Re: Map syscall nr to syscall name
Found something easier:
syscallent.sh ( similar to used by strace )
-
cat ${1+"$@"} |
sed -n 's/^#[ ]*define[ ][ ]*SYS_\([^ ]*\)[
]*[^0-9]*\([0-9]*\).*$/\1 \2/p
s/^#[ ]*define[ ][ ]*__NR_\([^ ]*\)[
]*[^0-9]*\([0-9]*\).*$/\1 \2/p
s/^#[ ]*define[ ][ ]*__NR_\([^ ]*\)[ ]*[^0-9()]*(__NR_Linux +
\([0-9]*\))$/\1 \2/p' |
sort -k2n | uniq |
awk '
BEGIN {
h = "#ifndef _H_SYSCALLENT\n#define
_H_SYSCALLENT\nchar *syscalls[] = { "
print h
}
{
s = "\"" $1 "\","
print s
}
END {
f = " };\n#endif"
print f
}
'
-
This creates header file:
#ifndef _H_SYSCALLENT
#define _H_SYSCALLENT
char *syscalls[] = {
"read",
"write",
"open",
"close",
"stat",
"fstat",
"lstat",
"poll",
"lseek",
"mmap",
..
.
...
}
#endif
-
included in makefile:
ARCH := $(shell getconf LONG_BIT)
ifeq ($(ARCH),64)
./syscallent.sh /usr/include/asm/unistd_64.h > $(INCDIR)/syscallent.h
else
./syscallent.sh /usr/include/asm/unistd_32.h > $(INCDIR)/syscallent.h
endif
-
Works fine for me. Just want to know if this will be portable method
and won't produce wrong result in any case.?
___
Kernelnewbies mailing list
Kernelnewbies@kernelnewbies.org
http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Map syscall nr to syscall name
> What arch? Try x86 , but looking for portable solution. > http://lxr.free-electrons.com/source/arch/x86/syscalls/syscall_64.tbl For my arch this is helpful. Thank you ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
reading dynamic array fields in ftrace
hi, some of the events in ftrace have dynamic array fields. Like : field:__data_loc char[] arg1; offset:24; size:4; signed:1; If i am sampling this particular event using perf_event_open(), how do i read this field i tried: #define get_str(field) (char *)get_dynamic_array(field) #define get_dynamic_array(field) \ ((void *)data + (data->__data_loc_##field & 0x)) as done in include/trace/ftrace,h But it gives garble data. TID:28578 PID:28578 TIME:258203626722378 CPU:4 Filename: ^\~@b�^O~H��^H�^? Will appreciate any help. Thanks -sahil ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Map syscall nr to syscall name
Hi all I am looking for an efficient way to convert syscall number to syscall name. I can get syscall number by enabling profiling using perf_event_open(), but cant find way to convert it to actual syscall name. Thanks --sahil ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Network Device Driver Interface
Hi I enabled sampling on net_dev_queue and net_dev_xmit using perf_event_open(). This is what i get for cmd: ping google.com -c 1 TID:21608 PID:21608 TIME:1022501870535899 CPU:5 DEV_QUEUE Skb: 0x880fc6389000 Len:98 TID:21608 PID:21608 TIME:1022501870541280 CPU:5 DEV_QUEUE Skb: 0x880fc6389000 Len:98 TID:21608 PID:21608 TIME:1022501870119689 CPU:7 DEV_QUEUE Skb: 0x880fc6389000 Len:70 TID:21608 PID:21608 TIME:1022501902225838 CPU:5 DEV_QUEUE Skb: 0x880fc4156100 Len:86 TID:21608 PID:21608 TIME:1022501870128677 CPU:7 DEV_XMIT Skb: 0x880fc6389000 Len:70 Ret:0 TID:21608 PID:21608 TIME:1022501870545283 CPU:5 DEV_XMIT Skb: 0x880fc6389000 Len:98 Ret:0 TID:21608 PID:21608 TIME:1022501870547378 CPU:5 DEV_XMIT Skb: 0x880fc6389000 Len:98 Ret:0 TID:21608 PID:21608 TIME:102250190223 CPU:5 DEV_XMIT Skb: 0x880fc4156100 Len:86 Ret:0 TID:21608 PID:21608 TIME:1022501870132327 CPU:7 DEV_RECV Skb: 0x880fc6389000 Len: 56 TID:21608 PID:21608 TIME:1022501902235039 CPU:5 DEV_RECV Skb: 0x880fc4156100 Len: 72 TID:21608 PID:21608 TIME:1022501870125880 CPU:7 DEV_RX Skb: 0x880fc6389000 Len: 56 TID:21608 PID:21608 TIME:1022501902229768 CPU:5 DEV_RX Skb: 0x880fc4156100 Len: 72 Here, net_dev_queue is called multiple times for same skb with changed length. What i understood till now reading this: http://www.cubrid.org/blog/dev-platform/understanding-tcp-ip-network-stack/ was that skb received by device driver from IP layer is queued by __dev_queue_xmit(): tracepoint net_dev_queue() exist here and transmitted to network device by dev_hard_start_xmit(): tracepoint net_dev_xmit() exist here. So, what is making it to queue skb again and what data it is adding to skb.? Thanks Regards ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Links to understand File System
