RE: Slow iSCSI tape performance
Direct throughput about 140MB/s From: open-iscsi@googlegroups.com [mailto:open-iscsi@googlegroups.com] On Behalf Of Lee Duncan Sent: 26 October 2020 22:51 To: open-iscsi Subject: Re: Slow iSCSI tape performance On Oct 25, 2020, at 10:42 AM, David C. Partridge wrote: I believe that it’s something to do with stopping Windows (at the target) from sending TURs to the tape every 30s or so. Okay, that makes sense. But that has nothing to do with open-iscsi, or even iSCSI at all. Setting streaming bit ? Is that something I can do with mt-st or mt commands? The best I am getting is about 29MB/s over a 1Gbit LAN L I was talking about the ability to tell st to write tape marks without waiting. This is very handy for streaming tape drives, since it allows it to stream tape marks as well. But it cannot be set with “mt” — it needs an ioctl(). What kind of throughput does the tape drive supply directly? Here’s my backup script: ... -- You received this message because you are subscribed to a topic in the Google Groups "open-iscsi" group. To unsubscribe from this topic, visit https://groups.google.com/d/topic/open-iscsi/jp7zMTdWbN8/unsubscribe. To unsubscribe from this group and all its topics, send an email to open-iscsi+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/open-iscsi/CCD69511-2C68-4703-9BDD-A1345922DA2D%40gmail.com <https://groups.google.com/d/msgid/open-iscsi/CCD69511-2C68-4703-9BDD-A1345922DA2D%40gmail.com?utm_medium=email_source=footer> . -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To unsubscribe from this group and stop receiving emails from it, send an email to open-iscsi+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/open-iscsi/003d01d6abfc%247c150930%24743f1b90%24%40perdrix.co.uk.
RE: Slow iSCSI tape performance
I believe that it’s something to do with stopping Windows (at the target) from
sending TURs to the tape every 30s or so.
Setting streaming bit ? Is that something I can do with mt-st or mt commands?
The best I am getting is about 29MB/s over a 1Gbit LAN L
Here’s my backup script:
root@charon:~/bin# cat backup-system
#!/bin/bash
# init
function pause(){
read -p "$*"
}
#
# Connect to the iSCSI tape drive and make sure it's set up
#
sudo iscsiadm -m node --targetname
"iqn.2008-08.com.starwindsoftware:mercury-hp1840" --portal
"192.168.129.66:3260" --login
sleep 5
sudo stinit -vv
# Set the device blocksize to 64k
set -v
sudo mt-st -f /dev/st0l setblk 65536
#
# Actually run the backup
#
sudo dd bs=16M if=/dev/disk/by-id/ata-KINGSTON_SVP100S296G_312Y10B7Y5SK | pv |
dd ibs=16M obs=64K of=/dev/st0l
set +v
pause 'Press [Enter] key to unload the tape ...'
sudo mt-st -f /dev/st0l offline
sudo iscsiadm -m node --targetname
"iqn.2008-08.com.starwindsoftware:mercury-hp1840" --portal
"192.168.129.66:3260" --logout
root@charon:~/
Thanks
From: open-iscsi@googlegroups.com [mailto:open-iscsi@googlegroups.com] On
Behalf Of The Lee-Man
Sent: 25 October 2020 16:51
To: open-iscsi
Subject: Re: Slow iSCSI tape performance
I haven't heard about disabling TUR for iSCSI tape improvement. Even if true,
I'm not sure how you'd do that. You'd need to modify your target IMHO to always
reply "ready" for TUR. But TUR is used to clear some conditions at the target,
if present, so not sure about the semantics of ignoring TURs. Have you tried
setting the streaming bit for the tape drive?
On Wednesday, October 21, 2020 at 6:43:22 AM UTC-7 david.p...@perdrix.co.uk
wrote:
I've seen a report that disabling Test Unit Ready across the iSCSI link can
hugely improve performance of remote tape drives.
Is this something I do at the machine hosting the tape drive or at the client?
Is it relevant to open iscsi?
Thanks
David
--
You received this message because you are subscribed to a topic in the Google
Groups "open-iscsi" group.
To unsubscribe from this topic, visit
https://groups.google.com/d/topic/open-iscsi/jp7zMTdWbN8/unsubscribe.
To unsubscribe from this group and all its topics, send an email to
open-iscsi+unsubscr...@googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/open-iscsi/4ad354c3-5d6a-4b1f-b978-afee5d1219aen%40googlegroups.com
.
--
You received this message because you are subscribed to the Google Groups
"open-iscsi" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to open-iscsi+unsubscr...@googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/open-iscsi/007401d6aaf6%2448aef2b0%24da0cd810%24%40perdrix.co.uk.
RE: LTO-4 iSCSI performance less than expected ...
Hmmm I couldn’t find anything about this in the stinit docs. Dave From: open-iscsi@googlegroups.com [mailto:open-iscsi@googlegroups.com] On Behalf Of The Lee-Man Sent: 03 April 2017 20:05 To: open-iscsi Subject: Re: LTO-4 iSCSI performance less than expected ... On Friday, March 31, 2017 at 2:23:30 PM UTC-7, david.partri...@perdrix.co.uk wrote: I don't know? How do I find out? Should I have it set? Have you set the Write Immediate Filemark option for the st driver? There are a couple of ways to enable writing immediate filemarks in the st driver. One is to use the MTWEOFI ioctl(). If you have access to the source code for your application, this is a good way to go. But I added a user-settable option with kernel commit c743e44fbb1f8668941e83de07662b1ecd33d083. It allows you to tell the st driver to write immediate file marks by setting a sysfs attribute. -- -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To unsubscribe from this group and stop receiving emails from it, send an email to open-iscsi+unsubscr...@googlegroups.com. To post to this group, send email to open-iscsi@googlegroups.com. Visit this group at https://groups.google.com/group/open-iscsi. For more options, visit https://groups.google.com/d/optout.
RE: Problem with iSCSI connected LTO-2 tape drive
FWIW I still think the best solution is to suspend the NOP-Out polling (of active) while a device command is being processed. This way you get the best of both worlds However I do see the attraction of a documentation only fix J Cheers Dave From: open-iscsi@googlegroups.com [mailto:open-iscsi@googlegroups.com] On Behalf Of The Lee-Man Sent: 22 December 2016 16:51 To: open-iscsi Subject: Re: Problem with iSCSI connected LTO-2 tape drive Hi David: I have created Issue#35 for this on github. On Thursday, December 15, 2016 at 2:00:15 PM UTC-8, David C. Partridge wrote: You’re right, it is in section 8.2. Maybe it needs to be said in 8.1.1 as well? Dave From: open-iscsi@googlegroups.com [mailto:open-iscsi@googlegroups.com] On Behalf Of Lee Duncan Sent: 15 December 2016 19:41 To: open-iscsi@googlegroups.com Subject: Re: Problem with iSCSI connected LTO-2 tape drive On Dec 15, 2016, at 7:14 AM, david.partri...@perdrix.co.uk wrote: Lee, It would appear that the guilty party was: node.conn[0].timeo.noop_out_interval = 5 node.conn[0].timeo.noop_out_timeout = 5 I changed both of these to 0 for the tape device and the problem went away. Excellent. Please note that the README.gz for open-scsi doesn't actually say that this is what you need to do to disable the NOP-out polling, so could I suggest that this be stated explicitly. My README says, in section 8.2: For this setup, you can turn off iSCSI pings by setting: node.conn[0].timeo.noop_out_interval = 0 node.conn[0].timeo.noop_out_timeout = 0 I must admit that I find it hard to imagine that an iSCSI target would reply to a NOP-out while it was processing a command such as a tape fsf or even tape erase (whose timeout is 6 * the long-timeout of 4 hours). Should perhaps the NOP-out polling be suspended while a command is being processed? Or alternatively maybe the NOP-out polling be completely disabled by default with something in the README.gz file that explains WHEN you might want it and how to enable it. It's certainly clear that (at least) the MS iSCSI initiator doesn't send NOP-out polls. open-iscsi is normally used to deal with discs. When it’s used with tape it’s not unusual to find bugs or design errors that we did not know were present. Perhaps a small blurb in the README about dealing with tape, suggesting turning NOOP/ping off. Please feel free to post a pull request on github or suggest a patch on this list. Regards Dave -- Lee Duncan "Choice means saying no to one thing so you can say yes to another." -- Dan Millman -- You received this message because you are subscribed to a topic in the Google Groups "open-iscsi" group. To unsubscribe from this topic, visit https://groups.google.com/d/topic/open-iscsi/ViC-za8eHdc/unsubscribe. To unsubscribe from this group and all its topics, send an email to open-iscsi+unsubscr...