[rrd-users] How to Create the rrd that storeor update million of requests per second

Kashif Qazi kaqazi at etilizepak.com
Fri Feb 13 22:12:53 CET 2009

nate-4 wrote:
> Kashif Qazi wrote:
>> Hi All,
>> I have to store each request data to rrd database. the request
>> granularity
>> can be more or less than one million hits per second.
>> can rrd support granularity in milli/micro seconds.
>> how to create the rrd that can take one million samples per second is
>> this
>> possible.
> I believe rrdtool has a maximum resolution of 1 update per second per
> file. The amount of disk I/O required to do a million samples per second,
> even if rrd's format did support it, are pretty astronomical.
> What you probably want is some sort of entirely in-memory database,
> I'm not sure what product to suggest.
> nate
> _______________________________________________
> rrd-users mailing list
> rrd-users at lists.oetiker.ch
> https://lists.oetiker.ch/cgi-bin/listinfo/rrd-users

Thanks Nate,

For your quick response, i highly appreciate it.

The data is not entirely in memory.

The data is very huge in csv files  containing usage statistics of
webService  hits.

Kashif Ahmed Qazi
View this message in context: http://n2.nabble.com/How-to-Create-the-rrd-that-storeor-update--million-of-requests-per-second-tp2319825p2323837.html
Sent from the RRDtool Users Mailinglist mailing list archive at Nabble.com.

More information about the rrd-users mailing list