Improve multithreaded performance with memory prefetching (#14017)
This PR is based on: https://github.com/valkey-io/valkey/pull/861
> ### Memory Access Amortization
> (Designed and implemented by [dan
touitou](https://github.com/touitou-dan))
>
> Memory Access Amortization (MAA) is a technique designed to optimize
the performance of dynamic data structures by reducing the impact of
memory access latency. It is applicable when multiple operations need to
be executed concurrently. The principle behind it is that for certain
dynamic data structures, executing operations in a batch is more
efficient than executing each one separately.
>
> Rather than executing operations sequentially, this approach
interleaves the execution of all operations. This is done in such a way
that whenever a memory access is required during an operation, the
program prefetches the necessary memory and transitions to another
operation. This ensures that when one operation is blocked awaiting
memory access, other memory accesses are executed in parallel, thereby
reducing the average access latency.
>
> We applied this method in the development of dictPrefetch, which takes
as parameters a vector of keys and dictionaries. It ensures that all
memory addresses required to execute dictionary operations for these
keys are loaded into the L1-L3 caches when executing commands.
Essentially, dictPrefetch is an interleaved execution of dictFind for
all the keys.
### Implementation of Redis
When the main thread processes clients with ready-to-execute commands
(i.e., clients for which the IO thread has parsed the commands), a batch
of up to 16 commands is created. Initially, the command's argv, which
were allocated by the IO thread, is prefetched to the main thread's L1
cache. Subsequently, all the dict entries and values required for the
commands are prefetched from the dictionary before the command
execution.
#### Memory prefetching for main hash table
As shown in the picture, after https://github.com/redis/redis/pull/13806
, we unify key value and the dict uses no_value optimization, so the
memory prefetching has 4 steps:
1. prefetch the bucket of the hash table
2. prefetch the entry associated with the given key's hash
3. prefetch the kv object of the entry
4. prefetch the value data of the kv object
we also need to handle the case that the dict entry is the pointer of kv
object, just skip step 3.
MAA can improves single-threaded memory access efficiency by
interleaving the execution of multiple independent operations, allowing
memory-level parallelism and better CPU utilization. Its key point is
batch-wise interleaved execution. Split a batch of independent
operations (such as multiple key lookups) into multiple state machines,
and interleave their progress within a single thread to hide the memory
access latency of individual requests.
The difference between serial execution and interleaved execution:
**naive serial execution**
```
key1: step1 → wait → step2 → wait → done
key2: step1 → wait → step2 → wait → done
```
**interleaved execution**
```
key1: step1 → step2 → done
key2: step1 → step2 → done
key3: step1 → step2 → done
↑ While waiting for key1’s memory, progress key2/key3
```
#### New configuration
This PR involves a new configuration `prefetch-batch-max-size`, but we
think it is a low level optimization, so we hide this config:
When multiple commands are parsed by the I/O threads and ready for
execution, we take advantage of knowing the next set of commands and
prefetch their required dictionary entries in a batch. This reduces
memory access costs. The optimal batch size depends on the specific
workflow of the user. The default batch size is 16, which can be
modified using the 'prefetch-batch-max-size' config.
When the config is set to 0, prefetching is disabled.
