[PVE-User] CEPH - benchmark

[lord_Niedzwiedz]

         I have non heterogenic network and hardware.
CEPH about        Write 1160MB/sec,     Read 1820 MB/sec

One nvme drive started going crazy.
The performance of the entire array dropped catastrophically.
The system said nothing.
I wonder if there is any mechanism in CEPH/Proxmox that informs us about 
this automatically ??


I quickly wrote a script that periodically checks performance.

root at tjall1:~# cat /Backup/script/Ceph.sh

#!/bin/sh
#        Ceph test by sir_Misiek at o2.pl
#        Grzegorz Mi$kiewicz
#        19.09.2023

MINWRITE=600
MINREAD=1200
POOL1=ceph-lxc
POOL2=ceph-vm

WRITE=`rados bench -p $POOL1 120 write --no-cleanup | grep "Bandwidth "| 
awk '{ print $3}'`
READ=`rados bench -p $POOL1 60 rand| grep "Bandwidth "| awk '{ print $3}'`

  echo Write = $WRITE
  echo READ = $READ

# We cut out everything before the dot. Converts a floating point value 
to an integer.
WRITE_INT=${WRITE%%.*}
READ_INT=${READ%%.*}

if [ ${MINWRITE} -ge "${WRITE_INT}" ]; then
     echo "Ceph slow write on pool($POOL1): ${WRITE} MB/sec"
   fi

if [ ${MINREAD} -ge "${READ_INT}" ]; then
     echo "Ceph slow read on pool($POOL1): ${WRITE} MB/sec"
   fi

rados -p $POOL1 cleanup > /dev/null
rados -p $POOL1 cleanup; sync; rados -p $POOL2 cleanup; sync

exit