similar to: Samba Client Performance

I have a Dell server with four bonded, gigabit interfaces. Bonding mode is 802.3ad, xmit_hash_policy=layer3+4. When testing this setup with iperf, I never get more than a total of about 3Gbps throughput. Is there anything to tweak to get better throughput? Or am I running into other limits (e.g. was reading about tcp retransmit limits for mode 0). The iperf test was run with iperf -s on the

Hi all, I am trying to get some decent speed out of a vanilla Debian (Proxmox) box and am running out of ideas. Basically I can exchange data at 110MB/sec (raw, nfs, ftp) but not with Samba shares. I tried almost every samba tuning tip I could find to no avail. The only optimisation left to smb.conf at the moment is debug level = 0. As one can see the robocopy throughput is merely half of what

Hi all. I have a problem with the cifs module in my gigabit network. I get the following performance: 95 mbytes/s with FTP 65 mbytes/s with samba, windows 7 client 8 mbytes/ with the cifs module on opensuse 11.4 I have tried all the solutions found on google, such as directio, modifying rsize and wsize, with no improvements. Any advice? Is this the right place to discuss issues with cifs? P

Hello, I recently set up a samba cluster with 4 nodes using ctdb. The systems are virtual Citrix xen machines running SuSE SLES11Sp2 with samba 3.6.3. The shared filesystem needed for ctdb is on a ocfs2 share stored on a ISCSI target. The cluster is running fine and ip takeover etc is working fine as well. To find out how the cluster would performe in real life with many clients accessing

Hi all, I've got two gigabit ethernet interfaces bonded in CentOS 5.6. I've set "miimode=1000" and I've tried "mode=" 0, 4 and 6. I've not been able to get better than 112MB/sec, which is the same as the non-bonded interfaces. My config files are: === cat /etc/sysconfig/network-scripts/ifcfg-{eth1,eth2,bond0} # SN1 HWADDR=00:30:48:fd:26:71

2.4.18 kernel) using 3 x 60GB WD 7200 IDE drives on a 7500-4 controller I could get peak I/O of 452 MBytes/sec, and a sustainable I/O rate of over 100 MBytes/sec. That is not exactly a 'dunno' performance situation. These tests were done using dbench and RAID5. Let's get that right: 100 MBytes/sec == 800 Mbits/sec, which is just a tad over 100 Mbits/sec (the bottleneck if you use

I have two boxes for the purpose of testing traffic control and my knowledge thereof (which is at the inkling stage). The boxes are connected by 100Mbit ethernet cards via a switch. For egress traffic via eth0 I achieve a throughput that is close to the specified CEILing, particularly for values above 1mbit. Ingress traffic does not seem so well behaved. Above about 1mbit rates achieved are

Hello folks, I'm seeing a couple of things that I can't figure out. Samba version - 2.2.a3 (samba-2.2.0.cvs040920001.tar.bz2 is where the source is built from) PDC is Win2k server Client is Win2k pro Samba share on linux 2.4.1 Security = share I cannot connect at all from clients. If I do a net view from the client to the samba server I get: System error 64 has occurred The

connection will remain a TCP connection unless it is broken and restarted. Usually if I stop the client and wait for about 30 seconds to reconnect, there is a much greater chance that the MTU probes work fine, and in about 30 seconds MTU is fixed to 1416. Every time when the MTU probing fails, I see latency between 700 - 1000 ms with 32 byte pings over a LAN. Every time when the MTU probing does

Hi. Here are the relevant details about the setup: SunOS 4.1.4 gcc 2.7.2.2 tcp wrappers 7.5 egd 0.6 (doesn't really come into play at compile time) The following only pertains to the compilation (and linking) stage. Code and patches are SunOS specific. -- The following functions are missing in SunOS: strerror, atexit, memmove. I wrote simple replacements in term of on_exit and bcopy

