HP MSL 2024 SCSI 1840 drive throughput

[Marino Meloni_1]

you can check the polling collecting a support ticket.
you can check the polling setting details to "everything"
then select "Classic support ticket"
and "enhanced SCSI COmmand History"

here you can see the scsi commands and the time of the events

Marino

[KEN_SYD]

Thank you for quick response.

However, can you instruct me where to find these settings and classic ticket? From LTT or Tape Library?

Then I need to send the ticket to HP engineer right?

[Curtis Ballard]

I can't explain the strange behavior with reporting the same speed for different compression ratios with your drive however if you are able to get 177MB/s out of a parallel SCSI system then it is extremely unlikely that anything at the drive end is causing your performance problem. 177MB/s over parallel SCSI is quite good and most systems I have worked on can't hit that speed regardless of what type storage device is on the other end of the bus.

Disabling the polling is good but unlikely to help much as the same polling would have been going on when you ran the performance test.

To check for the polling you need to use L&TT, select the "support ticket" button, select "Extract device data", then select "view" then follow the instructions you were given earlier to find the data in the ticket.

[KEN_SYD]

Hi Curtis,

Thank you for you comments.
Is speed with or without compression the same because of hardware compression is enable?

[Curtis Ballard]

I reviewed the log file you attached with your performance testing. I see results for 2:1 compression at 177MB/s, results for all zeros at 177MB/s, and results for 1.6:1 at 177MB/s.

All of those make sense. The drive is capable of 192MB/s with 1.6:1 compression so if the system tops out at 177MB/s then 1.6:1 and higher compression ratios will all yield the same results.

I also see results for uncompressed data at 111MB/s which seems reasonable with the drive maximum speed when everything is perfect being 120MB/s.

The results in that test look reasonable to me. I did see that there were conflicting results from the drive assessment test. I would say that the tape used for the first test probably wasn't quite perfect. Since the second test passed as long as the drive is working correctly I wouldn't worry about the first test issue.

[KEN_SYD]

Follow your guide. I found the TUR now only 1 per second or less as following screenshot.
However test speed remains the same at 177 MB/s.

If this is the maximum, how can I explain to my manager if he ask why?

The dev test is write data directly from memory to tape, thus we can say because of the source bottle-neck?

[KEN_SYD]

Hi All,

I have a question about LTT Dev perf Test logic.

Does random data type mean LTT will send to tape a data that randomly from zero compression to 4:1 compression?

When I did a test each compression ratio with hardware compression enable, throuput is almost the same at around 170MB/s. However, throughput for random data type is only around 105 MB/s. it looks like the test data cannot be compress anymore (native speed)

[Curtis Ballard]

Random data means that the data in the output buffer for writing to tape is random and random data is not compressible so the transfer rate should be somewhere close but probably a bit below the native rate.

If you are getting 177 MB/s when running the performance test with 1.6:1 compressible data and but only 107 MB/s when running a backup with 1.5:1 compressible data I think the performance test did its job.

The bottleneck is not your drive or your host - the data either is not getting to the backup application or out of the backup application fast enough. Your backup application is only pushing the drive at about 60% of the hardware capability.

[KEN_SYD]

Thank you for your information Curtis.

I have done some test on Arcserve that backup from a remote server and a local server seperately, throughput for each server is around 5.6 GB/min (~93MB/s).
I then backup these two servers using multistream, total throughput is also around 6GB/min only.
I then questioned Arcserve why throughput seems to be limited at 6GB/min, while tape driver can write faster?
Arcserve asked me to use LTT to test with random data type. The throughput was around 105 Mb/s so Arcserve concluded that my data does not have good compression ratio, that why throughput is just arround 6GB/min.
Does that make sense, Curtis?

ArcServe also said compression ratio and throughput affect each other more or less but it's usually not the linearity. That means if my data average compression ratio is 1.35, throughout won't be 120*1.35?

I'm garthering all information to make a final report.
Thanks.

[Curtis Ballard]

HP LTO tape drive performance scales pretty linear with compression ratios up past 2:1. Eventually it won't scale linearly anymore but with anything under 2:1 it should.

The L&TT utility will report what compression ratio was achieved on the most recent operation if you use it to pull a support ticket following a backup.

If L&TT reports 1:1 compression then the maximum speed you could get would be the 120MB/s but if L&TT reports 1.5:1 then the drive could have accepted data at 180 MB/s and your system can push data at 177 MB/s with 1.6:1 compressible data so I have to assume that the data just wasn't being provided fast enough if you didn't hit the 177 MB/s.