Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
(Advanced) Redis
Search
Jan De Poorter
February 12, 2013
Programming
8
400
(Advanced) Redis
Everything we learned at a client project using Redis - Talk given at #ArrrrUG
Jan De Poorter
February 12, 2013
Tweet
Share
Other Decks in Programming
See All in Programming
インターフェース設計のコツとツボ
togishima
2
710
カクヨムAndroidアプリのリブート
numeroanddev
0
410
Enterprise Web App. Development (2): Version Control Tool Training Ver. 5.1
knakagawa
1
110
コードに語らせよう――自己ドキュメント化が内包する楽しさについて / Let the Code Speak
nrslib
6
1.4k
The Evolution of Enterprise Java with Jakarta EE 11 and Beyond
ivargrimstad
1
630
業務自動化をJavaとSeleniumとAWS Lambdaで実現した方法
greenflagproject
1
100
Use Perl as Better Shell Script
karupanerura
0
690
F#で自在につくる静的ブログサイト - 関数型まつり2025
pizzacat83
0
290
Elixir で IoT 開発、 Nerves なら簡単にできる!?
pojiro
1
120
List Unfolding - 'unfold' as the Computational Dual of 'fold', and how 'unfold' relates to 'iterate'"
philipschwarz
PRO
0
190
Benchmark
sysong
0
140
[初登壇@jAZUG]アプリ開発者が気になるGoogleCloud/Azure+wasm/wasi
asaringo
0
130
Featured
See All Featured
Visualization
eitanlees
146
16k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
8
650
jQuery: Nuts, Bolts and Bling
dougneiner
63
7.8k
Building Applications with DynamoDB
mza
95
6.4k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
47
2.8k
Building Better People: How to give real-time feedback that sticks.
wjessup
367
19k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
252
21k
Site-Speed That Sticks
csswizardry
10
630
A designer walks into a library…
pauljervisheath
206
24k
Code Reviewing Like a Champion
maltzj
524
40k
Making the Leap to Tech Lead
cromwellryan
134
9.3k
Facilitating Awesome Meetings
lara
54
6.4k
Transcript
(advanced) Redis Advanced is between brackets because we don’t claim
to be advanced users, we just have gained a lot of experience
Jan De Poorter @defv
Redis?
NoSQL
:-D
No, but srsly
Redis is an in-memory key-value data-structure server
in memory with “best effort” persistence
Data structure server Strings SET, SETNX, GET, INCR, DECR, APPEND,
... Hashes HSET, HGET, HGETALL, HDEL, HLEN, ... Lists LPUSH, LPOP, LINDEX, LLEN, LRANGE, ... Sets & Sorted sets SADD, SPOP, SMEMBERS, SDIFF, ZADD, ...
some libraries Ruby redis-rb (gem) hiredis-rb (gem) Node redis (npm)
hiredis (npm)
Q-Music Our use case was the API for the new
Q-Music website and the iPhone and Android applications.
High volume
Pub-Sub
BG jobs with Sidekiq
Some do’s
Serialize values
2 class QApi::Redis 3 class << self 4 def redis
5 @redis ||= Redis.new(config) 6 end ... 181 def set(key, data) 182 redis.set key, to_json(data) 183 end 184 185 def get(key) 186 from_json redis.get(key) 187 end 188 216 private 217 def from_json(result) 218 case result 219 when Array 220 result.map { |r| from_json(r) } 221 when Hash 222 result 223 when nil 224 nil 225 else 226 MultiJson.decode(result) 227 end 228 rescue MultiJson::DecodeError 229 result 230 end 231 232 def to_json(data) 233 MultiJson.encode(data) 234 end 262 end 263 end
Save references
# Write LPUSH plays {“id”: 42, ”title”:”99 Bottles of Rum”}
LPUSH plays {“id”: 49, ”title”:”The Drunken Sailor”} LPUSH plays {“id”: 42, ”title”:”99 Bottles of Rum”} # Read LRANGE plays 0 -1 don’t do this
it’s fine with 100 items
but becomes huge with 90 000 items
or 1 000 000 Justin Bieber mentions ;-)
# Write SET tracks:42 {“id”: 42, ”title”:”99 Bottles of Rum”}
SET tracks:49 {“id”: 42, ”title”:” The Drunken Sailor”} LPUSH plays tracks:42 LPUSH plays tracks:49 LPUSH plays tracks:42 # Read LRANGE plays 0 -1 MGET tracks:42 tracks:49 do this instead
or in Ruby 82 def list_from_references(list, options) 83 references =
redis.lrange list, 84 options[:start], options[:stop] 85 if references.any? 86 from_json redis.mget(*references) 87 else 88 [] 89 end 90 end
Some don’t’s
RDB vs AOF
RDB does fork()
doubling memory usage
Our dataset was 4GB
We had ~8GB of memory
No BGSAVE’s for 4 days
:-(
appendonly yes
Slow(er) start-up
Can be optimized
Monitoring
data:~$ redis-cli redis > INFO redis_version:2.4.16 ... connected_clients:152 ... used_memory:2744963744
used_memory_human:2.56G used_memory_peak:6150240632 used_memory_peak_human:5.73G ... changes_since_last_save:9576 last_save_time:1360661315 redis >
PUBLISH & SUBSCRIBE overload
WebSocket clients
1 client == 1 connection == 1 subscription
Works perfect in development
Works perfect in staging
but in production...
1 new event
sent to 3500 connected clients
Takes about 0.3 seconds
Up to 4 messages per second
:-(
Move logic to websocket server
:-(
1 type of msg == 1 subscription
:-)
MULTI / EXEC
> MULTI OK > RENAME bl:1 bld:1 QUEUED > RENAME
bl:2 bld:2 QUEUED > EXEC 1) OK 2) OK
Works great on 1000’s of commands
Not so much on 1 million commands...
Don’t exceed ~10k commands in 1 transaction
master/slave
no library support
DIY
We didn’t
Limited connections
Redis < 2.6
/* Max number of fd supported */ #define AE_SETSIZE (1024*10)
No more then ~10k connections allowed
Redis >= 2.6
The sky is the limit
(actually, the linux max FD is the limit)
Questions?