wei.kukey <wei.kukey@gmail.com>
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
Co-authored-by: Madelyn Olson <madelyneolson@gmail.com>
Co-authored-by: Binbin <binloveplay1314@qq.com>
Co-authored-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
In markNodeAsFailingIfNeeded we will count needed_quorum and failures,
needed_quorum is the half the cluster->size and plus one, and
cluster-size
is the size of primary node which contain slots, but when counting
failures, we dit not check if primary has slots.
Only the primary has slots that has the rights to vote, adding a new
clusterNodeIsVotingPrimary to formalize this concept.
Release notes:
bugfix where nodes not in the quorum group might spuriously mark nodes
as failed
---------
Signed-off-by: Binbin <binloveplay1314@qq.com>
Co-authored-by: Ping Xie <pingxie@outlook.com>
When there is a link failure while an ongoing MEET request is sent the
sending node stops sending anymore MEET and starts sending PINGs. Since
every node responds to PINGs from unknown nodes with a PONG, the
receiving node never adds the sending node. But the sending node adds
the receiving node when it sees a PONG. This can lead to asymmetry in
cluster membership. This changes makes the sender keep sending MEET
until it sees a PONG, avoiding the asymmetry.
---------
Signed-off-by: Sankar <1890648+srgsanky@users.noreply.github.com>
In ad28d222edcef9d4496fd7a94656013f07dd08e5, we added a Lua eval
scripts eviction. If the script was previously added via EVAL, we
promote it to SCRIPT LOAD, prevent it from being evicted later.
Signed-off-by: Binbin <binloveplay1314@qq.com>
Added a wait_for_condition to avoid the timing issue.
```
*** [err]: query buffer resized correctly in tests/unit/querybuf.tcl
Expected 11 >= 16384 && 11 <= 32770 (context: type eval line 24 cmd {assert {$orig_test_client_qbuf >= 16384 && $orig_test_client_qbuf <= $MAX_QUERY_BUFFER_SIZE}} proc ::test)
*** [err]: query buffer resized correctly when not idle in tests/unit/querybuf.tcl
Expected 11 > 32768 (context: type eval line 14 cmd {assert {$orig_test_client_qbuf > 32768}} proc ::test)
*** [err]: query buffer resized correctly with fat argv in tests/unit/querybuf.tcl
query buffer should not be resized when client idle time smaller than 2s
```
Signed-off-by: Uri Yagelnik <uriy@amazon.com>
We've been seeing some pretty consistent failures from
`test-valgrind-test` and `test-sanitizer-address` because of the
querybuf test periodically failing. I tracked it down to the test
periodically taking too long and the client cron getting triggered. A
simple solution is to just disable the cron during the key race
condition. I was able to run this locally for 100 iterations without
seeing a failure.
Example:
https://github.com/valkey-io/valkey/actions/runs/9474458354/job/26104103514
and
https://github.com/valkey-io/valkey/actions/runs/9474458354/job/26104106830.
Signed-off-by: Madelyn Olson <matolson@amazon.com>
Make the one backwards compatible config change we are allowed to
replace for removing master from our API.
`masterauth` and `masteruser` are still used as an alias, but aren't
explicitly referenced. As an addendum to
https://github.com/valkey-io/valkey/pull/591, it would be good to have
this in 8. Given the related PR for updated other references for master,
I just updated the ones around this specific change.
Signed-off-by: Madelyn Olson <madelyneolson@gmail.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>
"Client blocked on XREADGROUP while stream's slot is migrated" uses the
migrate command, which requires special handling for TLS and non-tls.
This was not being handled, so was throwing an error.
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
Test `query buffer resized correctly` start to fail
(https://github.com/valkey-io/valkey/actions/runs/9278013807) with
non-jemalloc allocators after
https://github.com/valkey-io/valkey/pull/258 PR.
With Jemalloc we allocate ~20K for the query buffer, in the test we read
1 byte in the first read, in the second read we make sure we have at
least 16KB free place in the query buffer and we have as Jemalloc
allocated 20KB, But with non jemalloc we allocate in the first read
exactly 16KB. in the second read we check and see that we don't have
16KB free space as we already read 1 byte hence we reallocate this time
greedly (*2 of the requested size of 16KB+1) hence the test condition
that the querybuf size is < 32KB is no longer true
The `query buffer resized correctly test` starts
[failing](https://github.com/valkey-io/valkey/actions/runs/9278013807)
with non-jemalloc allocators after PR #258 .
With jemalloc, we allocate ~20KB for the query buffer. In the test, we
read 1 byte initially and then ensure there is at least 16KB of free
space in the buffer for the second read, which is satisfied by
jemalloc's 20KB allocation. However, with non-jemalloc allocators, the
first read allocates exactly 16KB. When we check again, we don't have
16KB free due to the 1 byte already read. This triggers a greedy
reallocation (doubling the requested size of 16KB+1), causing the query
buffer size to exceed the 32KB limit, thus failing the test condition.
