bullet cache - freebsdivoras/slides/bsdcan2012-bulletcache.pdf · introducing the bullet cache...
TRANSCRIPT
![Page 2: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/2.jpg)
What is it?
● People know what memcached is... mostly● Example use case:
– So you have a web page which is just dynamic enough so you can't cache it completely as an HTML dump
– You have a SQL query on this page whichis 99.99% always the same (same query, same answer)
– ...so you cache it
![Page 3: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/3.jpg)
Why a cache server?
● Sharing between processes– … on different servers
● In environments which do not implement application persistency
– CGI, FastCGI– PHP
● Or you're simply lazy and want something which works...
![Page 4: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/4.jpg)
A little bit of history...
● This started as my “pet project”...– It's so ancient, when I first started working
on it, Memcached was still single-threaded– It's gone through at least one rewrite and
a whole change of concept
● I made it because of the frustration I felt while working with Memcached
– Key-value databases are so very basic– “I could do better than that” :)
![Page 5: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/5.jpg)
Now...
● Used in production in my university's project
● Probably the fastest memory cache engine available (in specific circumstances)
● Available in FreeBSD ports (databases/mdcached)
● Has a 20-page User Manual :)
![Page 6: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/6.jpg)
What's wrong with memcached?
● Nothing much – it's solid work● The classic problem:
cache expiry / invalidation– memcached accepts a list of records to
expire (inefficient, need to maintain this list)
● It's fast – but is it fast enough?– Does it really make use of multiple CPUs
as efficiently as possible?
![Page 7: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/7.jpg)
Introducing the Bullet Cache
1. Offers a smarter data structure to the user side than a simplekey-value pair
2. Implements “interesting” internal data structures
3. Some interesting bells & whistles
![Page 8: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/8.jpg)
User-visible structure
● Traditional (memcached) style:– Key-value pairs– Relatively short keys (255 bytes)– ASCII-only keys (?)– (ASCII-only protocol)– Multi-record operations only with a list of
records– Simple atomic operations (relatively
inefficient - atoi())
![Page 9: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/9.jpg)
Introducing record tags
● They are metadata● Constraints:
– Must be fast (they are NOT db indexes)– Must allow certain types of bulk operations
● The implementation:– Both key and value are signed integers– No limit on the number of tags per record– Bulk queries: (tkey X) && (tval1, [tval2...])
![Page 10: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/10.jpg)
Record tags
● I heard you like key-value records so I've put key-value records into your key-value records...
record key record value
k v k v k v ...
generic metadata
![Page 11: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/11.jpg)
Metadata queries (1)
● Use case example: a web application has a page “/contacts” which contains data from several SQL queries as well as other sources (LDAP)
– Tag all cached records with(tkey,tval) = (42, hash(“/contacts”))
– When constructing page, issue query:get_by_tag_values(42, hash(“/contacts”))
– When expiring all data, issue query:del_by_tag_values(42, hash(“/contacts”))
![Page 12: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/12.jpg)
Metadata queries (2)
● Use case example: Application objects are stored (serialized, marshalled) into the cache, and there's a need to invalidate (expire) all objects of a certain type
– Tag records with(tkey, tval) = (object_type, instance_id)
– Expire withdel_by_tag_values(object_type, instance_id)
– Also possible: tagging object interdependance
![Page 13: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/13.jpg)
Under the hood
● It's “interesting”...● Started as a C project, now mostly
converted to C++ for easier modularization
– Still uses C-style structures and algorithms for the core parts – i.e. not std::containers
● Contains tests and benchmarks within the main code base
– C and PHP client libraries
![Page 14: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/14.jpg)
The main data structure
● A “forest of trees”, anchored in hash table buckets
● Buckets are directly addressed by hashing record keys
● Buckets are protected by rwlocks
RWlock node
node
node
node
node
node
Red-blacktree
RWlock node
node
node
node
node
node
Red-blacktree
hash value = H1
hash value = H2
. . .
tree root
tree root
Hash table
![Page 15: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/15.jpg)
Basic operation
1.Find h = Hash(key)
2.Acquire lock #h
3.Find record in RBtree indexed by key
4.Perform operation
5.Release lock #h
RWlock
node
node
node
node
node
node
Red-blacktree
RWlock
node
node
node
node
node
node
Red-blacktree
hash value = H1
hash value = H2
. . .
tree root
tree root
Hash table
1
2
3
4
5
OP
end
![Page 16: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/16.jpg)
Record tags follow a similar pattern
● The tags index the main structure and are maintained (almost) independently
Hash value = H1
RWlock
TK1 TK2 TK3 TK4
Hash value = H2
RWlock
TK1 TK2 TK3 TK4
...
