Recent content by anthem00

I don't have a benchmark for it, but the "response" while using it seems to corroborate. What I'm talking about is this - if you don't specify a ZIL, ZFS will do this automatically, but it will carve out a section in your main zdev to do it. My understanding is that it will write out to this...

sync=disabled is a necessary option if not using ZIL. However, the ZIL gives you a performance boost as well and lays things out for the drives better. Basically by aggregating all the writes (essentially in memory), and then batch writing them out, the drives basically get used more in...

If you are that concerned with CPU, stick with the 1366 DP chipset. Then you can always drop the second xeon chip in there. I would perhaps stick with the lower tdW chips (maybe 80 or 95W chips rather than the higher wattage ones). ZFS really doesn't utilize that much cpu in the overall...

Honestly, I'd skip the SSD for ESXi and OI. I have higher failures with SSD than normal drives for machines that stay on perpetually. It's not a big performance gain. If you're power is stable then a small traditional drive is just as good for ESXi. ESXi can essentially be booted from...

how hard were you running the stress tests ? Nexenta reported (and we have had it happen twice), when you pound on a set of sata drives connected to SAS chain, not sure if its the sas expander or something to do with the sata signalling, but ALL the drives go offline (or in error). Luckily we...

zfs can easily run on 4gb of memory. It will also use everything you can throw at it (96, 192, 255gb, etc). It uses all the memory in the system minus 1gb as a first level read cache. So, while it can utilize that, it doesn't necessarily have to have it. Cpu - it isn't very cpu intensive, so...

Thats pretty funny. The OP wants a "free" solution and this is for what - a 20-30K solution. . . :-). Might as well recommend EMC at that point. . .

Are you sure you aren't network bandwidth constrained here ? Local speed is capable of anything, but it sounds like you're using Intel ET gigabit interconnects - which means its 1GB from a host to a SAN. 1Gbit/sec at wire speed is approximately 120 megabytes - which is what you are reporting...

Depends on what you are using it for. If you are using raidz/2 vdevs then generally you're looking at more archival/WORM/lower iops activities (there are some ways to cheat that, but thats another point). In terms of varying sizes, I personally don't feel it's a big deal. You do have to make...

Actually that 1gb/tb of storage isn't really correct. That is only if you plan on running deduplication to hold the dedup tables. .. I've seen some very well performing zfs setups with 4gb total ram. Will ZFS use every big of ram you throw at it ? Yes, but so will any other decent data...

Depends on what the home user is doing.. . I would argue that certain home users do need those enterprise features and should invest in nearline drives over sata drives. . I would also argue that (assuming RAFF does help), that any home user that have drives in a high density configuration...

RAFF is for high concentration drive chassis to counter the effect of rotational vibration. Now, how does that not affect certain home users who are building high density storage platforms using SM, Chenbro, Norco chassis ???? I would argue that you have to look at the application and not just...

at that point you're talking SAS. Not even enterprise SATA.

One should expand on this a bit though. I agree for the most part but maybe we should look at the application rather than the marketplace (consumer vs enterprise). If the application that you are using it (high intensity raid, large SAN, VM, etc) then your needs are different than a normal...

Unfortunately the price of Enterprise grade drives is not just a "little" to some. I believe for the 3tb SATA drives are at 180 or so. The same enterprise Constellation ES.2 is close to double (330). Do I agree with the above posters that it is worth it - absolutely. Do I run enterprise...