| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAMP44s0u3-=umxue1Oo=1C1MnQ8AbWeL2P3N_S8A5BK4NRwX2w@mail.gmail.com> Date: Thu, 10 May 2012 10:24:28 +0200 From: Felipe Contreras <felipe.contreras@...il.com> To: Arnd Bergmann <arnd@...db.de> Cc: Linux Kernel Mailing List <linux-kernel@...r.kernel.org> Subject: Re: Big I/O latencies, except when iotop is hooked On Wed, May 9, 2012 at 7:56 PM, Arnd Bergmann <arnd@...db.de> wrote: > The first thing you should check is whether the partitions are > properly aligned, using 'fdisk -l -u /dev/sdX'. I aligned it to 4MiB, it doesn't make much of a difference. > Of course none of this will tell you why iotop makes any difference. After trying a bit more I can still see the problem with iotop, I could swear it happens much less often, but I can't really be sure now. I tried with different io schedulers, and it seems cfq does better, I also tried different priorities, but the issue was still there. I also tried to setup the crypto partition with align-payload, to no avail, and to get rid of crypto altogether. I also tried with multiple ext4 format options, but they seemed to make matters worst. I finally tried on a normal disk device, and it works perfectly there (even with encryption); so the issue happens only on SSD/usb key. Cheers. -- Felipe Contreras -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@...r.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists