cloudbytestorage / touchstone Goto Github PK

- sanitize, sort, filter
  - [ -z $vm_id ] || vm_id_list="${vm_id_list}\n$vm_id"
  - vm_id_list=$( echo -e $vm_id_list | sort -g | uniq -d )
  - [ "$vm_id_list" = "" ] || \
        { f_error "Conflicting VM IDs: ${vm_id_list}. Exiting" ; exit 1 ; }

- filter, extract, regex
  - vm_name="${vm_found##*/}" # Remove path, leaving VM name
  - vm_id=${vm_name##*[!0-9]} # Remove name, leaving VM ID

- conditional checks
  - f_info "Starting all VMs in $host_vmdir"
  - if [ $( ls $host_vmdir | wc -l ) = 0 ]; then
      f_error "No VMs found. Exiting"
      exit 1
    fi

- Searches for the line which does not start with 
  - # or 
  - single quote (‘) or 
  - double front slashes (//)
  - grep  -v "^#\|^'\|^\/\/" comments

- cut usage
  - extract first 3 chars of each line from a file
    - cut -c1-3 test.txt
  - start from 3rd character till end of each line
    - cut -c3- test.txt
  - first 8 characters
    - cut -c-8 test.txt
  - first field of each line delimited by :
    - cut -d':' -f1 /etc/passwd
  - fields 1 through 4, 6 & 7
    - grep "/bin/bash" /etc/passwd | cut -d':' -f1-4,6,7
  - select only if line contains the delimiter
    - grep "/bin/bash" /etc/passwd | cut -d'|' -s -f1
  - select all except specific fields
    - grep "/bin/bash" /etc/passwd | cut -d':' --complement -s -f7
  - change output delimiter for display
    - grep "/bin/bash" /etc/passwd | cut -d':' -s -f1,6,7 --output-delimiter='#'
  - change output delimiter to newline
    - grep bala /etc/passwd | cut -d':' -f1,6,7 --output-delimiter=$'\n'

- grep supports some special character classes
  - [:digit:]   Only the digits 0 to 9
  - [:alnum:]   Any alphanumeric character 0 to 9 OR A to Z or a to z.
  - [:alpha:]   Any alpha character A to Z or a to z.
  - [:blank:]   Space and TAB characters only.
  - These are always used inside square brackets in the form [[:digit:]]

- grep all the process Ids of ntpd daemon process
  - grep -e "ntpd\[[[:digit:]]\+\]" /var/log/messages.4

- print the matched line, along with the 3 lines after it.
  - grep -A 3 -i "example" demo_text
- search for a given string in a file (case in-sensitive search)
  - grep -i "the" demo_file
- search for a given string recursively in all files
  - grep -r "ramesh" *

- find files using file names (case in-sensitive)
  - find -iname "abc.txt"
- execute commands on files found by the find command
  - find -iname "abc.txt" -exec md5sum {} \;

- login to remote host
  - ssh -l root remote.dns.com

- ignore white space while comparing
  - diff -w abc.txt abc2.txt

- copy all images to an external hard-drive
  - ls *.jpg | xargs -n1 -i cp {} /hard-drive/dir
- search all imgs in the system and archive
  - find / -name *.jpg - type f -print | xargs tar -cvzf images.tar.gz
- download all the URLs frm a file
  - cat url-file.txt | xargs wget -c

- file size in human readable format
  - ls -lh
- order files based on last modified time
  - ls -ltr
- visual classification of file with special characters 
  - ls -F

- view the contents of *.zip without unzipping
  - unzip -l abc.zip

- check status of all services
  - service --status-all

- view current running processes
  - ps -ef | more
- view current running processes in a tree structure
  - ps -efH | more

- view memory including the total line
  - free -t
- view memory in GB
  - free -g

- file system disk space usage in bytes
  - df -k
- file system disk space usage in human readable
  - df -h
- display the type of file system e.g. ext4
  - df -T

- find where a specific unix command exists
  - whereis ls
  - whereis top

  - [openstack-dev] Announcing the OpenStack Health Dashboard

  - libUCL / UCL as FreeBSD config question

   - https://github.com/Inuits/monitoring-plugins

   - https://gist.github.com/pconerly/5498503

   - http://stromberg.dnsalias.org/~strombrg/NFS-troubleshooting-2.html

   - https://github.com/michaeldexter/vmrc

   - https://github.com/zfsonlinux/zfs-auto-snapshot/blob/master/src/zfs-auto-snapshot.sh

  - [openstack-dev] [nova][infra][bugs] Grafana Dashboard for Bugs

  - https://forums.freebsd.org/threads/sharing-of-dtrace-scripts.32855/

  - Eliot is a Python logging system that outputs causal chains of actions 
  - happening within and across process boundaries.
  - A logical trace of the system's operation.
  - https://github.com/ClusterHQ/eliot

iostat=`which iostat 2>/dev/null`
bc=`which bc 2>/dev/null`

# Ensuring we have the needed tools:
( [ ! -f $iostat ] || [ ! -f $bc ] ) && \
    ( echo "ERROR: iostat and bc needs to be installed to run this plugin\n\tuse: apt-get install iostat bc\n" && exit -1 )

[{rabbit, [{vm_memory_high_watermark,3.090625},{log_levels,[{connection,warn}]}]}].

