Performance Counters Linux
We are using counters provided by metricbeat modules,
iostat, sar
Server Stats
CPU [Command: /proc/stat]
CPU Total
( ( system.cpu.user.pct + system.cpu.system.pct ) /
system.cpu.cores ) * 100
Total User
( system.cpu.user.pct / system.cpu.cores ) * 100
Total System
( system.cpu.system.pct / system.cpu.cores ) * 100
CPUIOWait
( system.cpu.iowait.pct / system.cpu.cores ) * 100
Above 4 metrics were extracted from metricsets system.cpu.user.pct,
system.cpu.system.pct and system.cpu.cores
system.cpu.user.pct The percentage of CPU time spent
in user space. On multi-core systems, you can have percentages that are greater than 100%. For example, if 3
cores are at 60% use, then the system.cpu.user.pct will be 180%.
system.cpu.system.pct The percentage of CPU time
spent in kernel space.
system.cpu.cores The number of CPU cores present on
the host.
system.cpu.iowait.pct The percentage of CPU time spent
in wait (on disk)
Memory [Command: /proc/meminfo]
Total Memory (MB)
( system.memory.total
/ 1024 / 1024 )
Total amount of physical RAM in the machine
Used Memory (MB)
( system.memory.used.bytes / 1024 / 1024 )
Amount of physical memory used by system
Actual Used Memory (MB) { MemFree - Buffers – Cached }
( system.memory.actual.used.bytes
/ 1024 / 1024 )
Total Swap Memory (MB)
( system.memory.swap.total.bytes / 1024 / 1024 )
Used Swap Memory (MB)
( system.memory.swap.used.bytes / 1024 / 1024 )
Disk [Command: iostat -dxk]
DiskReadsPerSec
The number of read requests that were issued to the device
per second.
DiskWritesPerSec
The number of write requests that were issued to the device
per second.
DiskReadKBPerSec
The number of read requests that were issued to the device
per second.
DiskWriteKBPerSec
The number of kilobytes written to the device per second.
DiskQueueLength
The average queue length of the requests that were issued to
the device.
DiskReadWaitTime
The average time (in milliseconds) for read requests issued
to the device to be served.
DiskWriteWaitTime
The average time (in milliseconds) for write requests issued
to the device to be served.
Network [Command: sar -n DEV]
ReceivedBytesRate
Total number of kilobytes received per second.
TransmittedBytesRate
Total number of kilobytes transmitted per second.
PacketsReceivedRate
Total number of packets received per second.
PacketsTransmittedRate
Total number of packets transmitted per second.
MongoDB Insights
the server information.
MongoDB operation counters [Command: db.serverStatus().opcounters]
This visualization gives count of following number of
operations since mongo instance start
Command
The total number of commands issued to the database since
the mongod instance last started.
Delete
The total number of delete operations received since the
mongod instance last started.
GetMore
The total number of getmore operations received since the
mongod instance last started.
Insert
The total number of insert operations received since the
mongod instance last started.
Query
The total number of queries received since the mongod
instance last started.
Update
The total number of update operations received since the
mongod instance last started.
MongoDB WiredTiger Cache [Command: db.serverStatus().wiredTiger.cache]
WiredTiger is tefault srorage engines used in mongodb. It
has some cool features like MVCC, Document level concurrency and journal
(write-ahead log).
Default internal cache size is larger of either:
·
50% of (RAM - 1GB), or
·
256 MB
Max
Maximum cache size
Used
Size in byte of the data currently in cache.
Dirty
Size in bytes of the dirty data in the cache.
This is the size of the dirty data in the cache. This value
should be less than the bytes currently in the cache value. Looking at these
values, we can determine if we need to up the size of the cache for our
instance. Additionally, we can look at the wiredTiger.cache.bytes read into
cache value for read-heavy applications. If this value is consistently high,
increasing the cache size may improve overall read performance.
MongoDB asserts [Command: db.serverStatus().asserts]
number of assertions raised since the MongoDB process
started. If there are non-zero values for the asserts, you should check log
file for information.
Message
The number of message assertions raised since the MongoDB
process started.
Regular
The number of regular assertions raised since the MongoDB
process started.
Rollover
The number of times that the rollover counters have rolled
over since the last time the MongoDB process started. The counters will
rollover to zero after 230 assertions. Use this value to provide context to the
other values in the asserts data structure.
User
The number of “user asserts” that have occurred since the
last time the MongoDB process started. These are errors that user may generate,
such as out of disk space or duplicate key. You can prevent these assertions by
fixing a problem with your application or deployment.
Warning
the number of warnings raised since the MongoDB process
started.
MongoDB Concurrent transactions Read [Command: db.serverStatus().wiredTiger.concurrentTransactions]
Returns information on the number of concurrent of read and
write transactions allowed into the WiredTiger storage engine. Default value is
128.
Read Available
Number of concurrent read tickets available.
Read Used
Number of concurrent read transaction in progress.
Write Available
Number of concurrent read tickets available.
Write Used
Number of concurrent read transaction in progress.
Modelling - Mongo DB - Wired Tiger - Log Writes [Command: db.serverStatus().wiredTiger.log]
Log Writes
Number of write operations.
