[
https://issues.apache.org/jira/browse/CASSANDRA-13241?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15888600#comment-15888600
]
Ariel Weisberg commented on CASSANDRA-13241:
--------------------------------------------
Based on
http://duartes.org/gustavo/blog/post/how-the-kernel-manages-your-memory/ and
http://lxr.linux.no/linux+v2.6.28.1/arch/ia64/include/asm/page.h#L174 it seems
like the kernel introduces it's own 8-bytes of overhead per 4k page.
I think it's worth doing something more efficient with the offsets and then
reducing the chunk size to at least memory utilization parity with what we have
today. We should at least push it to the free lunch point. I'm still
researching integer compression options to see how cheap we can make offset
storage. The algorithms are out there it's the implementations that are a chore.
> Lower default chunk_length_in_kb from 64kb to 4kb
> -------------------------------------------------
>
> Key: CASSANDRA-13241
> URL: https://issues.apache.org/jira/browse/CASSANDRA-13241
> Project: Cassandra
> Issue Type: Wish
> Components: Core
> Reporter: Benjamin Roth
>
> Having a too low chunk size may result in some wasted disk space. A too high
> chunk size may lead to massive overreads and may have a critical impact on
> overall system performance.
> In my case, the default chunk size lead to peak read IOs of up to 1GB/s and
> avg reads of 200MB/s. After lowering chunksize (of course aligned with read
> ahead), the avg read IO went below 20 MB/s, rather 10-15MB/s.
> The risk of (physical) overreads is increasing with lower (page cache size) /
> (total data size) ratio.
> High chunk sizes are mostly appropriate for bigger payloads pre request but
> if the model consists rather of small rows or small resultsets, the read
> overhead with 64kb chunk size is insanely high. This applies for example for
> (small) skinny rows.
> Please also see here:
> https://groups.google.com/forum/#!topic/scylladb-dev/j_qXSP-6-gY
> To give you some insights what a difference it can make (460GB data, 128GB
> RAM):
> - Latency of a quite large CF: https://cl.ly/1r3e0W0S393L
> - Disk throughput: https://cl.ly/2a0Z250S1M3c
> - This shows, that the request distribution remained the same, so no "dynamic
> snitch magic": https://cl.ly/3E0t1T1z2c0J
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
