Hello Folks,

I've an virtualized environment running with VMware  where Cassandra is humming 
on NFS mounted storage. As the application load increases ,they increase number 
of nodes in data center however writes are getting slower, nodes are flapping 
and application complains in write performance. I can see compaction is getting 
behind, flush writers are struggling - symptoms that points to storage system 
but system Admins says they have expensive, topnotch SSDs under data volume.

I know having nfs is not recommended though getting totally new h/w is not 
possible at this time. I'm wondering if  there is better way to utilize 
available SAN resources to run with Cassandra ? I'll much appreciate your 
insight here.

Thanks/Asad


Nfsiostat
=======================
$ nfsiostat /cassandra/data
172.XX.XX.16:/vol/cns_mount_0020_data mounted on /cassandra/data:

   op/s         rpc bklog
839.33            0.00
read:             ops/s            kB/s           kB/op         retrans         
avg RTT (ms)    avg exe (ms)
                236.611         13471.729        56.936       20 (0.0%)         
  6.125          13.236
write:            ops/s            kB/s           kB/op         retrans         
avg RTT (ms)    avg exe (ms)
                302.627         19048.744        62.945        3 (0.0%)         
 23.154         253.329

nodetool tpstats
==============
$ nodetool tpstats
Pool Name                         Active   Pending      Completed   Blocked  
All time blocked
ReadStage                              0         0        3474362         0     
            0
MiscStage                              0         0              0         0     
            0
CompactionExecutor                    12       337          47130         0     
            0
MutationStage                        256    238996      313857751         0     
            0
MemtableReclaimMemory                  0         0          27081         0     
            0
PendingRangeCalculator                 0         0             37         0     
            0
GossipStage                            0         0         173852         0     
            0
SecondaryIndexManagement               0         0              0         0     
            0
HintsDispatcher                        0         0              0         0     
            0
RequestResponseStage                   0         0      337132828         0     
            0
Native-Transport-Requests              1         0      120206509         0     
      7073177
ReadRepairStage                        0         0           8934         0     
            0
CounterMutationStage                   0         0              0         0     
            0
MigrationStage                         1         2            102         0     
            0
MemtablePostFlush                      1       223          27753         0     
            0
PerDiskMemtableFlushWriter_0           2         2          27095         0     
            0
ValidationExecutor                     0         0              0         0     
            0
Sampler                                0         0              0         0     
            0
MemtableFlushWriter                    5       175          27093         0     
            0
InternalResponseStage                  0         0             46         0     
            0
ViewMutationStage                      0         0              0         0     
            0
AntiEntropyStage                       0         0              0         0     
            0
CacheCleanupExecutor                   0         0              0         0     
            0

Message type           Dropped
READ                         0
RANGE_SLICE                  0
_TRACE                       0
HINT                    944297
MUTATION              15707984
COUNTER_MUTATION             0
BATCH_STORE                  0
BATCH_REMOVE                 0
REQUEST_RESPONSE             0
PAGED_RANGE                  0
READ_REPAIR               3195

Reply via email to