2022-01-02 08:50:15 +01:00
|
|
|
# This test suite tests shutdown when there are lagging replicas connected.
|
|
|
|
|
|
|
|
|
|
# Fill up the OS socket send buffer for the replica connection 1M at a time.
|
|
|
|
|
# When the replication buffer memory increases beyond 2M (often after writing 4M
|
|
|
|
|
# or so), we assume it's because the OS socket send buffer can't swallow
|
|
|
|
|
# anymore.
|
|
|
|
|
proc fill_up_os_socket_send_buffer_for_repl {idx} {
|
|
|
|
|
set i 0
|
|
|
|
|
while {1} {
|
|
|
|
|
incr i
|
|
|
|
|
populate 1024 junk$i: 1024 $idx
|
|
|
|
|
after 10
|
|
|
|
|
set buf_size [s $idx mem_total_replication_buffers]
|
|
|
|
|
if {$buf_size > 2*1024*1024} {
|
|
|
|
|
break
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
foreach how {sigterm shutdown} {
|
|
|
|
|
test "Shutting down master waits for replica to catch up ($how)" {
|
2024-08-21 23:59:02 +08:00
|
|
|
start_server {overrides {save "" repl-backlog-size 1MB}} {
|
|
|
|
|
start_server {overrides {save "" repl-backlog-size 1MB}} {
|
2022-01-02 08:50:15 +01:00
|
|
|
set master [srv -1 client]
|
|
|
|
|
set master_host [srv -1 host]
|
|
|
|
|
set master_port [srv -1 port]
|
|
|
|
|
set master_pid [srv -1 pid]
|
|
|
|
|
set replica [srv 0 client]
|
|
|
|
|
set replica_pid [srv 0 pid]
|
|
|
|
|
|
|
|
|
|
# Config master.
|
|
|
|
|
$master config set shutdown-timeout 300; # 5min for slow CI
|
|
|
|
|
$master config set repl-backlog-size 1; # small as possible
|
|
|
|
|
$master config set hz 100; # cron runs every 10ms
|
|
|
|
|
|
|
|
|
|
# Config replica.
|
|
|
|
|
$replica replicaof $master_host $master_port
|
|
|
|
|
wait_for_sync $replica
|
|
|
|
|
|
|
|
|
|
# Preparation: Set k to 1 on both master and replica.
|
|
|
|
|
$master set k 1
|
|
|
|
|
wait_for_ofs_sync $master $replica
|
|
|
|
|
|
|
|
|
|
# Pause the replica.
|
Attempt to solve MacOS CI issues in GH Actions (#12013)
The MacOS CI in github actions often hangs without any logs. GH argues that
it's due to resource utilization, either running out of disk space, memory, or CPU
starvation, and thus the runner is terminated.
This PR contains multiple attempts to resolve this:
1. introducing pause_process instead of SIGSTOP, which waits for the process
to stop before resuming the test, possibly resolving race conditions in some tests,
this was a suspect since there was one test that could result in an infinite loop in that
case, in practice this didn't help, but still a good idea to keep.
2. disable the `save` config in many tests that don't need it, specifically ones that use
heavy writes and could create large files.
3. change the `populate` proc to use short pipeline rather than an infinite one.
4. use `--clients 1` in the macos CI so that we don't risk running multiple resource
demanding tests in parallel.
5. enable `--verbose` to be repeated to elevate verbosity and print more info to stdout
when a test or a server starts.
2023-04-12 09:19:21 +03:00
|
|
|
pause_process $replica_pid
|
2022-01-02 08:50:15 +01:00
|
|
|
|
|
|
|
|
# Fill up the OS socket send buffer for the replica connection
|
|
|
|
|
# to prevent the following INCR from reaching the replica via
|
|
|
|
|
# the OS.
|
|
|
|
|
fill_up_os_socket_send_buffer_for_repl -1
|
|
|
|
|
|
|
|
|
|
# Incr k and immediately shutdown master.
|
|
|
|
|
$master incr k
|
|
|
|
|
switch $how {
|
|
|
|
|
sigterm {
|
|
|
|
|
exec kill -SIGTERM $master_pid
|
|
|
|
|
}
|
|
|
|
|
shutdown {
|
2024-04-09 10:38:09 -04:00
|
|
|
set rd [valkey_deferring_client -1]
|
2022-01-02 08:50:15 +01:00
|
|
|
$rd shutdown
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
wait_for_condition 50 100 {
|
|
|
|
|
[s -1 shutdown_in_milliseconds] > 0
|
|
|
|
|
} else {
|
|
|
|
|
fail "Master not indicating ongoing shutdown."