![Page 17: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/17.jpg)
Concurrency and locking
● Concurrency is great – the default configuration starts 256 record buckets and 64 tag buckets
● Locking is without ordering assumptions– *_trylock() for everything– rollback-and-retry– No deadlocks
● Livelocks on the other hand need to be investigated
![Page 18: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/18.jpg)
Two-way linking betweenrecords and tags
RWlock node
node
node
node
node
node
RWlock node
node
node
node
node
node
hash value = H1
hash value = H2
. . .
tree root
tree root
Hash table
hash value = H1
RWlock
TK1 TK2 TK3 TK4
hash value = H2
RWlock
TK1 TK2 TK3 TK4
...
![Page 19: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/19.jpg)
Concurrency
● Scenario 1:– A record is
referenced → need to hold N tag bucket locks
● Scenario 2:– A tag is
referenced → need to hold M record bucket locks
4 8 16 32 64 128 256
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
NCPU=64, SHARED NCPU=64, EXCLUSIVE
NCPU=8, SHARED NCPU=8, EXCLUSIVE
Number of hash table buckets (H)
Pe
rce
nta
ge
of u
nco
nte
ste
d lo
ck a
cqu
isiti
on
s (
U)
Percentage of uncontested lock acquisitions
![Page 20: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/20.jpg)
Multithreading models
● Aka “which thread does what”● Three basic tasks:
– T1: Connection acceptance– T2: Network IO– T3: Payload work
● The big question: how to distribute these into threads?
![Page 21: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/21.jpg)
Multithreading models
● SPED : Single process, event driven● SEDA : Staged, event-driven architecture● AMPED : Asymmetric, multi-process,
event-driven● SYMPED : Symmetric, multi-process,
event driven Model New connection handler
Network IO handler
Payload work
SPED 1 thread In connection thread In connection thread
SEDA 1 thread N1 threads N2 threads
SEDA-S 1 thread N threads N threads
AMPED 1 thread 1 thread N threads
SYMPED 1 thread N threads In network thread
![Page 22: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/22.jpg)
All the models are event-driven
● The “dumb” model: thread-per-connection
● Not really efficient– (FreeBSD has experimented with KSE and
M:N threading but that didn't work out)
● IO events: via kqueue(2)● Inter-thread synchronization: queues
signalled with CVs
![Page 23: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/23.jpg)
SPED
● Single-threaded, event-driven● Very efficient on
single-CPU systems● Most efficient if
the operation isvery fast (comparedto network IO andevent handling)
● Used in efficient Unix network servers
![Page 24: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/24.jpg)
SEDA
● Staged, event-driven● Different task threads
instantiated indifferent numbers
● Generally,N1 != N2 != N3
● The most queueing● The most separation
of tasks – most CPUs used
T1
T2
T2
T2
T3
T3
T3
T3
![Page 25: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/25.jpg)
AMPED
● Asymmetric multi-process event-driven● Asymmetric: N(T2) != N(T3)● Assumes network IO
processing is cheapcompared tooperation processing
● Moderate amount of queuing● Can use arbitrary number of CPUs
T1 T2 T3
T3
T3
![Page 26: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/26.jpg)
SYMPED
● Symmetric multi-process event-driven● Symmetric: grouping of tasks● Assumes network IO
and operation processing are similarlyexpensive but uniform
● Sequential processinginside threads
● Similar to multiple instances of SPED
T1
T2+T3
T2+T3
T2+T3
![Page 27: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/27.jpg)
Multithreading modelsin Bullet Cache
● Command-line configuration:– n : number of network threads– t : number of payload threads
● n=0, t=0 : SPED● n=1, t>0 : AMPED● n>0, t=0 : SYMPED● n>1, t>0 : SEDA● n>1, t>1, n=t : SEDA-S (symmetrical)
![Page 28: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/28.jpg)
How does that work?
● SEDA: the same network loop accepts connections and network IO
● Others: The network IO threads accept messages, then either:
– process them in-thread or – queue them on worker thread queues
● Response messages are either sent in-thread from whichever thread generates them or finished with the IO event code
![Page 29: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/29.jpg)
Performance of various models
20 40 60 80 100 120 140
0
50
100
150
200
250
300
350
400
450
500
SPED SEDA SEDA-S AMPED SYMPED
Number of clients
Th
ou
sa
nd
s o
f tra
ns
act
ion
s/s
Except in specialcircumstances,
SYMPED is best
![Page 30: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/30.jpg)
Why is SYMPED efficient?
