Skip to content

Commit e956a3f

Browse files
committed
Run on a single node for LSI firmware test
1 parent 096766d commit e956a3f

6 files changed

+9
-4
lines changed

README.md

Lines changed: 5 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -28,6 +28,7 @@ My use case is to test a base install of the following stack:
2828
1. 3x Dell R620 servers
2929
* Each: CPU(s) 32 x Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (2 Sockets)
3030
* 256 MB Ram
31+
* PERC H710P
3132
* 4x 556GB SAAS drives
3233
2. Proxmox 6.4 VE
3334
3. ZFS Raid 10
@@ -332,11 +333,13 @@ rpool 53.1G 1.03T 0 127 0 3.46M
332333
rpool 53.1G 1.03T 0 19 0 285K
333334
```
334335

335-
# Perc H310 replacement
336+
# PERC H710P replacement
337+
338+
See [H310/H710/H710P/H810 Mini & Full Size IT Crossflashing](https://fohdeesha.com/docs/perc/).
336339

337340
Comparison of the random read/write job1 between two configurations on the same node:
338341

339-
1. Dell stock firmware for Perc H310.
342+
1. Dell stock firmware for PERC H710P.
340343
2. LSI initiator target (IT) mode firmware.
341344

342345
The hypothesis is the 512MB of cache on the dell firmware is causing a large

fio.yaml

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -6,13 +6,15 @@ metadata:
66
labels:
77
app: fio
88
spec:
9-
parallelism: 3
10-
completions: 3
9+
parallelism: 1
10+
completions: 1
1111
template:
1212
metadata:
1313
labels:
1414
app: fio
1515
spec:
16+
nodeSelector:
17+
kubernetes.io/hostname: k1-bf30
1618
affinity:
1719
podAntiAffinity:
1820
requiredDuringSchedulingIgnoredDuringExecution:
76.3 KB
Loading
143 KB
Loading
168 KB
Loading
243 KB
Loading

0 commit comments

Comments
 (0)