Archive for the ‘ Storage ’ Category
CentOS 7 [root@]# cat /etc/redhat-release CentOS Linux release 7.3.1611 (Core) Problem: mkfs.xfs warning: device is not properly aligned [root@]# parted -a optimal /dev/mapper/mpathb mkpart primary 0% 100% [root@]# parted /dev/mapper/mpathb align-check opt 1 1 aligned parted /dev/mapper/mpathb p Model: Linux device-mapper (multipath) (dm) Disk /dev/mapper/mpathb: 21.5GB Sector size (logical/physical): 512B/512B Partition Table: gpt Disk Flags: […]
Simple and short info for databases/nosql. # get list tuned-adm list – latency-performance – oracle # check which is active tuned-adm active Current active profile: balanced # set tuned-adm profile latency-performance Check whether the service is enabled: [root@db8 sd-docker-creator]# systemctl list-unit-files | grep tuned tuned.service enabled Check how it works: # change governor echo powersave […]
Terminology: fio = https://github.com/axboe/fio/ us = microsecond = (1 / 1 000 000) second stdev = standard deviation Quick explanation: 1. Latency: 2. IOps Detailed information are available in FIO’s How-To (ยง 6.0 Interpreting the output) Example of my configuration (random writes): [global] bs=4k ioengine=libaio iodepth=4 # was 1g size=1g direct=1 runtime=60 # directory=/bcache directory=/emcpower […]
I encountered the problem that after I chose backend device as /dev/emcpowera3 I have seen 16+1 bcache-devices (bcache0-bcache16). It reflected from the fact that bcache saw all links (reading the bcache signatures). The solution apears to be very simple: vi /usr/lib/udev/rules.d/69-bcache.rules was: KERNEL==”fd*|sr*”, GOTO=”bcache_end” should be: KERNEL==”fd*|sr*|sd*”, GOTO=”bcache_end” How it looked before I changed udev […]
Bcache is not enabled by default in CentOS 7.1. However, you do not need to recompile whole kernel. It is sufficient to compile module and add it to existing kernel. yum groupinstall “Development Tools” -y yum install kernel-headers -y Unfortunately, kernel headers do not include all you need. You have to download adequate kernel sources […]
# Annoying… mdadm –create /dev/md3 –level=1 –raid-disks=2 /dev/nvme0n1p3 /dev/nvme1n1p3 [root@db7 ~]# parted /dev/nvme0n1 p Model: Unknown (unknown) Disk /dev/nvme0n1: 400GB Sector size (logical/physical): 512B/512B Partition Table: gpt Disk Flags: Number Start End Size File system Name Flags 1 1049kB 40.0GB 40.0GB primary raid 2 40.0GB 80.0GB 40.0GB mysql raid 3 80.0GB 84.0GB 4000MB xd raid […]
First of all you cannot block automapping, so: # elasticsearch.yml index.mapper.dynamic: true Pre-mapping of your river doesn’t resolve the problem. # part of the river configuration: “type_mapping”: { “mytype” : { “properties” : { “location” : { “type” : “geo_point” } } } Tip: If your node does not work after installation of the plugin […]
First of all I use my own script (called quick-confession) which get me info about processors, ram, discs, etc. You can get it here. It contains the instruction how to compile sysbench. I am also used to test the configuration with iozone and filebench. I am using xfs for database storage and tune it as […]
The aim of the operation was to enlarge the space in the database volume. My colleague replaced the disks in the storage (hot plug). I was forced to perform the entire operation remotely. The LSI controller saw the new disks, however the OS and the Iscsi software thought that the device was still 360GB in […]
When the economy meets the performance the iScsi comes into play! I am using 1Gb ethernet between the target and the initiator (both on CentOs 6.3). The target consists of the 3ware controller with 4 SSD Ocz Vertex 3. So, the backing-store is the device /dev/sda/ (/etc/tgt/targets.conf). Next, Parted and LVM configured on the target […]