You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@cassandra.apache.org by vincent gromakowski <vi...@gmail.com> on 2016/04/01 13:16:53 UTC
cassandra disks cache on SSD
I am looking for way to optimize large reads.
I have seen using SSD is a good option but out of budget, so I am looking
for a way to use some kind of tiering with few SSD caching hot data from
HDD.
I have identified two solutions and would like to get opinions from you and
if you have any experience using them:
- use ZFS with L2ARC functionality
- use Rapiddisk/Rapidcache Linux kernel module
Any opinion ? Constraints ? REX ?
Thanks
Re: cassandra disks cache on SSD
Posted by Mateusz Korniak <ma...@ant.gliwice.pl>.
On Friday 01 April 2016 21:48:08 vincent gromakowski wrote:
> 2016-04-01 19:27 GMT+02:00 Mateusz Korniak <ma...@ant.gliwice.pl>:
> > We are using lvmcache for that.
>
> Can you provide me a approximate estimation of performance gain ?
I suspect it depends on frequently read data size. If it fits into caching
SSDs.
In our scenario, adding one 250GB SSD to nodes owning 1.2 TB resulted in 75%
read cache hit ratio.
It was enough to stop nodes being I/O bound and application to work without
read timeouts.
--
Mateusz Korniak
"(...) mam brata - poważny, domator, liczykrupa, hipokryta, pobożniś,
krótko mówiąc - podpora społeczeństwa."
Nikos Kazantzakis - "Grek Zorba"
Re: cassandra disks cache on SSD
Posted by Bryan Cheng <br...@blockcypher.com>.
Hi Vincent, have you already tried the more common tuning operations like
row cache?
I haven't done any disk level caching like this (we use SSD's exclusively),
but you may see some benefit from putting your commitlog on a separate
conventional HDD if you haven't tried this already. This may push your
read/write pattern to do more sequential access.
On Fri, Apr 1, 2016 at 12:48 PM, vincent gromakowski <
vincent.gromakowski@gmail.com> wrote:
> Can you provide me a approximate estimation of performance gain ?
>
> 2016-04-01 19:27 GMT+02:00 Mateusz Korniak <ma...@ant.gliwice.pl>:
>
>> On Friday 01 April 2016 13:16:53 vincent gromakowski wrote:
>> > (...) looking
>> > for a way to use some kind of tiering with few SSD caching hot data from
>> > HDD.
>> > I have identified two solutions (...)
>>
>> We are using lvmcache for that.
>> Regards,
>> --
>> Mateusz Korniak
>> "(...) mam brata - poważny, domator, liczykrupa, hipokryta, pobożniś,
>> krótko mówiąc - podpora społeczeństwa."
>> Nikos Kazantzakis - "Grek Zorba"
>>
>>
>
Re: cassandra disks cache on SSD
Posted by vincent gromakowski <vi...@gmail.com>.
Can you provide me a approximate estimation of performance gain ?
2016-04-01 19:27 GMT+02:00 Mateusz Korniak <ma...@ant.gliwice.pl>:
> On Friday 01 April 2016 13:16:53 vincent gromakowski wrote:
> > (...) looking
> > for a way to use some kind of tiering with few SSD caching hot data from
> > HDD.
> > I have identified two solutions (...)
>
> We are using lvmcache for that.
> Regards,
> --
> Mateusz Korniak
> "(...) mam brata - poważny, domator, liczykrupa, hipokryta, pobożniś,
> krótko mówiąc - podpora społeczeństwa."
> Nikos Kazantzakis - "Grek Zorba"
>
>
Re: cassandra disks cache on SSD
Posted by Mateusz Korniak <ma...@ant.gliwice.pl>.
On Friday 01 April 2016 13:16:53 vincent gromakowski wrote:
> (...) looking
> for a way to use some kind of tiering with few SSD caching hot data from
> HDD.
> I have identified two solutions (...)
We are using lvmcache for that.
Regards,
--
Mateusz Korniak
"(...) mam brata - poważny, domator, liczykrupa, hipokryta, pobożniś,
krótko mówiąc - podpora społeczeństwa."
Nikos Kazantzakis - "Grek Zorba"