69b0ccb4b8
Cross-referenced all 70+ KB files against official Oracle docs. Critical fixes: - ExaCS: storage was flash cache not usable disk (76.8→190.8 TB QR), added X11M, removed X10M - ADB-S: OCPU→ECPU migration, 26ai as default, cross-region RTO 15→10 min - Compute: E5 max 94→126, A2 80→78, added E6/A4/BM shapes, 11 GPU shapes - Storage: Higher Perf IOPS 35K→50K, UHP 450K→300K, File Storage 25K→50K - DBCS: E5.Flex max 94→64, storage 80→150 TB, added 26ai - Networking: FastConnect +400 Gbps, NSG max 120 rules Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
71 lines
2.2 KiB
YAML
71 lines
2.2 KiB
YAML
---
|
|
last_verified: 2026-03-14
|
|
description: Storage performance characteristics across OCI storage tiers.
|
|
---
|
|
|
|
storage_tiers:
|
|
adb_serverless:
|
|
type: "Exadata managed storage"
|
|
iops_random_read: "Up to 600K per ADB instance"
|
|
iops_random_write: "Workload dependent"
|
|
throughput: "Scales with OCPUs"
|
|
latency_read_us: "<200 (Smart Scan eligible)"
|
|
latency_write_us: "<500"
|
|
notes: "Performance scales with OCPU count, Exadata Smart Scan offloads queries"
|
|
|
|
exadata_storage:
|
|
type: "Exadata Smart Storage"
|
|
iops_random_read: "Up to 6.4M per rack (X9M)"
|
|
throughput_gbps: "Up to 100 GB/s (X9M)"
|
|
smart_scan: true
|
|
flash_cache: true
|
|
hcc: true
|
|
notes: "Highest performance tier, Smart Scan can offload full table scans"
|
|
|
|
block_volume_balanced:
|
|
type: "Block Volume (Balanced)"
|
|
iops_per_gb: 60
|
|
max_iops: 25000
|
|
throughput_kbps_per_gb: 480
|
|
max_throughput_mbps: 480
|
|
latency_us: "Sub-millisecond"
|
|
|
|
block_volume_higher_performance:
|
|
type: "Block Volume (Higher Performance)"
|
|
iops_per_gb: 75
|
|
max_iops: 50000
|
|
throughput_kbps_per_gb: 600
|
|
max_throughput_mbps: 680
|
|
latency_us: "Sub-millisecond"
|
|
|
|
block_volume_uhp:
|
|
type: "Block Volume (Ultra High Performance)"
|
|
max_iops: 300000
|
|
max_throughput_mbps: 2680
|
|
notes: "Requires UHP-enabled shapes"
|
|
|
|
object_storage:
|
|
type: "Object Storage"
|
|
throughput: "High (parallel multipart uploads)"
|
|
latency: "Milliseconds (first byte)"
|
|
use_for: "Backups, archives, unstructured data"
|
|
not_for: "Random IOPS workloads"
|
|
|
|
file_storage:
|
|
type: "File Storage (NFS)"
|
|
max_iops: 50000
|
|
max_throughput_mbps: 1200
|
|
latency: "Sub-millisecond"
|
|
use_for: "Shared file access, NFS workloads"
|
|
|
|
sizing_from_source:
|
|
exadata_to_adb:
|
|
notes: "ADB-S on Exadata infra — performance is comparable or better"
|
|
recommendation: "Map directly, ADB auto-tunes storage"
|
|
physical_server_to_block_volume:
|
|
notes: "Match IOPS and throughput requirements to block volume tier"
|
|
recommendation: "Use Higher Performance for database, Balanced for app tier"
|
|
san_to_block_volume:
|
|
notes: "SAN IOPS vary widely — get actual metrics"
|
|
recommendation: "Size for P95 IOPS, test with fio before migration"
|