On Sun, Aug 10, 2014 at 10:01 PM, Chris Murphy <lists@xxxxxxxxxxxxxxxxx> wrote: > > On Aug 7, 2014, at 9:31 AM, Chris Murphy <lists@xxxxxxxxxxxxxxxxx> wrote: > >> # btrfs send /mnt/320G/2012april_HDD_fullbackup.ro.0/ | btrfs receive /mnt/500G/ >> At subvol /mnt/320G/2012april_HDD_fullbackup.ro.0/ >> At subvol 2012april_HDD_fullbackup.ro.0 >> ERROR: send ioctl failed with -12: Cannot allocate memory >> ERROR: unexpected EOF in stream. >> >> >> kernel-3.16.0-1.fc21.x86_64 >> btrfs-progs-3.14.2-3.fc21.x86_64 >> >> >> Both the source and destination were recently (< 24 hours) created with the above versions. >> >> Bug report here: >> https://bugzilla.kernel.org/show_bug.cgi?id=81781 >> >> dmesg excerpt with debug kernel here: >> https://bugzilla.kernel.org/attachment.cgi?id=145331 > > This isn't reproducible by only changing kernels to 3.14.15-100.fc19.x86_64, so it's a regression in 3.16. Hi Chris, Can you try the following patch and confirm if it helps? https://patchwork.kernel.org/patch/4705171/ > What's also interesting is the performance is much worse with 3.14 compared to 3.16. I get ~8.3MB/s with 3.14, and ~21.8MB/s with 3.16; all other factors are identical. Yes, not surprising however because 3.15/16 brought in some optimizations such as using readahead when reading file data for example. Thanks > > > Chris Murphy-- > To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html -- Filipe David Manana, "Reasonable men adapt themselves to the world. Unreasonable men adapt the world to themselves. That's why all progress depends on unreasonable men." -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
