read performance much worse than write?

ACHOU_SIMG — Wed, 04 Jun 2025 20:03:05 GMT

Hi,

2-node FAS8040 with flash cache running in clustered ontap 8.3GA with 10GbE ports.

From a Linux client with single 10GbE connection, I ran several tests using iozone to obtain write/rewrite and read/reread performance numbers for an NFS mounted volume on NetApp. I notice all runs produce reads much less than writes. As an example,

kB            reclen    write       rewrite      read       reread      random read     random write
8388608       4    2774799 2079447   111926 4616036 3701496           2193816
8388608       8    2963944 3444805   111376 5532988 5025833    2742466
8388608      16 3227913 3766890    110325 5083604 5953205        3247727
...

Notice for all record lengths, reads are in ~100MB/sec while writes are much higher, 2.7 - 3GB/sec.

1. I question the numbers for writes in the range of 3GB/sec which is excessively high even over 10Gbps link.

2. the 'read' numbers are way smaller than writes which does not make sense to me.

Could someone shed some lights on what I've missed?

Thanks,

Re: read performance much worse than write?

marcusgross — Wed, 17 Aug 2016 13:36:55 GMT

Hi,

the file you're testing with, should be much bigger than the RAM and cache in the box.

Otherwise you measure the cache throughput.

Marcus

topic read performance much worse than write? in ONTAP Discussions

read performance much worse than write?

Re: read performance much worse than write?