varun-r-mallya/sysprof
1
0
Fork 0
mirror of https://github.com/varun-r-mallya/sysprof.git synced 2026-02-11 07:30:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make it compile with kernel 2.6.11

Browse Source 
Tue Apr  5 14:34:43 2005  Søren Sandmann  <sandmann@redhat.com>

	* sysprof-module.c (x_access_process_vm): Make it compile with
	kernel 2.6.11

	* TODO: updates
This commit is contained in:
Søren Sandmann
2005-04-05 18:37:13 +00:00
committed by Søren Sandmann Pedersen
parent 4a4a5fc5ca
commit 700cf9c967
3 changed files with 20 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
ChangeLog
View File

@ -1,3 +1,10 @@
Tue Apr 5 14:34:43 2005 Søren Sandmann <sandmann@redhat.com>
* sysprof-module.c (x_access_process_vm): Make it compile with
kernel 2.6.11
* TODO: updates
Mon Apr 4 00:57:11 2005 Soeren Sandmann <sandmann@redhat.com> Mon Apr 4 00:57:11 2005 Soeren Sandmann <sandmann@redhat.com>
* sysprof.c: Busy cursors in many more places. * sysprof.c: Busy cursors in many more places.

11
TODO
View File

@ -27,6 +27,11 @@ Before 1.0:
Before 1.2: Before 1.2:
- Make busy cursors more intelligent
- when you click something in the main list and we don't respond
within 50ms (or perhaps when we expect to not be able to do
so (can we know the size in advance?))
- instead of as we do now: set the busy cursor unconditionally
- Reorganise stackstash and profile - Reorganise stackstash and profile
- stackstash should just take traces of addresses without knowing - stackstash should just take traces of addresses without knowing
@ -116,13 +121,13 @@ Later:
call malloc(), couldn't call printf(), etc. call malloc(), couldn't call printf(), etc.
- figure out a way to deal with both disk and CPU. Need to make sure that - figure out a way to deal with both disk and CPU. Need to make sure that
things that are UNINTERRUPTIBLE while there are RUNNING tasks is not things that are UNINTERRUPTIBLE while there are RUNNING tasks are not
consider bad. considered bad.
Not entirely clear that the sysprof visualization is right for disk. Not entirely clear that the sysprof visualization is right for disk.
Maybe assign a size of n to traces with n *unique* disk access (ie. Maybe assign a size of n to traces with n *unique* disk access (ie.
disk accesses that are not made by any other stack trace). disk accesses that are not required by any other stack trace).
Or assign values to nodes in the calltree based on how many diskaccesses Or assign values to nodes in the calltree based on how many diskaccesses
are contained in that tree. Ie., if I get rid of this branch, how many are contained in that tree. Ie., if I get rid of this branch, how many

5
sysprof-module.c
View File

@ -17,6 +17,7 @@
#include "sysprof-module.h" #include "sysprof-module.h"
#include <linux/version.h>
MODULE_LICENSE("GPL"); MODULE_LICENSE("GPL");
MODULE_AUTHOR("Soeren Sandmann (sandmann@daimi.au.dk)"); MODULE_AUTHOR("Soeren Sandmann (sandmann@daimi.au.dk)");
@ -115,8 +116,12 @@ static int x_access_process_vm(struct task_struct *tsk, unsigned long addr, void
if (bytes > PAGE_SIZE-offset) if (bytes > PAGE_SIZE-offset)
bytes = PAGE_SIZE-offset; bytes = PAGE_SIZE-offset;
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,11)
flush_cache_page(vma, addr); flush_cache_page(vma, addr);
#endif
maddr = kmap(page); maddr = kmap(page);
if (write) { if (write) {
copy_to_user_page(vma, page, addr, copy_to_user_page(vma, page, addr,