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Wake up replica and check if master has waited for it.
|
|
|
|
|
after 20; # 2 cron intervals
|
Attempt to solve MacOS CI issues in GH Actions (#12013)
The MacOS CI in github actions often hangs without any logs. GH argues that
it's due to resource utilization, either running out of disk space, memory, or CPU
starvation, and thus the runner is terminated.
This PR contains multiple attempts to resolve this:
1. introducing pause_process instead of SIGSTOP, which waits for the process
to stop before resuming the test, possibly resolving race conditions in some tests,
this was a suspect since there was one test that could result in an infinite loop in that
case, in practice this didn't help, but still a good idea to keep.
2. disable the `save` config in many tests that don't need it, specifically ones that use
heavy writes and could create large files.
3. change the `populate` proc to use short pipeline rather than an infinite one.
4. use `--clients 1` in the macos CI so that we don't risk running multiple resource
demanding tests in parallel.
5. enable `--verbose` to be repeated to elevate verbosity and print more info to stdout
when a test or a server starts.
2023-04-12 09:19:21 +03:00
|
|
|
resume_process $replica_pid
|
2022-01-02 08:50:15 +01:00
|
|
|
wait_for_condition 300 1000 {
|
|
|
|
|
[$replica get k] eq 2
|
|
|
|
|
} else {
|
|
|
|
|
fail "Master exited before replica could catch up."
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Check shutdown log messages on master
|
|
|
|
|
wait_for_log_messages -1 {"*ready to exit, bye bye*"} 0 100 500
|
|
|
|
|
assert_equal 0 [count_log_message -1 "*Lagging replica*"]
|
|
|
|
|
verify_log_message -1 "*1 of 1 replicas are in sync*" 0
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
} {} {repl external:skip}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
test {Shutting down master waits for replica timeout} {
|
2024-08-21 23:59:02 +08:00
|
|
|
start_server {overrides {save "" repl-backlog-size 1MB}} {
|
|
|
|
|
start_server {overrides {save "" repl-backlog-size 1MB}} {
|
2022-01-02 08:50:15 +01:00
|
|
|
set master [srv -1 client]
|
|
|
|
|
set master_host [srv -1 host]
|
|
|
|
|
set master_port [srv -1 port]
|
|
|
|
|
set master_pid [srv -1 pid]
|
|
|
|
|
set replica [srv 0 client]
|
|
|
|
|
set replica_pid [srv 0 pid]
|
|
|
|
|
|
|
|
|
|
# Config master.
|
|
|
|
|
$master config set shutdown-timeout 1; # second
|
|
|
|
|
|
|
|
|
|
# Config replica.
|
|
|
|
|
$replica replicaof $master_host $master_port
|
|
|
|
|
wait_for_sync $replica
|
|
|
|
|
|
|
|
|
|
# Preparation: Set k to 1 on both master and replica.
|
|
|
|
|
$master set k 1
|
|
|
|
|
wait_for_ofs_sync $master $replica
|
|
|
|
|
|
|
|
|
|
# Pause the replica.
|
Attempt to solve MacOS CI issues in GH Actions (#12013)
The MacOS CI in github actions often hangs without any logs. GH argues that
it's due to resource utilization, either running out of disk space, memory, or CPU
starvation, and thus the runner is terminated.
This PR contains multiple attempts to resolve this:
1. introducing pause_process instead of SIGSTOP, which waits for the process
to stop before resuming the test, possibly resolving race conditions in some tests,
this was a suspect since there was one test that could result in an infinite loop in that
case, in practice this didn't help, but still a good idea to keep.
2. disable the `save` config in many tests that don't need it, specifically ones that use
heavy writes and could create large files.
3. change the `populate` proc to use short pipeline rather than an infinite one.
4. use `--clients 1` in the macos CI so that we don't risk running multiple resource
demanding tests in parallel.
5. enable `--verbose` to be repeated to elevate verbosity and print more info to stdout
when a test or a server starts.