---------
Co-authored-by: Uri Yagelnik <uriy@amazon.com>
Co-authored-by: Ozan Tezcan <ozantezcan@gmail.com>
2025-06-05 08:57:43 +08:00
|
|
|
#
|
|
|
|
# Copyright (c) 2009-Present, Redis Ltd.
|
|
|
|
# All rights reserved.
|
|
|
|
#
|
|
|
|
# Copyright (c) 2025-present, Valkey contributors.
|
|
|
|
# All rights reserved.
|
|
|
|
#
|
|
|
|
# Licensed under your choice of (a) the Redis Source Available License 2.0
|
|
|
|
# (RSALv2); or (b) the Server Side Public License v1 (SSPLv1); or (c) the
|
|
|
|
# GNU Affero General Public License v3 (AGPLv3).
|
|
|
|
#
|
|
|
|
# Portions of this file are available under BSD3 terms; see REDISCONTRIBUTIONS for more information.
|
|
|
|
#
|
|
|
|
|
2021-06-22 17:50:17 +08:00
|
|
|
source tests/support/cli.tcl
|
|
|
|
|
2021-03-01 22:04:44 +08:00
|
|
|
test {CONFIG SET port number} {
|
|
|
|
start_server {} {
|
2021-03-02 02:53:02 +08:00
|
|
|
if {$::tls} { set port_cfg tls-port} else { set port_cfg port }
|
|
|
|
|
2021-03-01 22:04:44 +08:00
|
|
|
# available port
|
|
|
|
set avail_port [find_available_port $::baseport $::portcount]
|
2021-03-02 02:53:02 +08:00
|
|
|
set rd [redis [srv 0 host] [srv 0 port] 0 $::tls]
|
|
|
|
$rd CONFIG SET $port_cfg $avail_port
|
2021-03-01 22:04:44 +08:00
|
|
|
$rd close
|
2021-03-02 02:53:02 +08:00
|
|
|
set rd [redis [srv 0 host] $avail_port 0 $::tls]
|
2021-03-01 22:04:44 +08:00
|
|
|
$rd PING
|
|
|
|
|
|
|
|
# already inuse port
|
2021-03-02 02:53:02 +08:00
|
|
|
catch {$rd CONFIG SET $port_cfg $::test_server_port} e
|
2021-03-01 22:04:44 +08:00
|
|
|
assert_match {*Unable to listen on this port*} $e
|
|
|
|
$rd close
|
|
|
|
|
|
|
|
# make sure server still listening on the previous port
|
2021-03-02 02:53:02 +08:00
|
|
|
set rd [redis [srv 0 host] $avail_port 0 $::tls]
|
2021-03-01 22:04:44 +08:00
|
|
|
$rd PING
|
|
|
|
$rd close
|
|
|
|
}
|
2021-06-09 20:13:24 +08:00
|
|
|
} {} {external:skip}
|
2021-03-01 22:04:44 +08:00
|
|
|
|
|
|
|
test {CONFIG SET bind address} {
|
|
|
|
start_server {} {
|
|
|
|
# non-valid address
|
2021-04-27 23:02:23 +08:00
|
|
|
catch {r CONFIG SET bind "999.999.999.999"} e
|
2021-03-01 22:04:44 +08:00
|
|
|
assert_match {*Failed to bind to specified addresses*} $e
|
|
|
|
|
|
|
|
# make sure server still bound to the previous address
|
2021-03-02 02:53:02 +08:00
|
|
|
set rd [redis [srv 0 host] [srv 0 port] 0 $::tls]
