hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Abhijit Pol <a...@rocketfuel.com>
Subject Re: Hbase read performance with increasing number of client threads
Date Tue, 14 Sep 2010 06:51:55 GMT
Noticed discussion on this thread. We filed HBASE-2939 with patch


On Thu, Sep 9, 2010 at 11:10 PM, tsuna <tsunanet@gmail.com> wrote:

> On Thu, Sep 9, 2010 at 1:48 PM, MauMau <maumau307@gmail.com> wrote:
> > From: "tsuna" <tsunanet@gmail.com>
> >> In my recent loadtests on my HBase-heavy application (be it with
> >> HBase's traditional client or with asynchbase) I've always been CPU
> >> bound (except sometimes HBase's traditional client incurs too much
> >> lock contention to really max out the CPU cores, but this is entirely
> >> unrelated to the code you're quoting above).
> >
> > Thank you for sharing your precious experience and knowledge. I
> understood.
> > I'm relieved to know that many threads in one HBase client process can
> max
> > out CPUs in most cases. I'm sorry to have interrupted discussion.
>
> Note that HBase clients aren't always CPU-bound, but all my recent
> loadtests for my application are.  Some clients can be network-bound,
> but for those clients adding more connections won't buy you anything
> if the NIC is already maxed out.  Your mileage will vary wildly
> depending on how you use HBase.
>
> --
> Benoit "tsuna" Sigoure
> Software Engineer @ www.StumbleUpon.com
>

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message