This PR adjusted the test query buffer upper limit to be 32KB +2.
Signed-off-by: Uri Yagelnik <uriy@amazon.com>
When LRU/LFU enabled, Valkey does not allow using shared objects, as
value objects may be shared among many different keys and they can't
share LRU/LFU information.
However `maxmemory-policy` is modifiable at runtime. If LRU/LFU is not
enabled at start, but then enabled when some shared objects are already
used, there could be some confusion in LRU/LFU information.
For `set` command it is OK since it is going to create a new object when
LRU/LFU enabled, but `get` command will not unshare the object and just
update LRU/LFU information.
So we may duplicate the object in this case. It is a one-time task for
each key using shared objects, unless this is the case for so many keys,
there should be no serious performance degradation.
Still, LRU will be updated anyway, no matter LRU/LFU is enabled or not,
because `OBJECT IDLETIME` needs it, unless `maxmemory-policy` is set to
LFU. So idle time of a key may still be messed up.
---------
Signed-off-by: chentianjie.ctj <chentianjie.ctj@alibaba-inc.com>
Signed-off-by: Chen Tianjie <TJ_Chen@outlook.com>
In #11012, we changed the way command durations were computed to handle
the same command being executed multiple times. In #11970, we added an
assert if the duration is not properly reset, potentially indicating
that a call to report statistics was missed.
I found an edge case where this happens - easily reproduced by blocking
a client on `XGROUPREAD` and migrating the stream's slot. This causes
the engine to process the `XGROUPREAD` command twice:
1. First time, we are blocked on the stream, so we wait for unblock to
come back to it a second time. In most cases, when we come back to
process the command second time after unblock, we process the command
normally, which includes recording the duration and then resetting it.
2. After unblocking we come back to process the command, and this is
where we hit the edge case - at this point, we had already migrated the
slot to another node, so we return a `MOVED` response. But when we do
that, we don’t reset the duration field.
Fix: also reset the duration when returning a `MOVED` response. I think
this is right, because the client should redirect the command to the
right node, which in turn will calculate the execution duration.
Also wrote a test which reproduces this, it fails without the fix and
passes with it.
---------
Signed-off-by: Nitai Caro <caronita@amazon.com>
Co-authored-by: Nitai Caro <caronita@amazon.com>
In #53, we will cache the CLUSTER SLOTS response to improve the
throughput and reduct the latency.
In the code snippet below, the second cluster slots will use the
old hostname:
```
config set cluster-preferred-endpoint-type hostname
config set cluster-announce-hostname old-hostname.com
multi
cluster slots
config set cluster-announce-hostname new-hostname.com
cluster slots
exec
```
When updating the hostname, in updateAnnouncedHostname, we will set
CLUSTER_TODO_SAVE_CONFIG and we will do a clearCachedClusterSlotsResponse
in clusterSaveConfigOrDie, so harmless in most cases.
Move the clearCachedClusterSlotsResponse call to clusterDoBeforeSleep
instead of scheduling it to be called in clusterSaveConfigOrDie.
Signed-off-by: Binbin <binloveplay1314@qq.com>
_This change is the thing I suggested to redis when it was BSD, and is
not just migration - this is of course more advanced_
### Issue
There is weird difference in syntax between BITPOS and BITCOUNT:
```
BITPOS key bit [start [end [BYTE | BIT]]]
BITCOUNT key [start end [BYTE | BIT]]
```
I think this might cause confusion in terms of usability.
It was not just a syntax typo error, and really works differently.
The results below are with unstable build:
```
> get TEST:ABCD
"ABCD"
> BITPOS TEST:ABCD 1 0 -1
(integer) 1
> BITCOUNT TEST:ABCD 0 -1
(integer) 9
> BITPOS TEST:ABCD 1 0
(integer) 1
> BITCOUNT TEST:ABCD 0
(error) ERR syntax error
```
### What did I fix
simply changes logic, to accept BITCOUNT also without 'end' - 'end'
become optional, like BITPOS
```
> GET TEST:ABCD
"ABCD"
> BITPOS TEST:ABCD 1 0 -1
(integer) 1
> BITCOUNT TEST:ABCD 0 -1
(integer) 9
> BITPOS TEST:ABCD 1 0
(integer) 1
> BITCOUNT TEST:ABCD 0
(integer) 9
```
Of course, I also fixed syntax hint:
```
# ASIS
> BITCOUNT key [start end [BYTE|BIT]]
# TOBE
> BITCOUNT key [start [end [BYTE|BIT]]]
```
### Moreover ...
I hadn't noticed that there was very small dead code in these command
logic, when I wrote PR to redis.
