On Mon, Jun 29, 2009 at 06:55:40PM +0800, Vladislav Bolkhovitin wrote: > Ronald Moesbergen, on 06/29/2009 02:26 PM wrote: > > 2009/6/29 Wu Fengguang <fengguang.wu@xxxxxxxxx>: > >> On Sat, Jun 20, 2009 at 08:29:31PM +0800, Vladislav Bolkhovitin wrote: > >>> Wu Fengguang, on 06/20/2009 07:55 AM wrote: > >>>> On Fri, Jun 19, 2009 at 03:04:36AM +0800, Andrew Morton wrote: > >>>>> On Sun, 7 Jun 2009 06:45:38 +0800 > >>>>> Wu Fengguang <fengguang.wu@xxxxxxxxx> wrote: > >>>>> > >>>>>>>> Do you have a place where the raw blktrace data can be retrieved for > >>>>>>>> more in-depth analysis? > >>>>>>> I think your comment is really adequate. In another thread, Wu Fengguang pointed > >>>>>>> out the same issue. > >>>>>>> I and Wu also wait his analysis. > >>>>>> And do it with a large readahead size :) > >>>>>> > >>>>>> Alan, this was my analysis: > >>>>>> > >>>>>> : Hifumi, can you help retest with some large readahead size? > >>>>>> : > >>>>>> : Your readahead size (128K) is smaller than your max_sectors_kb (256K), > >>>>>> : so two readahead IO requests get merged into one real IO, that means > >>>>>> : half of the readahead requests are delayed. > >>>>>> > >>>>>> ie. two readahead requests get merged and complete together, thus the effective > >>>>>> IO size is doubled but at the same time it becomes completely synchronous IO. > >>>>>> > >>>>>> : > >>>>>> : The IO completion size goes down from 512 to 256 sectors: > >>>>>> : > >>>>>> : before patch: > >>>>>> : 8,0 3 177955 50.050313976 0 C R 8724991 + 512 [0] > >>>>>> : 8,0 3 177966 50.053380250 0 C R 8725503 + 512 [0] > >>>>>> : 8,0 3 177977 50.056970395 0 C R 8726015 + 512 [0] > >>>>>> : 8,0 3 177988 50.060326743 0 C R 8726527 + 512 [0] > >>>>>> : 8,0 3 177999 50.063922341 0 C R 8727039 + 512 [0] > >>>>>> : > >>>>>> : after patch: > >>>>>> : 8,0 3 257297 50.000760847 0 C R 9480703 + 256 [0] > >>>>>> : 8,0 3 257306 50.003034240 0 C R 9480959 + 256 [0] > >>>>>> : 8,0 3 257307 50.003076338 0 C R 9481215 + 256 [0] > >>>>>> : 8,0 3 257323 50.004774693 0 C R 9481471 + 256 [0] > >>>>>> : 8,0 3 257332 50.006865854 0 C R 9481727 + 256 [0] > >>>>>> > >>>>> I haven't sent readahead-add-blk_run_backing_dev.patch in to Linus yet > >>>>> and it's looking like 2.6.32 material, if ever. > >>>>> > >>>>> If it turns out to be wonderful, we could always ask the -stable > >>>>> maintainers to put it in 2.6.x.y I guess. > >>>> Agreed. The expected (and interesting) test on a properly configured > >>>> HW RAID has not happened yet, hence the theory remains unsupported. > >>> Hmm, do you see anything improper in the Ronald's setup (see > >>> http://sourceforge.net/mailarchive/forum.php?thread_name=a0272b440906030714g67eabc5k8f847fb1e538cc62%40mail.gmail.com&forum_name=scst-devel)? > >>> It is HW RAID based. > >> No. Ronald's HW RAID performance is reasonably good. I meant Hifumi's > >> RAID performance is too bad and may be improved by increasing the > >> readahead size, hehe. > >> > >>> As I already wrote, we can ask Ronald to perform any needed tests. > >> Thanks! Ronald's test results are: > >> > >> 231 MB/s HW RAID > >> 69.6 MB/s HW RAID + SCST > >> 89.7 MB/s HW RAID + SCST + this patch > >> > >> So this patch seem to help SCST, but again it would be better to > >> improve the SCST throughput first - it is now quite sub-optimal. > >> (Sorry for the long delay: currently I have not got an idea on > >> how to measure such timing issues.) > >> > >> And if Ronald could provide the HW RAID performance with this patch, > >> then we can confirm if this patch really makes a difference for RAID. > > > > I just tested raw HW RAID throughput with the patch applied, same > > readahead setting (512KB), and it doesn't look promising: > > > > ./blockdev-perftest -d -r /dev/cciss/c0d0 > > blocksize W W W R R R > > 67108864 -1 -1 -1 5.59686 5.4098 5.45396 > > 33554432 -1 -1 -1 6.18616 6.13232 5.96124 > > 16777216 -1 -1 -1 7.6757 7.32139 7.4966 > > 8388608 -1 -1 -1 8.82793 9.02057 9.01055 > > 4194304 -1 -1 -1 12.2289 12.6804 12.19 > > 2097152 -1 -1 -1 13.3012 13.706 14.7542 > > 1048576 -1 -1 -1 11.7577 12.3609 11.9507 > > 524288 -1 -1 -1 12.4112 12.2383 11.9105 > > 262144 -1 -1 -1 7.30687 7.4417 7.38246 > > 131072 -1 -1 -1 7.95752 7.95053 8.60796 > > 65536 -1 -1 -1 10.1282 10.1286 10.1956 > > 32768 -1 -1 -1 9.91857 9.98597 10.8421 > > 16384 -1 -1 -1 10.8267 10.8899 10.8718 > > 8192 -1 -1 -1 12.0345 12.5275 12.005 > > 4096 -1 -1 -1 15.1537 15.0771 15.1753 > > 2048 -1 -1 -1 25.432 24.8985 25.4303 > > 1024 -1 -1 -1 45.2674 45.2707 45.3504 > > 512 -1 -1 -1 87.9405 88.5047 87.4726 > > > > It dropped down to 189 MB/s. :( > > Ronald, > > Can you, please, rerun this test locally on the target with the latest > version of blockdev-perftest, which produces much more readable results, Is blockdev-perftest public available? It's not obvious from google search. > for the following 6 cases: > > 1. Default vanilla 2.6.29 kernel, default parameters, including read-ahead Why not 2.6.30? :) > 2. Default vanilla 2.6.29 kernel, 512 KB read-ahead, the rest is default How about 2MB RAID readahead size? That transforms into about 512KB per-disk readahead size. > 3. Default vanilla 2.6.29 kernel, 512 KB read-ahead, 64 KB > max_sectors_kb, the rest is default > > 4. Patched by the Fengguang's patch http://lkml.org/lkml/2009/5/21/319 > vanilla 2.6.29 kernel, default parameters, including read-ahead > > 5. Patched by the Fengguang's patch vanilla 2.6.29 kernel, 512 KB > read-ahead, the rest is default > > 6. Patched by the Fengguang's patch vanilla 2.6.29 kernel, 512 KB > read-ahead, 64 KB max_sectors_kb, the rest is default Thanks, Fengguang -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
