I have been waiting for caching fixes related to LSFS since April. Supposedly the fixes are in coming soon.

L1 cache working great is news to me. It slows our LSFS targets by a factor 5-10 in the current build.

I agree, most builds of v6 were reliable as an anvil. This v8 reminds me of 6 years ago when they announced 5.0 HA. We became Starwind partners and made the mistake of adopting that right away and lost an entire production Exchange system.

They have kept me updated with status, but fixes are still in development. I have taken the system out of production while we wait.

I will be extremely nervous to trust the system with production loads going forward though.

I have sent in all logs requested multiple times. So I don't believe you are waiting on me for anything. I would offer a word of caution to anyone considering the latest build of Virtual SAN. We currently lose multiple access rules upon service restart or node reboot, causing iSCSI initiators in our...

Tickets, submitted again.

Thanks,
Kurt

Far from it. I can only get decent performance from LSFS if L1 and L2 cache are disabled. I submitted an email about one of my HA nodes completely dropping two devices with just a reboot. And now every time I restart either node I lose portions of my initiator access rules.

Upgraded to the latest version and created a new LSFS Dedup HA target. Write performance went down to 200-300 iops for 4K random/sequential write mix. 64K pure sequential write performance dropped to 10MB/s. Those are unusable numbers. Read performance is still 10000 iops for 4K mix and 1700MB/s for...

The build posted today mentions issues with L2. Should I stay away from it for now? Also, is dedup safe now?

Interesting, how does Starwind track what should be pulled or kept in L2 cache then?

Do you recommend Write Back or Write through on L2 SSD cache. The SSD's are Samsung 845DC EVO's rated at 30% of total drive size writes per day.

Anatoly (staff) wrote:That sounds like a good plan!
You may consider using part of Flash as L2 cache actually.

As part of the spinning disk LSFS targets? If so how much?

RAID5 is disk, RAID0 is flash. We were going to put the LSFS on the spinning disk and standard thick images on the SSD's.

Testing was two HP servers running 2012 R2 with multiple clustered LSFS dedup targets connected to Windows Hyper-V hosts running a myriad of low cluster size random and large cluster size sequential iometer and atto tests. -16 cores per host -20GB of RAM per host -RAID5 and RAID0 SSD (just to compar...

We are redeploying our 4TB HA license as v8 from v6 on different hardware. In our testing LSFS with deduplication had much greater performance than the existing installation. I have noticed on the forums some concerns with LSFS taking up two much disk space, taking forever to start a node after rebo...