Tag Info

Hot answers tagged

14

Short answer: This is the results of network latency and a serial workload (as you imposed by using direct=1, sync=1 and iodepth=1). Long answer: using direct=1, sync=1 and iodepth=1 you created a serial workload, as new writes can not be queued before the previous write was committed and confirmed. In other word, writes submission rate strictly depend on ...


6

With SSD's the only generic recommendation is to buy the right drive for your workload. See this answer for the rationale. The warranty for the Samsung SSD 850 Pro may be ten years, but that covers mechanical failures and does not cover you when you exceed the still "somewhat limited" total write capacity limit. Associated with the failure rates and ...


2

The main advantage of hardware RAID is the protected write back cache which will boost performance when dealing with synchronized writes (eg: databases). Your should absolutely avoid RAID cards without protected write back cache, as they often are much slower than software RAID. At the same time, not all RAID controllers play well with SSDs. The main reason ...


2

NVMe is PCIe based, and using different drivers designed for that. You can essentially take an M2 formfactor NVM, pop it into the appropriate adaptor, and run it on any linux, windows or BSD system with appropriate drivers. Essentially all NVMe does is standardises PCIe based SSDs to a single set of drivers, designed to take full advantage of them. ...


2

Assuming this is a hardware RAID 1+0 and there's a controller managing the devices, just let the drive fail. Imagine this were a spinning hard disk. Do you care why or how it failed... or just that it failed? RAID controllers use a variety of parameters to determine drive and array health. S.M.A.R.T. statistics are just one element of this... But an SSD ...


2

4xSSD(512Gig) in a RAID10 you have redundancy (+) you have only 1TB of usable space (-) you have x2 speed (+) 2xSSD(1Tb) no redundancy (-) you have 2TB of usable space (+) you have normal speed (N) 2xSSD(1Tb) RAID0 no redundancy (-) you have 2TB of usable space (+) you have x2 speed (+) As for the lifetime of them, that model is pretty good, ...


1

In the documentation for Modifying a DB Instance to Use a Different Storage Type there is the following note: You cannot modify an existing SQL Server DB instance to change storage type or modify storage allocation. And as you say, you can't restore a snapshot into another storage type. I think your best option is your number 3. Export your database, ...


1

Due to how MLC SSDs work, they need a decently-sized local DRAM cache to absorb incoming writes while simultaneously write to the backing NAND. However, hardware RAID cards often disable the disk's cache and exclusively rely on own (on-card) DRAM cache. While this is not a problem with classic HDD, the intrinsic not-overwriting nature of NAND chips (and ...


1

Write capacity is one of the biggest myths surrounding SSDs, and was only really an issue with the very early drives. Most SSDs will last decades before reaching their write capacity - well beyond the useful life of any drive. See this article for more info. That said, if you really want to check how much data has been written to an SSD, you should be able ...


1

My two cents... NVMe got the various SSD mfg to focus on and adopt a base standard... Basically you can get Nand Flash performance from an SSD connected to NVMe servers for NET less. Also their is more NVMe over fabric features (that I am not that familiar with yet) See https://www.brighttalk.com/webcast/663/132761 Content "The Performance Impact of NVMe ...


1

Nope. HP controllers don't offer a mixed mode like what you're asking for. Which specific server model (and storage controller) are you planning to use? If you buy a DL3x0p series Gen8 server with an onboard P-series RAID controller, there is a secret "HBA" mode that will disable all RAID features. If you buy a DL3x0e series, there are some messy storage ...


1

Linux software RAID (md) supports passing discard ops down to its components. When those components are SATA devices, they turn into ATA TRIM commands. See for example: Implementing Linux fstrim on SSD with software md-raid Depending on your access pattern, 2x SSDs concatenated could be as fast as RAID0. e.g. random IO scattered across the entire disk ...



Only top voted, non community-wiki answers of a minimum length are eligible