[infinispan-dev] Cachestores performance

Tue Jul 2 08:47:08 EDT 2013

It would be nice to have a deck of "cheat sheets" on the expected use
cases and guarantees: to me it looks like everyone is trying to solve
a different problem / having a different problem in mind.

My own take on it:

Scenario #1
I'll primarily use Infinispan with DIST, and I don't care much for
other options. Reliability is guaranteed via numOwners>1, NOT by
persisting to disk: if a node fails, I kill the VM (the machine, not
the Java process) and start new ones to compensate: I'm assuming cloud
nodes, so it's likely that when a failed node is gone, the disk is
gone as well, with all the carefully stored data.
I will use Infinispan primarily to absorb write spikes - so a "synch
flush" is no good for me - and to boost read performance by as much
memory I can throw at it.
CacheStore is used for two reasons:
 - overflow (LIRS+passivation) for then the memory is not enough
 - clean shutdown: you can think of it as a way to be able to upgrade
some component in the system (Infinispan or my own); I would expect
some kind of "JMX flush" operation to do a clean shutdown without data
loss.

Given such a scenario, I am not interested at all in synchronous
storage. Before we commit into a design which is basically assuming
the need for synchronous storage guarantees, I'd like to understand
what kind of use case it's aiming to solve.

It would be great to document each such use case and put down a table
of things which can be expected, which features should not be expected
(be very explicit on the limitations), and how basic operations are
expected to be performed in the scenario: like how do you do a rolling
upgrade in Scenario 1# ? How do you do a backup? And of course some
configurations & code examples.

Only then we would be able to pick a design (or multiple ones); for my
use case the proposal from Karsten seems excellent, so I'm wondering
why I should be looking for alternatives, and wondering why everyone
is still wasting time on different discussions :-D

I'm pretty sure there is people looking forward for a synch-CacheStore
too: if you could nail down such a scenario however I'm pretty sure
that some other considerations would not be taken into account (like
consistency of data when reactivating a dormant node), so I suspect
that just implementing such a component would actually not make any
new architecture possible, as you would get blocked by other problems
which need to be solved too.. better define all expectations asap!

To me this thread smells of needing the off-heap Direct Memory buffers
which I suggested [long time ago] to efficiently offload internal
buffers, but failing to recognise this we're pushing responsibility to
an epic level complex CacheStore.. guys let's not forget that a mayor
bottleneck of CacheStores today is the SPI it has to implement, we
identified several limitations in the contract in the past which
prevent a superior efficiency: we're working towards a mayor release
now so I'd rather focus on the API changes which will make it possible
to get decent performance even without changing any storage engine..
I'm pretty sure Cassandra (to pick one) doesn't scale too bad.