|
2021-03-01 22:04:44 +08:00
|
|
|
$rd PING
|
|
|
|
$rd close
|
|
|
|
}
|
2021-06-09 20:13:24 +08:00
|
|
|
} {} {external:skip}
|
2021-06-22 17:50:17 +08:00
|
|
|
|
2021-07-11 14:54:07 +08:00
|
|
|
# Attempt to connect to host using a client bound to bindaddr,
|
|
|
|
# and return a non-zero value if successful within specified
|
|
|
|
# millisecond timeout, or zero otherwise.
|
|
|
|
proc test_loopback {host bindaddr timeout} {
|
|
|
|
if {[exec uname] != {Linux}} {
|
|
|
|
return 0
|
|
|
|
}
|
|
|
|
|
|
|
|
after $timeout set ::test_loopback_state timeout
|
|
|
|
if {[catch {
|
|
|
|
set server_sock [socket -server accept 0]
|
|
|
|
set port [lindex [fconfigure $server_sock -sockname] 2] } err]} {
|
|
|
|
return 0
|
|
|
|
}
|
|
|
|
|
|
|
|
proc accept {channel clientaddr clientport} {
|
|
|
|
set ::test_loopback_state "connected"
|
|
|
|
close $channel
|
|
|
|
}
|
|
|
|
|
|
|
|
if {[catch {set client_sock [socket -async -myaddr $bindaddr $host $port]} err]} {
|
|
|
|
puts "test_loopback: Client connect failed: $err"
|
|
|
|
} else {
|
|
|
|
close $client_sock
|
|
|
|
}
|
|
|
|
|
|
|
|
vwait ::test_loopback_state
|
|
|
|
close $server_sock
|
|
|
|
|
|
|
|
return [expr {$::test_loopback_state == {connected}}]
|
|
|
|
}
|
|
|
|
|
2021-06-25 00:48:18 +08:00
|
|
|
test {CONFIG SET bind-source-addr} {
|
2021-07-11 14:54:07 +08:00
|
|
|
if {[test_loopback 127.0.0.1 127.0.0.2 1000]} {
|
2021-06-25 00:48:18 +08:00
|
|
|
start_server {} {
|
|
|
|
start_server {} {
|
|
|
|
set replica [srv 0 client]
|
|
|
|
set master [srv -1 client]
|
|
|
|
|
|
|
|
$master config set protected-mode no
|
|
|
|
|
|
|
|
$replica config set bind-source-addr 127.0.0.2
|
|
|
|
$replica replicaof [srv -1 host] [srv -1 port]
|
|
|
|
|
|
|
|
wait_for_condition 50 100 {
|
|
|
|
[s 0 master_link_status] eq {up}
|
|
|
|
} else {
|
|
|
|
fail "Replication not started."
|
|
|
|
}
|
|
|
|
|
|
|
|
assert_match {*ip=127.0.0.2*} [s -1 slave0]
|
|
|
|
}
|
|
|
|
}
|
2021-07-11 14:54:07 +08:00
|
|
|
} else {
|
|
|
|
if {$::verbose} { puts "Skipping bind-source-addr test." }
|
2021-06-25 00:48:18 +08:00
|
|
|
}
|
|
|
|
} {} {external:skip}
|
|
|
|
|
2021-06-22 17:50:17 +08:00
|
|
|
start_server {config "minimal.conf" tags {"external:skip"}} {
|
|
|
|
test {Default bind address configuration handling} {
|
|
|
|
# Default is explicit and sane
|
|
|
|
assert_equal "* -::*" [lindex [r CONFIG GET bind] 1]
|
|
|
|
|
|
|
|
# CONFIG REWRITE acknowledges this as a default
|
|
|
|
r CONFIG REWRITE
|
|
|
|
assert_equal 0 [count_message_lines [srv 0 config_file] bind]
|
|
|
|
|
|
|
|
# Removing the bind address works
|
|
|
|
r CONFIG SET bind ""
|
|
|
|
assert_equal "" [lindex [r CONFIG GET bind] 1]
|
|
|
|
|
|
|
|
# No additional clients can connect
|
|
|
|
catch {redis_client} err
|
|
|
|
assert_match {*connection refused*} $err
|
|
|
|
|
|
|
|
# CONFIG REWRITE handles empty bindaddr
|
|
|
|
r CONFIG REWRITE
|
|
|
|
assert_equal 1 [count_message_lines [srv 0 config_file] bind]
|
|
|
|
|
|
|
|
# Make sure we're able to restart
|
|
|
|
restart_server 0 0 0 0
|
|
|
|
|
|
|
|
# Make sure bind parameter is as expected and server handles binding
|
|
|
|
# accordingly.
|
Add reply_schema to command json files (internal for now) (#10273)
Work in progress towards implementing a reply schema as part of COMMAND DOCS, see #9845
Since ironing the details of the reply schema of each and every command can take a long time, we
would like to merge this PR when the infrastructure is ready, and let this mature in the unstable branch.
Meanwhile the changes of this PR are internal, they are part of the repo, but do not affect the produced build.
### Background
In #9656 we add a lot of information about Redis commands, but we are missing information about the replies
### Motivation
1. Documentation. This is the primary goal.
2. It should be possible, based on the output of COMMAND, to be able to generate client code in typed
languages. In order to do that, we need Redis to tell us, in detail, what each reply looks like.