[Nov 13 2015 10:04:56 : DEFAULTAUT] [0] WARN: Failed to connect to the Switch, 
  Exception: Failed Connect to the Switch, 
  Exception:  read error: No child processes. /usr/bin/ssh: 
  symbol lookup error: /usr/bin/ssh: undefined symbol: FIPS_mode
[Nov 13 2015 10:04:56 : DEFAULTAUT] [0] WARN: SSH and Telnet are currently 
  supported only for Physical Switches

[Nov 13 2015 09:52:49 : STAFBASE  ] [0] FRAMEWORK: Executing STAF command: 
staf localhost VTAF_Host connect agent 14.10.1.13 userid vsphere.local@administrator 
  password :9:Test@1234 ssl
[Nov 13 2015 09:52:53 : STAFBASE  ] [0] FRAMEWORK: RC:5169
[Nov 13 2015 09:52:53 : STAFSDK   ] [0] WARN: Error on Connection to 14.10.1.13, RC:5169,
  ...:Cannot complete login due to an incorrect user name or password.:9:...
[Nov 13 2015 09:52:53 : MAIN      ] [0] ERROR: Trouble creating test instance, 
  Error on Connection to host 14.10.1.13

something related to "Invalid Login" 
while trying to add ESX at Workbench's Installation Helper window:

  disk /dev/sda: 21.4 GB, ...
  disk /dev/sdb: 3221 MB, ...
  disk /dev/sdc: 3221 MB,...

echo "scsi add-single-device <H> <B> <T> <L>" > /proc/scsi/scsi
  <H> : Host
  <B> : Bus (Channel)
  <T> : Target (Id)
  <L> : LUN numbers

  echo "scsi add-single-device 0 0 2 0">/proc/scsi/scsi 
  fdisk -l

In one Windows VM e.g. 64 bit 2008 r2
set the scsi controller to para virtual
while installing go for custom install
the driver wont be detected
from the floppy drive of esx select the paravirtual driver of the windows
rescan
format the primary partition

  - upgrade elastistor but not elasticenter
    - test various features
    - check if supportability criteria is met
  - upgrade elasticenter but not elastistor
    - test various features
    - check if supportability criteria is met

  - setup
    - run various EC list commands
    - compare the time taken with some preconfigured time
  - run
    - create iscsi volume
    - mount @ client side & run IO Meter
    - create DR on another site
    - run overnight
    - create a clone for the iscsi volume
  - analyze
    - same as setup
    - check the IO Meter status
    - run zfs commands over ssh
    - stop IO Meter & repeat analyze steps

  - build error injection into response of eccli
  - this will help in testing clients s.a openstack

  - response in cli format
  - response in json format

- escli vsm list
  - escli cbdpd run status --vsmid
  - escli cbdpd lsof --vsmid
  - escli cbdpd job list --vsmid
    - escli cbdpd job status --vsmid --jobid
    - escli cbdpd job log status --since x-minutes --vsmid --jobid
    - escli cbdpd job retention check --vsmid --jobid --retention
- NOTE - We shall remove the snapshot comparison to a different escli call.

  - use-case should have an estimated timeout property.
  - steps within a use-case should have a timeout property.

  Disk /dev/sdm: 1073.7 GB, 1073741824000 bytes
  255 heads, 63 sectors/track, 130541 cylinders
  Units = cylinders of 16065 * 512 = 8225280 bytes
  Sector size (logical/physical): 512 bytes / 4096 bytes (wrong size)
  I/O size (minimum/optimal): 32768 bytes / 1048576 bytes
  Disk identifier: 0x9c046880

  Disk /dev/sdk: 107.4 GB, 107374182400 bytes
  255 heads, 63 sectors/track, 13054 cylinders
  Units = cylinders of 16065 * 512 = 8225280 bytes
  Sector size (logical/physical): 512 bytes / 512 bytes  (correct size )
  I/O size (minimum/optimal): 4096 bytes / 4096 bytes
  Disk identifier: 0x0c2096b6

