StorPool 18.02 Release Change Log

18.02.1030.2e4eab8 – -> 18.02.1064.a911b3f64

  • Improvements in python-bindings, monitoring services, cgroup tools

  • Adds improved transaction times and other fixes for the storpool_mgmt service

  • Updates dependencies for cpupowerutils, now not depending on kernel-tools

18.02.1030.2e4eab8 – -> 18.02.1103.8ed067780

  • Adds stability improvements in the quorum keeping service in unstable networking conditions.

  • Updates the detection for hardware accelerated NICs for the bnxt_en driver in the cgroup configuration helper tools.

  • Improvements in API responsiveness during dematerialization

  • Improvements in reporting services and tooling

  • Removes excessive debug print logging

18.02.953.79d8ee7 – -> 18.02.1030.2e4eab8

  • Adds fix for storpool_beacon service backup nets detection with single-vlan and misconfigured network

  • Adds support for Samsung PM981 NVMe drives

  • Adds support for up to 7 server instances on a single node

  • Improves snapshot dematerialization without impact processing of other API calls

  • Adds fix for snapshot space miscalcuated gains for snapshots with very small amount of data

  • The CLI now properly shows all units in KiB, MiB, GiB to prevent any confusion

  • Adds a new service storpool_abrtsync, which will automatically send reports from aborted services (repsync deprecated and removed on the first run of storpool_abrtsync)

  • Handles per-host alerts in storpool_stat for processes in the root cgroup and unreachable API (for nodes configured to access it)

  • Consolidates most cron tasks in a single cron job handled by the storpool_periodic tool

  • Renames the storpool_initdisk’s’ --force option to the unabmiguous --wipe-all-data

  • Includes various other improvements in the storpool_server, storpool_beacon services, python bindings, cgroup setup tools and in the disk stress testing tool

18.02.944.478cc9f – -> 18.02.953.79d8ee7

  • Fixes in automation for rebasing long volume-snapshot chains

  • Speed up TRIM operations for volumes exposed through iSCSI, now ~600GB/s instead of 2-12GB/s

  • Adds SP_PREFERRED_PORT option, enabling active-backup redundant networking

  • Improvements in relocator in aggregate heavy enviroments, such as HDD-only placement templates

  • Improvements in balancer tools when mixing drives in the same placement group

18.02.886.f6b2fcf20 – -> 18.02.944.478cc9f

  • Add storpool_process tool for listing and reclassifying processes in their intended cgroups

  • Add the storpool_cg tool for creating cgroups based on predefined config or by autodetecting settings based on installed services and hardware

  • The monitor collector tool now detects the SSL CA list location

  • The multi-server-helper tool now supports configurations with selectable number of SSD only instances

  • Fix for the storpool_initdisk tool when the underlying devices are with a long PCI address

  • Improvements in storpool_stat collecting service, now gathering data for services network traffic and iostat for all drives, including system ones

  • Fixed inventory collection not updating the latest kernel booted

18.02.847.b09fd4bec – -> 18.02.886.f6b2fcf20

  • The storpool_initdisk tool now handles NVMe journals for hard disk drives

  • The storpool_initdisk tool now lists empty NVMe partitions

  • Fix storpool_controller service might end up in storpool.slice cgroup on systemd daemon-reload

  • Add support for 4.19+ & OFED in the storpool_rdma kernel module

  • Fix templates status output when the same placement group is used more than once

  • Drops support for Ubuntu 14.04 and Debian 8 distributions

  • Various other improvements in internal tools and services

18.02.763.0aa70d7 – -> 18.02.847-b09fd4bec

  • Workaround for bnx2x based NICs getting in partial reset when large-receive-offload is disabled

  • Improvements in TRIM performance on top of a StorPool volume

  • Improvements in recovery times with remote backups

  • Python bindings python3 support

  • Added proxy support for sending monitoring and statistics data

  • Various other improvements in internal tools and services

18.02.458.ac2f823 – -> 18.02.763.0aa70d7

  • Support for 4k native NVMe devices

  • Support for Intel Optane drives

  • Support for Micron 9200MAX NVMe

  • Support for AMD EPYC hardware sleep

  • Support for Intel X550 in hardware accelerated mode with ixgbe driver

  • Support for MTU 1500 with bnx2x and ixgbe based NICs

  • Updates in tools for automatic hardware acceleration configuration

  • Updated on-boot hugepages reservation mechanism

  • Performance and stability improvements in API service

  • Updated ixgbe driver based acceleration to evade issues with in-kernel driver

  • Updated ixgbe driver based acceleration with support for Debian 9 based nodes

  • Added Ubuntu 18.04 LTS support

  • Updates in statistics gathering - support for sending to secondary databases, cgroups memory statistics, various reliability and performance improvements

  • Updated dependencies

  • Various reliability and stability improvements in internal tools and services

18.02.370.2b8c3c3 – -> 18.02.458.ac2f823

  • Support for Kubernetes

  • Support for ARM64 architecture

  • Support for POWER architecture

  • Improvements in the installation procedure, VF helper included

  • hardware acceleration for NICs with bnx2x driver

  • Initial support for Alpine Linux

  • New API call to quickly return just the status of all volumes

  • Changes in the way data on the underlying drives is aggregated in a more efficient manner

  • New hardware support - Micron 9200 NVMe

  • Native 4k drives support

  • Various improvements in internal tools, monitoring and services

18.02.334.c204ed2 – -> 18.02.370.2b8c3c3

  • Add support for Samsung PM1725a NVMe

  • Add new tool, transfer_status to show the status of the currently running bridge transfers