I found it now, when write code again, so I wrote it in valkey.
``` c
/* asis unstable */
/* bitcountCommand() */
if (!strcasecmp(c->argv[4]->ptr,"bit")) isbit = 1;
// ...
if (c->argc < 4) {
if (isbit) end = (totlen<<3) + 7;
else end = totlen-1;
}
/* bitposCommand() */
if (!strcasecmp(c->argv[5]->ptr,"bit")) isbit = 1;
// ...
if (c->argc < 5) {
if (isbit) end = (totlen<<3) + 7;
else end = totlen-1;
}
```
Bit variable (actually int) "isbit" is only being set as 1, when 'BIT'
is declared.
But we were checking whether 'isbit' is true or false in this 'if'
phrase, even if isbit could never be 1, because argc is always less than
4 (or 5 in bitpos).
I think this minor fixes will make valkey command operation more
consistent.
Of course, this PR contains just changing args from "required" to
"optional", so it will never hurt previous users.
Thanks,
---------
Signed-off-by: LiiNen <kjeonghoon065@gmail.com>
Co-authored-by: Madelyn Olson <34459052+madolson@users.noreply.github.com>
This PR optimizes client query buffer handling in Valkey by introducing
a shared query buffer that is used by default for client reads. This
reduces memory usage by ~20KB per client by avoiding allocations for
most clients using short (<16KB) complete commands. For larger or
partial commands, the client still gets its own private buffer.
The primary changes are:
* Adding a shared query buffer `shared_qb` that clients use by default
* Modifying client querybuf initialization and reset logic
* Copying any partial query from shared to private buffer before command
execution
* Freeing idle client query buffers when empty to allow reuse of shared
buffer
* Master client query buffers are kept private as their contents need to
be preserved for replication stream
In addition to the memory savings, this change shows a 3% improvement in
latency and throughput when running with 1000 active clients.
The memory reduction may also help reduce the need to evict clients when
reaching max memory limit, as the query buffer is the main memory
consumer per client.
---------
Signed-off-by: Uri Yagelnik <uriy@amazon.com>
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
Co-authored-by: Madelyn Olson <madelyneolson@gmail.com>
The races are between the '$rd' client and the 'r' client in the test
case.
Test case "client input output and command process statistics" in
unit/introspection.
---------
Signed-off-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
This aligns the behaviour with established Valkey commands with a
TIMEOUT argument, such as BLPOP.
Fix#422
Signed-off-by: Ping Xie <pingxie@google.com>
After READONLY, make a cluster replica behave as its primary regarding
returning ASK redirects and TRYAGAIN.
Without this patch, a client reading from a replica cannot tell if a key
doesn't exist or if it has already been migrated to another shard as
part of an ongoing slot migration. Therefore, without an ASK redirect in
this situation, offloading reads to cluster replicas wasn't reliable.
Note: The target of a redirect is always a primary. If a client wants to
continue reading from a replica after following a redirect, it needs to
figure out the replicas of that new primary using CLUSTER SHARDS or
similar.
This is related to #21 and has been made possible by the introduction of
Replication of Slot Migration States in #445.
----
Release notes:
During cluster slot migration, replicas are able to return -ASK
redirects and -TRYAGAIN.
---------
Signed-off-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
This commit adds a logic to cache `CLUSTER SLOTS` response for reduced
latency and also updates the cache when a change in the cluster is
detected.
Historically, `CLUSTER SLOTS` command was deprecated, however all the
server clients have been using `CLUSTER SLOTS` and have not migrated to
`CLUSTER SHARDS`. In future this logic can be added to any other
commands to improve the performance of the engine.
---------
Signed-off-by: Roshan Khatri <rvkhatri@amazon.com>
Commit 07ed0eafa98a66 introduced some SCAN improvements, but some
changes were postponed to a later version (8.0), which this PR finishes:
1. Prepare to move the TYPE filtering to the scan callback as well. this
was put on hold since it has side effects that can be considered a
breaking change, which is that we will not attempt to do lazy expire
(delete) a key that was filtered by not matching the TYPE (changing it
would mean TYPE filter starts behaving the same as MATCH filter already
does in that respect).
2. when the specified key TYPE filter is an unknown type, server will
reply a error immediately instead of doing a full scan that comes back
empty handed.
Fixes#235
Release notes:
> SCAN: Expired keys that don't match the TYPE argument for the SCAN are
no longer deleted by SCAN
Signed-off-by: Viktor Söderqvist <viktor.soderqvist@est.tech>
This patch try to correct the actual allocated size from allocator
when call sdsRedize to align the logic with sdsnewlen function.
Maybe the https://github.com/valkey-io/valkey/pull/453 optimization
should depend on this.
Signed-off-by: Lipeng Zhu <lipeng.zhu@intel.com>