@googlegroups.com. To post to this group, send email to open-iscsi@googlegroups.com. Visit this group at https://groups.google.com/group/open-iscsi. For more options, visit https://groups.google.com/d/optout. -- You received this message because you are subscribed to a topic in the Google Groups "open-iscsi" group. To unsubscribe from this topic, visit https://groups.google.com/d/topic/open-iscsi/ViC-za8eHdc/unsubscribe. To unsubscribe from this group and all its topics, send an email to open-iscsi+unsubscr...@googlegroups.com. To post to this group, send email to open-iscsi@googlegroups.com. Visit this group at https://groups.google.com/group/open-iscsi. For more options, visit https://groups.google.com/d/optout. -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To unsubscribe from this group and stop receiving emails from it, send an email to open-iscsi+unsubscr...@googlegroups.com. To post to this group, send email to open-iscsi@googlegroups.com. Visit this group at https://groups.google.com/group/open-iscsi. For more options, visit https://groups.google.com/d/optout.
RE: Problem with iSCSI connected LTO-2 tape drive
You’re right, it is in section 8.2. Maybe it needs to be said in 8.1.1 as well? Dave From: open-iscsi@googlegroups.com [mailto:open-iscsi@googlegroups.com] On Behalf Of Lee Duncan Sent: 15 December 2016 19:41 To: open-iscsi@googlegroups.com Subject: Re: Problem with iSCSI connected LTO-2 tape drive On Dec 15, 2016, at 7:14 AM, david.partri...@perdrix.co.uk wrote: Lee, It would appear that the guilty party was: node.conn[0].timeo.noop_out_interval = 5 node.conn[0].timeo.noop_out_timeout = 5 I changed both of these to 0 for the tape device and the problem went away. Excellent. Please note that the README.gz for open-scsi doesn't actually say that this is what you need to do to disable the NOP-out polling, so could I suggest that this be stated explicitly. My README says, in section 8.2: For this setup, you can turn off iSCSI pings by setting: node.conn[0].timeo.noop_out_interval = 0 node.conn[0].timeo.noop_out_timeout = 0 I must admit that I find it hard to imagine that an iSCSI target would reply to a NOP-out while it was processing a command such as a tape fsf or even tape erase (whose timeout is 6 * the long-timeout of 4 hours). Should perhaps the NOP-out polling be suspended while a command is being processed? Or alternatively maybe the NOP-out polling be completely disabled by default with something in the README.gz file that explains WHEN you might want it and how to enable it. It's certainly clear that (at least) the MS iSCSI initiator doesn't send NOP-out polls. open-iscsi is normally used to deal with discs. When it’s used with tape it’s not unusual to find bugs or design errors that we did not know were present. Perhaps a small blurb in the README about dealing with tape, suggesting turning NOOP/ping off. Please feel free to post a pull request on github or suggest a patch on this list. Regards Dave -- Lee Duncan "Choice means saying no to one thing so you can say yes to another." -- Dan Millman -- You received this message because you are subscribed to a topic in the Google Groups "open-iscsi" group. To unsubscribe from this topic, visit https://groups.google.com/d/topic/open-iscsi/ViC-za8eHdc/unsubscribe. To unsubscribe from this group and all its topics, send an email to open-iscsi+unsubscr...@googlegroups.com. To post to this group, send email to open-iscsi@googlegroups.com. Visit this group at https://groups.google.com/group/open-iscsi. For more options, visit https://groups.google.com/d/optout. -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To unsubscribe from this group and stop receiving emails from it, send an email to open-iscsi+unsubscr...@googlegroups.com. To post to this group, send email to open-iscsi@googlegroups.com. Visit this group at https://groups.google.com/group/open-iscsi. For more options, visit https://groups.google.com/d/optout.