  • Add new tool, sDump to print network stats in human-readable format

  • Fix for data transfer issues caused by the kernel remapping some of StorPool’s memory

  • Add preliminary support for Ubuntu 18.04

  • Work-around for kernel crashes caused by bugs in the ixgbe kernel driver when using acceleration

  • Add stats collection for per-CPU statistics, to be available in https://analytics.storpool.com/

18.02.206.06d240e – -> 18.02.334.c204ed2

  • Add additional logging for storpool_bridge service

  • Higher default parallelism for the storpool_bridge transfers

  • Lower CPU usage, higher efficiency for storpool_block during TRIM operations

  • Exit when the support for hardware sleep is not available and hardware sleep is requested

  • Added additional network statistics through the use of the statsDump tool and storpool_ping tools, added netlatency tool to quickly measure and report the network latency from one of the nodes to the other participants in the cluster

  • Added support for storpool_bd kernel module with 4.10+ kernels and storpool_rdma with 4.15+ kernels

  • storpool_server/storpool_initdisk/storpool_nvmed now support hotplug NVMe devices

  • Various other reliability fixes and improvements

18.02.178.9d29cd7 – -> 18.02.206.06d240e

  • No longer ignore snapshots being deleted when re-basing long snapshot-volume chains

  • Fix a bug in handling aborted iSCSI operations in storpool_iscsi service

  • Fix in storpool_server to not forget to delete moved snapshot objects

  • Add support for centos 7.5 in the storpool_rdma kernel module

  • Add support for 4.14+ & OFED in the storpool_rdma kernel module

  • Add support for 4.12+ in the storpool_pci kernel module

  • Improve some of the diagnostic and monitoring tools

  • Make the “recovery” state of a task clearly visible in the output of storpool task list

18.02.164.7277e8c – -> 18.02.178.9d29cd7

  • Disable check of BBU status for genreport

  • Fix service name and symlinks on CentOS 6 for the storpool_controller service

  • Fix installing dependency packages on Ubuntu 14.04

  • Fix the installation of the CentOS 6 cgmove init script

  • Remove “reload” for init scripts, as it’s not supported by the StorPool services and actually does “restart”

  • Add /usr/lib/storpool/get_tech_support - Collects useful information to be sent to support for initial troubleshooting in case of no access to the cluster.

18.02.119.b8796bb – -> 18.02.164.7277e8c

  • Use port 443 (instead of 8086) in the storpool_stat service to get through firewalls more easily

  • Let the StorPool CLI prompt be customized using the SP_CLI_PROMPT variable

  • Add support for GCC 7

  • Strip the zero VLAN tag in the storpool_rdma module

  • Multiple fixes and improvements on the server and bridge services

  • Remove log entries for recovered objects (prevents syslog flooding)

  • Handle the new fio 3.1+ log format in the disk_tester tool

  • Improve the fio test scripts

  • Run the mgmt and bridge services in a separate memory cgroup - mgmt.slice

  • Add the SP_CPU_DMA_LATENCY variable to the storpool.conf.example file (more info at https://access.redhat.com/articles/65410 and https://www.kernel.org/doc/Documentation/power/pm_qos_interface.txt)

  • Add a check for the status of the BBU/Cache Vault of RAID controllers

  • Improve repsync service

  • Add a tool for filtering git logs

  • Add a tool for rotating snapshots on number of volumes

  • Add a tool for to quickly check the network latency to other nodes in the cluster (uses addresses in /etc/storpool.conf)

18.01.91.edf2ec3 – -> 18.02.119.b8796bb

  • New protocol based on IP/UDP, requires new interface configuration

  • New module to handle raw PCI devices (NVMe, NIC Virtual Function, etc.)

  • New service storpool_nvmed handling NVME devices

  • Native hardware acceleration for selected NICs:

  • Intel ixgbe, i40e drivers through the use of VF interfaces, requires ixgbevf-helper

  • Mellanox mlx4 and mlx5 drivers

  • Show interfaces with hardware acceleration enabled in the CLI

  • Support more than one StorPool cluster in the same network using a clusterId to differentiate them

  • Support up to 16 StorPool server instances (multiserver) per node

  • Bridge redundancy, now multiple bridges may run at the same time with only one active at a given time

  • Bridge lower CPU when recovering objects with very small amount of actual data

  • Improve the site-to-site throughput on higher-latency connections

  • Support 4.15+ kernels and gcc 7

  • Let the configuration in /etc/storpool.conf.d/*.conf override the one in /etc/storpool.conf

  • Install the storpool_stat statistics collection tool

  • Added a configuration option to skip the dependency installation

  • Various reliability fixes and improvements

18.01.41.eacd2bf – -> 18.01.91.edf2ec3

  • Various small fixes and improvements

  • Only execute the storpool_cgmove tool on boot

  • Remove an unused/obsolete service (machine-cgsetup)

  • Add example cgroup configuration for Debian 9

  • Install modules for all installed kernels on the system and for the latest available one in the package

  • Install genreport on all nodes and add non-API related checks

  • Add support for Intel P4500

  • Add the /usr/lib/storpool/balancer.sh tool

  • Bump the maximum number of volumes+snapshots to 30000

18.01.2.d5c0646 – -> 18.01.41.eacd2bf

  • Keep and update the balancer state through transactions

  • Various improvements and optimizations in the re-balancing tools

  • Add a flag to distinguish snapshots not being deleted due to multiple children

  • Fix storpool_bridge to not send older data and TRIMs

  • The storpool net list CLI output now includes the currently expected number of voting beacons