cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Peter Schuller <>
Subject Re: what causes MESSAGE-DESERIALIZER-POOL to spike
Date Mon, 26 Jul 2010 19:56:03 GMT
> MESSAGE-DESERIALIZER-POOL         1    682008        1818682

On the (unverified by me) assumption that disk reads en up in this
stage as Anthony indicates, and looking at the above line and the
iostat output, makes me want to suggest that maybe the read
concurrency is set to 1 and you need to increase it in order to fully
utilize your disks.

That said, I have no idea why you would have as many as 682 THOUSAND
pending for that stage (but I'm not sure at what granularity these are
scheduled so perhaps it is normal for e.g. big slicing reads? I don't

/ Peter Schuller

View raw message