User contributions for Admin

4 January 2024

• 15:1115:11, 4 January 2024 diff hist +107‎ Storcli ‎ →‎remove a dedicated (DHS) or global hot spare (GHS)? Tag: Visual edit
• 15:0915:09, 4 January 2024 diff hist −3‎ Storcli ‎ →‎remove a dedicated (DHS) or global hot spare (GHS)? Tag: Visual edit
• 14:3314:33, 4 January 2024 diff hist +53‎ Linux file permission ‎ →‎Creating defaults access control lists on directories current Tag: Visual edit
• 14:3214:32, 4 January 2024 diff hist −386‎ Linux file permission ‎No edit summary Tag: Visual edit
• 14:0114:01, 4 January 2024 diff hist +18‎ N File:Linux extended acl.png ‎No edit summary current
• 13:5113:51, 4 January 2024 diff hist +24‎ N File:Linux regular permission.png ‎No edit summary current
• 13:4813:48, 4 January 2024 diff hist +2,430‎ Manual:SS System/Storage Pool ‎No edit summary current Tag: Visual edit
• 13:4613:46, 4 January 2024 diff hist +39,144‎ N Manual:SS System/Snapshot ‎ Created page with "= ZFS Snapshot = The best part of ZFS would be its ability to perform snapshots. Snapshots are '''point-in-time''', '''read-only''' versions of the filesystem. T'''o make the snapshot data writeable you have to ZFS clone it'''. Snapshots can happen at any time of day and can be stored as long as you have enough space in the zpool and restore data from a Point-In-Time, Instantly. Some usage scenarios with ZFS Snapshots 1.     '''File system snapshots and rolling ba..." current Tag: Visual edit
• 13:3713:37, 4 January 2024 diff hist +32‎ Manual:SS System ‎ →‎Head node Tag: Visual edit
• 13:3513:35, 4 January 2024 diff hist +21‎ Manual:SS System/Storage Pool Sharing ‎ →‎Set NFS share on current Tag: Visual edit
• 13:3213:32, 4 January 2024 diff hist +945‎ Manual:SS System/NFS ‎ →‎Check NFS version current Tag: Visual edit
• 13:3013:30, 4 January 2024 diff hist +2,722‎ N Manual:SS System/NFS ‎ Created page with " == NFS on SS System == By default, ZFS supports integrated NFS v3. However, NFSv2/3 handles permissions solely based on UID and GID. File permissions on the server are matched against user- and group ids on client. '''That is why NFSv<4 is by design insecure''' in environments where users have root access to the client machines; UID spoofing is trivial in that case. NFS shares are exported by default with the option <code>root_squash</code>, which will map all client r..." Tag: Visual edit
• 13:2213:22, 4 January 2024 diff hist +29‎ Manual:SS System ‎ →‎Head node Tag: Visual edit
• 13:2013:20, 4 January 2024 diff hist +601‎ Manual:SS System/Storage Pool Sharing ‎ →‎All connected Samba sessions list Tag: Visual edit
• 13:2013:20, 4 January 2024 diff hist +31‎ N File:Nfs connection verify on window.png ‎No edit summary current
• 13:1913:19, 4 January 2024 diff hist +19‎ N File:NFS mount on window.png ‎No edit summary current
• 13:1713:17, 4 January 2024 diff hist +32‎ N File:Check nfs mount status on window.png ‎No edit summary current
• 13:1613:16, 4 January 2024 diff hist +13‎ N File:Nfs on window.png ‎No edit summary current
• 13:1213:12, 4 January 2024 diff hist +1,106‎ Manual:SS System/Storage Pool Sharing ‎ →‎SMB mount on Linux Client Tag: Visual edit
• 13:1213:12, 4 January 2024 diff hist +24‎ N File:Smb disconnect on window.png ‎No edit summary current
• 13:0913:09, 4 January 2024 diff hist −37,274‎ Manual:SS System ‎ →‎Head node Tags: Replaced Visual edit
