drtprod: put tpcc init and run scripts on workload-scale #132162
Conversation
|
This change is |
This patch ensures that we put the `tpcc_init.sh` and `tpcc_run.sh` file while creating `workload-scale` Epic: none Release note: None
vidit-bhat
force-pushed
the
tpcc-drt-scale
branch
from
5cbf9c2
to
b4f71b4
Compare
vidit-bhat
requested review from
herkolategan,
renatolabs,
shailendra-patel and
nameisbhaskar
and removed request for
a team
| export ROACHPROD_DNS="drt.crdb.io" | ||
| ./roachprod sync | ||
| sleep 20 | ||
| PGURLS=$(./roachprod pgurl drt-scale:1-150 | sed s/\'//g) |
There was a problem hiding this comment.
nit: passing only cluster name drt-scale would give pgurl for all nodes. In case if we decide to not have exact 150 nodes.
| PGURLS=$(./roachprod pgurl drt-scale:1-150 | sed s/\'//g) | ||
|
|
||
| ./cockroach workload init tpcc \ | ||
| --warehouses 3000 \ |
There was a problem hiding this comment.
For 150 scale node the plan is to have 150K warehouses.
|
|
||
| set -o pipefail | ||
|
|
||
| TPCC_DB=cct_tpcc |
There was a problem hiding this comment.
Any reason why are we changing the db name from tpcc to cct_tpcc.
| @@ -34,7 +36,7 @@ while true; do | |||
| --tolerate-errors \ | |||
| --password tpcc \ | |||
| --families \ | |||
| "${PGURLS_ARR[@]}" | tee $LOG | |||
| $PGURLS | tee $LOG | |||
There was a problem hiding this comment.
--warehouses 3000, --active-warehouses 1500 value of this flags need to be changed.
Also we need to think about values of following flags to get the cpu around 60%.
-concurrency 128
--max-rate 7000
|
As discussed, lets hold back on this change. I would prefer it to be more generic scripts that takes inputs from teh YAML file for parameters like warehouses. This can go in after #131942 changes. After that I have another change in the queue where we have parameterised tpocc init. |
|
Closed in favour of #132307 |
This patch ensures that we put the
tpcc_init.shand
tpcc_run.shfile while creatingworkload-scaleEpic: none
Release note: None