cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Todd Burruss <>
Subject Re: CMS GC initial-mark taking 6 seconds , bad?
Date Thu, 20 Oct 2011 17:32:53 GMT
Are you using cassandra's caching?  If you are then you will need to play
around with the RAM setting to find a sweet spot.  A low hit rate on the
cache (which is counter productive anyway) will cause more GC.  A high hit
rate, less GC.

If you are not caching, no need to use a large heap as the OS will do a
fine job of caching the data files for you.  And in fact I would run with
a smaller'ish heap to give the OS more room - how much depends on a
variety of things (how many column families, how often repair, write/read
ratio) - so testing is the best course of action

On 10/20/11 6:38 AM, "Maxim Potekhin" <> wrote:

>Hello Aaron,
>I happen to have 48GB on each machines I use in the cluster. Can I
>assume that I can't really use all of this memory productively? Do you
>have any suggestion related to that? Can I run more than one instance on
>Cassandra on the same box (using different ports) to take advantage of
>this memory, assuming the disk has enough bandwidth?
>On 9/25/2011 11:37 AM, aaron morton wrote:
>> It does seem long and will be felt by your application.
>> Are you running a 47GB heap ? Most peeps seem to think 8 to 12 is about
>>the viable maximum.
>> Cheers
>> -----------------
>> Aaron Morton
>> Freelance Cassandra Developer
>> @aaronmorton
>> On 25/09/2011, at 7:14 PM, Yang wrote:
>>> I see the following in my GC log
>>> 1910.513: [GC [1 CMS-initial-mark: 2598619K(26214400K)]
>>> 13749939K(49807360K), 6.0696680 secs] [Times: user=6.10 sys=0.00,
>>> real=6.07 secs]
>>> so there is a stop-the-world period of 6 seconds. does this sound bad
>>> ? or 6 seconds is OK  and we should expect the built-in
>>> fault-tolerance of Cassandra handle this?
>>> Thanks
>>> Yang

View raw message