[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAK2Ky6yg6bShW5nsw5k08yrNeNcRWDqyr07q4B4nB99Z+g6UCQ@mail.gmail.com>
Date: Fri, 15 Nov 2013 13:45:11 +0800
From: 韩磊 <bonben1989@...il.com>
To: Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: A problem about IO scheduler in kernel
These days I was programming about IO scheduler called
"Simple_Deadline" in kernel.
"Simple_Deadline" is based on "deadline-iosched".The algorithm is very
simple.It have two lists,one is read,the other is write.A request
enter lists based its weight which count accord to the request's
size,read or write. And when dispatch a request just compare the
weight between read list and write list,the smaller one dispatches.
When I modprobe this module and run it,if a bit of IO come,it works
well.But when runs a large number IO,the system will crash. Can you
help me to find the problem? I am so sad and helpless about it.
When system crashed,the screen display some information:
Message from syslogd@han at Nov 15 13:12:03 ...
kernel:------------[ cut here ]------------
Message from syslogd@han at Nov 15 13:12:03 ...
kernel:invalid opcode: 0000 [#1] SMP
Message from syslogd@han at Nov 15 13:12:03 ...
kernel:last sysfs file:
/sys/devices/pci0000:00/0000:00:04.0/0000:05:00.0/host0/port-0:0/end_device-0:0/target0:0:0/0:0:0:0/block/sda/queue/scheduler
Message from syslogd@han at Nov 15 13:12:03 ...
kernel:Stack:
Message from syslogd@han at Nov 15 13:12:03 ...
kernel:Call Trace:
Message from syslogd@han at Nov 15 13:12:03 ...
kernel:Code: 2a 48 89 fe 4c 89 e7 e8 35 ff 01 00 48 8b 83 80 00 00 00
83 e0 03 4c 09 e0 4c 8b 64 24 08 48 89 83 80 00 00 00 48 8b 1c 24 c9
c3 <0f> 0b eb fe 66 90 55 48 89 e5 0f 1f 44 00 00 45 31 c0 48 89 f9
The code in accessory! Please help find the bugs! Thank you!
View attachment "deadline_simple-iosched.c" of type "text/x-csrc" (15650 bytes)
Powered by blists - more mailing lists