Date: Mon, 31 Mar 2008 16:01:32 -0600 From: Scott Long <scottl@samsco.org> To: Ivan Voras <ivoras@freebsd.org> Cc: freebsd-current@freebsd.org Subject: Re: Are large RAID stripe sizes useful with FreeBSD? Message-ID: <47F15F3C.9060100@samsco.org> In-Reply-To: <9bbcef730803311434s48d3269cs1e8ae0fd1eb7ffc3@mail.gmail.com> References: <fsr7fb$hl0$1@ger.gmane.org> <47F147D8.3030905@samsco.org> <9bbcef730803311409ha25effam9dd522c9084783ad@mail.gmail.com> <47F15772.5010104@samsco.org> <9bbcef730803311434s48d3269cs1e8ae0fd1eb7ffc3@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Ivan Voras wrote: > On 31/03/2008, Scott Long <scottl@samsco.org> wrote: > >> For writes, the performance penalty of smaller I/O's (assuming no RAID-5 >> effects) is minimal; most caching controllers and drives will batch the >> concurrent requests together, so the only loss is in the slight overhead >> of the extra transaction setup and completion. For reads, the penalty >> can be greater because the controller/disk will try to execute the first >> request immediately and not wait for the second part to be requested, >> leading to the potential for extra rotational and head movement delays. >> Many caching RAID controllers offer a read-ahead feature to counteract >> this. However, while my testing has shown little measurable benefit to >> this, YMMV. > > Thank you, this is the kind of explanation I hoping for. One more > thing: is TCQ (e.g. the SCSI variant) orthogonal to this? If you have a RAID controller in front of the disks then the effects of TCQ are hidden from the OS; it might ultimately make the controller complete requests faster, but the controller already looks to the OS like a disk with a really deep queue. When you're dealing directly with the disks then TCQ/NCQ is required in order for batching of concurrent requests to occur. Scott
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?47F15F3C.9060100>