PERC5i throughput [was: possible issues with Dell/Perc5 raid]
Kevin Kobb
kkobb at skylinecorp.com
Tue May 15 16:31:56 UTC 2007
Tom Judge wrote:
> Randy Schultz wrote:
>> On Tue, 15 May 2007, Kevin Kobb spaketh thusly:
>>
>> -}These reports on poor performance using mpt seem to be on SATA
>> -}drives. Has anybody been seeing this using SAS drives? -}
>> -}We are testing Dell PE840s with hot swap SAS drives, and seem to
>> get
>> decent -}performance, though I haven't run any benchmarks yet. Any
>> opinions if the -}PERC5i/mfi is a better choice than the SAS5iR/mpt
>> combination?
>>
>> Would it be possible for you to install blogbench and give it a quick
>> run while your system is idle? We will be ordering a new box in 1-2
>> months that we need high disk I/O capabilities. We've been looking
>> at
>> the PERC5i set up RAID 5 with 4-6 SAS drives. I'ld be interested in
>> what you're seeing for throughput on the PERC5i.
>>
>
> I have attached some blogbench tests from the following configs:
>
> Perc5i 4 * SAS 15K RPM 146 Gig disks in raid 5.
>
>
> Perc5e 15 * SATA 7.2K RPM 500 Gig disks in raid 50 (3 raid 5 volumes
> 5 disks each)
>
>
> Other configurations that I may be able to test are 2 SATA in raid 1
> and 2 SAS in raid 1 (both on perc5i).
Ok, I installed blogbench (which I have not used before) and ran a
couple of quick tests.
I have a SAS 5iR controller, (not a PERC5 though) on a PE840, with 2 GB
RAM, and 2 146 GB 10K RPM hot plug drives in a RAID 1.
I ran the test and noticed:
"mpt0: QUEUE FULL EVENT: Bus 0x00 Target 0x20 Depth 121" messages in my
logs.
Then I ran, camcontrol tags 0:0:0 -N 119 -v, and ran it again.
I didn't get any messages this time and got the results indicated in
test 2.
-------------- next part --------------
Frequency = 10 secs
Scratch dir = [/var/blogbench/]
Spawning 3 writers...
Spawning 1 rewriters...
Spawning 5 commenters...
Spawning 100 readers...
Benchmarking for 30 iterations.
The test will run during 5 minutes.
Nb blogs R articles W articles R pictures W pictures R comments W comments
17 55260 973 39370 880 32248 3650
28 134486 532 98010 549 86733 3106
30 134573 257 101060 146 107526 4947
34 98176 280 68817 192 76737 2610
42 146159 569 101205 526 108409 4214
44 113053 103 77234 95 80420 4117
47 123475 58 82482 60 101734 4138
53 116878 333 79349 328 100729 4242
62 129703 491 88760 511 102082 2740
75 56569 1017 39268 646 43163 3330
78 78428 125 53036 107 60883 5010
83 41037 452 28260 301 31707 4043
88 41144 492 28448 407 29760 4011
93 104037 347 71189 473 81383 3972
100 138044 287 95126 316 106019 5474
103 136079 187 94750 203 107826 5754
106 80718 230 55433 146 67429 3845
111 29693 326 21125 284 23386 3978
120 47330 400 31754 381 36253 4219
123 104226 342 70924 341 85267 4291
128 120925 808 87777 533 97476 2673
129 158526 163 114288 116 135061 3884
134 33258 389 23219 328 31020 4083
140 56495 362 39954 323 49051 3525
142 130233 223 93422 220 110732 2766
150 63513 603 46071 326 57740 4760
155 19686 305 13779 288 14446 3257
160 56576 511 40326 390 46761 4171
162 15760 188 11627 193 15065 3569
166 33365 176 23615 251 27148 4420
Final score for writes: 166
Final score for reads : 53465
-------------- next part --------------
Frequency = 10 secs
Scratch dir = [/var/blogbench/]
Spawning 3 writers...
Spawning 1 rewriters...
Spawning 5 commenters...
Spawning 100 readers...
Benchmarking for 30 iterations.
The test will run during 5 minutes.
Nb blogs R articles W articles R pictures W pictures R comments W comments
39 104065 1902 92397 1908 81915 1920
52 89671 812 75477 796 64955 2786
63 40679 526 33195 646 31461 2682
78 51740 1173 42408 778 35679 3384
88 113424 624 91326 546 78975 2915
91 46138 275 37605 254 33564 5530
97 36149 370 28729 231 26711 2891
101 85994 274 68781 101 63879 4942
116 48741 646 39656 758 33324 3320
124 26635 436 20939 492 19201 3246
129 62322 387 50055 356 42611 3542
133 34041 176 27625 103 23844 4214
136 70655 187 57334 92 47747 3775
140 91423 268 73591 322 64109 3731
145 40426 310 32623 369 30511 4642
149 51952 350 43269 207 36259 3263
155 45495 313 37330 294 32495 4303
161 71781 381 59076 337 53068 5047
166 82942 245 67613 221 58052 4236
167 107542 138 87544 114 71804 2991
176 114451 480 93543 204 80621 5079
178 149129 107 122331 141 102999 2691
180 125073 168 102207 106 87452 5430
181 152969 77 123829 74 106024 5851
187 161513 395 130680 131 112562 4197
189 175944 186 138771 32 122199 5258
192 154242 196 121718 214 102413 2791
197 215053 416 168652 274 144365 2056
201 199915 342 155300 317 131471 2108
205 189504 141 146564 64 124165 1588
Final score for writes: 205
Final score for reads : 45783
More information about the freebsd-performance
mailing list