Cheers,
Sanne

On 2 July 2013 10:09, Radim Vansa <rvansa at redhat.com> wrote:
> Hi,
>
> I've written down this proposal for the implementation of new cache store.
>
> https://community.jboss.org/wiki/BrnoCacheStoreDesignProposal
>
> WDYT?
>
> Radim
>
> ----- Original Message -----
> | From: "Radim Vansa" <rvansa at redhat.com>
> | To: "infinispan -Dev List" <infinispan-dev at lists.jboss.org>
> | Sent: Thursday, June 27, 2013 2:37:43 PM
> | Subject: Re: [infinispan-dev] Cachestores performance
> |
> |
> |
> | ----- Original Message -----
> | | From: "Galder Zamarreño" <galder at redhat.com>
> | | To: "infinispan -Dev List" <infinispan-dev at lists.jboss.org>
> | | Sent: Thursday, June 27, 2013 1:52:11 PM
> | | Subject: Re: [infinispan-dev] Cachestores performance
> | |
> | | > As for Karsten's FCS implementation, I too have issues with the key set
> | | > and
> | | > value offsets being solely in memory.  However I think that could be
> | | > improved by storing only a certain number of keys/offsets in memory, and
> | | > flushing the rest to disk again into an index file.
> | |
> | | ^ Karsten's implementation makes this relatively easy to achieve because it
> | | already keeps this mapping in a LinkedHashMap (with a given max entries
> | | limit [1]) assuming removeEldestEntry() is overriden to flush to disk older
> | | entries. Some extra logic would be needed to bring back data from the disk
> | | too… but your suggestion below is also quite interesting...
> |
> | I certainly wouldn't call this easy task, because the most problematic part
> | is what we will do when the whole entry (both key and value) are gone from
> | memory and we want to read them - that requires keeping some searchable
> | structure on-disk. And that's the hard stuff.
> |
> | |
> | | > I believe LevelDB follows a similar design, but I think Karsten's FCS
> | | > will
> | | > perform better than LevelDB since it doesn't attempt to maintain a sorted
> | | > structure on disk.
> | |
> | | ^ In-memory, the structure can optionally be ordered if it's bound [1],
> | | otherwise it's just a normal map. How would be store it at the disk level?
> | | B+ tree with hashes of keys and then linked lists?
> |
> | Before choosing "I love B#@& trees, let's use B#@& trees!", I'd find out what
> | requirements do we have for the structure. I believe that the index itself
> | should not be considered persistent, as it can be rebuilt when preloading
> | the data (sequentially reading the data is fast, therefore we can afford do
> | this indexing preload), the reason of the index being on-disk is that we
> | don't have enough memory to store all keys, or even key hashes. Therefore it
> | does not have to be updated synchronously with the writes. It should be
> | mostly read-optimized then, because that's the thing where we need
> | synchronous access to this structure.
> |
> | |
> | | > One approach to maintaining keys and offsets in memory could be a
> | | > WeakReference that points to the key stored in the in-memory
> | | > DataContainer.  Once evicted from the DC, then the CacheStore impl would
> | | > need to fetch the key again from the index file before looking up the
> | | > value in the actual store.
> | |
> | | ^ Hmmm, interesting idea… has the potential to safe the memory space by not
> | | having to keep that extra data structure in the cache store.
> |
> | You mean to mix the DataContainer with xCacheEntry implementation and the
> | cache store implementation? Is that possible from design perspective?
> | Speaking about different kind of references, we may even optimize
> | not-well-tuned eviction by SoftReferences, so that even if the entry was
> | evicted from main DataContainer, we'd keep the value referenced from the
> | cache-store (and this does not have to be loaded from disk if referenced
> | before garbage collection). But such thought may be premature optimization.
> | For having eviction managed in relation with GC we should rather combine
> | this with PhantomReferences, where entries would be written to cache upon
> | finalization.
> |
> | |
> | | > This way we have hot items always in memory, semi-hot items with offsets