• 13:0313:03, 4 January 2024 diff hist +8,257‎ N Manual:SS System/Storage Pool Sharing ‎ Created page with " ==Sharing pool== ===ZFS shared list (NFS/SMB)=== To distinguish native NFS share, ZFS share uses '''/etc/dfs/sharetab''' file for SMB and NFS share automatically. ===List all shared information=== Administrator can show all the list of dataset that has been shared by using following command<syntaxhighlight lang="bash"> $ zfs list -r -o name,sharenfs,sharesmb,mountpoint NAME      SHARENFS                               SHARESMB  MOUNTPOINT zssd    ..." Tag: Visual edit
• 12:5512:55, 4 January 2024 diff hist +4,470‎ Manual:SS System/Storage Pool ‎ →‎1.1.7         check pool and dataset Tag: Visual edit
• 12:5112:51, 4 January 2024 diff hist +1,228‎ Manual:SS System/Storage Pool ‎ →‎Set minimum ZFS properties Tag: Visual edit
• 12:5012:50, 4 January 2024 diff hist +776‎ Manual:SS System/Diskinfo ‎ →‎References current Tag: Visual edit
• 12:4912:49, 4 January 2024 diff hist −53‎ Manual:SS System/Storage Pool ‎ →‎1.1.7         check pool and dataset Tag: Visual edit
• 12:4712:47, 4 January 2024 diff hist +16,717‎ N Manual:SS System/Storage Pool ‎ Created page with " ==Hot Spare automatic replacement== One of the key features of ZFS is detect failed hard disk and replace it with healthy spare drive automatically. The '''hot spare device''' means that the device(s) is not a part of active device in a pool, but if one of active device in the pool fails, the hot spare device(s) will replaces the failed device automatically. ===Add/Remove spare drive=== <syntaxhighlight lang="bash"> Add new hard drive(s) into storage pool #zpool add zss..." Tag: Visual edit
• 12:3912:39, 4 January 2024 diff hist +17‎ Manual:SS System/Network ‎No edit summary current Tag: Visual edit
• 12:3912:39, 4 January 2024 diff hist +285‎ N Manual:SS System/Network ‎ Created page with " ==Network MTU size== To maximize data transfer throughput, zstorage has been set up with the largest MTU size (9000) so called as jumbo frame instead of general 1500. Overall data transaction speed would be enough with connect to a proper enterprise performance of 10G network switch." Tag: Visual edit
• 12:3712:37, 4 January 2024 diff hist +4,823‎ N Manual:SS System/Diskinfo ‎ Created page with " == Disks in zstoreage (default Head + JBOD mode) == $ lsblk --scsi -o name,model,serial == Head LOG and Cache Configuration == Head node has two M.2 NVMe disk. The default zstorage has been configured one for OS (Samsung 970 EVO Plus 1TB) the other for ZFS Cache/LOG using device (Intel Optane 1TB). The Intel Optane parted with four partitions as 25% (238.5GB) of 1TB and plan to use LOG for zssd and zsas as well as cache for zssd and zsas. nvme1n1     259:0   ..." Tag: Visual edit
• 12:2612:26, 4 January 2024 diff hist −194‎ Manual:SS System ‎ →‎Scope and license Tag: Visual edit
• 12:2012:20, 4 January 2024 diff hist +41,268‎ N Manual:SS System ‎ Created page with "== HPCMATE SS (Scalable Storage) System Manual == To provide scalable storage solution that can be tunable for various workload of storage, HPCMATE provides the best practice of ZFS environment storage system. This page describes how to apply pre-installed software and how to maintain the system. Like DLS system, all SS system based on HPCMATE system level optimized Ubuntu. == Type of SS system == Scalable storage system can be configured many combination. HPCMATE pr..." Tag: Visual edit