3. We would like to build a fuzzer that verifies the reply structure (for now we use the existing
testsuite, see the "Testing" section)
### Schema
The idea is to supply some sort of schema for the various replies of each command.
The schema will describe the conceptual structure of the reply (for generated clients), as defined in RESP3.
Note that the reply structure itself may change, depending on the arguments (e.g. `XINFO STREAM`, with
and without the `FULL` modifier)
We decided to use the standard json-schema (see https://json-schema.org/) as the reply-schema.
Example for `BZPOPMIN`:
```
"reply_schema": {
"oneOf": [
{
"description": "Timeout reached and no elements were popped.",
"type": "null"
},
{
"description": "The keyname, popped member, and its score.",
"type": "array",
"minItems": 3,
"maxItems": 3,
"items": [
{
"description": "Keyname",
"type": "string"
},
{
"description": "Member",
"type": "string"
},
{
"description": "Score",
"type": "number"
}
]
}
]
}
```
#### Notes
1. It is ok that some commands' reply structure depends on the arguments and it's the caller's responsibility
to know which is the relevant one. this comes after looking at other request-reply systems like OpenAPI,
where the reply schema can also be oneOf and the caller is responsible to know which schema is the relevant one.
2. The reply schemas will describe RESP3 replies only. even though RESP3 is structured, we want to use reply
schema for documentation (and possibly to create a fuzzer that validates the replies)
3. For documentation, the description field will include an explanation of the scenario in which the reply is sent,
including any relation to arguments. for example, for `ZRANGE`'s two schemas we will need to state that one
is with `WITHSCORES` and the other is without.
4. For documentation, there will be another optional field "notes" in which we will add a short description of
the representation in RESP2, in case it's not trivial (RESP3's `ZRANGE`'s nested array vs. RESP2's flat
array, for example)
Given the above:
1. We can generate the "return" section of all commands in [redis-doc](https://redis.io/commands/)
(given that "description" and "notes" are comprehensive enough)
2. We can generate a client in a strongly typed language (but the return type could be a conceptual
`union` and the caller needs to know which schema is relevant). see the section below for RESP2 support.
3. We can create a fuzzer for RESP3.
### Limitations (because we are using the standard json-schema)
The problem is that Redis' replies are more diverse than what the json format allows. This means that,
when we convert the reply to a json (in order to validate the schema against it), we lose information (see
the "Testing" section below).
The other option would have been to extend the standard json-schema (and json format) to include stuff
like sets, bulk-strings, error-string, etc. but that would mean also extending the schema-validator - and that
seemed like too much work, so we decided to compromise.
Examples:
1. We cannot tell the difference between an "array" and a "set"
2. We cannot tell the difference between simple-string and bulk-string
3. we cannot verify true uniqueness of items in commands like ZRANGE: json-schema doesn't cover the
case of two identical members with different scores (e.g. `[["m1",6],["m1",7]]`) because `uniqueItems`
compares (member,score) tuples and not just the member name.
### Testing
This commit includes some changes inside Redis in order to verify the schemas (existing and future ones)
are indeed correct (i.e. describe the actual response of Redis).
To do that, we added a debugging feature to Redis that causes it to produce a log of all the commands
it executed and their replies.
For that, Redis needs to be compiled with `-DLOG_REQ_RES` and run with
`--reg-res-logfile <file> --client-default-resp 3` (the testsuite already does that if you run it with
`--log-req-res --force-resp3`)
You should run the testsuite with the above args (and `--dont-clean`) in order to make Redis generate
`.reqres` files (same dir as the `stdout` files) which contain request-response pairs.
These files are later on processed by `./utils/req-res-log-validator.py` which does:
1. Goes over req-res files, generated by redis-servers, spawned by the testsuite (see logreqres.c)
2. For each request-response pair, it validates the response against the request's reply_schema
(obtained from the extended COMMAND DOCS)
5. In order to get good coverage of the Redis commands, and all their different replies, we chose to use
the existing redis test suite, rather than attempt to write a fuzzer.
#### Notes about RESP2
1. We will not be able to use the testing tool to verify RESP2 replies (we are ok with that, it's time to
accept RESP3 as the future RESP)
2. Since the majority of the test suite is using RESP2, and we want the server to reply with RESP3
so that we can validate it, we will need to know how to convert the actual reply to the one expected.
- number and boolean are always strings in RESP2 so the conversion is easy
- objects (maps) are always a flat array in RESP2
- others (nested array in RESP3's `ZRANGE` and others) will need some special per-command
handling (so the client will not be totally auto-generated)
Example for ZRANGE:
```
"reply_schema": {
"anyOf": [
{
"description": "A list of member elements",
"type": "array",
"uniqueItems": true,
"items": {
"type": "string"
}
},
{
"description": "Members and their scores. Returned in case `WITHSCORES` was used.",
"notes": "In RESP2 this is returned as a flat array",
"type": "array",
"uniqueItems": true,
"items": {
"type": "array",
"minItems": 2,
"maxItems": 2,
"items": [
{
"description": "Member",
"type": "string"
},
{
"description": "Score",
"type": "number"
}
]
}
}
]
}
```
### Other changes
1. Some tests that behave differently depending on the RESP are now being tested for both RESP,
regardless of the special log-req-res mode ("Pub/Sub PING" for example)
2. Update the history field of CLIENT LIST
3. Added basic tests for commands that were not covered at all by the testsuite
### TODO
- [x] (maybe a different PR) add a "condition" field to anyOf/oneOf schemas that refers to args. e.g.
when `SET` return NULL, the condition is `arguments.get||arguments.condition`, for `OK` the condition
is `!arguments.get`, and for `string` the condition is `arguments.get` - https://github.com/redis/redis/issues/11896
- [x] (maybe a different PR) also run `runtest-cluster` in the req-res logging mode
- [x] add the new tests to GH actions (i.e. compile with `-DLOG_REQ_RES`, run the tests, and run the validator)
- [x] (maybe a different PR) figure out a way to warn about (sub)schemas that are uncovered by the output
of the tests - https://github.com/redis/redis/issues/11897
- [x] (probably a separate PR) add all missing schemas
- [x] check why "SDOWN is triggered by misconfigured instance replying with errors" fails with --log-req-res
- [x] move the response transformers to their own file (run both regular, cluster, and sentinel tests - need to
fight with the tcl including mechanism a bit)
- [x] issue: module API - https://github.com/redis/redis/issues/11898
- [x] (probably a separate PR): improve schemas: add `required` to `object`s - https://github.com/redis/redis/issues/11899
Co-authored-by: Ozan Tezcan <ozantezcan@gmail.com>
Co-authored-by: Hanna Fadida <hanna.fadida@redislabs.com>
Co-authored-by: Oran Agra <oran@redislabs.com>
Co-authored-by: Shaya Potter <shaya@redislabs.com>
2023-03-11 16:14:16 +08:00
|
|
|
# (it seems that rediscli_exec behaves differently in RESP3, possibly
|
|
|
|
# because CONFIG GET returns a dict instead of a list so redis-cli emits
|
|
|
|
# it in a single line)
|
|
|
|
if {$::force_resp3} {
|
|
|
|
assert_equal {{bind }} [rediscli_exec 0 config get bind]
|
|
|
|
} else {
|
|
|
|
assert_equal {bind {}} [rediscli_exec 0 config get bind]
|
|
|
|
}
|
2021-06-22 17:50:17 +08:00
|
|
|
catch {reconnect 0} err
|
|
|
|
assert_match {*connection refused*} $err
|
|
|
|
|
|
|
|
assert_equal {OK} [rediscli_exec 0 config set bind *]
