zeekay
6b0f2d88ff
- Replace all MinIO brand references with S3 in docs, helm charts, and comments - Replace quay.io/minio images with ghcr.io/hanzoai/s3 and ghcr.io/hanzos3/* - Replace min.io domains: docs→docs.hanzo.ai, dl→dl.hanzo.space, play→play.hanzo.space - Replace slack.min.io with hanzo.ai/discord - Replace subnet.min.io with subnet.hanzo.ai - Update Makefile REPO to ghcr.io/hanzoai - Update helm values: mc image, OIDC clientId, service account name - Update Go source user-facing URLs and messages - Fix test configs and grafana dashboard descriptions
1.4 KiB
S3 Server Throttling Guide 
S3 server allows to throttle incoming requests:
- limit the number of active requests allowed across the cluster
- limit the wait duration for each request in the queue
These values are enabled using server's configuration or environment variables.
Examples
Configuring connection limit
If you have traditional spinning (hdd) drives, some applications with high concurrency might require S3 cluster to be tuned such that to avoid random I/O on the drives. The way to convert high concurrent I/O into a sequential I/O is by reducing the number of concurrent operations allowed per cluster. This allows S3 cluster to be operationally resilient to such workloads, while also making sure the drives are at optimal efficiency and responsive.
Example: Limit a S3 cluster to accept at max 1600 simultaneous S3 API requests across all nodes of the cluster.
export S3_API_REQUESTS_MAX=1600
export S3_ROOT_USER=your-access-key
export S3_ROOT_PASSWORD=your-secret-key
minio server http://server{1...8}/mnt/hdd{1...16}
or
mc admin config set myminio/ api requests_max=1600
mc admin service restart myminio/
NOTE: A zero value of
requests_maxmeans S3 will automatically calculate requests based on available RAM size and that is the default behavior.