search for: wmem_max

...received. 109709802 packet receive errors 7239 packets sent We had checked all the kernel configurations and set them as recommended. This is the settings and tests we have done Server: net.core.rmem_default = 2097152 net.core.wmem_default = 2097152 net.core.rmem_max = 8388608 net.core.wmem_max = 8388608 strace -fttt -o /tmp/server.trace iperf -s -u -p 2222 -w 6m -i 5 -l 1k Client: net.core.rmem_default = 2097152 net.core.wmem_default = 2097152 net.core.rmem_max = 8388608 net.core.wmem_max = 8388608 strace -fttt -o /tmp/client.trace iperf -p 2222 -u -w 6m -i 5 -t 60 -c 192.168.1.2 -b 990...

...sly, I cannot seem to get above 25MB/sec from each. It starts off with a large burst like each can do 100MB/sec, but then in a couple of seconds, tapers off to the 15-40MB/sec until the dd finishes. Things I have tried (installed on the host and the guests) net.core.rmem_max = 16777216 net.core.wmem_max = 16777216 net.ipv4.tcp_rmem = 4096 87380 16777216 net.ipv4.tcp_wmem = 4096 65536 16777216 net.ipv4.tcp_no_metrics_save = 1 net.ipv4.tcp_moderate_rcvbuf = 1 # recommended to increase this for 1000 BT or higher net.core.netdev_max_backlog = 2500 sysctl -w net.ipv4.tcp_congestion_control=cubi...

...nt RcvbufErrors: 44017 <--- this When this number increases, we see SIP errors, and in particular Qualify packets are lost, and temporarily disable handsets, causing all sorts of minor chaos. I have already tuned from the defaults of: net.core.rmem_max = 131071 net.core.wmem_max = 131071 net.core.rmem_default = 111616 net.core.wmem_default = 111616 net.core.optmem_max = 10240 net.core.netdev_max_backlog = 1000 up to: net.core.rmem_max = 1048575 net.core.wmem_max = 1048575 net.core.rmem_default = 1048575 net.core.wmem_default = 1048575 net.core.optmem_max = 10485...

...hosts I have use these params: - On /etc/grub.conf: kernel /vmlinuz-2.6.18-164.11.1.el5 ro root=LABEL=/ elevator=deadline quiet - On sysctl.conf # Special network params net.core.rmem_default = 8388608 net.core.wmem_default = 8388608 net.core.rmem_max = 16777216 net.core.wmem_max = 16777216 net.ipv4.tcp_rmem = 1048576 4194304 16777216 net.ipv4.tcp_wmem = 1048576 4194304 16777216 # Disable netfilter on bridges. net.bridge.bridge-nf-call-ip6tables = 0 net.bridge.bridge-nf-call-iptables = 0 net.bridge.bridge-nf-call-arptables = 0 # Virtual machines spec...

Hi list (and happy new year), I'm experiencing some troubles using Samba (4.1.17 debian version) over VPN. Basically we've following setup : PC === LAN ===> VPN (WAN) ==== LAN ===> Samba file Server Copying big (say > 1MiB) files from PC to Samba file server almost always ends up with a NT_STATUS_IO_TIMEOUT error (or "a network error occured" if trying to copy from

...ndBuf = bytes (OS default) Sets the socket send buffer size for the UDP socket, in bytes. If unset, the default buffer size will be used by the operating system. OS, CentOS, just would like to know, if I increase the the /proc/sys/net/core/rmem_max and /proc/sys/net/core/wmem_max to 10MB by below command(in order to increase the UDP buffer size): sysctl -w net.core.rmem_max=10485760 ; sysctl -w net.core.wmem_max=10485760 but keep /proc/sys/net/core/rmem_default and /proc/sys/net/core/wmem_dafault unchanged, which is 200KB. and I don’t have any UDPRcvBuf and UDPSndBuf conf...

Sysctl Values ------------------------------------------- net.core.rmem_max = 16777216 net.core.wmem_max = 16777216 net.ipv4.tcp_rmem = 4096 87380 16777216 net.ipv4.tcp_wmem = 4096 65536 16777216 net.ipv4.tcp_window_scaling = 1 # vm.max-readahead = ? # vm.min-readahead = ? # HW Controler Off # max-readahead = 1024 # min-readahead = 256 # Memory over-commit # vm.overcommit_memory=2 # Memory to acti...

...s looks something like this: augeas {"sysctl.conf": provider => "augeas", context => "/files/etc/sysctl.conf", changes => [ "set net.core.wmem_default 262144", "set net.core.wmem_max 262144", "set kernel.sem 250 32000 100 128", ], } When I do a ''puppetd -v -d --no-daemonize --onetime'' on my node, I get the following error: "err: //Node...Failed to retrieve current state of resource: Provider au...

We use SMB to transfer large files (between 1GB and 5GB) from RedHat AS4 Content Storage servers to Windows clients with 6 DVD burners and robotic arms and other cool gadgets. The servers used to be Windows based, but we're migrating to RedHat for a host of reasons. Unfortunately, the RedHat Samba servers are about 2.5 times slower than the Windows servers. Windows will copy a 1GB file

....conf: # Controls default receive buffer size (bytes) net.core.rmem_default = 262144 # Controls IP default send buffer size (bytes) net.core.wmem_default = 262144 # Controls IP maximum receive buffer size (bytes) net.core.rmem_max = 262144 # Controls IP maximum send buffer size (bytes) net.core.wmem_max = 262144 # Controls TCP memory utilization (pages) net.ipv4.tcp_mem = 49152 65536 98304 # Controls TCP sliding receive window buffer (bytes) net.ipv4.tcp_rmem = 4096 87380 16777216 # Controls TCP sliding send window buffer (bytes) net.ipv4.tcp_wmem = 4096 65536 16777216 Ross S. W. Walker Infor...

....0.0.0 up brctl addbr br0 brctl addif br0 eth0 brctl addif br0 eth1 # brctl stp br0 on/off doesn't matter # configure bridge interface ifconfig br0 10.20.30.40 up route add -net 224.0.0.0 netmask 240.0.0.0 dev br0 # try to send a fixed amount of multicast UDP traffic nbytes=`cat /proc/sys/net/wmem_max` nbytes=$(( $nbytes * 2 )) dd if=/dev/zero bs=$nbytes count=1 | nc -nuvw1 224.0.0.123 1234 # arguments to nc: # -w1 "wait 1sec" causes nc to exit after sending the _complete_ amount # -n no names, -v verbose, -u UDP to multicast 224.0.0.123 port 1234 If both links are connected, the dd...

Hi, I''m doing some test on a network 10 gb nics and xen with version 3.1 i''m measuring 2.5 gb/sec from domU to an external physical machine with iperf. switching to 3.2 has reduced the measured performance to 40-50 Mb/sec. did anything change in the network interface? can someone help me? thanks _______________________________________________ Xen-users mailing list

...e no difference. Relevant /etc/sysctl.conf parameters: vm.dirty_ratio = 50 vm.dirty_background_ratio = 1 vm.dirty_expire_centisecs = 1000 vm.dirty_writeback_centisecs = 100 vm.min_free_kbytes = 65536 net.core.rmem_default = 262144 net.core.rmem_max = 262144 net.core.wmem_default = 262144 net.core.wmem_max = 262144 net.core.netdev_max_backlog = 25000 net.ipv4.tcp_reordering = 127 net.ipv4.tcp_rmem = 4096 87380 16777216 net.ipv4.tcp_wmem = 4096 65536 16777216 net.ipv4.tcp_max_syn_backlog = 8192 net.ipv4.tcp_no_metrics_save = 1 The {r,w}mem_{max,default} values are twice what they were previously; ch...

Hi, We've been running tinc for a while now but, have started hitting a bottleneck where the number of packets/sec able to be processed by our Tinc nodes is maxing out around 4,000 packets/sec. Right now, we are using the default cipher and digest settings (so, blowfish and sha1). I've been testing using aes-256-cbc for the cipher and seeing ~5% increases across the board. Each Tinc node

Hi all, I have a rhel 5.1 xen server with two rhel 3 ES hvm guests installed. Both rhel3 guests use an internal xen bridge (xenbr1) which it isn''t binded to any physical interface host. On this bridge throughput it is very very poor, only 2.5 Mbs. How can I increase this throughput??? Many thanks. -- CL Martinez carlopmart {at} gmail {d0t} com

...o > consume them) /usr/sbin/ifconfig eth0 txqueuelen 100 ______________________________________________ ifcfg-eth0: ETHTOOL_OPTS="-K ${DEVICE} tso on lro off; -G ${DEVICE} rx 128 tx 128" ______________________________________________ sysctl.conf: net.core.rmem_max = 65536 net.core.wmem_max = 65536 net.core.rmem_default = 32768 net.core.wmem_default = 32768 net.ipv4.tcp_rmem = 4096 32768 65536 net.ipv4.tcp_wmem = 4096 32768 65536 net.ipv4.tcp_mem = 4096 32768 65536 net.ipv4.udp_mem = 4096 32768 65536 net.ipv4.tcp_moderate_rcvbuf = 1 net.ipv4.tcp_sack = 1 net.ipv4.tcp_dsack = 1 _______...

...uelen 100 > ______________________________________________ > > ifcfg-eth0: > > ETHTOOL_OPTS="-K ${DEVICE} tso on lro off; -G ${DEVICE} rx 128 tx 128" > ______________________________________________ > > sysctl.conf: > > net.core.rmem_max = 65536 > net.core.wmem_max = 65536 > net.core.rmem_default = 32768 > net.core.wmem_default = 32768 > net.ipv4.tcp_rmem = 4096 32768 65536 > net.ipv4.tcp_wmem = 4096 32768 65536 > net.ipv4.tcp_mem = 4096 32768 65536 > net.ipv4.udp_mem = 4096 32768 65536 > net.ipv4.tcp_moderate_rcvbuf = 1 > net.ipv4.tcp...

OS: CentOS 5.0 x86. Hi, I am using CentOS 5.0 at home, ADSL ~16 Mbps/~1 Mbps Internet connection and my ping time to my ISP is 160-170 msec. When downloading something with Firefox, I am getting download speeds of about 100-180 KB/sec (for example when downloading SP2 of XP from MS server). Are the CentOS networking settings OK for this kind of latency, or do I have to change some settings?

Hello All: I've been requested to add some TCP tuning parameters to some CentOS 5.4 systems. These tunings are for the TCP receive buffer windows: net.core.rmem_max net.core.wmem_max Information on this tuning is broadly available: http://fasterdata.es.net/TCP-tuning/linux.html http://www.speedguide.net/read_articles.php?id=121 Potential downsides are available: http://www.29west.com/docs/THPM/udp-buffer-sizing.html >From the above, the rmem size is a function of the numb...

Im trying to improve my internal apache proxy. It has to deliver a lot of little/medium sized files. But every transfer starts with the usual small window size. While this is good for internet connections it is not as good for only internal connections where the environment is sane. I have tryed to tune initial window size via /proc/sys/net/ipv4/tcp_congestion_control tryed already