Storevirtual 3200 Latency Issue

[Johannes_we]

I have that latency issue as well but with a box that´s running SSD and NL but a volume that is AO permitted so all of it is kept in the SSD Tier.

But i still dont get more than ~100MB/s out of it when testing a vmdk on a iSCSI VMFS...

[GuillaumeRainer]

just to figure out some bits: a friend of mine (I worked as something like a presales consultant at HP at some time 12 years ago), brought up the SV3200 initially had some problems doing 802.3ad bonding.

I was puzzled, because we did 802.3ad because it was dog slow on regular ALB bonding. Since the first 13.1 update, we have always had active-active bonding; currently, I'm trying to talk our network guys to disable the portchannel to do yet another performance test, this time on ALB.

So, are you using ALB or 802.3ad/LACP on your 10G interfaces ? 

[referencepoint]

I have tried ALB, active-passive and 802.3ad on 10GbE. Performance seems to be equally poor, regardless of what I choose.

[Johannes_we]

I´m using ALB

[GuillaumeRainer]

thx, to me it also seemed as if the bond type doesn't really matter.

any news on the calls ?

[SVprodmgr]

Here is a quick update on the concerns.   The StoreVirtual engineering team is working on performance related issues posted here and those fed in through our Technical Support organization.  We recently released the StoreVirtual DSM for Microsoft and this is showing improvement for Windows hosts.    We are working a couple other items and are anticipating a software update shortely.  HPE Technical Support is planning a sweep through open cases starting next week to make customers aware of available fixes and status on pending items.    It is important that customer issues related to SV3200 performance have an open HPE Case Number.  This will insure they get a call during this and subsequent call sweeps.   We appreciate your support and patience.

 Amy Mitchell

HPE StoreVirtual Product Manager

[GuillaumeRainer]

In all due honesty - we are talking about an SSD tier which should have ~1msec latency; SV3200 is running 27msec and showing up to 665msec. It is not about performance, but rather the complete and utter lack thereof in combination with vmware.
Since the array we all bought is under standard warranty (or more) and does not work "as designed" in some decent fashion, every owner should indeed have an open trouble ticket. 

What´s bugging me is tickets are held back in level2 (hello, india) with some bogus claims of not having enough performance data or other. trying out RDM, VMFS, RDM+ATS, RDM+ATS+RRqueue, then VMFS+ATS+RRqueue, re-discussing if VMFS is really needed, ...
so, if the array was really working fine at hp labs, there should easily be some walkthrough, a list of tuneables and a performance sheet readily available. Instead, I have been doing benchmarks for three months and the only replies I get in some timely fashion are comments in this thread - at least they are entertaining, much more so than the phone support introducing you to yet another round of "let´s benchmark the world to be a better place". 

So, when is the software update due ? the same goes for the DSM (the array should give a decent performance without it in the first place, but...), which I heard of in November already. 

[mtroper]

Hi Amy

Same issues here. Write latency is way to high. Support ticked 5319837770 is logged.

(all possible fixes were already tried (disable ATM, disable ACK, Path policies, ect)

Unfortunatly Ive get no answer from HP support.... (case is logged since 4 days. not a single reply)

If you tell people to log a support case, you should at least anser their cases with the actual status of investigation!

[GuillaumeRainer]

Dear Amy,

I had 3 hours of benchmarking yesterday (using a windows virtual machine with iometer), just to find out copying data to a vmfs LUN happens at around 9-12 MB/sec.
I can only repeat what I told the supporter: Put a proliant, an hp/10g switch, the hp vmware image and an SV3200 together and measure VMFS performance. If it works out at xxxK IOPs / low latency, we could compare the setup and try to figure out what may be different. If not, it would be the perfect starting point to find out what doesn't work out...

Since the cases are currently not put to L3 and just kept in the loop waiting for news, my hopes for the big change are pretty nil. case 5315737219 (6 months ago) yielded no results since the wrong benchmarks showed acceptable numbers and the current call chain 5319053973 is stuck somewhere between L2 and L3 waiting for me to provide yet another round of config data on how my servers are doing. Sorry, I want reference numbers and at least some starting point instead of being blocked waiting for Godot.

[referencepoint]

These are the kind of figures I'm seeing too. My cases 5318573642 and 5318573642 aren't going anywhere at the moment, and I'm actively persuing getting the unit returned and possibly exchanged for an alternative storage appliance. Currently we have spent over 6 months configuring this new setup and are nowhere. We are wasting a lot of time and money.