|
|
|
|
reconnect 0
|
|
|
|
r ping
|
|
|
|
} {PONG}
|
|
|
|
|
|
|
|
test {Protected mode works as expected} {
|
|
|
|
# Get a non-loopback address of this instance for this test.
|
|
|
|
set myaddr [get_nonloopback_addr]
|
|
|
|
if {$myaddr != "" && ![string match {127.*} $myaddr]} {
|
2021-06-22 18:30:20 +08:00
|
|
|
# Non-loopback client should fail by default
|
2021-06-22 17:50:17 +08:00
|
|
|
set r2 [get_nonloopback_client]
|
|
|
|
catch {$r2 ping} err
|
|
|
|
assert_match {*DENIED*} $err
|
|
|
|
|
|
|
|
# Bind configuration should not matter
|
|
|
|
assert_equal {OK} [r config set bind "*"]
|
|
|
|
set r2 [get_nonloopback_client]
|
|
|
|
catch {$r2 ping} err
|
|
|
|
assert_match {*DENIED*} $err
|
|
|
|
|
|
|
|
# Setting a password should disable protected mode
|
|
|
|
assert_equal {OK} [r config set requirepass "secret"]
|
|
|
|
set r2 [redis $myaddr [srv 0 "port"] 0 $::tls]
|
|
|
|
assert_equal {OK} [$r2 auth secret]
|
|
|
|
assert_equal {PONG} [$r2 ping]
|
|
|
|
|
|
|
|
# Clearing the password re-enables protected mode
|
|
|
|
assert_equal {OK} [r config set requirepass ""]
|
|
|
|
set r2 [redis $myaddr [srv 0 "port"] 0 $::tls]
|
|
|
|
assert_match {*DENIED*} $err
|
|
|
|
|
|
|
|
# Explicitly disabling protected-mode works
|
|
|
|
assert_equal {OK} [r config set protected-mode no]
|
|
|
|
set r2 [redis $myaddr [srv 0 "port"] 0 $::tls]
|
|
|
|
assert_equal {PONG} [$r2 ping]
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
Improve multithreaded performance with memory prefetching (#14017)
This PR is based on: https://github.com/valkey-io/valkey/pull/861
> ### Memory Access Amortization
> (Designed and implemented by [dan
touitou](https://github.com/touitou-dan))
>
> Memory Access Amortization (MAA) is a technique designed to optimize
the performance of dynamic data structures by reducing the impact of
memory access latency. It is applicable when multiple operations need to
be executed concurrently. The principle behind it is that for certain
dynamic data structures, executing operations in a batch is more
efficient than executing each one separately.
>
> Rather than executing operations sequentially, this approach
interleaves the execution of all operations. This is done in such a way
that whenever a memory access is required during an operation, the
program prefetches the necessary memory and transitions to another
operation. This ensures that when one operation is blocked awaiting
memory access, other memory accesses are executed in parallel, thereby
reducing the average access latency.
>
> We applied this method in the development of dictPrefetch, which takes
as parameters a vector of keys and dictionaries. It ensures that all
memory addresses required to execute dictionary operations for these
keys are loaded into the L1-L3 caches when executing commands.
Essentially, dictPrefetch is an interleaved execution of dictFind for
all the keys.
### Implementation of Redis
When the main thread processes clients with ready-to-execute commands
(i.e., clients for which the IO thread has parsed the commands), a batch
of up to 16 commands is created. Initially, the command's argv, which
were allocated by the IO thread, is prefetched to the main thread's L1
cache. Subsequently, all the dict entries and values required for the
commands are prefetched from the dictionary before the command
execution.
#### Memory prefetching for main hash table
As shown in the picture, after https://github.com/redis/redis/pull/13806
, we unify key value and the dict uses no_value optimization, so the
memory prefetching has 4 steps:
1. prefetch the bucket of the hash table
2. prefetch the entry associated with the given key's hash
3. prefetch the kv object of the entry
4. prefetch the value data of the kv object
we also need to handle the case that the dict entry is the pointer of kv
object, just skip step 3.
MAA can improves single-threaded memory access efficiency by
interleaving the execution of multiple independent operations, allowing
memory-level parallelism and better CPU utilization. Its key point is
batch-wise interleaved execution. Split a batch of independent
operations (such as multiple key lookups) into multiple state machines,
and interleave their progress within a single thread to hide the memory
access latency of individual requests.
