July 2011 - kernelnewbies@kernelnewbies.org - Kernelnewbies Mailing Lists

Changes in block layer for IOScheduler Insertion selection
by mani Feb. 6, 2012

Feb. 6, 2012

Dear All, I am working on linux kernel 2.6.32.9 tegra NVIDIA board. I am getting ~8MBps speed of the Nand disk if i use hdparm hdparm -t /dev/mtdblock3 i made changes in block layer of kernel as below:- block/blk-core.c static inline void add_request(struct request_queue *q, struct request *req) { drive_stat_acct(req, 1); /* * elevator indicated where it wants this request to be * inserted at elevator_merge time */ __elv_add_request(q, req, ELEVATOR_INSERT_BACK, 0); //__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0); } changed ELEVATOR_INSERT_SORT to ELEVATOR_INSERT_BACK it improves my NAND speed to 10MBps. I am using "noop" I/O scheduler. Will this change have any adverse effect in kernel ? or any other side effect as far as i am using only Nand no Hard disk. Thanks Mani

3 4

What does drop_caches do?
by Prateek Sharma Aug. 24, 2011

Aug. 24, 2011

Hello everyone, I've been trying to understand the role of the pagecache, starting with drop_caches and observing what it does. From my understanding of the code (fs/drop_caches.c) , it walks over all the open files/inodes, and invalidates all the mapped pages. Pages which are *not* dropped are either dirty,in-use,anonymous,mapped(to pagetable),or writeback) . Is my understanding correct? But, when i run drop_caches, there are still some pages which show up as cached. Why arent all cache pages getting dropped ? My confusion runs much deeper. What exactly constitutes the pagecache? All filebacked pages ? mmaped files ? If i copy a bunch of files, why does my cache get polluted with those pages? Thanks for reading. I'd be grateful if someone can enlighten me about some pagecache internals . (Please keep me CC'ed) <begin experiment> root@tripitz:/etc/apt# free -m total used free shared buffers cached Mem: 1995 1854 140 0 79 700 -/+ buffers/cache: 1074 920 Swap: 4767 762 4005 root@tripitz:/etc/apt# echo 3 > /proc/sys/vm/drop_caches root@tripitz:/etc/apt# free -m total used free shared buffers cached Mem: 1995 1373 621 0 0 363 -/+ buffers/cache: 1009 985 Swap: 4767 762 4005 <end experiment>

3 2

question about staging tree branches
by Prashant Shah Aug. 23, 2011

Aug. 23, 2011

Hi, There are 4 branches in the staging tree remotes/staging/master remotes/staging/ralink remotes/staging/staging-linus remotes/staging/staging-next Is the staging-linus is what Linus merges and staging-next is merged by linux-next tree ? What is ra-link for ? Regards.

3 3

Can i allocate 4GB virtual addresses (more than a certain limit) using vmalloc?
by sandeep kumar Aug. 22, 2011

Aug. 22, 2011

Hi all, The following link gives the memory map for the arm architecture. http://www.arm.linux.org.uk/developer/memory.txt I have the following doubts.. 1) Any chipset(based on arm) manufacturer(qualcom,samsung..) should follow the same memory map. Is it hardly constrained or can be changed? Where are this constraints are implemented in the kernel source tree? 2) while i was student, i read in OS concepts that, "Virtual memory gives an illusion to a process, that it has always a larger continuous address space (even more than RAM) available to it." So i thought i could allocate howmuch ever memory i want. But seeing the above link,i observed there is some limitation in the address space created by the vmalloc(). So i m now thinking that vmalloc has some limit. Please make me clear these things.... With regards, Sandeep Kumar Anantapalli,

6 7

Re: about gcc-3.4.6
by esmaeil mirzaee Aug. 12, 2011

Aug. 12, 2011

On Fri, Jul 29, 2011 at 7:46 AM, Pravin Shedage <pravinshedage2008(a)gmail.com > wrote: > Hi Samuel, > > check the FTP link > ftp://ftp.mirrorservice.org/sites/sourceware.org/pub/gcc/releases/ > Actually I have gcc-3.4.6.tar.bz2 for process of installation I did: untar the file ./configure make but I've got error some of the error is: In function ‘open’, inlined from ‘collect_execute’ at ./collect2.c:1537:20: /usr/include/bits/fcntl2.h:51:24: error: call to ‘__open_missing_mode’ declared with attribute error: open with O_CREAT in second argument needs 3 arguments make[1]: *** [collect2.o] Error 1 make[1]: Leaving directory `/home/esmaeil/Documents/software/gcc-3.4.6/gcc' make: *** [all-gcc] Error 2 > > @enjoy.... > > > > On Fri, Jul 29, 2011 at 4:53 PM, Bernd Petrovitsch < > bernd(a)petrovitsch.priv.at> wrote: > >> Hi! >> >> On Fre, 2011-07-29 at 07:14 -0400, esmaeil mirzaee wrote: >> > apologize in advance, I know here is related the kernel but my >> >> Than why do you post here in the first place? >> >> [...] >> > I need gcc-3.4.6 for do work with ubuntu kernel and install some stuff >> > I needed. >> >> You can find the source on http.//gcc.gnu.org/ or - surpise! - via >> Google. >> >> > Again I'm so sorry for interrupt. >> >> No, you are not. >> Bernd >> -- >> Bernd Petrovitsch Email : bernd(a)petrovitsch.priv.at >> LUGA : http://www.luga.at >> >> >> _______________________________________________ >> Kernelnewbies mailing list >> Kernelnewbies(a)kernelnewbies.org >> http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies >> > > > > > > Thanks & Regards, > ---------PraviN--------- > > >

