suggested parameters? not sure, but i found a few links: http://www.mjmwired.net/kernel/Documentation/filesystems/ext4.txt===>official list of parameters here.
http://www.kernel.org/pub/linux/kernel/people/christoph/largeblocksize/4/overview==> RATIONALIZING on large blocksize. but this is only v4. At v7, the following patch it larger than the hardware can support (memmap): http://lkml.indiana.edu/hypermail/linux/kernel/0709.1/0708.html On Apr 8, 6:05 pm, shnaxe <shn...@gmail.com> wrote: > On Apr 8, 5:32 pm, shnaxe <shn...@gmail.com> wrote: > > > ... > > since i use a 64bit version on a 64bit system i should be able to use > > larger blocks (have to check the pagesize again...), ext4 allows > > blocks to be up to 64kb instead of only 4kb. > > > also when running mkfs.ext4 without any filesystem-type specified a > > blocksize of 4096 is chosen, so i wonder if i should manually override > > this to lets say 16384 or even 32768 and lower the number of inodes > > accordingly (/4 or /8)? > > ah, well at least this issue has been cleared; i was at first > surprised to see that 'getconf PAGE_SIZE' returns 4096 running a 64bit > linux on a system with a 64bit amd-cpu (note: blocksize must not > exceed the sysstems pageesize!). > so i read a bit further into various discussions about pagesizes and > came to realize that amd's 64bit processors were also designed for 4k > pages. > > its summed up on two postings i found: > > Chris Snook posted to the linux-kernel mailing-list of vger.kernel.org > on Nov 12 2007: > "PAGE_SIZE is highly architecture-dependent. While it is true that 4K > pages are typical on 32-bit architectures, and 64-bit architectures > have historically introduced 8K pages, this is by no means a > requirement. x86_64 uses the same page sizes that are available on > i686+PAE, so you get 4K base pages. alpha and sparc64 typically use 8K > base pages, though they have other options as well. ia64 defaults to > 16K, though it can do 4K, 8K, and a bunch of larger base sizes. ppc64 > does 4K and 64K. s390 uses 4K base pages in both 31-bit and 64-bit > kernels. If x86_64 processors are released with TLBs that can handle > 8K pages, it'll be straightforward to add that feature, but otherwise > it would require faking it in software, which has lots of pitfalls and > does nothing to improve TLB efficiency." > > Helge Hafting replied there on Nov 13 2007: > "...there are no connection at all between the page size and > the number of bits the processor uses. > > The cpu designer simply makes independent decisions for both cases. > So i386 uses 4kB pages because intel designed their processor that > way. > And x86_64 uses 4kB pages because AMD designed the architecture that > way. > And some processors use 8kB or 16kB pages because that is how they > work. > A few processors offer a selection of page sizes, it is then up to the > architecture maintainer to make a choice between them. No such choice > exists for intel/amd, unless you count the unrealistic option > of using generic 2MB pages. > > Having said that, it is possible to get a feel of what a 8kB page > system will be like on intel, by always allocating pages in pairs." > > so well, i guess i'll have to stick to a blocksize of 4kb. > but still at least one thing remains: > > > another question is if keeping the number of inodes rather small etc > > makes still sense with ext4, but i don't see a reason why this > > shouldn't be the case.