• 11:1111:11, 4 January 2024 diff hist +111‎ Systemd tips and tricks ‎ →‎How to permanently disable EEE (Energy Efficient Ethernet) on network card Tag: Visual edit
• 11:0511:05, 4 January 2024 diff hist +843‎ Systemd tips and tricks ‎No edit summary Tag: Visual edit

3 January 2024

• 15:2615:26, 3 January 2024 diff hist −3‎ Storcli ‎ →‎Install storcli under Ubuntu Tag: Visual edit
• 15:2515:25, 3 January 2024 diff hist +95‎ Private:DLS tuning ‎ →‎DLS network tuning Tag: Visual edit
• 14:2614:26, 3 January 2024 diff hist +227‎ Private:DLS tuning ‎ →‎DLS ulimit tuning Tag: Visual edit
• 14:2414:24, 3 January 2024 diff hist +138‎ Private:DLS tuning ‎ →‎DLS network tuning Tag: Visual edit
• 14:2314:23, 3 January 2024 diff hist +948‎ Linux kernel parameter ‎ →‎net.core.somaxconn current Tag: Visual edit
• 14:1314:13, 3 January 2024 diff hist +1,003‎ N Private:DLS tuning ‎ Created page with " == DLS network tuning == https://enterprise-support.nvidia.com/s/article/linux-sysctl-tuning <syntaxhighlight lang="bash"> #Increase number of connection net.core.somaxconn=2048 #Disable the TCP timestamps option for better CPU utilization: net.ipv4.tcp_timestamps=0 #Increase the maximum length of processor input queues: net.core.netdev_max_backlog=250000 #Enable the TCP selective acks option for better throughput: net.ipv4.tcp_sack=1 #how much of the socket buffer..." Tag: Visual edit
• 13:0013:00, 3 January 2024 diff hist 0‎ Vmstat ‎ →‎References current Tag: Visual edit
• 12:5912:59, 3 January 2024 diff hist +1,359‎ Ulimit ‎No edit summary current Tag: Visual edit
• 12:5412:54, 3 January 2024 diff hist +35‎ Linux kernel parameter ‎ →‎References Tag: Visual edit
• 12:5312:53, 3 January 2024 diff hist +44‎ Vmstat ‎ →‎References Tag: Visual edit
• 12:5112:51, 3 January 2024 diff hist +333‎ Linux kernel parameter ‎No edit summary Tag: Visual edit
• 12:5012:50, 3 January 2024 diff hist +3,177‎ N Vmstat ‎ Created page with "The '''<code>vmstat</code>''' (virtual memory statistics) is a built-in monitoring utility in Linux. <ref>https://phoenixnap.com/kb/vmstat-command</ref> The command is used to obtain information about memory, system processes, paging, interrupts, block I/O, disk, and CPU scheduling. Users can observe system activity virtually in real-time by specifying a sampling period. == Output meaning == <syntaxhighlight lang="bash"> $ vmstat -n 1 procs -----------memory----------..." Tag: Visual edit
• 12:3712:37, 3 January 2024 diff hist +4‎ Network traffic ‎ →‎Network monitoring tools Tag: Visual edit
• 12:3612:36, 3 January 2024 diff hist +1,162‎ N Linux kernel parameter ‎ Created page with "== net.core.somaxconn == somaxconn is used to set the maximum number of connections that can be queued for a socket. This parameter is used to prevent a flood of connection requests from overwhelming the system. The maximum value for the <code>net.core.somaxconn</code> parameter depends on the system and kernel version. The default value for the <code>net.core.somaxconn</code> Linux kernel parameter is typically 128 and the maximum value is around 65535 on most systems..." Tag: Visual edit
• 12:2812:28, 3 January 2024 diff hist +31‎ N Kernel kernel param ‎ Admin moved page Kernel kernel param to Kernel boot param over redirect current Tag: New redirect
• 12:2812:28, 3 January 2024 diff hist 0‎ m Kernel boot param ‎ Admin moved page Kernel kernel param to Kernel boot param over redirect current