knowledge-base/SERVER-CONFIG.md

⚙️ Server configuration — best practices podle workloadu

Obecná BIOS/UEFI nastavení

Nastavení	Doporučení	Zdůvodnění
Boot mode	UEFI	Secure Boot, GPT, větší disky
Power profile	Performance / OS Control	Max výkon, C-States disabled
Hyper-Threading	Enabled	+30-50 % throughput pro multi-thread
Virtualization	Enabled (VT-x/AMD-V)	Nutné pro hypervisor, containers
SR-IOV	Enabled	GPU, NIC passthrough
NUMA	Enabled	NUMA-aware scheduling
ACPI	Enabled	Power management, OS-level
Security Boot	Enabled	Secure boot chain
TPM	Enabled	Measured boot, key storage

---

1. Databázové servery

Volba CPU

DB typ	CPU preference	Zdůvodnění
OLTP (PostgreSQL, MySQL)	High clock, moderate cores	Nízká latence na transakci, limited parallelism
OLAP (ClickHouse, Snowflake)	Many cores, AVX-512	Columnstore, high parallelism
In-memory (Redis, Memcached)	High clock, low cache latency	Single-threaded (Redis), RAM bandwidth
Document (MongoDB)	Balance (clock × cores)	Mixed workload
Distributed (Cassandra, Scylla)	Many cores, high cache	Shard-per-core (Scylla), compaction

Storage layout

Mount point    FS       RAID     Disk type    Účel
─────────────  ─────    ─────    ──────────   ──────────────────
/               ext4    1 (mirror)  2× SSD    OS, binární soubory
/data           xfs     10 (stripe) 4-8× NVMe Databázová data
/wal            xfs     1 (mirror) 2× NVMe   Write-ahead log (PostgreSQL)
/tmp            tmpfs   —          RAM       Dočasné soubory

PostgreSQL specific

Parametr	Doporučení	Poznámka
shared_buffers	25 % RAM	Cache databázových bloků
effective_cache_size	75 % RAM	Odhad OS cache pro query planner
work_mem	4-64 MB per operation	SORT, HASH JOIN (correlate s max_connections)
maintenance_work_mem	1-10 % RAM	VACUUM, CREATE INDEX, ANALYZE
wal_buffers	64-256 MB	Write-ahead log buffer
max_connections	50-500	Connection pooling (PgBouncer)
random_page_cost	1.1 (NVMe), 4 (HDD)	Index scan cost (NVMe = téměř seq scan)
effective_io_concurrency	200 (NVMe), 2 (HDD)	Parallel I/O

MySQL / MariaDB specific

Parametr	Doporučení	Poznámka
innodb_buffer_pool_size	70-80 % RAM	Hlavní cache InnoDB
innodb_log_file_size	1-4 GB	Redo log, čím větší tím lepší write perf
innodb_flush_log_at_trx_commit	1 (ACID) / 2 (perf)	1 = fsync každou transakci
innodb_io_capacity	2000 (NVMe) / 200 (HDD)	IOPS limit
innodb_write_io_threads	4-8	Parallel write threads
max_connections	100-500	Connection pooling doporučen

MongoDB specific

Parametr	Doporučení	Poznámka
WiredTiger cache	50-80 % RAM	Storage engine cache
WiredTiger compression	Snappy / Zstd	Komprese disku (zlib je pomalý)
filesystem	XFS	Doporučený FS (ext4 OK, NTFS ne)
ReadConcern/WriteConcern	majority/majority	Pro důležitá data

Kernel tuning pro DB

# /etc/sysctl.d/99-database.conf

vm.swappiness = 1              # Minimalizuj swap, preferuj cache
vm.dirty_ratio = 30            # % RAM before background flush
vm.dirty_background_ratio = 5  # Start flush at 5 %
vm.nr_hugepages = 0            # Huge pages pokud DB podporuje (PostgreSQL, MongoDB)
net.core.rmem_max = 134217728
net.core.wmem_max = 134217728
net.ipv4.tcp_rmem = 4096 87380 134217728
net.ipv4.tcp_wmem = 4096 65536 134217728
net.core.somaxconn = 4096

# I/O scheduler (NVMe = none, SSD = mq-deadline, HDD = kyber/bfq)
# echo none > /sys/block/nvme0n1/queue/scheduler

---

2. Hypervisor host (ESXi / KVM / Hyper-V)

CPU a NUMA

Nastavení	Doporučení	Poznámka
Overcommit ratio	1:1 až 4:1 (vCPU:pCPU)	Podle workloadu (1:1 DB, 4:1 web)
NUMA-aware sizing	VM ≤ 1 NUMA node	Cross-NUMA penalty ~1.5-2× latence
CPU pinning	Dedikované VM: ano	Zamezí context switching
C-States	Disabled (in BIOS)	Nižší latence, vyšší spotřeba
P-State	OS control / Performance	HW power management
Hyper-Threading	Enabled	Více vCPU, watch for noisy neighbor

Storage pro hypervisor

VM storage:
├── OS datastore          RAID 1 (2× SATA SSD) — ESXi boot, images
├── VM datastore (gold)   RAID 10 (4× NVMe) — critical VMs, DB
├── VM datastore (silver) RAID 5 (6× SAS SSD) — general VMs
└── VM datastore (bronze) RAID 6 (8× SATA HDD) — backup, archive

Swap datastore:                   1× NVMe nebo SATA SSD (dedikovaný)

Network design

Traffic	VLAN	Speed	NIC teaming
Management	Mgmt VLAN	1 GbE	Active/Passive
VM traffic	VM VLANs	25/100 GbE	LACP (802.3ad)
Storage	Storage VLAN	25/100 GbE	LACP / RDMA
vMotion	vMotion VLAN	25/100 GbE	Dedikovaný, multi-NIC
FT (Fault Tolerance)	FT VLAN	10 GbE	Dedikovaný, low latency

BIOS pro hypervisor

Nastavení	Hodnota	Zdůvodnění
Hyper-Threading	Enabled	Vyšší VM density
Virtualization Technology	Enabled	VT-x/AMD-V
VT-d / IOMMU	Enabled	Passthrough, SR-IOV
Power Management	Performance / OS	Minimalizace latence VM
C-States	Disabled	Nižší latence VM exit
NUMA	Enabled	NUMA-aware VM placement
SR-IOV	Enabled	NIC/GPU virtualizace

---

3. Kubernetes node

Node profily

Role	CPU	RAM	Storage	Network	Use case
General purpose	16-32 cores	64-128 GB	1× NVMe OS + 1×NVMe local	Web, API, microservices
Memory optimized	32-64 cores	256-512 GB	1× NVMe OS + 2×NVMe local	In-memory cache, DB
Compute optimized	64-128 cores	128-256 GB	1× NVMe OS	Batch, CI/CD
GPU node	32-64 cores	512-1024 GB	1× NVMe OS + 4-8×NVMe local	AI/ML training, inference
Storage node	16-32 cores	64-128 GB	4-12× NVMe/SATA (Ceph/Longhorn)	SDS, persistent volumes

Kernel tuning

# /etc/sysctl.d/99-kubernetes.conf
net.bridge.bridge-nf-call-iptables = 1
net.bridge.bridge-nf-call-ip6tables = 1
net.ipv4.ip_forward = 1
net.ipv4.conf.all.forwarding = 1

# Connection tracking (pro NodePort, Service)
net.netfilter.nf_conntrack_max = 2097152
net.netfilter.nf_conntrack_tcp_timeout_established = 86400

# File watchers (pro kubelet, containerd)
fs.inotify.max_user_instances = 8192
fs.inotify.max_user_watches = 524288

# Memory management
vm.swappiness = 0
vm.overcommit_memory = 1      # Allow overcommit (CRI-O, containerd)
vm.panic_on_oom = 0
kernel.panic = 10
kernel.panic_on_oops = 1

Container storage

Typ	Doporučení	Poznámka
OS disk	RAID 1 (2× NVMe)	Ext4/XFS, 100-200 GB
Container runtime image	RAID 1 (2× NVMe)	/var/lib/containerd, 200-500 GB
Local PV	Single NVMe	Raw device, no RAID
Rook/Ceph OSD	Raw NVMe/SATA	HBA/IT mode, no RAID
Longhorn	Raw NVMe/SATA	Ext4/XFS per volume

---

4. Storage server (Ceph / MinIO / NAS)

Ceph OSD node

Komponenta	Doporučení	Poznámka
CPU	1-2 cores per OSD	Do 12 OSD na node (24 cores)
RAM	4-8 GB per OSD + OS	BlueStore cache, 16-64 GB min
Network	2× 25/100 GbE	Public + Cluster network
Storage	10-12× NVMe/SATA SSD OSD	HBA/IT mode, žádný RAID
OS disk	2× SATA SSD RAID 1	OS, Ceph MON/MGR

BIOS pro Ceph:

• SATA/NVMe: AHCI/NVMe mode (ne RAID)
• C-States: Disabled (nižší latence OSD)
• NUMA: Enabled
• Power: Performance

MinIO node

Komponenta	Doporučení
CPU	8-16 cores (32+ pro erasure coding)
RAM	32-64 GB + 1 GB per 1 TB storage
Storage	4-16× NVMe (direct, no RAID)
Network	2× 25/100 GbE
OS	Ubuntu / RHEL, XFS (pro data)

NAS (TrueNAS / FreeNAS)

• ZFS: RAID-Z1/Z2/Z3, compression (lz4, zstd), dedup
• ARC cache: 1 GB per 1 TB storage (max 64 GB)
• L2ARC: NVMe cache (optional, read-heavy)
• SLOG: NVDIMM / Optane (sync write, ZIL)
• Network: 2-4× 10/25 GbE LACP

---

5. Web / API servery

Parametr	Doporučení
CPU	High clock, 8-32 cores
RAM	32-128 GB
Storage	2× NVMe RAID 1 (OS + app)
OS	Ubuntu / RHEL, optimized kernel
Network	2× 10/25 GbE (bonding)

Kernel tuning:

net.ipv4.tcp_tw_reuse = 1
net.ipv4.tcp_fin_timeout = 15
net.core.somaxconn = 65535
net.ipv4.tcp_max_syn_backlog = 65535
net.core.netdev_max_backlog = 65535

---

Rychlý decision tree — výběr serveru

Jaký workload?
│
├── Databáze (OLTP)
│   → EPYC, high clock, 8-16 GB/core, RAID10 NVMe, huge pages
│
├── Databáze (OLAP)
│   → Xeon AMX/AVX-512, 16-64 GB/core, many cores
│
├── Virtualizace
│   → EPYC, many cores, 4-8 GB/core, shared storage (SAN/NFS/vSAN)
│
├── Kubernetes
│   → EPYC, balance, 2-4 GB/core, local NVMe
│
├── AI/ML training
│   → GPU node (H100/B200), NVLink, InfiniBand, liquid cooling
│
├── AI/ML inference
│   → A100/H200, MIG, large VRAM, PCIe 5.0
│
├── Storage (Ceph/SDS)
│   → EPYC (PCIe lanes), HBA mode, 4-8 GB/OSD
│
└── Web / API
    → EPYC, high clock, 2-4 GB/core, 10 GbE

## Zdroje

Odkazy, knihy a standardy: [sources/infrastructure/sources.md](sources/infrastructure/sources.md)