Page 1 of 4
LSFS Production ready?
Posted: Sun Mar 01, 2015 10:38 pm
by camealy
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 reboot (creating?), getting stuck on resync, etc. Having used StarWind since v4 I am scared to use new features earlier in their release cycle.
Do the benefits of LSFS come at the cost of reliability? Should we use dedup?
Thanks!
Kurt
Re: LSFS Production ready?
Posted: Mon Mar 02, 2015 4:33 pm
by fbifido
Can you give a little detail on the testing you did, including your hardware spec and setup ?
Thanks.
Re: LSFS Production ready?
Posted: Mon Mar 02, 2015 4:38 pm
by camealy
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 compare the two in performance)
-Two 10Gbe crossover sync and heartbeat paths
-Two 10Gbase-T iSCSI paths through Nexus 5K and 2K fabric
Re: LSFS Production ready?
Posted: Fri Mar 06, 2015 4:13 pm
by Anatoly (staff)
quick double-check - so you are running with All-Flash, correct?
Re: LSFS Production ready?
Posted: Fri Mar 06, 2015 4:37 pm
by camealy
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.
Re: LSFS Production ready?
Posted: Tue Mar 10, 2015 5:57 pm
by Anatoly (staff)
That sounds like a good plan!
You may consider using part of Flash as L2 cache actually.
Re: LSFS Production ready?
Posted: Tue Mar 10, 2015 6:40 pm
by camealy
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?
Re: LSFS Production ready?
Posted: Tue Mar 10, 2015 7:19 pm
by Anatoly (staff)
Usually we recommend the L2 Flash cache size would be ~10% of the HA storage size (i.e. 100Gb for 1TB).
Re: LSFS Production ready?
Posted: Tue Mar 10, 2015 9:18 pm
by camealy
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.
Re: LSFS Production ready?
Posted: Thu Mar 12, 2015 4:22 pm
by Anatoly (staff)
We recommend Write-Through mode for L2
Re: LSFS Production ready?
Posted: Thu Mar 12, 2015 4:29 pm
by camealy
Interesting, how does Starwind track what should be pulled or kept in L2 cache then?
Re: LSFS Production ready?
Posted: Tue Mar 17, 2015 7:03 pm
by Anatoly (staff)
Well, it works using LRU (Least Recently Used) algorithm, which basically discards the least recently used items first.
Re: LSFS Production ready?
Posted: Tue Mar 31, 2015 8:31 pm
by camealy
The build posted today mentions issues with L2. Should I stay away from it for now? Also, is dedup safe now?
Re: LSFS Production ready?
Posted: Wed Apr 01, 2015 2:04 pm
by Vladislav (Staff)
You are welcome to use latest build, but L2 cache will be disabled. Dedup should be ok.
Re: LSFS Production ready?
Posted: Wed Apr 01, 2015 2:45 pm
by camealy
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 64K sequential read.
Is this a result of LSFS changes or is something wrong with my deployment?