You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@cassandra.apache.org by Clint Kelly <cl...@gmail.com> on 2014/11/16 18:12:43 UTC
What time range does nodetool cfhistograms use?
Hi all,
Over what time range does "nodetool cfhistograms" operate?
I am using Cassandra 2.0.8.39.
I am trying to debug some very high 95th and 99th percentile read
latencies in an application that I'm working on.
I tried running nodetool cfhistograms to get a flavor for the
distribution of read latencies and also to see how many SSTables our
reads are using, and I saw different results yesterday versus this
morning, so I assume the time window is fairly tight (like an hour or
so). I vaguely recall Aaron Morton talking about this during the
training course I took at Cassandra Summit, but I cannot find my notes
and I think the behavior of the tool with regard to time windows
changed from version to version.
Thanks!
-Clint
Re: What time range does nodetool cfhistograms use?
Posted by Clint Kelly <cl...@gmail.com>.
Thanks for the quick reply! I completely forgot about proxyhistograms!
On Sun, Nov 16, 2014 at 1:56 PM, DuyHai Doan <do...@gmail.com> wrote:
> "Does it show statistics for just the current node on which I am running,
> or for the entire cluster?" --> only current node.
>
> "Are the read latencies shown the latencies within a single host, or are
> they the end-to-end latencies from the coordinator node?" --> cfhistograms
> shows metrics at table/node level, proxyhistograms shows metrics at
> cluster/coordinator level
>
> On Sun, Nov 16, 2014 at 10:31 PM, Clint Kelly <cl...@gmail.com>
> wrote:
>
>> Thanks, Mark!
>>
>> A couple of other questions about the command:
>>
>> * Does it show statistics for just the current node on which I am
>> running, or for the entire cluster?
>> * Are the read latencies shown the latencies within a single host, or
>> are they the end-to-end latencies from the coordinator node?
>>
>> -Clint
>>
>>
>> On Sun, Nov 16, 2014 at 10:05 AM, Mark Reddy <ma...@gmail.com>
>> wrote:
>> > Hi Clint,
>> >
>> > The values of SSTables, Write Latency and Read Latency will be reset on
>> node
>> > start/restart and after running the cfhistograms command itself.
>> >
>> > The values of Row Size and Column Count are calculated at startup and
>> then
>> > re-evaluated during compaction.
>> >
>> >
>> > Mark
>> >
>> >
>> > On 16 November 2014 17:12, Clint Kelly <cl...@gmail.com> wrote:
>> >>
>> >> Hi all,
>> >>
>> >> Over what time range does "nodetool cfhistograms" operate?
>> >>
>> >> I am using Cassandra 2.0.8.39.
>> >>
>> >> I am trying to debug some very high 95th and 99th percentile read
>> >> latencies in an application that I'm working on.
>> >>
>> >> I tried running nodetool cfhistograms to get a flavor for the
>> >> distribution of read latencies and also to see how many SSTables our
>> >> reads are using, and I saw different results yesterday versus this
>> >> morning, so I assume the time window is fairly tight (like an hour or
>> >> so). I vaguely recall Aaron Morton talking about this during the
>> >> training course I took at Cassandra Summit, but I cannot find my notes
>> >> and I think the behavior of the tool with regard to time windows
>> >> changed from version to version.
>> >>
>> >> Thanks!
>> >>
>> >> -Clint
>> >
>> >
>>
>
>
Re: What time range does nodetool cfhistograms use?
Posted by DuyHai Doan <do...@gmail.com>.
"Does it show statistics for just the current node on which I am running,
or for the entire cluster?" --> only current node.
"Are the read latencies shown the latencies within a single host, or are
they the end-to-end latencies from the coordinator node?" --> cfhistograms
shows metrics at table/node level, proxyhistograms shows metrics at
cluster/coordinator level
On Sun, Nov 16, 2014 at 10:31 PM, Clint Kelly <cl...@gmail.com> wrote:
> Thanks, Mark!
>
> A couple of other questions about the command:
>
> * Does it show statistics for just the current node on which I am
> running, or for the entire cluster?
> * Are the read latencies shown the latencies within a single host, or
> are they the end-to-end latencies from the coordinator node?