Very useful. Thank you. ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Links to understand File System
Hi all, I am reading Understanding the linux kernel CH15(ext2 and ext3 file systems) and have even started implementation of File system from scratch for learning purpose by following this : https://github.com/psankar/simplefs Any leads on other links/papers to understand VFS->FS->disk flow better.? Thank you Sahil ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Eudyptula challenge
On Wed, Mar 25, 2015 at 10:55:34AM -0500, Jonathan Jin wrote: > Doesn't matter; those are the rules of the Challenge, for better or > worse. It seems as though any mention of Challenge specifics is enough > to get participants removed, period. I started again from first challenge. > It's much better to find the "root" of the problem that you are trying > to solve -- that is, the parts of the problem that, in this case, have > nothing directly to do with the Eudyptula Challenge itself -- and ask > about that, rather than ask about the logistical specifics of the > Challenge like you did. > > By the way, don't top-post. See: > http://kernelnewbies.org/mailinglistguidelines Yeah that makes sense actually. Thank you Jonathan. ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Eudyptula challenge
Got removed :( i wasn't asking for implementation help :( On 25 March 2015 at 19:25, Giedrius Statkevičius wrote: > On 2015.03.25 15:22, sahil aggarwal wrote: >> Hi all, >> >> I am on task5, little says to read ch 14 (device model) of LDD3 but ch >> 13 (USB driver) seems to be the one i should read. I have already been >> following this book and reached ch5, would it be ok to jump to ch >> 13/14 directly.? >> >> Moreover reading /Documentation/usb/hotplug.txt seems to help me >> solving the challenge. So should i read ch 13/14 of continue reading >> in order.? > > Don't ask for help with eudyptula challenge on mailing lists. You may be > removed from the challenge. > > -- > With regards / Su pagarba, > Giedrius ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Eudyptula challenge
Hi all, I am on task5, little says to read ch 14 (device model) of LDD3 but ch 13 (USB driver) seems to be the one i should read. I have already been following this book and reached ch5, would it be ok to jump to ch 13/14 directly.? Moreover reading /Documentation/usb/hotplug.txt seems to help me solving the challenge. So should i read ch 13/14 of continue reading in order.? Thanks Regards ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Scull Driver - Read
Hi Pranay
Thanks a lot. That cleared it all.
On 21 March 2015 at 13:45, Pranay Srivastava wrote:
> Hi Sahil
>
> On Fri, Mar 20, 2015 at 6:14 PM, sahil aggarwal wrote:
>> Does it mean that in kernel space the direction bitfields are reversed.?
>
> No it doesn't mean that.
>
>>
>> On 20 March 2015 at 18:12, sahil aggarwal wrote:
>>> Hi Pranay,
>>>
>>> Can you help me with this too.? In case of _IOC_READ why VERIFY_WRITE
>>> and in case of _IOC_WRITE why VERIFY_READ.? . Book says its kernel
>>> oriented so concept of read and write is reversed.
