pending requests

[dimos_alevizos]

Hello,
we recently installed a clustered system and we're using cacti to graph traffic and nfs ops via a perl script.

The problem is that the script suddenly stopped working.
When I try the query using zedi I get the same error :

<?xml version="1.0" encoding="UTF-8"?>

<netapp  xmlns="http://www.netapp.com/filer/admin" version="1.21">

  <perf-object-get-instances>

    <counters>

      <counter>nfsv3_ops</counter>

    </counters>

    <filter-data></filter-data>

    <instances>

      <instance>mailvs</instance>

    </instances>

    <objectname>nfsv3</objectname>

    <privilege-level></privilege-level>

  </perf-object-get-instances>

</netapp>

<?xml version='1.0' encoding='UTF-8' ?>

<netapp version='1.21' xmlns='http://www.netapp.com/filer/admin'>

    <!-- Output of perf-object-get-instances [Execution Time: 125 ms] -->

    <results errno='13001' status='failed' reason='System busy: 10 requests on table "perf_object_get_instances" have been pending for 70767 seconds.'/>

</netapp>

Is there a way to make the API respond again ?

[phubbard]

Not an answer but wanted to add I've seen the same behavior after running a perfstat.

Error: show failed: System busy: 10 requests on table "perf_object_list_info" have been pending for 3436 seconds

NetApp Release 8.2.1RC1D2 Cluster-Mode

It appears the perfstat did not exit cleanly and/or something is wedged. Should be interesting to see how to clear

this up. Other NetApp tools such as Balance have stopped collecting as well.