The difference between serial execution and interleaved execution:
**naive serial execution**
```
key1: step1 → wait → step2 → wait → done
key2: step1 → wait → step2 → wait → done
```
**interleaved execution**
```
key1: step1 → step2 → done
key2: step1 → step2 → done
key3: step1 → step2 → done
↑ While waiting for key1’s memory, progress key2/key3
```
#### New configuration
This PR involves a new configuration `prefetch-batch-max-size`, but we
think it is a low level optimization, so we hide this config:
When multiple commands are parsed by the I/O threads and ready for
execution, we take advantage of knowing the next set of commands and
prefetch their required dictionary entries in a batch. This reduces
memory access costs. The optimal batch size depends on the specific
workflow of the user. The default batch size is 16, which can be
modified using the 'prefetch-batch-max-size' config.
When the config is set to 0, prefetching is disabled.
---------
Co-authored-by: Uri Yagelnik <uriy@amazon.com>
Co-authored-by: Ozan Tezcan <ozantezcan@gmail.com>
2025-06-05 08:57:43 +08:00
|
|
|
|
|
|
|
start_server {config "minimal.conf" tags {"external:skip"} overrides {enable-debug-command {yes} io-threads 2}} {
|
|
|
|
set server_pid [s process_id]
|
|
|
|
# Since each thread may perform memory prefetch independently, this test is
|
|
|
|
# only run when the number of IO threads is 2 to ensure deterministic results.
|
|
|
|
if {[r config get io-threads] eq "io-threads 2"} {
|
|
|
|
test {prefetch works as expected when killing a client from the middle of prefetch commands batch} {
|
|
|
|
# Create 16 (prefetch batch size) +1 clients
|
|
|
|
for {set i 0} {$i < 16} {incr i} {
|
|
|
|
set rd$i [redis_deferring_client]
|
|
|
|
}
|
|
|
|
|
|
|
|
# set a key that will be later be prefetch
|
|
|
|
r set a 0
|
|
|
|
|
|
|
|
# Get the client ID of rd4
|
|
|
|
$rd4 client id
|
|
|
|
set rd4_id [$rd4 read]
|
|
|
|
|
|
|
|
# Create a batch of commands by suspending the server for a while
|
|
|
|
# before responding to the first command
|
|
|
|
pause_process $server_pid
|
|
|
|
|
|
|
|
# The first client will kill the fourth client
|
|
|
|
$rd0 client kill id $rd4_id
|
|
|
|
|
|
|
|
# Send set commands for all clients except the first
|
|
|
|
for {set i 1} {$i < 16} {incr i} {
|
|
|
|
[set rd$i] set a $i
|
|
|
|
[set rd$i] flush
|
|
|
|
}
|
|
|
|
|
|
|
|
# Resume the server
|
|
|
|
resume_process $server_pid
|
|
|
|
|
|
|
|
# Read the results
|
|
|
|
assert_equal {1} [$rd0 read]
|
|
|
|
catch {$rd4 read} err
|
|
|
|
assert_match {I/O error reading reply} $err
|
|
|
|
|
|
|
|
# verify the prefetch stats are as expected
|
|
|
|
set info [r info stats]
|
|
|
|
set prefetch_entries [getInfoProperty $info io_threaded_total_prefetch_entries]
|
|
|
|
assert_range $prefetch_entries 2 15; # With slower machines, the number of prefetch entries can be lower
|
|
|
|
set prefetch_batches [getInfoProperty $info io_threaded_total_prefetch_batches]
|
|
|
|
assert_range $prefetch_batches 1 7; # With slower machines, the number of batches can be higher
|
|
|
|
|
|
|
|
# Verify the final state
|
|
|
|
$rd15 get a
|
|
|
|
assert_equal {OK} [$rd15 read]
|
|
|
|
assert_equal {15} [$rd15 read]
|
|
|
|
}
|
|
|
|
|
|
|
|