>>>
>>> if(_IOC_DIR(cmd) & _IOC_READ)
>>> err = !access_ok(VERIFY_WRITE, (void __user*)arg, _IOC_SIZE(cmd));
>>> else if(_IOC_DIR(cmd) & _IOC_WRITE)
>>> err = !access_ok(VERIFY_READ, (void __user*)arg, _IOC_SIZE(cmd));
>>> if(err)
>>> return -EFAULT;
>>>
>>> Thanks
>>> Regards
>>>
>>>
>>>
>>>
>>>
>>>
>>> On 20 March 2015 at 12:36, sahil aggarwal wrote:
>>>> Hi Pranay
>>>>
>>>> Well explained.
>>>>
>>>> Thank you.
>>>>
>>>> On 20 March 2015 at 11:46, Pranay Srivastava wrote:
>>>>> Hi Sahil
>>>>>
>>>>> On Sun, Mar 15, 2015 at 10:17 AM, sahil aggarwal
>>>>> wrote:
>>>>>> hi all,
>>>>>>
>>>>>> Going through scull driver code, i see read function reads only till
>>>>>> end of 1 quantum, so do kernel call read multiple times if count from
>>>>>> q_pos exceeds quantum size limit.?
>>>>>>
>>>>>>
>>>>>> Ref: ldd3.
>>>>>>
>>>>>> if(count > quantum - q_pos)
>>>>>> count = quantum - q_pos;
>>>>>> if(copy_to_user(buf, dptr->data[s_pos] + q_pos,count)){
>>>>>> retval = -EFAULT;
>>>>>> goto out;
>>>>>> }
>>>>>
>>>>> If you are not using the default read/write routines, then its up to
>>>>> you to code that.
>>>>>
>>>>> Kernel doesn't do multiple read calls. It'll do only what you asked it
>>>>> for no more but it can do less. For example, a file is say 100 KiB and
>>>>> you are reading say 4KiB in a loop when do you stop?
>>>>>
>>>>> Simply put it's the user space application which is doing the looping
>>>>> and repeatedly doing read calls because it assumes that file isn't
>>>>> finished.
>>>>>
>>>>> So again when do you stop reading from the file, without knowing size
>>>>> of the file.?
>>>>>
>>>>>> *f_pos += count;
>>>>>> retval = count;
>>>>>>
>>>>>> Thanks
>>>>>> Regards
>>>>>>
>>>>>> ___
>>>>>> Kernelnewbies mailing list
>>>>>> Kernelnewbies@kernelnewbies.org
>>>>>> http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
>>>>>
>>>>>
>>>>>
>>>>> --
>>>>> ---P.K.S
>
>
>
> --
> ---P.K.S
___
Kernelnewbies mailing list
Kernelnewbies@kernelnewbies.org
http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Scull Driver - Read
Does it mean that in kernel space the direction bitfields are reversed.?
On 20 March 2015 at 18:12, sahil aggarwal wrote:
> Hi Pranay,
>
> Can you help me with this too.? In case of _IOC_READ why VERIFY_WRITE
> and in case of _IOC_WRITE why VERIFY_READ.? . Book says its kernel
> oriented so concept of read and write is reversed.
>
> if(_IOC_DIR(cmd) & _IOC_READ)
> err = !access_ok(VERIFY_WRITE, (void __user*)arg, _IOC_SIZE(cmd));
> else if(_IOC_DIR(cmd) & _IOC_WRITE)
> err = !access_ok(VERIFY_READ, (void __user*)arg, _IOC_SIZE(cmd));
> if(err)
> return -EFAULT;
>
> Thanks
> Regards
>
>
>
>
>
>
> On 20 March 2015 at 12:36, sahil aggarwal wrote:
>> Hi Pranay
>>
>> Well explained.
>>
>> Thank you.
>>
>> On 20 March 2015 at 11:46, Pranay Srivastava wrote:
>>> Hi Sahil
>>>
>>> On Sun, Mar 15, 2015 at 10:17 AM, sahil aggarwal
>>> wrote:
>>>> hi all,
>>>>
>>>> Going through scull driver code, i see read function reads only till
>>>> end of 1 quantum, so do kernel call read multiple times if count from
>>>> q_pos exceeds quantum size limit.?
>>>>
>>>>
>>>> Ref: ldd3.
