Re: LTO-4 iSCSI performance less than expected ...

Of course it turns out the data for that test was highly compressible. So the actual speed over the network was around 33-40MB/s Rumour has it that the Jumbo Frame capable ethernet cards arrive today. I'll let U know if that changes anything. Dave -- You received this message because you

Re: LTO-4 iSCSI performance less than expected ...

Well that was interesting - I booted up the application I used for BU of my Windows systems and used that to backup this Linux box over the network to the iSCSI connected drive. Result using SW compression I was getting about 90-130MB/s So confused why dd etc. was so darn slow ... Dave On

Re: LTO-4 iSCSI performance less than expected ...

Before doing the dd I issued: mt-st -f /dev/st0l setblk 65536 stsetoptions 0x8000 which was happily accepted, but it made no difference to the throughput. Looking at the server hosting the tape, the network was only running at about 37% capacity (32MB/s). Zipping the output of dd and writing

Re: LTO-4 iSCSI performance less than expected ...

Thanks Lee, It would appear that stoptions and setstoptiosn are synonyms. 35 is the command code for MTWEOFI not the mask for enabling it as you say. I misread the header file. So yes 0x8000 seems to be correct. I'll give it a try. Dave -- You received this message because you are

Re: LTO-4 iSCSI performance less than expected ...

On Friday, April 14, 2017 at 4:31:05 AM UTC-7, david.partri...@perdrix.co.uk wrote: > > Let's try another tack. > > Will "mt-st -f /dev/st0l /stoptions 35" turn on MTWEOFI? > > Dave > Hi Dave: I don't know. I download mt-st, which I've never seen before, and perhaps you mean: > # mt-st -f

Re: LTO-4 iSCSI performance less than expected ...

Let's try another tack. Will "mt-st -f /dev/st0l /stoptions 35" turn on MTWEOFI? Dave -- 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

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

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

Re: LTO-4 iSCSI performance less than expected ...

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? > -- 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,

Re: LTO-4 iSCSI performance less than expected ...

On Monday, March 27, 2017 at 9:03:59 AM UTC-7, david.partri...@perdrix.co.uk wrote: > > I'm connecting my Linux server to an LTO-4 tape drive over a 1 gigabit LAN > with very little other activity. > > Doing some hand waving, I guess that I should allow ten bits per byte and > a protocol

Re: LTO-4 iSCSI performance less than expected ...

Hi there, Uli, Yes I did listen to the drive - no it wasn't shoe-shining. DD direct gave a slightly slower throughput. Dave -- 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,

Antw: LTO-4 iSCSI performance less than expected ...

>>> schrieb am 27.03.2017 um 18:03 in Nachricht : > I'm connecting my Linux server to an LTO-4 tape drive over a 1 gigabit LAN > with very little other activity. > > Doing some hand waving, I guess that I

LTO-4 iSCSI performance less than expected ...

I'm connecting my Linux server to an LTO-4 tape drive over a 1 gigabit LAN with very little other activity. Doing some hand waving, I guess that I should allow ten bits per byte and a protocol overhead of around 40%. That gets me to about 60MB/s which I know is about half what the drive is