-
Notifications
You must be signed in to change notification settings - Fork 3.8k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
drtprod: put tpcc init and run scripts on workload-scale #132162
Conversation
This patch ensures that we put the `tpcc_init.sh` and `tpcc_run.sh` file while creating `workload-scale` Epic: none Release note: None
5cbf9c2
to
b4f71b4
Compare
export ROACHPROD_DNS="drt.crdb.io" | ||
./roachprod sync | ||
sleep 20 | ||
PGURLS=$(./roachprod pgurl drt-scale:1-150 | sed s/\'//g) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: passing only cluster name drt-scale
would give pgurl for all nodes. In case if we decide to not have exact 150 nodes.
PGURLS=$(./roachprod pgurl drt-scale:1-150 | sed s/\'//g) | ||
|
||
./cockroach workload init tpcc \ | ||
--warehouses 3000 \ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
--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. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We will revisit this.
Closed in favour of #132307 |
This patch ensures that we put the
tpcc_init.sh
and
tpcc_run.sh
file while creatingworkload-scale
Epic: none
Release note: None