Hi everyone, I'm trying to use samba in a small video post production house but we are not getting the performance we expected. Our setup: - CenOS 5.6 x86-64 - samba.x86_64 (3.0.33-3.29.el5_6.2 and 3.6.0rc1) - Intel based server (One 4 core Xeon E5620 @ 2.40GHz, 8 GB RAM) - 4 Intel Gigagit ethernet NIC ports with 802.3ad bonding connected to a switch configured tu use 802.3ad - 8 2TB 7.2

Hi, I am seeing a performance degradation while using libvirt to start my vm (kvm). vm is fedora 12 and host is also fedora 12, both with 2.6.32.10-90.fc12.i686. Here are the statistics from iperf : >From VM: [ 3] 0.0-30.0 sec 199 MBytes 55.7 Mbits/sec >From host : [ 3] 0.0-30.0 sec 331 MBytes 92.6 Mbits/sec libvirt command as seen from ps output : /usr/bin/qemu-kvm -S -M

Hello list, I have two differents installation Xen Hypervisor on two identical physical server, on the same switch : The problem is on my new server (Xen 4.0.1 with pvops kernel 2.6.32.24), I have bad performance on bandwidth I have test with a files copy and "iperf". Result iperf average: Transfert Bandwidth XEN-A -> Windows

I did some testing using samba-3.0.0 as a server and two identical clients one Running W2K and other running Win XP pro. If I write a big file using the W2K client, I'm getting about 25 Mbytes/sec but if I run the same testing using the Win XP Pro, this client only is able to get 12.5 Mbytes/sec. There is a problem between XP and samba?

Hi all, I'm confused of small files (no bigger than 50k ) transfers speed through samba,which is very slow on my machine. Bellow is a real case, -- SuSE professional 9.2, kernel 2.6.11,Samba 3.0.14a,reiserfs -- Dual AMD Opteron,4G mem,Giga byte LAN -- 2 raid 5 make up of 16 SATA hard disks -- set readhead to 1024 I tested raids speed using bonnie++ and get 450 Mbytes/s at 16GB files

Hi, I am testing tinc for a very large scale deployment. I am using tinc-1.1 for testing. test results below are for tinc in switch mode. all other settings are default. test is performed in LAN env. 2 different hosts. I am getting only 24.6 Mbits/sec when tinc is used. without tinc on the same hosts/link I get 95 to 100 Mbits/sec using iperf. Over Tinc: iperf -c 192.168.9.9 -b 100m -l 32k -w

Hi. Try add this to your config in global section. socket options = SO_KEEPALIVE TCP_NODELAY IPTOS_THROUGHPUT SO_RCVBUF=262140 SO_SNDBUF=262140 max xmit = 262140 stat cache = yes max stat cache size = 262140 server max protocol = SMB2_10 server min protocol = NT1 client min protocol = NT1 client max protocol = SMB2_10 getwd cache = yes read raw = yes write raw = yes level2 oplocks = yes locking =

Hi, I want to do some analysis of NTOP data. Currently I have installed NTOP on Centos 5.1 and I am able to see some network data being graphed. But there is no documentation given whether NTOP is showing Network Throughput in MBytes or MBits for ex I am getting Throughput Min: 163.7k , Max: 3.0 M and Last 859.4k and there are some options like anomalia, upper,lower and trend (30min). Under

Hello everybody, althought there are a lot of discussions on Samba's performance, I would like to share my results trying to connect Samba running on a Linux box to a Win95 workstation on a fast ethernet network. If any of you could have some ideas or suggestions , please mail me (cc: teo@flex.ro) because I am not (yet) on this mail list. First of all, may I present you : 1. THE SERVER -

If I try to rsync OpenOffice-directory (OO as an example, 155 MBytes) to Solaris8-machine/rsync-server it takes 4-5 minutes, about 70 MBytes gets transfered and eventually rsync.exe/winXP "dies"; actually winXP's net doesn't responde anymore and I have to boot whole machine! But when I try to do same between Linux and Solaris everything works fine, transfer speed is about