Modelling - Mongo DB - Wired Tiger - Log Writes (Bytes) [Command: db.serverStatus().wiredTiger.log]
Log Writes (Bytes)
Number of bytes written into the log.
Modelling - Mongo DB - Wired Tiger - Log Syncs [Command: db.serverStatus().wiredTiger.log]
Log Syncs
Number of sync operations.
Modelling - Mongo DB - Wired Tiger - Log Max Size (Bytes) [Command: db.serverStatus().wiredTiger.log]
Log Max Size (Bytes)
Maximum file size. This is constant value set.
Modelling - Mongo DB - Wired Tiger - Log Flushes [Command: db.serverStatus().wiredTiger.log]
Log Flushes
Number of flush operations.
Modelling - Mongo DB - Wired Tiger - Log Scans [Command: db.serverStatus().wiredTiger.log]
Log Scans
Number of scan operations.
Modelling - Mongo DB - Wired Tiger - Log Size [Command: db.serverStatus().wiredTiger.log]
Log Size (Bytes)
Total log size in bytes.
Modelling - Mongo DB - Wired Tiger - Log Cache Pages Read [Command: db.serverStatus().wiredTiger.log]
Cache Pages Read
Number of pages read into the cache. If this value is
consistently high, increasing the cache size may improve overall read performance.
Modelling - Mongo DB - Wired Tiger - Log Cache Pages Write [Command: db.serverStatus().wiredTiger.log]
Cache Pages Write
Number of pages written from the cache.
Modelling - Mongo DB - Wired Tiger - Cache Pages Evicted[Command: db.serverStatus().wiredTiger.log]
Cache Pages Evicted
Number of pages evicted from the cache.
Modelling - Mongo DB - Wired Tiger - Cache Dirty
Bytes[Command: db.serverStatus().wiredTiger.log]
Cache Dirty Bytes
Size in bytes of the dirty data in the cache. This value
should be less than the bytes currently in the cache value.
Modelling - Mongo DB - Resident Memory (MB) [Command: db.serverStatus().mem]
Resident Memory (MB)
The amount of RAM, in megabytes (MB), currently used by the
database process.
Modelling - Mongo DB - Virtual Memory (MB) [Command: db.serverStatus().mem]
Virtual Memory (MB)
The amount, in megabytes (MB), of virtual memory used by the
mongod process.
Modelling - Mongo DB - Memory Stats (MB) [Command: db.serverStatus().mem]
Resident
The amount of RAM, in megabytes (MB), currently used by the
database process.
Virtual
The amount, in megabytes (MB), of virtual memory used by the
mongod process.
Mapped
The amount of mapped memory, in megabytes (MB), used by the
database. Because MongoDB uses memory-mapped files, this value is likely to be
to be roughly equivalent to the total size of your database or databases.
Mapped with Journal
The amount of mapped memory, in megabytes (MB), including
the memory used for journaling.
Modelling - Mongo DB – Objects
Modelling - Mongo DB – Objects
Modelling - Mongo DB - Total Connections Created [Command: db.serverStatus().connections]
Total Connections Created
The total number of current clients connected to this
instance
Modelling - Mongo DB - Current Connections Created [Command: db.serverStatus().connections]
Current Connections Created
The total number of current clients connected to this
instance
Modelling - Mongo DB - Available Connections Created [Command: db.serverStatus().connections]
Available Connections Created
The total number of unused connections available to clients
for this instance
Modelling - Mongo DB - Indexes and Collections
Indexes
Number of indexes
Collections
Number of collections
MongoDB Journalling
To provide durability in the event of a failure, MongoDB
uses write ahead logging to journal files in Disk. WiredTiger uses checkpoints
to recover.
With journaling, WiredTiger creates one journal record for
each client initiated write operation. The journal record includes any internal
write operations caused by the initial write. For example, an update to a
document in a collection may result in modifications to the indexes; WiredTiger
creates a single journal record that includes both the update operation and its
associated index modifications.
MongoDB configures WiredTiger to use in-memory buffering for
storing the journal records. Threads coordinate to allocate and copy into their
portion of the buffer. All journal records up to 128 kB are buffered.
WiredTiger syncs the buffered journal records to disk upon many
conditions.
Below picture depicts the simple illustration is log write operations
Reference
https://stackify.com/mongodb-performance-tuning/
https://www.elastic.co/guide/en/beats/metricbeat
https://github.com/elastic/beats/blob/master/metricbeat
https://docs.mongodb.com/manual/reference/command/serverStatus/
https://muralidba.blogspot.com/2018/04/what-are-read-and-write-tickets-in.html
https://medium.com/@Alibaba_Cloud/performing-data-write-operations-with-mongodb-2486f42990ad
https://docs.mongodb.com/manual/core/journaling/
https://stackify.com/mongodb-performance-tuning/
https://www.elastic.co/guide/en/beats/metricbeat
https://github.com/elastic/beats/blob/master/metricbeat
https://docs.mongodb.com/manual/reference/command/serverStatus/
https://muralidba.blogspot.com/2018/04/what-are-read-and-write-tickets-in.html
https://medium.com/@Alibaba_Cloud/performing-data-write-operations-with-mongodb-2486f42990ad
https://docs.mongodb.com/manual/core/journaling/
MongoDB Jounal
Below picture depicts the simple illustration is log write operations
