mirror of
https://github.com/redis/redis.git
synced 2026-05-28 04:02:46 -04:00
05859cdd7e
## Problem After #14608 (Reply Copy Avoidance), when copy avoidance kicks in, bulk string replies are sent by reference instead of being copied into the output buffer. The referenced bytes are not counted in `reply_bytes`, which causes: 1. `getClientOutputBufferMemoryUsage()` underestimates the actual memory usage, so output buffer limits may not be triggered in time, allowing clients to consume unbounded memory. 2. Client eviction does not account for the referenced bytes, making it ineffective when copy avoidance is used. 3. `omem` reported in `CLIENT LIST` / `CLIENT INFO` does not reflect the true output buffer memory footprint. ## Solution Track the bytes of referenced bulk strings in the output buffer with two per-client counters: 1. reply_bytes_shared - the logical size of all BULK_STR_REF payloads in the output buffer. Updated incrementally whenever a reference is added/removed. Represents memory the client is "charged" for even though it is shared with the keyspace. 2. reply_bytes_unshared — the subset of the above where the referenced object's refcount == 1 (i.e. the key has been deleted from the keyspace), so the memory is kept alive solely by this client's output buffer and would actually be freed on disconnect. Maintained as a lazy cache refreshed via updateClientUnsharedReplyBytes(). ## Info field CLIENT LIST / CLIENT INFO — two new fields, plus refined semantics for existing ones: Field | Meaning -- | -- omem | (semantics changed) logical output-buffer memory, now including shared memory referenced from the keyspace. Still excludes client->buf so static clients show 0. omem-shared | (new) shared output-buffer memory (referenced bulk strings, not solely owned by this client). omem-unshared | (new) unshared output-buffer memory (referenced bulk strings solely owned by this client; freed on disconnect). tot-mem | (semantics refined) actual memory usage — includes omem-unshared, excludes omem-shared to avoid double-counting keyspace memory. INFO memory — two new fields mirroring the above: Field | Meaning -- | -- mem_clients_normal | (semantics changed) actual memory usage of normal clients (includes unshared, excludes shared). mem_clients_normal_shared | (new) aggregate shared output-buffer memory across normal clients. mem_clients_normal_unshared | (new) aggregate unshared output-buffer memory across normal clients. MEMORY STATS — schema extended with the matching keys: Field | Meaning -- | -- clients.normal.shared | (new) aggregate shared output-buffer memory across normal clients. clients.normal.unshared | (new) aggregate unshared output-buffer memory across normal clients. ## Bug Fix Fix missing closeClientOnOutputBufferLimitReached() call when adding a referenced robj to the reply --------- Co-authored-by: oranagra <oran@redislabs.com>
47 lines
No EOL
1.7 KiB
Tcl
47 lines
No EOL
1.7 KiB
Tcl
proc get_reply_buffer_size {cname} {
|
|
|
|
set clients [split [string trim [r client list]] "\r\n"]
|
|
set c [lsearch -inline $clients *name=$cname*]
|
|
if {![regexp rbs=(\[a-zA-Z0-9-\]+) $c - rbufsize]} {
|
|
error "field rbs not found in $c"
|
|
}
|
|
return $rbufsize
|
|
}
|
|
|
|
start_server {tags {"replybufsize"}} {
|
|
|
|
test {verify reply buffer limits} {
|
|
# In order to reduce test time we can set the peak reset time very low
|
|
r debug replybuffer peak-reset-time 100
|
|
|
|
# Create a simple idle test client
|
|
variable tc [redis_client]
|
|
$tc client setname test_client
|
|
|
|
# make sure the client is idle for 1 seconds to make it shrink the reply buffer
|
|
wait_for_condition 10 100 {
|
|
[get_reply_buffer_size test_client] >= 1024 && [get_reply_buffer_size test_client] < 2046
|
|
} else {
|
|
set rbs [get_reply_buffer_size test_client]
|
|
fail "reply buffer of idle client is $rbs after 1 seconds"
|
|
}
|
|
|
|
r set bigval [string repeat x 8192] ;# Keep value <= 16KB to avoid copy-avoidance, which shares memory and slows tot-mem growth.
|
|
|
|
# In order to reduce test time we can set the peak reset time very low
|
|
r debug replybuffer peak-reset-time never
|
|
|
|
wait_for_condition 10 100 {
|
|
[$tc mget bigval bigval bigval bigval ; get_reply_buffer_size test_client] >= 16384 && [get_reply_buffer_size test_client] < 32768
|
|
} else {
|
|
set rbs [get_reply_buffer_size test_client]
|
|
fail "reply buffer of busy client is $rbs after 1 seconds"
|
|
}
|
|
|
|
# Restore the peak reset time to default
|
|
r debug replybuffer peak-reset-time reset
|
|
|
|
$tc close
|
|
} {0} {needs:debug}
|
|
}
|
|
|