> | | > in
> | | > memory and values on disk, and cold items needing to be read off disk
> | | > entirely (both offset and value).  Also for write-through and
> | | > write-behind, as long as the item is hot or warm (key and offset in
> | | > memory), writing will be pretty fast.
> | |
> | | My worry about Karsten's impl is writing actually. If you look at the last
> | | performance numbers in [2], where we see the performance difference of
> | | force=true and force=false in Karsten's cache store compared with LevelDB
> | | JNI, you see that force=false is fastest, then JNI LevelDB, and the
> | | force=true. Me wonders what kind of write guarantees LevelDB JNI provides
> | | (and the JAVA version)...
> |
> | Just for clarification: the fast implementation is without force at all, the
> | slower is with force(false). Force(true) means updating metadata (such as
> | access times?) which is not required for cache-store.
> | But the numbers suggest that the random access with syncing is really not a
> | good option, and that we should rather use the temporary append-only log,
> | which would be persisted into structured DB by different thread (as LevelDB
> | does, I suppose).
> |
> | Thinking about all the levels and cache structures optimizing the read
> | access, I can see four levels of search structures: key + value (usual
> | DataContainer), key + offset, hash + offset, all on disk. The "hash +
> | offset" may seem superflous but for some use-cases with big keys it may be
> | worth sparing a few disk look-ups.
> |
> | Radim
> |
> | | >
> | | > On 27 Jun 2013, at 10:33, Radim Vansa <rvansa at redhat.com> wrote:
> | | >
> | | >> Oops, by the cache store I mean the previously-superfast
> | | >> KarstenFileCacheStore implementation.
> | | >>
> | | >> ----- Original Message -----
> | | >> | From: "Radim Vansa" <rvansa at redhat.com>
> | | >> | To: "infinispan -Dev List" <infinispan-dev at lists.jboss.org>
> | | >> | Sent: Thursday, June 27, 2013 11:30:53 AM
> | | >> | Subject: Re: [infinispan-dev] Cachestores performance
> | | >> |
> | | >> | I have added FileChannel.force(false) flushes after all write
> | | >> | operations
> | | >> | in
> | | >> | the cache store, and now the comparison is also updated with these
> | | >> | values.
> | | >> |
> | | >> | Radim
> | | >> |
> | | >> | ----- Original Message -----
> | | >> | | From: "Radim Vansa" <rvansa at redhat.com>
> | | >> | | To: "infinispan -Dev List" <infinispan-dev at lists.jboss.org>
> | | >> | | Sent: Thursday, June 27, 2013 8:54:25 AM
> | | >> | | Subject: Re: [infinispan-dev] Cachestores performance
> | | >> | |
> | | >> | | Yep, write-through. LevelDB JAVA used FileChannelTable
> | | >> | | implementation
> | | >> | | (-Dleveldb.mmap), because Mmaping is not implemented very well and
> | | >> | | causes
> | | >> | | JVM crashes (I believe it's because of calling non-public API via
> | | >> | | reflection
> | | >> | | - I've found post from the Oracle JVM guys discouraging the
> | | >> | | particular
> | | >> | | trick
> | | >> | | it uses). After writing the record to the log, it calls
> | | >> | | FileChannel.force(true), therefore, it should be really on the disc
> | | >> | | by
> | | >> | | that
> | | >> | | moment.
> | | >> | | I have not looked into the JNI implementation but I expect the same.
> | | >> | |
> | | >> | | By the way, I have updated [1] with numbers when running on more
> | | >> | | data
> | | >> | | (2 GB
> | | >> | | instead of 100 MB). I won't retype it here, so look there. The
> | | >> | | performance
> | | >> | | is much lower.
> | | >> | | I may try also increase JVM heap size and try with a bit more data
> | | >> | | yet.
> | | >> | |
> | | >> | | Radim
> | | >> | |
> | | >> | | [1] https://community.jboss.org/wiki/FileCacheStoreRedesign
> | | >> | |
> | | >> | | ----- Original Message -----
> | | >> | | | From: "Erik Salter" <an1310 at hotmail.com>
> | | >> | | | To: "infinispan -Dev List" <infinispan-dev at lists.jboss.org>
> | | >> | | | Sent: Wednesday, June 26, 2013 7:40:19 PM
> | | >> | | | Subject: Re: [infinispan-dev] Cachestores performance
> | | >> | | |
> | | >> | | | These were write-through cache stores, right?  And with LevelDB,
