Document the built-in ycsb workload #4343
Conversation
|
This change is |
There was a problem hiding this comment.
Reviewable status:
complete! 0 of 0 LGTMs obtained (waiting on @danhhz)
v2.2/cockroach-workload.md, line 53 at r1 (raw file):
`startrek` | Loads a `startrek` database, with two tables, `episodes` and `quotes`.<br><br>For this workload, you run only `workload init` to load the data. The `workload run` subcommand is not applicable. `tpcc` | Simulates a transaction processing workload using a rich schema of multiple tables.<br><br>For this workload, you run `workload init` to load the schema and then `workload run` to generate data. `ycsb` | The Yahoo! Cloud Serving Benchmark.<br><br>For this workload, you run `workload init` to load the schema and then `workload run` to generate data.
@robert-s-lee or @drewdeally, can either of you help me describe the characteristics of this workload better?
There was a problem hiding this comment.
Reviewable status:
v2.2/cockroach-workload.md, line 53 at r1 (raw file):
Previously, jseldess (Jesse Seldess) wrote…
@robert-s-lee or @drewdeally, can either of you help me describe the characteristics of this workload better?
Something about "high-scale key value stores"
v2.2/cockroach-workload.md, line 146 at r1 (raw file):
Flag | Description -----|------------ `--concurrency` | The number of concurrent workers.<br><br>**Applicable commands:** `init` or `run`<br>**Default:** `8`
default is 2 * num cpus, it just shows up with the multiplication already applied (maybe i should put something about this in the flag description?)
v2.2/cockroach-workload.md, line 164 at r1 (raw file):
`--splits` | Number of [splits](split-at.html) to perform before starting normal operations.<br><br>**Applicable commands:** `init` or `run` `--tolerate-errors` | Keep running on error.<br><br>**Applicable command:** `run` `--workload` | The type of workload to run (`A` - `F`).<br><br>**Applicable commands:** `init` or `run`<br>**Default:** `B`
it's worth explaining each of these. some info is here https://github.com/brianfrankcooper/YCSB/wiki/Core-Workloads
There was a problem hiding this comment.
Reviewable status:
v2.2/cockroach-workload.md, line 53 at r1 (raw file):
Previously, danhhz (Daniel Harrison) wrote…
Something about "high-scale key value stores"
Combined the above and input from @drewdeally.
v2.2/cockroach-workload.md, line 146 at r1 (raw file):
Previously, danhhz (Daniel Harrison) wrote…
default is 2 * num cpus, it just shows up with the multiplication already applied (maybe i should put something about this in the flag description?)
Thanks. Yes, would probably be good to be explicit about this in the description. And this applies to other workloads as well, right?
v2.2/cockroach-workload.md, line 164 at r1 (raw file):
Previously, danhhz (Daniel Harrison) wrote…
it's worth explaining each of these. some info is here https://github.com/brianfrankcooper/YCSB/wiki/Core-Workloads
For now, just linking to that page. When we write separate docs on using this an other built-in workloads to calibrate a cluster, I can go into more depth in our docs.
Fixes #4186.