Docker provides several options for limiting CPU with containers - one of the more common switches is '--cpus' - which allows you to limit the number of CPU's a container can use - for example if I wanted to ensure a container only used 1 and a half processors I could issue:
docker run -it --name windowscorecapped --cpus 1.5 microsoft/windowsservercore cmd.exe
There is also a switch called '--cpu-shares' which allows you to delegate which containers would get priority (weighted) access to CPU cycles during (and only during) contention - the default value is 1024 - which can be set to either lower or higher:
docker run -it --name windowscorecapped --cpus 1.5 --cpu-shares 1500 microsoft/windowsservercore cmd.exe
RAM
Docker on Windows uses a light-weight HyperV VM to create the containers and as a result has the default 2GB memory limit - we can increase this using the -m switch e.g.:
docker run -it --name windowscorecapped --memory 4G microsoft/windowsservercore cmd.exe
Disk I/O
Docker provides a few options to control I/O throughput - one of the more useful options is the '--blkio-weight' switch which can be found under the 'docker run' command.
--blkio-weight takes an integer between 10 and 1000 - although by default is set to 0 - which disables it.
Unfortunately at this time it appears like the Windows implementation of Docker does not support this feature:
docker: Error response from daemon: invalid option: Windows does not support BlkioWeight.
So instead for Windows we have 'io-maxiops' and 'io-maxbandwidth'.
Neither are as good as the 'blkio-weight' - the 'io-maxiops' is not great because what size of data are you basing the iops calculation on - for example a read or write block size of 8KB might get a very different result then that of a 64KB block.
There are numerous tools that can help simulate disk i/o for different situations - for example databases read / writes which will typically be small but many. One of these tools can be obtained from Microsoft - called diskspd.
Let's firstly create a normal (unthrottled) container and perform some benchmarks:
docker run -it --name windowscore microsoft/windowsservercore cmd.exe
If you are on Windows Server Core you can download it using PowerShell e.g.:
Invoke-WebRequest -Uri "http://url.com/disk.zip" -OutFile "C:\Disk.zip"
and since Microsoft didn't bother to include a command line unzip utility (not even in Windows 10!) we have to use PowerShell to unzip it:
powershell.exe -nologo -noprofile -command "& { Add-Type -A 'System.IO.Compression.FileSystem'; [IO.Compression.ZipFile]::ExtractToDirectory('C:\Disk.zip', 'disk'); }"
We can then run it like follows (note: This config is aimed at a SQL server - you should change the block size etc. dependant on the use of the server / targeted application):
diskspd –b8K –d30 –o4 –t8 –h –r –w25 –L –Z1G –c5G C:\iotest.dat
Read IO
thread | bytes | I/Os | MB/s | I/O per s | AvgLat | LatStdDev | file
-----------------------------------------------------------------------------------------------------
0 | 55533568 | 6779 | 1.77 | 225.96 | 8.442 | 35.928 | C:\iotest.dat (5120MB)
1 | 64618496 | 7888 | 2.05 | 262.93 | 7.412 | 34.584 | C:\iotest.dat (5120MB)
2 | 53665792 | 6551 | 1.71 | 218.36 | 7.792 | 31.946 | C:\iotest.dat (5120MB)
3 | 63733760 | 7780 | 2.03 | 259.33 | 6.919 | 30.835 | C:\iotest.dat (5120MB)
4 | 32374784 | 3952 | 1.03 | 131.73 | 14.018 | 44.543 | C:\iotest.dat (5120MB)
5 | 62357504 | 7612 | 1.98 | 253.73 | 7.571 | 33.976 | C:\iotest.dat (5120MB)
6 | 53354496 | 6513 | 1.70 | 217.10 | 8.352 | 35.517 | C:\iotest.dat (5120MB)
7 | 65290240 | 7970 | 2.08 | 265.66 | 7.016 | 33.599 | C:\iotest.dat (5120MB)
-----------------------------------------------------------------------------------------------------
total: 450928640 | 55045 | 14.33 | 1834.80 | 8.064 | 34.699
Write IO
thread | bytes | I/Os | MB/s | I/O per s | AvgLat | LatStdDev | file
-----------------------------------------------------------------------------------------------------
0 | 18046976 | 2203 | 0.57 | 73.43 | 28.272 | 56.258 | C:\iotest.dat (5120MB)
1 | 21463040 | 2620 | 0.68 | 87.33 | 23.235 | 49.989 | C:\iotest.dat (5120MB)
2 | 17686528 | 2159 | 0.56 | 71.97 | 31.750 | 64.613 | C:\iotest.dat (5120MB)
3 | 20946944 | 2557 | 0.67 | 85.23 | 25.756 | 56.673 | C:\iotest.dat (5120MB)
4 | 11157504 | 1362 | 0.35 | 45.40 | 47.233 | 72.614 | C:\iotest.dat (5120MB)
5 | 21438464 | 2617 | 0.68 | 87.23 | 23.498 | 50.224 | C:\iotest.dat (5120MB)
6 | 17784832 | 2171 | 0.57 | 72.37 | 30.173 | 59.930 | C:\iotest.dat (5120MB)
7 | 21282816 | 2598 | 0.68 | 86.60 | 24.409 | 55.087 | C:\iotest.dat (5120MB)
-----------------------------------------------------------------------------------------------------
and then create a new container - this time capping the max i/o:
docker run -it --name windowscorecapped --io-maxiops 100 microsoft/windowsservercore cmd.exe
and again download and unzip diskspd and run the benchmark again with:
diskspd –b8K –d30 –o4 –t8 –h –r –w25 –L –Z1G –c5G C:\iotest.dat
Read IO
thread | bytes | I/Os | MB/s | I/O per s | AvgLat | LatStdDev | file
-----------------------------------------------------------------------------------------------------
0 | 5390336 | 658 | 0.17 | 21.93 | 13.552 | 114.205 | C:\iotest.dat (5120MB)
1 | 5849088 | 714 | 0.19 | 23.80 | 12.530 | 109.649 | C:\iotest.dat (5120MB)
2 | 5619712 | 686 | 0.18 | 22.87 | 10.098 | 98.537 | C:\iotest.dat (5120MB)
3 | 4931584 | 602 | 0.16 | 20.07 | 22.938 | 147.832 | C:\iotest.dat (5120MB)
4 | 5758976 | 703 | 0.18 | 23.43 | 15.490 | 122.039 | C:\iotest.dat (5120MB)
5 | 5611520 | 685 | 0.18 | 22.83 | 10.078 | 98.006 | C:\iotest.dat (5120MB)
6 | 5283840 | 645 | 0.17 | 21.50 | 13.776 | 114.819 | C:\iotest.dat (5120MB)
7 | 5169152 | 631 | 0.16 | 21.03 | 18.774 | 133.842 | C:\iotest.dat (5120MB)
-----------------------------------------------------------------------------------------------------
total: 43614208 | 5324 | 1.39 | 177.46 | 14.486 | 117.836
Write IO
thread | bytes | I/Os | MB/s | I/O per s | AvgLat | LatStdDev | file
-----------------------------------------------------------------------------------------------------
0 | 1867776 | 228 | 0.06 | 7.60 | 487.168 | 493.073 | C:\iotest.dat (5120MB)
1 | 1941504 | 237 | 0.06 | 7.90 | 464.425 | 492.295 | C:\iotest.dat (5120MB)
2 | 1851392 | 226 | 0.06 | 7.53 | 500.177 | 493.215 | C:\iotest.dat (5120MB)
3 | 1769472 | 216 | 0.06 | 7.20 | 487.016 | 492.672 | C:\iotest.dat (5120MB)
4 | 1843200 | 225 | 0.06 | 7.50 | 480.479 | 492.992 | C:\iotest.dat (5120MB)
5 | 1826816 | 223 | 0.06 | 7.43 | 507.046 | 492.908 | C:\iotest.dat (5120MB)
6 | 1761280 | 215 | 0.06 | 7.17 | 516.741 | 492.909 | C:\iotest.dat (5120MB)
7 | 1826816 | 223 | 0.06 | 7.43 | 484.961 | 492.556 | C:\iotest.dat (5120MB)
-----------------------------------------------------------------------------------------------------
As seen from the results above there is a significant difference in iops and latency between the two containers.
The other option is to throttle based on maximum bandwidth per second - for example based on 5mbps:
docker run -it --name windowscorebandwdith --io-maxbandwidth=5m microsoft/windowsservercore cmd.exe
No comments:
Post a Comment