> | | >> | | | this was
> | | >> | | | through to the database file itself?
> | | >> | | |
> | | >> | | | Erik
> | | >> | | |
> | | >> | | | -----Original Message-----
> | | >> | | | From: infinispan-dev-bounces at lists.jboss.org
> | | >> | | | [mailto:infinispan-dev-bounces at lists.jboss.org] On Behalf Of Radim
> | | >> | | | Vansa
> | | >> | | | Sent: Wednesday, June 26, 2013 11:24 AM
> | | >> | | | To: infinispan -Dev List
> | | >> | | | Subject: [infinispan-dev] Cachestores performance
> | | >> | | |
> | | >> | | | Hi all,
> | | >> | | |
> | | >> | | | according to [1] I've created the comparison of performance in
> | | >> | | | stress-tests.
> | | >> | | |
> | | >> | | | All setups used local-cache, benchmark was executed via Radargun
> | | >> | | | (actually
> | | >> | | | version not merged into master yet [2]). I've used 4 nodes just to
> | | >> | | | get
> | | >> | | | more
> | | >> | | | data - each slave was absolutely independent of the others.
> | | >> | | |
> | | >> | | | First test was preloading performance - the cache started and
> | | >> | | | tried
> | | >> | | | to
> | | >> | | | load
> | | >> | | | 1GB of data from harddrive. Without cachestore the startup takes
> | | >> | | | about 2
> | | >> | | | -
> | | >> | | | 4
> | | >> | | | seconds, average numbers for the cachestores are below:
> | | >> | | |
> | | >> | | | FileCacheStore:        9.8 s
> | | >> | | | KarstenFileCacheStore:  14 s
> | | >> | | | LevelDB-JAVA impl.:   12.3 s
> | | >> | | | LevelDB-JNI impl.:    12.9 s
> | | >> | | |
> | | >> | | | IMO nothing special, all times seem affordable. We don't benchmark
> | | >> | | | exactly
> | | >> | | | storing the data into the cachestore, here FileCacheStore took
> | | >> | | | about
> | | >> | | | 44
> | | >> | | | minutes, while Karsten about 38 seconds, LevelDB-JAVA 4 minutes
> | | >> | | | and
> | | >> | | | LevelDB-JNI 96 seconds. The units are right, it's minutes compared
> | | >> | | | to
> | | >> | | | seconds. But we all know that FileCacheStore is bloody slow.
> | | >> | | |
> | | >> | | | Second test is stress test (5 minutes, preceded by 2 minute
> | | >> | | | warmup)
> | | >> | | | where
> | | >> | | | each of 10 threads works on 10k entries with 1kB values (~100 MB
> | | >> | | | in
> | | >> | | | total).
> | | >> | | | 20 % writes, 80 % reads, as usual. No eviction is configured,
> | | >> | | | therefore
> | | >> | | | the
> | | >> | | | cache-store works as a persistent storage only for case of crash.
> | | >> | | |
> | | >> | | | FileCacheStore:         3.1M reads/s   112 writes/s  // on one
> | | >> | | | node
> | | >> | | | the
> | | >> | | | performance was only 2.96M reads/s 75 writes/s
> | | >> | | | KarstenFileCacheStore:  9.2M reads/s  226k writes/s  // yikes!
> | | >> | | | LevelDB-JAVA impl.:     3.9M reads/s  5100 writes/s
> | | >> | | | LevelDB-JNI impl.:      6.6M reads/s   14k writes/s  // on one
> | | >> | | | node
> | | >> | | | the
> | | >> | | | performance was 3.9M/8.3k - about half of the others
> | | >> | | | Without cache store:   15.5M reads/s  4.4M writes/s
> | | >> | | |
> | | >> | | | Karsten implementation pretty rules here for two reasons. First of
> | | >> | | | all,
> | | >> | | | it
> | | >> | | | does not flush the data (it calls only RandomAccessFile.write()).
> | | >> | | | Other
> | | >> | | | cheat is that it stores in-memory the keys and offsets of data
> | | >> | | | values in
> | | >> | | | the
> | | >> | | | database file. Therefore, it's definitely the best choice for this
> | | >> | | | scenario,
> | | >> | | | but it does not allow to scale the cache-store, especially in
> | | >> | | | cases
> | | >> | | | where
> | | >> | | | the keys are big and values small. However, this performance boost
> | | >> | | | is
> | | >> | | | definitely worth checking - I could think of caching the disk
> | | >> | | | offsets in
> | | >> | | | memory and querying persistent index only in case of missing
> | | >> | | | record,
> | | >> | | | with
> | | >> | | | part of the persistent index flushed asynchronously (the index can
> | | >> | | | be
> | | >> | | | always
> | | >> | | | rebuilt during the preloading for case of crash).