● The same thread receives the message and processes it
● No queueing– No context switching– In the optimal case: no any kind of
(b)locking delays
● Downsides:– Serializes network IO and processing
within the thread (which is ok if per-CPU)
![Page 31: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/31.jpg)
Notable performance optimizations
● “zero-copy” operation– Queries which do not involve complex
processing or record aggregation are are satisfied directly from data structures
● “zero-malloc” operation– The code re-uses memory buffers as much
as possible; the fast path is completely malloc()- and memcpy()-free
● Adaptive dynamic buffer sizes– malloc() usage is tracked to avoid realloc()
![Page 32: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/32.jpg)
State of the art
92 185 278 371 464 558 651 744 837 930 1023 1395 1861 2792 3723
200.000 TPS
400.000 TPS
600.000 TPS
800.000 TPS
1.000.000 TPS
1.200.000 TPS
1.400.000 TPS
1.600.000 TPS
1.800.000 TPS
2.000.000 TPS
System A (June 2010) System B (Jan 2011) System B (Jun 2011)
System C (Dec 2011) System D (Mar 2012)
Average record data size
Pe
rfo
rma
nce
![Page 33: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/33.jpg)
State of the art
92 185 278 371 464 558 651 744 837 930 1023 1395 1861 2792 3723
200.000 TPS
400.000 TPS
600.000 TPS
800.000 TPS
1.000.000 TPS
1.200.000 TPS
1.400.000 TPS
1.600.000 TPS
1.800.000 TPS
2.000.000 TPS
System A (June 2010) System B (Jan 2011) System B (Jun 2011)
System C (Dec 2011) System D (Mar 2012)
Average record data size
Pe
rfo
rma
nce
Xeon 5675, 6-core, 3 GHzXeon 5675, 6-core, 3 GHz+HTT
9-stable, March 2012
![Page 34: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/34.jpg)
… under certain conditions
● The optimal, fast path (zero-memcpy, zero-malloc, optimal buffers)
– Which is actually less important, we know that these algorithms are fast...
● Using Unix domain sockets– Much more important– FreeBSD's network stack (the TCP path) is
currently basically nonscalable to SMP?– UDP path is more scalable … WIP
![Page 35: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/35.jpg)
TCP vs Unix sockets
104 209 314 420 525 639 735 840 945 1050 1576 2102 3153 42040 TPS
100,000 TPS
200,000 TPS
300,000 TPS
400,000 TPS
500,000 TPS
600,000 TPS
700,000 TPS
800,000 TPS
900,000 TPS
1,000,000 TPS
System D / mdcached System D / memcached System D / redis
Average record size
![Page 36: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/36.jpg)
NUMA Effects
1 2 3 4 5 6 7 8 9 10 15 20 30 400 TPS
200,000 TPS
400,000 TPS
600,000 TPS
800,000 TPS
1,000,000 TPS
1,200,000 TPS
1,400,000 TPS
1,600,000 TPS
1,800,000 TPS
2,000,000 TPS
System D System D / NUMA System D / ULE
cpuset(4)-bound to a single socket
cpuset(4) client & server separate sockets
No cpuset(4)only ULE
It's unlikely that better NUMA support would help at all...
![Page 37: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/37.jpg)
Scalability wrt number of records
1.000 10.000 100.000 1.000.000 10.000.000
300.000 TPS
320.000 TPS
340.000 TPS
360.000 TPS
380.000 TPS
400.000 TPS
420.000 TPS
440.000 TPS
mdcached
![Page 38: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/38.jpg)
Bells & whistles
● Binary protocol (endian-dependant)● Extensive atomic operation set
– cmpset, add, fetchadd, readandclear
● “tstack” operations– Every tag (tk,tv) identifies a stack– Push and pop operations on records
● Periodic data dumps / chekpoints– Cache pre-warm (load from file)
![Page 39: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/39.jpg)
Usage ideas
● Application data cache, database cache– Semantically tag cached records– Efficient retrieval and expiry (deletion)
● Primary data storage– High-performance ephemeral storage– Optional periodic checkpoints
● Data sharing between app server nodes● Esoteric: distributed lock manager, stack
![Page 40: Bullet Cache - FreeBSDivoras/slides/BSDCan2012-BulletCache.pdf · Introducing the Bullet Cache 1.Offers a smarter data structure to the user side than a simple key-value pair 2.Implements](https://reader036.vdocuments.us/reader036/viewer/2022081611/5f0689437e708231d4187a1c/html5/thumbnails/40.jpg)
Bullet Cache
Balancing speed and usabilityin a cache server
http://www.sf.net/projects/mdcached
Ivan Voras <[email protected]>