>>>>
>>>> if(count > quantum - q_pos)
>>>> count = quantum - q_pos;
>>>> if(copy_to_user(buf, dptr->data[s_pos] + q_pos,count)){
>>>> retval = -EFAULT;
>>>> goto out;
>>>> }
>>>
>>> If you are not using the default read/write routines, then its up to
>>> you to code that.
>>>
>>> Kernel doesn't do multiple read calls. It'll do only what you asked it
>>> for no more but it can do less. For example, a file is say 100 KiB and
>>> you are reading say 4KiB in a loop when do you stop?
>>>
>>> Simply put it's the user space application which is doing the looping
>>> and repeatedly doing read calls because it assumes that file isn't
>>> finished.
>>>
>>> So again when do you stop reading from the file, without knowing size
>>> of the file.?
>>>
>>>> *f_pos += count;
>>>> retval = count;
>>>>
>>>> Thanks
>>>> Regards
>>>>
>>>> ___
>>>> Kernelnewbies mailing list
>>>> Kernelnewbies@kernelnewbies.org
>>>> http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
>>>
>>>
>>>
>>> --
>>> ---P.K.S
___
Kernelnewbies mailing list
Kernelnewbies@kernelnewbies.org
http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Scull Driver - Read
Hi Pranay,
Can you help me with this too.? In case of _IOC_READ why VERIFY_WRITE
and in case of _IOC_WRITE why VERIFY_READ.? . Book says its kernel
oriented so concept of read and write is reversed.
if(_IOC_DIR(cmd) & _IOC_READ)
err = !access_ok(VERIFY_WRITE, (void __user*)arg, _IOC_SIZE(cmd));
else if(_IOC_DIR(cmd) & _IOC_WRITE)
err = !access_ok(VERIFY_READ, (void __user*)arg, _IOC_SIZE(cmd));
if(err)
return -EFAULT;
Thanks
Regards
On 20 March 2015 at 12:36, sahil aggarwal wrote:
> Hi Pranay
>
> Well explained.
>
> Thank you.
>
> On 20 March 2015 at 11:46, Pranay Srivastava wrote:
>> Hi Sahil
>>
>> On Sun, Mar 15, 2015 at 10:17 AM, sahil aggarwal
>> wrote:
>>> hi all,
>>>
>>> Going through scull driver code, i see read function reads only till
>>> end of 1 quantum, so do kernel call read multiple times if count from
>>> q_pos exceeds quantum size limit.?
>>>
>>>
>>> Ref: ldd3.
>>>
>>> if(count > quantum - q_pos)
>>> count = quantum - q_pos;
>>> if(copy_to_user(buf, dptr->data[s_pos] + q_pos,count)){
>>> retval = -EFAULT;
>>> goto out;
>>> }
>>
>> If you are not using the default read/write routines, then its up to
>> you to code that.
>>
>> Kernel doesn't do multiple read calls. It'll do only what you asked it
>> for no more but it can do less. For example, a file is say 100 KiB and
>> you are reading say 4KiB in a loop when do you stop?
>>
>> Simply put it's the user space application which is doing the looping
>> and repeatedly doing read calls because it assumes that file isn't
>> finished.
>>
>> So again when do you stop reading from the file, without knowing size
>> of the file.?
>>
>>> *f_pos += count;
>>> retval = count;
>>>
>>> Thanks
>>> Regards
>>>
>>> ___
>>> Kernelnewbies mailing list
>>> Kernelnewbies@kernelnewbies.org
>>> http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
>>
>>
>>
>> --
>> ---P.K.S
___
Kernelnewbies mailing list
Kernelnewbies@kernelnewbies.org
http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Scull Driver - Read
Hi Pranay
Well explained.
Thank you.
On 20 March 2015 at 11:46, Pranay Srivastava wrote:
> Hi Sahil
>
> On Sun, Mar 15, 2015 at 10:17 AM, sahil aggarwal
> wrote:
>> hi all,
>>
>> Going through scull driver code, i see read function reads only till
>> end of 1 quantum, so do kernel call read multiple times if count from
>> q_pos exceeds quantum size limit.?
>>
>>
>> Ref: ldd3.