> | | >> | | |
> | | >> | | | The third test should have tested the scenario with more data to
> | | >> | | | be
> | | >> | | | stored
> | | >> | | | than memory - therefore, the stressors operated on 100k entries
> | | >> | | | (~100 MB
> | | >> | | | of
> | | >> | | | data) but eviction was set to 10k entries (9216 entries ended up
> | | >> | | | in
> | | >> | | | memory
> | | >> | | | after the test has ended).
> | | >> | | |
> | | >> | | | FileCacheStore:            750 reads/s         285 writes/s  //
> | | >> | | | one
> | | >> | | | node
> | | >> | | | had
> | | >> | | | only 524 reads and 213 writes per second
> | | >> | | | KarstenFileCacheStore:    458k reads/s        137k writes/s
> | | >> | | | LevelDB-JAVA impl.:        21k reads/s          9k writes/s  // a
> | | >> | | | bit
> | | >> | | | varying
> | | >> | | | performance
> | | >> | | | LevelDB-JNI impl.:     13k-46k reads/s  6.6k-15.2k writes/s  //
> | | >> | | | the
> | | >> | | | performance varied a lot!
> | | >> | | |
> | | >> | | | 100 MB of data is not much, but it takes so long to push it into
> | | >> | | | FileCacheStore that I won't use more unless we exclude this loser
> | | >> | | | from
> | | >> | | | the
> | | >> | | | comparison :)
> | | >> | | |
> | | >> | | | Radim
> | | >> | | |
> | | >> | | | [1] https://community.jboss.org/wiki/FileCacheStoreRedesign
> | | >> | | | [2] https://github.com/rvansa/radargun/tree/t_keygen
> | | >> | | |
> | | >> | | | -----------------------------------------------------------
> | | >> | | | Radim Vansa
> | | >> | | | Quality Assurance Engineer
> | | >> | | | JBoss Datagrid
> | | >> | | | tel. +420532294559 ext. 62559
> | | >> | | |
> | | >> | | | Red Hat Czech, s.r.o.
> | | >> | | | Brno, Purkyňova 99/71, PSČ 612 45
> | | >> | | | Czech Republic
> | | >> | | |
> | | >> | | |
> | | >> | | | _______________________________________________
> | | >> | | | infinispan-dev mailing list
> | | >> | | | infinispan-dev at lists.jboss.org
> | | >> | | | https://lists.jboss.org/mailman/listinfo/infinispan-dev
> | | >> | | |
> | | >> | | |
> | | >> | | | _______________________________________________
> | | >> | | | infinispan-dev mailing list
> | | >> | | | infinispan-dev at lists.jboss.org
> | | >> | | | https://lists.jboss.org/mailman/listinfo/infinispan-dev
> | | >> | |
> | | >> | | _______________________________________________
> | | >> | | infinispan-dev mailing list
> | | >> | | infinispan-dev at lists.jboss.org
> | | >> | | https://lists.jboss.org/mailman/listinfo/infinispan-dev
> | | >> |
> | | >> | _______________________________________________
> | | >> | infinispan-dev mailing list
> | | >> | infinispan-dev at lists.jboss.org
> | | >> | https://lists.jboss.org/mailman/listinfo/infinispan-dev
> | | >>
> | | >> _______________________________________________
> | | >> infinispan-dev mailing list
> | | >> infinispan-dev at lists.jboss.org
> | | >> https://lists.jboss.org/mailman/listinfo/infinispan-dev
> | | >
> | | > --
> | | > Manik Surtani
> | | > manik at jboss.org
> | | > twitter.com/maniksurtani
> | | >
> | | > Platform Architect, JBoss Data Grid
> | | > http://red.ht/data-grid
> | | >
> | | >
> | | > _______________________________________________
> | | > infinispan-dev mailing list
> | | > infinispan-dev at lists.jboss.org
> | | > https://lists.jboss.org/mailman/listinfo/infinispan-dev
> | |
> | |
> | | --
> | | Galder Zamarreño
> | | galder at redhat.com
> | | twitter.com/galderz
> | |
> | | Project Lead, Escalante
> | | http://escalante.io
> | |
> | | Engineer, Infinispan
> | | http://infinispan.org
> | |
> | |
> | | _______________________________________________
> | | infinispan-dev mailing list
> | | infinispan-dev at lists.jboss.org
> | | https://lists.jboss.org/mailman/listinfo/infinispan-dev
> |
> | _______________________________________________
> | infinispan-dev mailing list
> | infinispan-dev at lists.jboss.org
> | https://lists.jboss.org/mailman/listinfo/infinispan-dev
>
> _______________________________________________
> infinispan-dev mailing list
> infinispan-dev at lists.jboss.org
> https://lists.jboss.org/mailman/listinfo/infinispan-dev