2018-01-12 Class notes -- storage

Storage layer:

Two types of storage (not b+ tree, that's 2-3 steps up for indexing)

1. HDD

process to read data from HDD

1. move disk arm to connect cylinder (1-3ms)
2. wait for bits we want to rotate under disk heads. (10^4 rpm / 60 seconds * 2 ~ 1/300 seconds ~3ms)
3. read the data (mostly costless! seq scan @ 100MB/sec)
   --- the first bit takes millions time longer than the following sequential scan.

Because HDDs have physical limitations, SSDs get popular.

2. SSD

• all electronic, no moving parts;
• 5GB/sec seq transfer rate at high end.
• 10K "seeks" (refers to 1. 2. in HDD) per second high end (0.1ms).
• cost e.g. Samsung drive 15 TB. $$5k to 7k

HDD ~$1/GB, SSD ~$1/GB
15 TB ~150 HDD ~1SSD

• aggregated performance are actually similar!
• Latency doesn't change much

Given that latency is a huge concern, how to mitigate?

• organize data on the device into blocks (atomic units.... get 1bit, get all bits of it) "block" refers to a group of bits on the device.
• organize blocks into pages.
  * put related data into pages. -- e.g. b+ tree organize data with same key (e.g. time stamp) into the same pages.
• Use buffering -- keep important data to the lower level of system (close to CPU)

next time topics --- buffer: