[
https://issues.apache.org/jira/browse/CASSANDRA-6602?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13881656#comment-13881656
]
Tupshin Harper commented on CASSANDRA-6602:
-------------------------------------------
I do mean demonstrably optimal for exactly, and probably only, this type of
workload.
My claim is, that if all of the pieces I outlined above were implemented, and
as long as the following held:
1) partitions are sorted in natural time order, roughly approximating arrival
order
2) arrival order is always within 1/2 memtable duration, so that out of order
columns always self-correct before flushing
3) there are no node outages, or failure to fully replicate (no hints, and no
repaired data)
Then all data will be written exactly once, and no more, and that is optimal on
the write path.
Additionally, all data will be written in wide time chunks, so that only
queries that actually span that gap will require opening two sstables, and this
is also optimal behaviour on the read path.
Finally, if there are hints, there is still a substantial window to replay them
so that they still get written in correct order the first time.
If data gets delivered so far out of order that the above mechanisms do not
work, then the worst possible case is the need to replace one (or two, if the
outage spanned an sstable write) sstables through a combination of repair and a
very simple compaction.
> Enhancements to optimize for the storing of time series data
> ------------------------------------------------------------
>
> Key: CASSANDRA-6602
> URL: https://issues.apache.org/jira/browse/CASSANDRA-6602
> Project: Cassandra
> Issue Type: New Feature
> Components: Core
> Reporter: Tupshin Harper
> Fix For: 3.0
>
>
> There are some unique characteristics of many/most time series use cases that
> both provide challenges, as well as provide unique opportunities for
> optimizations.
> One of the major challenges is in compaction. The existing compaction
> strategies will tend to re-compact data on disk at least a few times over the
> lifespan of each data point, greatly increasing the cpu and IO costs of that
> write.
> Compaction exists to
> 1) ensure that there aren't too many files on disk
> 2) ensure that data that should be contiguous (part of the same partition) is
> laid out contiguously
> 3) deleting data due to ttls or tombstones
> The special characteristics of time series data allow us to optimize away all
> three.
> Time series data
> 1) tends to be delivered in time order, with relatively constrained exceptions
> 2) often has a pre-determined and fixed expiration date
> 3) Never gets deleted prior to TTL
> 4) Has relatively predictable ingestion rates
> Note that I filed CASSANDRA-5561 and this ticket potentially replaces or
> lowers the need for it. In that ticket, jbellis reasonably asks, how that
> compaction strategy is better than disabling compaction.
> Taking that to heart, here is a compaction-strategy-less approach that could
> be extremely efficient for time-series use cases that follow the above
> pattern.
> (For context, I'm thinking of an example use case involving lots of streams
> of time-series data with a 5GB per day ingestion rate, and a 1000 day
> retention with TTL, resulting in an eventual steady state of 5TB per node)
> 1) You have an extremely large memtable (preferably off heap, if/when doable)
> for the table, and that memtable is sized to be able to hold a lengthy window
> of time. A typical period might be one day. At the end of that period, you
> flush the contents of the memtable to an sstable and move to the next one.
> This is basically identical to current behaviour, but with thresholds
> adjusted so that you can ensure flushing at predictable intervals. (Open
> question is whether predictable intervals is actually necessary, or whether
> just waiting until the huge memtable is nearly full is sufficient)
> 2) Combine the behaviour with CASSANDRA-5228 so that sstables will be
> efficiently dropped once all of the columns have. (Another side note, it
> might be valuable to have a modified version of CASSANDRA-3974 that doesn't
> bother storing per-column TTL since it is required that all columns have the
> same TTL)
> 3) Be able to mark column families as read/write only (no explicit deletes),
> so no tombstones.
> 4) Optionally add back an additional type of delete that would delete all
> data earlier than a particular timestamp, resulting in immediate dropping of
> obsoleted sstables.
> The result is that for in-order delivered data, Every cell will be laid out
> optimally on disk on the first pass, and over the course of 1000 days and 5TB
> of data, there will "only" be 1000 5GB sstables, so the number of filehandles
> will be reasonable.
> For exceptions (out-of-order delivery), most cases will be caught by the
> extended (24 hour+) memtable flush times and merged correctly automatically.
> For those that were slightly askew at flush time, or were delivered so far
> out of order that they go in the wrong sstable, there is relatively low
> overhead to reading from two sstables for a time slice, instead of one, and
> that overhead would be incurred relatively rarely unless out-of-order
> delivery was the common case, in which case, this strategy should not be used.
> Another possible optimization to address out-of-order would be to maintain
> more than one time-centric memtables in memory at a time (e.g. two 12 hour
> ones), and then you always insert into whichever one of the two "owns" the
> appropriate range of time. By delaying flushing the ahead one until we are
> ready to roll writes over to a third one, we are able to avoid any
> fragmentation as long as all deliveries come in no more than 12 hours late
> (in this example, presumably tunable).
> Anything that triggers compactions will have to be looked at, since there
> won't be any. The one concern I have is the ramificaiton of repair.
> Initially, at least, I think it would be acceptable to just write one sstable
> per repair and not bother trying to merge it with other sstables.
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)