>>
>> if(count > quantum - q_pos)
>> count = quantum - q_pos;
>> if(copy_to_user(buf, dptr->data[s_pos] + q_pos,count)){
>> retval = -EFAULT;
>> goto out;
>> }
>
> If you are not using the default read/write routines, then its up to
> you to code that.
>
> Kernel doesn't do multiple read calls. It'll do only what you asked it
> for no more but it can do less. For example, a file is say 100 KiB and
> you are reading say 4KiB in a loop when do you stop?
>
> Simply put it's the user space application which is doing the looping
> and repeatedly doing read calls because it assumes that file isn't
> finished.
>
> So again when do you stop reading from the file, without knowing size
> of the file.?
>
>> *f_pos += count;
>> retval = count;
>>
>> Thanks
>> Regards
>>
>> ___
>> Kernelnewbies mailing list
>> Kernelnewbies@kernelnewbies.org
>> http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
>
>
>
> --
> ---P.K.S
___
Kernelnewbies mailing list
Kernelnewbies@kernelnewbies.org
http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Scull Driver - Read
hi all,
Going through scull driver code, i see read function reads only till
end of 1 quantum, so do kernel call read multiple times if count from
q_pos exceeds quantum size limit.?
Ref: ldd3.
if(count > quantum - q_pos)
count = quantum - q_pos;
if(copy_to_user(buf, dptr->data[s_pos] + q_pos,count)){
retval = -EFAULT;
goto out;
}
*f_pos += count;
retval = count;
Thanks
Regards
___
Kernelnewbies mailing list
Kernelnewbies@kernelnewbies.org
http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Missing sys_enter_open events
Hi all I am doing ftrace to track files being opened and mapped by process but sys_enter_open is getting missed and getname is being traced which is called by sys_open only. What is happening.? mem-2474 [005] 681774.985957: getnameprobe: (sys_execve+0x21/0x5a <- getname) arg1="bin/mem" mem-2474 [001] 683183.894867: sync_read: (vfs_read+0xab/0x107 <- do_sync_read) arg1=80 mem-2474 [001] 683183.894900: sync_read: (vfs_read+0xab/0x107 <- do_sync_read) arg1=1c0 mem-2474 [001] 683183.894902: sync_read: (vfs_read+0xab/0x107 <- do_sync_read) arg1=1c mem-2474 [001] 683183.894913: sync_read: (vfs_read+0xab/0x107 <- do_sync_read) arg1=80 mem-2474 [001] 683183.895113: sync_read: (vfs_read+0xab/0x107 <- do_sync_read) arg1=188 mem-2474 [001] 683183.895275: getnameprobe: (do_sys_open+0x3b/0x105 <- getname) arg1="/etc/ld.so.cache" mem-2474 [001] 683183.895316: getnameprobe: (do_sys_open+0x3b/0x105 <- getname) arg1="/lib/libc.so.6" mem-2474 [001] 683183.895321: sys_read(fd: 4, buf: 7fff8461a0f8, count: 340) mem-2474 [001] 683183.895328: sync_read: (vfs_read+0xab/0x107 <- do_sync_read) arg1=340 ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Tracing allocators of virtual memory and main memory
Sample Output: mem-3374 [005] 589012.489483: mm_fault: (do_page_fault+0x3b3/0x3d8 <- handle_mm_fault) arg1=512 mem-3374 [005] 589012.489486: mm_fault: (do_page_fault+0x3b3/0x3d8 <- handle_mm_fault) arg1=512 mem-3374 [005] 589012.489489: mm_fault: (do_page_fault+0x3b3/0x3d8 <- handle_mm_fault) arg1=512 mem-3374 [005] 589012.489493: mm_fault: (do_page_fault+0x3b3/0x3d8 <- handle_mm_fault) arg1=512 mem-3374 [005] 589012.489495: sys_brk -> 0x23f1000 mem-3374 [005] 589012.489500: kmem_cache_alloc: call_site=810fda40 ptr=880fbe4bf298 bytes_req=176 bytes_alloc=176 gfp_flags=GFP_KERNEL|GFP_ZERO mem-3374 [005] 589012.489501: sys_brk -> 0x2417000 mem-3374 [005] 589012.489504: mm_fault: (do_page_fault+0x3b3/0x3d8 <- handle_mm_fault) arg1=512 mem-3374 [005] 589012.489511: mm_page_alloc: page=ea00375619f0 pfn=16578386 order=0 migratetype=0 gfp_flags=GFP_KERNEL|GFP_REPEAT|GFP_ZERO mem-3374 [005] 589012.489512: kmem_cache_alloc: call_site=81101422 ptr=880fb765b6a8 bytes_req=48 bytes_alloc=48 gfp_flags=GFP_KERNEL mem-3374 [005] 589012.489513: kmem_cache_alloc: call_site=81101454 ptr=880fbe4c63a0 bytes_req=64 bytes_alloc=64 gfp_flags=GFP_KERNEL mem-3374 [005] 589012.489518: mm_page_alloc: page=ea0034cccf00 pfn=15818528 order=0 migratetype=2 gfp_flags=GFP_HIGHUSER_MOVABLE|GFP_ZERO mem-3374 [005] 589012.489520: mm_fault: (do_page_fault+0x3b3/0x3d8 <- handle_mm_fault) arg1=0 mem-3374 [005] 589012.489526: mm_page_alloc: page=ea0034b8d2e0 pfn=15795140 order=0 migratetype=2 gfp_flags=GFP_HIGHUSER_MOVABLE|GFP_ZERO mem-3374 [005] 589012.489527: mm_fault: (do_page_fault+0x3b3/0x3d8 <- handle_mm_fault) arg1=0 mem-3374 [005] 589012.489534: mm_fault: (do_page_fault+0x3b3/0x3d8 <- handle_mm_fault) arg1=512 mem-3374 [005] 589012.489536: mm_fault: (do_page_fault+0x3b3/0x3d8 <- handle_mm_fault) arg1=512 mem-3374 [005] 589012.489552: mark_page_acc: (unmap_vmas+0x553/0x812 <- mark_page_accessed) mem-3374 [005] 589012.489556: mark_page_acc: (unmap_vmas+0x553/0x812 <- mark_page_accessed) mem-3374 [005] 589012.489557: mark_page_acc: (unmap_vmas+0x553/0x812 <- mark_page_accessed) These are some lines of stats for a program which ask for 4096*5 bytes but dont touch them. If it touch those pages mm_page_alloc will increase. So is this correct way to capture brk,mmap and mm_page_alloc to analyze how much pages thread asked for and how many of it actually used.? Thank you Regards Sahil On 12 March 2015 at 08:40, SAHIL wrote: > Hi validis > > Actually i want to see how much total virtual pages it asked for and how many > it actually used, how many were put to swap, how many major page faults > happened and how many faults were handled from swap. > In short whole page level analysis of thread. > > Regards > Sahil Aggarwal > Contact-9988439647 > >> On Mar 12, 2015, at 7:24 AM, valdis.kletni...@vt.edu wrote: >> >> On Thu, 12 Mar 2015 07:09:32 +0530, SAHIL said: >> >>> Yeah right, pidstat which read /proc gives me VSZ ans RSS but i need to >>> backtrace when VSZ/RSS is high which indicates process is allocating memory >>> which it is not even using. >> >> Do you mean pages it isn't *currently* using, or has *never* used? >> >> Also, note that VSZ refers to the virtual size, which may include >> pages currently out on swap, while RSS refers to actually resident pages. >> >> And then there's the other great bugaboo, shared pages that are mapped by >> more >> than one process. >> >> What exactly are you trying to do? ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Tracing allocators of virtual memory and main memory
Hi all If i want to trace the allocators of virtual memory and main memory of process using ftrace on which functions i need to enable the probe.? Currently i have enabled sys_mmap,sys_brk for virtual allocations and mm_page_alloc, kmalloc, kmem_cache_alloc for main memory allocation. Will this give me whole picture of virtual and main memory allocations.? Thanks Regards Sahil ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Perf API vs Ftrace
Hi all Do anybody have experience using Perf API and Ftrace.? I am writing an application to profile a process and using Ftrace. But came to know that Perf provide API too so looking for some facts to benchmark efficiency. Thanks Sahil Regards ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Beginner in Kernel Development
Hey Raphael, I started doing it but got stuck at assembly code which i understand only partially. Should i spend more time understanding it or go further.? Thanks Regards Sahil On 24 February 2015 at 14:10, manoj kumar wrote: > Hello Raphael, > > I found this very useful. Thanks for sharing! > > Regards > Manoj > >> Date: Sat, 21 Feb 2015 09:21:11 -0200 >> Subject: Re: Beginner in Kernel Development >> From: raphaelcampos...@gmail.com >> To: sahil.ag...