Help Center/ Distributed Cache Service/ Drawer/ Adjust Bandwidth/ Burst Bandwidth Usage ≥
Updated on 2025-05-28 GMT+08:00
Share

Burst Bandwidth Usage ≥

Parameter Explanation

Burst bandwidth usage threshold for bandwidth increases.

Calculation

Burst bandwidth usage = Burst bandwidth/Shard bandwidth. The larger value between the metrics Output Flow and Input Flow is used for the burst bandwidth usage.

Scale-up objective

The bandwidth of a shard will be automatically scaled up when the burst bandwidth usage of the shard reaches the threshold. Later, the burst bandwidth usage will be 10% lower than the threshold.

For example, when the threshold is 70%, if the burst bandwidth usage of a shard reaches 70%, the bandwidth will be automatically scaled up, and the burst bandwidth usage will decrease to 60%. Therefore, Shard bandwidth after scale-up = Burst bandwidth/60%.

FAQs

Will bandwidth be automatically scaled down when burst bandwidth usage decreases?

No. To undo scale-up, manually change the target bandwidth to the assured bandwidth.

How to check the assured shard bandwidth and adjusted bandwidth?

On the manual bandwidth change page, Assured and Current of each shard are displayed. Assured bandwidth is the default shard bandwidth of an instance. If the bandwidth is adjusted, Current is the latest one.

How does instance bandwidth relate to shard bandwidth?

Their relationship is as follows:
  • Bandwidth of a single-node or master/standby instance = Bandwidth per shard
  • Bandwidth of a read/write splitting instance = Bandwidth per shard × Replica quantity
  • Bandwidth of a cluster instance = Bandwidth per shard × Shard quantity, or the total bandwidth of all shards if the bandwidth per shard varies
Parent Topic: Adjust Bandwidth