>
> -Clint
>
>
> On Sun, Nov 16, 2014 at 10:05 AM, Mark Reddy <ma...@gmail.com>
> wrote:
> > Hi Clint,
> >
> > The values of SSTables, Write Latency and Read Latency will be reset on
> node
> > start/restart and after running the cfhistograms command itself.
> >
> > The values of Row Size and Column Count are calculated at startup and
> then
> > re-evaluated during compaction.
> >
> >
> > Mark
> >
> >
> > On 16 November 2014 17:12, Clint Kelly <cl...@gmail.com> wrote:
> >>
> >> Hi all,
> >>
> >> Over what time range does "nodetool cfhistograms" operate?
> >>
> >> I am using Cassandra 2.0.8.39.
> >>
> >> I am trying to debug some very high 95th and 99th percentile read
> >> latencies in an application that I'm working on.
> >>
> >> I tried running nodetool cfhistograms to get a flavor for the
> >> distribution of read latencies and also to see how many SSTables our
> >> reads are using, and I saw different results yesterday versus this
> >> morning, so I assume the time window is fairly tight (like an hour or
> >> so). I vaguely recall Aaron Morton talking about this during the
> >> training course I took at Cassandra Summit, but I cannot find my notes
> >> and I think the behavior of the tool with regard to time windows
> >> changed from version to version.
> >>
> >> Thanks!
> >>
> >> -Clint
> >
> >
>
Re: What time range does nodetool cfhistograms use?
Posted by Clint Kelly <cl...@gmail.com>.
Thanks, Mark!
A couple of other questions about the command:
* Does it show statistics for just the current node on which I am
running, or for the entire cluster?
* Are the read latencies shown the latencies within a single host, or
are they the end-to-end latencies from the coordinator node?
-Clint
On Sun, Nov 16, 2014 at 10:05 AM, Mark Reddy <ma...@gmail.com> wrote:
> Hi Clint,
>
> The values of SSTables, Write Latency and Read Latency will be reset on node
> start/restart and after running the cfhistograms command itself.
>
> The values of Row Size and Column Count are calculated at startup and then
> re-evaluated during compaction.
>
>
> Mark
>
>
> On 16 November 2014 17:12, Clint Kelly <cl...@gmail.com> wrote:
>>
>> Hi all,
>>
>> Over what time range does "nodetool cfhistograms" operate?
>>
>> I am using Cassandra 2.0.8.39.
>>
>> I am trying to debug some very high 95th and 99th percentile read
>> latencies in an application that I'm working on.
>>
>> I tried running nodetool cfhistograms to get a flavor for the
>> distribution of read latencies and also to see how many SSTables our
>> reads are using, and I saw different results yesterday versus this
>> morning, so I assume the time window is fairly tight (like an hour or
>> so). I vaguely recall Aaron Morton talking about this during the
>> training course I took at Cassandra Summit, but I cannot find my notes
>> and I think the behavior of the tool with regard to time windows
>> changed from version to version.
>>
>> Thanks!
>>
>> -Clint
>
>
Re: What time range does nodetool cfhistograms use?
Posted by Mark Reddy <ma...@gmail.com>.
Hi Clint,
The values of SSTables, Write Latency and Read Latency will be reset on
node start/restart and after running the cfhistograms command itself.
The values of Row Size and Column Count are calculated at startup and
then re-evaluated during compaction.
Mark
On 16 November 2014 17:12, Clint Kelly <cl...@gmail.com> wrote:
> Hi all,
>
> Over what time range does "nodetool cfhistograms" operate?
>
> I am using Cassandra 2.0.8.39.
>
> I am trying to debug some very high 95th and 99th percentile read
> latencies in an application that I'm working on.
>
> I tried running nodetool cfhistograms to get a flavor for the
> distribution of read latencies and also to see how many SSTables our
> reads are using, and I saw different results yesterday versus this
> morning, so I assume the time window is fairly tight (like an hour or
> so). I vaguely recall Aaron Morton talking about this during the
> training course I took at Cassandra Summit, but I cannot find my notes
> and I think the behavior of the tool with regard to time windows
> changed from version to version.
>
> Thanks!
>
> -Clint
>