@gmail.com >> CC: kernelnewbies@kernelnewbies.org > >> >> Hi Sahil, >> >> Another good point to start and really know how the kernel works, is >> the "JamesM's kernel development tutorials". >> http://www.jamesmolloy.co.uk/tutorial_html/ >> >> In this tutorials, you'll understand and practice some details about >> the base of the kernel. >> >> The Eudyptula Challenge is very good too. >> >> regards, >> >> 2015-02-21 3:06 GMT-02:00 sahil aggarwal : >> > Hi all, >> > >> > I am using linux since past 9-10 months and have good programming skills >> > in >> > C/C++. Since past few weeks i am looking for good source to dive in >> > kernel >> > development but could not find the starting point and proper order of >> > learning to be followed to join the community. I will be grateful if >> > someone >> > could point me in right direction. >> > >> > Thanks >> > Regards >> > Sahil >> > >> > ___ >> > Kernelnewbies mailing list >> > Kernelnewbies@kernelnewbies.org >> > http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies >> > >> >> >> >> -- >> Raphael Campos Silva >> Ciência da Computação - IBILCE Rio Preto - SP >> Knowledge, exploit it. >> >> ___ >> Kernelnewbies mailing list >> Kernelnewbies@kernelnewbies.org >> http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Beginner in Kernel Development
Hi Raphael, This is really good tutorial. Totally beginner's stuff. :) Thanks On 21 February 2015 at 16:51, Raphael Campos Silva < raphaelcampos...@gmail.com> wrote: > Hi Sahil, > > Another good point to start and really know how the kernel works, is > the "JamesM's kernel development tutorials". > http://www.jamesmolloy.co.uk/tutorial_html/ > > In this tutorials, you'll understand and practice some details about > the base of the kernel. > > The Eudyptula Challenge is very good too. > > regards, > > 2015-02-21 3:06 GMT-02:00 sahil aggarwal : > > Hi all, > > > > I am using linux since past 9-10 months and have good programming skills > in > > C/C++. Since past few weeks i am looking for good source to dive in > kernel > > development but could not find the starting point and proper order of > > learning to be followed to join the community. I will be grateful if > someone > > could point me in right direction. > > > > Thanks > > Regards > > Sahil > > > > ___ > > Kernelnewbies mailing list > > Kernelnewbies@kernelnewbies.org > > http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies > > > > > > -- > Raphael Campos Silva > Ciência da Computação - IBILCE Rio Preto - SP > Knowledge, exploit it. > ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Re: Beginner in Kernel Development
Thanks for replying Sudip. This seems to be exactly what i was looking for: "A STARTING POINT ". I mailed them few hours ago but didnt get any respond. Do they usually take this much time to respond.? Regards. On 21 February 2015 at 11:00, Sudip Mukherjee wrote: > On Sat, Feb 21, 2015 at 10:36 AM, sahil aggarwal > wrote: > > Hi all, > > > > I am using linux since past 9-10 months and have good programming skills > in > > C/C++. Since past few weeks i am looking for good source to dive in > kernel > > development but could not find the starting point and proper order of > > learning to be followed to join the community. I will be grateful if > someone > > could point me in right direction. > > i found the best way to start is The Eudyptula Challenge , > > regards > sudip > ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
Beginner in Kernel Development
Hi all, I am using linux since past 9-10 months and have good programming skills in C/C++. Since past few weeks i am looking for good source to dive in kernel development but could not find the starting point and proper order of learning to be followed to join the community. I will be grateful if someone could point me in right direction. Thanks Regards Sahil ___ Kernelnewbies mailing list Kernelnewbies@kernelnewbies.org http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