  - run ps command
    - e.g. cat command is stuck
    - # ps auxwww | grep cat
    - # procstat -kk <pid that you get from ps>
    - # procstat -t <pid that you get from ps>
    - # procstat -S <pid that you get from ps>
    - # procstat -H <pid that you get from ps> 
    - # procstat -f <pid that you get from ps> 

  zpool status
  netstal -nal

  check_iops.sh

  df -kh
  check the space taken by log files
  check if logs have a separate partition

  restart rabbitmq
  check if rabbitmq log is getting updated else restart

  log4j-cloud.xml

  via global settings

  restart syslogd

  Analyze the queue depth of service
  If listen queue overflow parameter is 8 then 8 = 5 * 1.5 ~ 7.5
  Check for the TCP services with queue depth = 5 (from above calculations)

  - tcpdump -s 0 -w fifo.pcap host <nfs-server>
  - at nfs client run the operations e.g. ls -l

  - ps axHl
  - check for WCHAN
  - check if it is stuck within ZFS
  - TODO show an example !!!

  - check TSO settings for NFS
  - check above on both NFS server & client
  - check rsize=32768, wsize=32768 mount options for NFS mount.

  - if underlying storage is NFS, then check TSO
  - if underlying storage is NFS, then check rsize & wsize
  - check netstat -m   # look for mbuf cluster exhaustion
  - get the appropriate sysctl to check stats of your net driver

  - dual use of SSD for ZIL & L2
  - i.e. SSD gets hammered with writes from Write Caching & L2 feeding

bio_flush_disable=0 
  - Storage will wait for IO data to be written to the cache and actual physical location
bio_flush_disable=1 
  - Storage will wait for IO to be written to cache only.
  - Makes response to client faster.

/sbin/gmultipath refresh

glabel status | grep root | awk '{print $3}' |awk -F 'p2' '{print $1}'
glabel status |grep -v -w Name

gpart status |grep -v -w Name

/sbin/ifconfig bce3| grep netmask | cut -d' ' -f4
/sbin/ifconfig bce3| grep status | cut -c 10-

/usr/local/bin/ipmitool lan print |grep -v "IP Address Source" |grep "IP Address" | cut -d: -f2
/usr/local/bin/ipmitool  sdr type "Power Supply"
/usr/local/bin/ipmitool  sdr type "Fan"
/usr/local/bin/ipmitool  sdr type "Temperature"
/usr/local/bin/ipmitool -v sdr type "Temperature"

// diskPath /dev/ses0
// diskName ses0
sg_vpd --page=ei ses0 | grep -w NV_SUP=1
camcontrol modepage ses0 -m 0x08 | grep -w "WCE:  1"

// similarly
sg_vpd --page=ei pass0 | grep -w NV_SUP=1
camcontrol modepage pass0 -m 0x08 | grep -w "WCE:  1"

camcontrol devlist |grep ses |grep scbus1 |grep -v grep

/usr/sbin/getencstat -v /dev/ses1 |grep -E 'Array Device|Device Slot'  |grep -v grep
/usr/sbin/getencstat -v /dev/ses1 |grep -v grep
getencstat -v /dev/ses1 2>&1 |grep dev: |grep da0 |grep -v ada0 |grep -v grep
getencstat -v /dev/ses1 2>&1  |grep 'Element 0x1:' | grep -v grep

setobjstat /dev/ses1 0x1 0x80 0x00 0x02 0x00

/sbin/sysctl -a kern.disks

/usr/local/sbin/smartctl /dev/pass0 -H | grep  "SMART Health Status"
/usr/local/sbin/smartctl -x /dev/pass0|grep -i grown
/usr/local/sbin/smartctl --scan

ctladm port -l
ctladm wwpnlist

/usr/local/cb/bin/fcmgmt.sh fakeall /cf/conf/config.xml ALL ALL 0 1

/usr/local/bin/sg_logs -p 0x05 /dev/pass2

/usr/local/cb/bin/getdiskinfo.sh da0

/usr/local/bin/python /usr/local/agent/cloudbyte/sedutils.py  discover da0

// H/W issues @ elastistor
camcontrol devlist
refresh hardware @ elasticenter
move to maintainance @ elasticenter

// NFS Datastore gone down
sh /usr/local/cb/bin/services_bkptenant nfs start 1 1
sh /usr/local/cb/bin/services_bkptenant nfs stop 1 1
grep bkp * | grep nfs
grep bkp * | grep nfs | grep -v 3
vi /usr/local/cb/bin/services_bkptenant
/sbin/ifconfig bce3 alias 14.10.1.103/8 fib 1
grep "14.10.1.103" /var/log/cbc/starttsm_880fd73-23-2332-ah32.log
grep "14.10.1.103" /var/log/messages
vi starttsm_89dsgd-we2-as88-asas.log


// monitoring
gstat -f multi
zpool iostat 1
netstat -nal | grep 14.10.1.103 // vsm ip
lsof -p <pid>