2023-04-12 09:19:21 +03:00
|
|
|
pause_process $replica_pid
|
2022-01-02 08:50:15 +01:00
|
|
|
|
|
|
|
|
# Fill up the OS socket send buffer for the replica connection to
|
|
|
|
|
# prevent the following INCR k from reaching the replica via the OS.
|
|
|
|
|
fill_up_os_socket_send_buffer_for_repl -1
|
|
|
|
|
|
|
|
|
|
# Incr k and immediately shutdown master.
|
|
|
|
|
$master incr k
|
|
|
|
|
exec kill -SIGTERM $master_pid
|
|
|
|
|
wait_for_condition 50 100 {
|
|
|
|
|
[s -1 shutdown_in_milliseconds] > 0
|
|
|
|
|
} else {
|
|
|
|
|
fail "Master not indicating ongoing shutdown."
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Let master finish shutting down and check log.
|
|
|
|
|
wait_for_log_messages -1 {"*ready to exit, bye bye*"} 0 100 100
|
|
|
|
|
verify_log_message -1 "*Lagging replica*" 0
|
|
|
|
|
verify_log_message -1 "*0 of 1 replicas are in sync*" 0
|
|
|
|
|
|
|
|
|
|
# Wake up replica.
|
Attempt to solve MacOS CI issues in GH Actions (#12013)
The MacOS CI in github actions often hangs without any logs. GH argues that
it's due to resource utilization, either running out of disk space, memory, or CPU
starvation, and thus the runner is terminated.
This PR contains multiple attempts to resolve this:
1. introducing pause_process instead of SIGSTOP, which waits for the process
to stop before resuming the test, possibly resolving race conditions in some tests,
this was a suspect since there was one test that could result in an infinite loop in that
case, in practice this didn't help, but still a good idea to keep.
2. disable the `save` config in many tests that don't need it, specifically ones that use
heavy writes and could create large files.
3. change the `populate` proc to use short pipeline rather than an infinite one.
4. use `--clients 1` in the macos CI so that we don't risk running multiple resource
demanding tests in parallel.
5. enable `--verbose` to be repeated to elevate verbosity and print more info to stdout
when a test or a server starts.
2023-04-12 09:19:21 +03:00
|
|
|
resume_process $replica_pid
|
2022-01-02 08:50:15 +01:00
|
|
|
assert_equal 1 [$replica get k]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
} {} {repl external:skip}
|
|
|
|
|
|
|
|
|
|
test "Shutting down master waits for replica then fails" {
|
2024-08-21 23:59:02 +08:00
|
|
|
start_server {overrides {save "" repl-backlog-size 1MB}} {
|
|
|
|
|
start_server {overrides {save "" repl-backlog-size 1MB}} {
|
2022-01-02 08:50:15 +01:00
|
|
|
set master [srv -1 client]
|
|
|
|
|
set master_host [srv -1 host]
|
|
|
|
|
set master_port [srv -1 port]
|
|
|
|
|
set master_pid [srv -1 pid]
|
|
|
|
|
set replica [srv 0 client]
|
|
|
|
|
set replica_pid [srv 0 pid]
|
|
|
|
|
|
|
|
|
|
# Config master and replica.
|
|
|
|
|
$replica replicaof $master_host $master_port
|
|
|
|
|
wait_for_sync $replica
|
|
|
|
|
|
|
|
|
|
# Pause the replica and write a key on master.
|
Attempt to solve MacOS CI issues in GH Actions (#12013)
The MacOS CI in github actions often hangs without any logs. GH argues that
it's due to resource utilization, either running out of disk space, memory, or CPU
starvation, and thus the runner is terminated.
This PR contains multiple attempts to resolve this:
1. introducing pause_process instead of SIGSTOP, which waits for the process
to stop before resuming the test, possibly resolving race conditions in some tests,
this was a suspect since there was one test that could result in an infinite loop in that
case, in practice this didn't help, but still a good idea to keep.
2. disable the `save` config in many tests that don't need it, specifically ones that use
heavy writes and could create large files.
3. change the `populate` proc to use short pipeline rather than an infinite one.
4. use `--clients 1` in the macos CI so that we don't risk running multiple resource
demanding tests in parallel.
5. enable `--verbose` to be repeated to elevate verbosity and print more info to stdout
when a test or a server starts.