3 4

xx_initcall ( ) in kernel
by sumeet linux Aug. 8, 2011

Aug. 8, 2011

Dear friends, I want to know the basics xx_initcall ( ) in linux kernel. How this function works ? Observed in kernel code, many places late_initcall ( ), early_initcall ( ), arch_initcall ( ), core_initcall ( ) gets called. When did all these functions gets call during kernel initialization ? I am more interested in what is the sequence of these functions gets called one after another. Thank you. Regards, Sumeet

3 2

SRIO maintenance read hangs (mpc8548)
by shrikant hegde Aug. 4, 2011

Aug. 4, 2011

Hi all, I am working on srio; When i tried to send maintenance packet to switch it hangs. Symptom when i tried to read DIDCAR of switch,( i.e read 0x8000_0000 ), or HDIDLOCK (0x8000_0068 ), execution of code hangs; if i press break in code warrior its coming out with an error. register value dump EPWISR 0x80000000 -- physical or logical/transport error interrupt LTLEDCSR 0x08000000 -- illegal transaction decode, received request/response packet LTLCCCSR 0x82000000 Below are my system detail: Processor mpc8548 and Tsi578 switch. Processor is connected to switch on same board.I have written standalone code (no OS) to exercise srio, using code warrior. Processor side configurations Its configured to 1x, 2.5gbs, host. law and tlb are configured. 0x8000_0000 0x8FFF_FFFF maintenance window configured 0x8000_0000 0x8000_0FFF (4k) switch side configuration 1x,2.5gbs, swap disabled (configured during POR) Processor side link training bit is setting. Am I missing any configuration , in switch side or processor side ? Any pointer is very helpful. Forgive me if its a wrong forum to post srio queries. thanks shrikant -- View this message in context: http://old.nabble.com/SRIO-maintenance-read-hangs-%28mpc8548%29-tp30949266p… Sent from the kernelnewbies mailing list archive at Nabble.com.

2 1

Tasklet vs workqueues
by santhosh kumars Aug. 2, 2011

Aug. 2, 2011

Hi All, I took following lines from robert love linux kernel development. " If you need a schedulable entity to perform your bottom-half processing, you need work queues.They are the only bottom-half mechanisms that run in process context, and thus, the only ones that can sleep.This means they are useful for situations in which you need to allocate a lot of memory, obtain a semaphore, or perform block I/O. If you do not need a kernel thread to handle your deferred work, consider a tasklet instead ." Here some times tasklets also runs in kernel thread context(by ksoftirqd/n).So I want to know what is the exact difference between workqueue and tasklet. thanks, santosh.

3 4

Asynchronous read
by Da Zheng Aug. 2, 2011

Aug. 2, 2011

Hello, I'm trying to understand the read operation in VFS, and get confused by the asynchronous and synchronous operations. At the beginning, do_sync_read() invokes aio_read, which is generic_file_aio_read for ext4. generic_file_aio_read should be asynchronous read. But what really confuses me is do_generic_file_read, which is called by generic_file_aio_read. It seems to me do_generic_file_read implements synchronous read as this is the only function I can find that copy data to the user space by invoking the actor callback function. If do_generic_file_read is synchronous, how can generic_file_aio_read be asynchronous? In do_generic_file_read, if the data to be read isn't in the cache, normally page_cache_sync_readahead should be called. As far as I understand, when page_cache_sync_readahead returns, the pages will be ready in the cache, but the corresponding data in the disk isn't necessarily copied to the pages yet (because it eventually only invokes submit_bio to submit the IO requests to the block layer), so PageUptodate of the requested page might still return false, and then do_generic_file_read tries to invoke readpage to read the page again instead of waiting. Since the disk is always very slow, doesn't it just waste CPU time? Or do I miss something? Best, Da

2 2

Bond, round robin mis-configuration.
by Eduard Sinelnikov Aug. 2, 2011

Aug. 2, 2011

Hi, In the kernel 2.6.39.3 ( /drivers/net/bond/bond_main.c). In the function ‘bond_xmit_roundrobin’ The code check if the bond is active via ‘bond_is_active_slave(slave)’ Function call. Which actually checks if the slave is backup or active What is the meaning of slave being backup in round robin mode? Correct me if I wrong but in round robin every slave should send a packet, regardless of being active or backup. Thank you, Eduard

3 7