test {prefetch works as expected when changing the batch size while executing the commands batch} {
|
|
|
|
# Create 16 (default prefetch batch size) clients
|
|
|
|
for {set i 0} {$i < 16} {incr i} {
|
|
|
|
set rd$i [redis_deferring_client]
|
|
|
|
}
|
|
|
|
|
|
|
|
# Create a batch of commands by suspending the server for a while
|
|
|
|
# before responding to the first command
|
|
|
|
pause_process $server_pid
|
|
|
|
|
|
|
|
# Send set commands for all clients the 5th client will change the prefetch batch size
|
|
|
|
for {set i 0} {$i < 16} {incr i} {
|
|
|
|
if {$i == 4} {
|
|
|
|
[set rd$i] config set prefetch-batch-max-size 1
|
|
|
|
}
|
|
|
|
[set rd$i] set a $i
|
|
|
|
[set rd$i] flush
|
|
|
|
}
|
|
|
|
# Resume the server
|
|
|
|
resume_process $server_pid
|
|
|
|
# Read the results
|
|
|
|
for {set i 0} {$i < 16} {incr i} {
|
|
|
|
assert_equal {OK} [[set rd$i] read]
|
|
|
|
[set rd$i] close
|
|
|
|
}
|
|
|
|
|
|
|
|
# assert the configured prefetch batch size was changed
|
|
|
|
assert {[r config get prefetch-batch-max-size] eq "prefetch-batch-max-size 1"}
|
|
|
|
}
|
|
|
|
|
|
|
|
proc do_prefetch_batch {server_pid batch_size} {
|
|
|
|
# Create clients
|
|
|
|
for {set i 0} {$i < $batch_size} {incr i} {
|
|
|
|
set rd$i [redis_deferring_client]
|
|
|
|
}
|
|
|
|
|
|
|
|
# Suspend the server to batch the commands
|
|
|
|
pause_process $server_pid
|
|
|
|
|
|
|
|
# Send commands from all clients
|
|
|
|
for {set i 0} {$i < $batch_size} {incr i} {
|
|
|
|
[set rd$i] set a $i
|
|
|
|
[set rd$i] flush
|
|
|
|
}
|
|
|
|
|
|
|
|
# Resume the server to process the batch
|
|
|
|
resume_process $server_pid
|
|
|
|
|
|
|
|
# Verify responses
|
|
|
|
for {set i 0} {$i < $batch_size} {incr i} {
|
|
|
|
assert_equal {OK} [[set rd$i] read]
|
|
|
|
[set rd$i] close
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
test {no prefetch when the batch size is set to 0} {
|
|
|
|
# set the batch size to 0
|
|
|
|
r config set prefetch-batch-max-size 0
|
|
|
|
# save the current value of prefetch entries
|
|
|
|
set info [r info stats]
|
|
|
|
set prefetch_entries [getInfoProperty $info io_threaded_total_prefetch_entries]
|
|
|
|
|
|
|
|
do_prefetch_batch $server_pid 16
|
|
|
|
|
|
|
|
# assert the prefetch entries did not change
|
|
|
|
set info [r info stats]
|
|
|
|
set new_prefetch_entries [getInfoProperty $info io_threaded_total_prefetch_entries]
|
|
|
|
assert_equal $prefetch_entries $new_prefetch_entries
|
|
|
|
}
|
|
|
|
|
|
|
|
test {Prefetch can resume working when the configuration option is set to a non-zero value} {
|
|
|
|
# save the current value of prefetch entries
|
|
|
|
set info [r info stats]
|
|
|
|
set prefetch_entries [getInfoProperty $info io_threaded_total_prefetch_entries]
|
|
|
|
# set the batch size to 0
|
|
|
|
r config set prefetch-batch-max-size 16
|
|
|
|
|
|
|
|
do_prefetch_batch $server_pid 16
|
|
|
|
|
|
|
|
# assert the prefetch entries did not change
|
|
|
|
set info [r info stats]
|
|
|
|
set new_prefetch_entries [getInfoProperty $info io_threaded_total_prefetch_entries]
|
|
|
|
# With slower machines, the number of prefetch entries can be lower
|
|
|
|
assert_range $new_prefetch_entries [expr {$prefetch_entries + 2}] [expr {$prefetch_entries + 16}]
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|