2023-04-12 09:19:21 +03:00
|
|
|
pause_process $replica_pid
|
2022-01-02 08:50:15 +01:00
|
|
|
$master incr k
|
|
|
|
|
|
|
|
|
|
# Two clients call blocking SHUTDOWN in parallel.
|
2024-04-09 10:38:09 -04:00
|
|
|
set rd1 [valkey_deferring_client -1]
|
|
|
|
|
set rd2 [valkey_deferring_client -1]
|
2022-01-02 08:50:15 +01:00
|
|
|
$rd1 shutdown
|
|
|
|
|
$rd2 shutdown
|
Async IO threads (#758)
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
(https://github.com/valkey-io/valkey/blob/443d80f1686377ad42cbf92d98ecc6d240325ee1/.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>
2024-07-09 06:01:39 +03:00
|
|
|
wait_for_condition 50 100 {
|
|
|
|
|
[llength [lsearch -all [split [string trim [$master client list]] "\r\n"] *cmd=shutdown*]] == 2
|
|
|
|
|
} else {
|
|
|
|
|
fail "SHUTDOWN not called on all clients"
|
|
|
|
|
}
|
|
|
|
|
|
2022-01-02 08:50:15 +01:00
|
|
|
set info_clients [$master info clients]
|
|
|
|
|
assert_match "*connected_clients:3*" $info_clients
|
|
|
|
|
assert_match "*blocked_clients:2*" $info_clients
|
|
|
|
|
|
|
|
|
|
# Start a very slow initial AOFRW, which will prevent shutdown.
|
|
|
|
|
$master config set rdb-key-save-delay 30000000; # 30 seconds
|
|
|
|
|
$master config set appendonly yes
|
|
|
|
|
|
|
|
|
|
# Wake up replica, causing master to continue shutting down.
|
Attempt to solve MacOS CI issues in GH Actions (#12013)
The MacOS CI in github actions often hangs without any logs. GH argues that
it's due to resource utilization, either running out of disk space, memory, or CPU
starvation, and thus the runner is terminated.
This PR contains multiple attempts to resolve this:
1. introducing pause_process instead of SIGSTOP, which waits for the process
to stop before resuming the test, possibly resolving race conditions in some tests,
this was a suspect since there was one test that could result in an infinite loop in that
case, in practice this didn't help, but still a good idea to keep.
2. disable the `save` config in many tests that don't need it, specifically ones that use
heavy writes and could create large files.
3. change the `populate` proc to use short pipeline rather than an infinite one.
4. use `--clients 1` in the macos CI so that we don't risk running multiple resource
demanding tests in parallel.
5. enable `--verbose` to be repeated to elevate verbosity and print more info to stdout
when a test or a server starts.
2023-04-12 09:19:21 +03:00
|
|
|
resume_process $replica_pid
|
2022-01-02 08:50:15 +01:00
|
|
|
|
|
|
|
|
# SHUTDOWN returns an error to both clients blocking on SHUTDOWN.
|
|
|
|
|
catch { $rd1 read } e1
|
|
|
|
|
catch { $rd2 read } e2
|
|
|
|
|
assert_match "*Errors trying to SHUTDOWN. Check logs*" $e1
|
|
|
|
|
assert_match "*Errors trying to SHUTDOWN. Check logs*" $e2
|
|
|
|
|
$rd1 close
|
|
|
|
|
$rd2 close
|
|
|
|
|
|
|
|
|
|
# Check shutdown log messages on master.
|
|
|
|
|
verify_log_message -1 "*1 of 1 replicas are in sync*" 0
|
|
|
|
|
verify_log_message -1 "*Writing initial AOF, can't exit*" 0
|
|
|
|
|
verify_log_message -1 "*Errors trying to shut down*" 0
|
|
|
|
|
|
|
|
|
|
# Let master to exit fast, without waiting for the very slow AOFRW.
|
|
|
|
|
catch {$master shutdown nosave force}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
} {} {repl external:skip}
|
|
|
|
|
|
|
|
|
|
test "Shutting down master waits for replica then aborted" {
|
2024-08-21 23:59:02 +08:00
|
|
|
start_server {overrides {save "" repl-backlog-size 1MB}} {
|
|
|
|
|
start_server {overrides {save "" repl-backlog-size 1MB}} {
|
2022-01-02 08:50:15 +01:00
|
|
|
set master [srv -1 client]
|
|
|
|
|
set master_host [srv -1 host]
|
|
|
|
|
set master_port [srv -1 port]
|
|
|
|
|
set master_pid [srv -1 pid]
|
|
|
|
|
set replica [srv 0 client]
|
|
|
|
|
set replica_pid [srv 0 pid]
|
|
|
|
|
|
|
|
|
|
# Config master and replica.
|
|
|
|
|
$replica replicaof $master_host $master_port
|
|
|
|
|
wait_for_sync $replica
|
|
|
|
|
|
|
|
|
|
# Pause the replica and write a key on master.
|
Attempt to solve MacOS CI issues in GH Actions (#12013)
The MacOS CI in github actions often hangs without any logs. GH argues that
it's due to resource utilization, either running out of disk space, memory, or CPU
starvation, and thus the runner is terminated.
