similar to: aio_pthread on Debian?

Hello Volker, Thank you for the reply. I've seen your name mentioned several times against this topic :-) >What effect do you have in mind exactly? Read/write is done >asynchronously these days without that module as long as the >build detected pthreads. This is the thing... it looks like the Debian packages (stable + back port) are built without the --with-aio-support (at least

Hello list, I setup Iometer to test AIO for 100% random read. If "Transfer Request Size" is more than or equal to 256 kilobytes,in the beginning the transmission is good. But 3~5 seconds later,the throughput will drop to zero. Server OS: Ubuntu Server 14.04.1 LTS Samba: Version 4.1.6-Ubuntu Dialect: SMB 2.0 AIO settings : aio read size = 1 aio write size = 1 vfs objects =

Hi forks: I've been testing SMB2 with samba 3.6.4 performance these days, and I find a weird benchmark that SMB2 write performance is slower than SMB1 in 10Gb ethernet network. Server ----------------------- Linux: Redhat Enterprise 6.1 x64 Kernel: 2.6.31 x86_64 Samba: 3.6.4 (almost using the default configuration) Network: Chelsio T4 T420-SO-CR 10GbE network adapter RAID: Adaptec 51645 RAID

I'm trying to learn more about samba by experimenting with samba on FreeNAS. This involves a certain amount of reading how default smb4.conf parameters are set in FreeNAS and then reading the manpages for those parameters. Async I/O is implemented in samba in freenas via the aio_pthread VFS module. The manpage for vfs_aio_pthread states: "the smb.conf parameters aio read size and aio

Hi Folk, I am writing a Samba VFS module. The VFS CLOSE operation takes a longer time, much greater than 20s, to return. Looks this will cause Samba client server communication timeout. And Samba will load a new module, which is not what I want. I want Samba to wait, until VFS CLOSE operation finishes what it should do. I don't want Samba to load a new module. Can anyone tell me how/where to

Hello Volker, Thanks for kindly feedback :) > When the system is stalled, how many threads does the smbd >have active? /proc/pid/tasks will tell you. At the beginning ... pidstat -t|grep smbd 11:41:16 AM 0 5388 - 0.00 0.00 0.00 0.00 1 smbd 11:41:16 AM 0 - 5388 0.00 0.00 0.00 0.00 1 |__smbd 11:41:16 AM 0 5390

Hi Everyone, I have tried over the past several days, unsuccessfully, to have my Linux client access folders and files shared under Mac OS X server. Mac OS X Info: Version 10.9.5 Username: AJames Hostname: bulbasaur Steps I took to share a directory: - System Preferences - Sharing - File Sharing - Add Shared Folders and let Everyone have Read Only access. - Under "Options"

Hi list, I have been trying to enable AIO on ARMv5 Samba built with kernel headers 2.6.31.8, the configure indicated that AIO is supported via kernel headers and all went smooth (regarding the build process). Once I added the smb.conf 'aio write size=1' and tried to perform a file copy to the Samba share I noticed that 32K of the file (of the 1GB file) have been copied to the share but

** Low Priority ** Hi Volker, This is regarding your fix on recycled PIDs. I am an NCP developer from Novell and we use libsmbsharemodes library from Samba for Cross Protocols Locks between NCP, Samba and others. I have few queries regarding your fix. In your fix, you have added a new field called 'unique_id' in the server_id structure and we need to pass this in our call to samba

Hello, maybe there is someone they can help and answer a question why i get these network screen on my ctdb clusters. I have two ctdb clusters. One physical and one in a vmware enviroment. So when i transfer any files (copy) in a samba share so i get such network curves with performance breaks. I dont see that the transfer will stop but why is that so? can i change anything or does anybody know

Hi everyone; Have a Windows 2012 based workload that generates many (20K+ PPS) small reads (Wireshark tells me the individual packets are typically less than 200 bytes and are Read AndX Request) from eight or so hosts to a Samba server running on RHEL 6.5. Samba version is the latest Red Hat provided 3.6.9 version. Things are going quite a bit slower than expected (as compared to the same

Hi Ralph, Thanks for your suggestion. I have upgraded to Samba 4.1.14 (I know it's not the latest version but its the only version I could install on Gentoo at the moment). Unfortunately, my issues still persist. ----------------------------------------------------------------------- # smbclient -V Version 4.1.14 # smbtree -U AJames Enter AJames's password: WORKGROUP

Hello, Can someone help me to track down the source of this problem? I'm trying to access a file server running on a Belkin modem with an attached USB drive. Judging my the quality of the firmware on the device, I'd say there's a good chance of it being buggy. But it works well enough on a Windows machine, even one running inside Virtualbox under Linux. I therefore see no reason

On Tue, Jul 19, 2016 at 12:42:53PM -0700, Jeremy Allison wrote: > On Tue, Jul 19, 2016 at 12:49:09PM -0500, Russell R Poyner wrote: > > I'm tuning a samba 4.3 install on freebsd and I'm confused about aio > > settings. > > > > I've loaded the freebsd aio kernel module and tried various values > > or aio read size and aio write size, but it seems to

On Wed, Feb 11, 2015 at 10:27:50AM +0100, Nacho del Rey wrote: > Hi Volker and the list > > Yesterday the problem appeared again > > I could launch a strace command over a samba PID to see what was going on > and this is the result > > [PRO] [root at pf3il0024 ~]# strace -frp 57686 > Process 57686 attached - interrupt to quit > 0.000000 fcntl(14, F_SETLKW,

On Fri, Mar 06, 2015 at 01:38:26PM +0100, Nacho del Rey wrote: > Hi again Volker (& list) > > I think I am very closer of the problem. Sorry, but without access to this system I can't really say what is going on. Please talk to Oracle for support. Samba is running fine on a huge variety of file systems, and if ACFS gives you locking issues, I would request Oracle to fix their

In the vfs pages for aio_pthread, it gives as an example for aio read/write size, 1024 for each and states an "appropriate" value must be set. Byt in smb.conf it states that the only reasonable values are 0 or 1 (also that there's a default = 1 so no value need be given explicitly). Which of these is correct? Thanks, Stilez

> On Wed, Feb 11, 2015 at 11:13:42AM +0100, Volker Lendecke wrote: > > On Tue, Feb 10, 2015 at 08:59:21PM -0800, Jeremy Allison wrote: > > > Ah ok - I expected as much. snprintf seems to be > > > broken in that it's returning -1. > > > > > > Is this our snprintf or one from Solaris ? Can > > > you try and track down why it's returning

Hi Nagendra here I have existing a samba-3 installation which has a smb encrypt as mandatory i.e : smb encrypt* =* mandatory I am trying to connect to this machine's share with windows & I am getting the following error on the windows 8 client System error 5 has occurred. Access is denied. But I use the same client machine to access another windows-8 machine with SMB encryption I am

On Wed, Feb 11, 2015 at 11:44:24AM +0100, Nacho del Rey wrote: > Ok, it is becoming a nightmare ;-) > Last question Volker > > Is it possible the problem comes from a network device? > At job, we have been suffering problems with a F5 Load Balancer. It seems > that, randomly, it sets the transmission frame to 0 bytes during a while > and routing services don't work very