This PR contains multiple attempts to resolve this:
1. introducing pause_process instead of SIGSTOP, which waits for the process
to stop before resuming the test, possibly resolving race conditions in some tests,
this was a suspect since there was one test that could result in an infinite loop in that
case, in practice this didn't help, but still a good idea to keep.
2. disable the `save` config in many tests that don't need it, specifically ones that use
heavy writes and could create large files.
3. change the `populate` proc to use short pipeline rather than an infinite one.
4. use `--clients 1` in the macos CI so that we don't risk running multiple resource
demanding tests in parallel.
5. enable `--verbose` to be repeated to elevate verbosity and print more info to stdout
when a test or a server starts.
2023-04-12 09:19:21 +03:00
|
|
|
pause_process $replica_pid
|
2022-01-02 08:50:15 +01:00
|
|
|
$master incr k
|
|
|
|
|
|
|
|
|
|
# Two clients call blocking SHUTDOWN in parallel.
|
2024-04-09 10:38:09 -04:00
|
|
|
set rd1 [valkey_deferring_client -1]
|
|
|
|
|
set rd2 [valkey_deferring_client -1]
|
2022-01-02 08:50:15 +01:00
|
|
|
$rd1 shutdown
|
|
|
|
|
$rd2 shutdown
|
Async IO threads (#758)
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
(https://github.com/valkey-io/valkey/blob/443d80f1686377ad42cbf92d98ecc6d240325ee1/.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>
2024-07-09 06:01:39 +03:00
|
|
|
wait_for_condition 50 100 {
|
|
|
|
|
[llength [lsearch -all [split [string trim [$master client list]] "\r\n"] *cmd=shutdown*]] == 2
|
|
|
|
|
} else {
|
|
|
|
|
fail "SHUTDOWN not called on all clients"
|
|
|
|
|
}
|
|
|
|
|
|
2022-01-02 08:50:15 +01:00
|
|
|
set info_clients [$master info clients]
|
|
|
|
|
assert_match "*connected_clients:3*" $info_clients
|
|
|
|
|
assert_match "*blocked_clients:2*" $info_clients
|
|
|
|
|
|
|
|
|
|
# Abort the shutdown
|
|
|
|
|
$master shutdown abort
|
|
|
|
|
|
|
|
|
|
# Wake up replica, causing master to continue shutting down.
|
Attempt to solve MacOS CI issues in GH Actions (#12013)
The MacOS CI in github actions often hangs without any logs. GH argues that
it's due to resource utilization, either running out of disk space, memory, or CPU
starvation, and thus the runner is terminated.
This PR contains multiple attempts to resolve this:
1. introducing pause_process instead of SIGSTOP, which waits for the process
to stop before resuming the test, possibly resolving race conditions in some tests,
this was a suspect since there was one test that could result in an infinite loop in that
case, in practice this didn't help, but still a good idea to keep.
2. disable the `save` config in many tests that don't need it, specifically ones that use
heavy writes and could create large files.
3. change the `populate` proc to use short pipeline rather than an infinite one.
4. use `--clients 1` in the macos CI so that we don't risk running multiple resource
demanding tests in parallel.
5. enable `--verbose` to be repeated to elevate verbosity and print more info to stdout
when a test or a server starts.
2023-04-12 09:19:21 +03:00
|
|
|
resume_process $replica_pid
|
2022-01-02 08:50:15 +01:00
|
|
|
|
|
|
|
|
# SHUTDOWN returns an error to both clients blocking on SHUTDOWN.
|
|
|
|
|
catch { $rd1 read } e1
|
|
|
|
|
catch { $rd2 read } e2
|
|
|
|
|
assert_match "*Errors trying to SHUTDOWN. Check logs*" $e1
|
|
|
|
|
assert_match "*Errors trying to SHUTDOWN. Check logs*" $e2
|
|
|
|
|
$rd1 close
|
|
|
|
|
$rd2 close
|
|
|
|
|
|
|
|
|
|
# Check shutdown log messages on master.
|
|
|
|
|
verify_log_message -1 "*Shutdown manually aborted*" 0
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
} {} {repl external:skip}
|