search for: so_

Mostly out of curiosity: I've seen people advising that we set SO_{RCV,SND}BUF to 8192 as an optimization. I added a call to getsockopt() to grab the old (default) value before setting it to the new, and it turns out (on DG/UX), that the default value is 8760 (or 8704, when you throw in the fact that packets are travelling between different sublans), so the 8192...

Hi. Between 2 linux (2.6.11 client and 2.6.14 server) machines connected by a 100Mb link I get samba performance copying a file from the client to the server through a smbmounted share of around 4.2MB/s Is this to be expected? Or can it be improved (and if so, how?) I've tried tweaking SO_(SND/RCV)BUF (after reading numerous articles on samba performance...), but it doesn't seem to have any effect. Unfortunately, I can't use jumbo frames at this moment either. I've tried this with shares on ReiserFS and XFS and there is no difference in the transfer rate. Both machines a...

R 3.5.1 is installed under Linux Mint 19 from binaries r-base and r-base-dev from ubuntu bionic-cran35.? Mysteriously, packages using libRblas cannot be compiled.? I get: libRblas.so: cannot open shared object file: No such file or directory.? And indeed, I find no libRblas.so. Any ideas about how to fix this? Thanks, Steve

...4-pc-linux-gnu (64-bit) Running under: Ubuntu 18.04.1 LTS Matrix products: default BLAS: /usr/lib/x86_64-linux-gnu/openblas/libblas.so.3 LAPACK: /usr/lib/x86_64-linux-gnu/libopenblasp-r0.2.20.so [...] If Mint follows the setup I use for the Debian package, then you _never have libRblas.so_ because we use the _external_ BLAS. This allows you to switch to Atlas (tuned BLAS), OpenBLAS (multithreaded), Intel MKL (multithreaded and possibly a little faster than OpenBLAS but much bigger), ... Dirk -- http://dirk.eddelbuettel.com | @eddelbuettel | edd at debian.org

..."Command: module reload chan_iax2.so\r\n\r\n"); $wrets=fgets($socket,128); fputs($socket, "Action: Reload\r\n"); fputs($socket, "Command: dialplan reload\r\n\r\n"); $wrets=fgets($socket,128); The first (module reload chan_sip.so) and second (module reload chan_iax2.so_ gets executed properly, but the last one does not, i' getting an error: ERROR[2067]: utils.c:968 ast_carefulwrite: write() returned error: Broken pipe ERROR[2067]: utils.c:968 ast_carefulwrite: write() returned error: Broken pipe Has anyone encountered this? TIA. Regards Ron

...og level = 3 debug level = 3 log file = /var/log/log.%m max log size = 5000 security = domain password server = <NT Domain PDC> encrypt passwords = yes #per www.freibergnet.de (Martin Welk) # following is used under 3.3-RELEASE socket options = IPTOS_LOWDELAY TCP_NODELAY SO_SNDBUF=262144 SO_RCVBUF=262144 # following is used under 3.3-RELEASE # socket options = IPTOS_LOWDELAY TCP_NODELAY SO_SNDBUF=132072 SO_RCVBUF=132072 os level = 0 wins server = 129.79.1.200 dns proxy = no #============================ Share Definitions ============================== (r...

...attempted modifying a few settings as per suggestions found when searching for a solution to this. the only non-default portions are [global] read raw = yes write raw = yes oplocks = yes max xmit = 65535 dead time = 15 getwd cache = yes ... socket options = IPTOS_LOWDELAY SO_SNDBUF=8192 SO_RCVBUF=8192 without the SO_* options set as above, the throughput is much worse, with less than 1 MBps coming through. can pull pretty much full linespeed (12 MBps =~ 100 Mbps) using scp from this same server, so it's not likely errors on the interface. just to be clear # net...

Samba version 3.0.25b-1.1.cc I cant seem to transfer files over 40gb from a windows machine --> samba share. as far as socket options im using socket options = TCP_NODELAY SO_RCVBUF=8192 SO_SNDBUF=8192 SO_KEEPALIVE Is there any other tweaks I can use to help make this system more reliable? I get random errors.."network path not found" or something similar.. = Aconcagua Expedition with Alpine Ascents Aconcagua Expedition with America's Guide Service. I...

...u 18.04.1 LTS > > Matrix products: default > BLAS: /usr/lib/x86_64-linux-gnu/openblas/libblas.so.3 > LAPACK: /usr/lib/x86_64-linux-gnu/libopenblasp-r0.2.20.so > [...] > > > If Mint follows the setup I use for the Debian package, then you _never have > libRblas.so_ because we use the _external_ BLAS. This allows you to switch > to Atlas (tuned BLAS), OpenBLAS (multithreaded), Intel MKL (multithreaded and > possibly a little faster than OpenBLAS but much bigger), ... > > Dirk >

...n\ n *passwd:*password*updated*successfully* username map = /etc/user.map username level = 2 unix password sync = yes debug level = 0 max log size = 1000 nameresolveorder = lmhosts host bcast wins time server = yes deadtime = 60 socket options = TCP_NODELAY IPTOS_LOWDELAY SO_KEEPALIVE SO_RCVBUF=16384 SO_S NDBUF=16384 load printers = no mangling method = hash2 character set = iso8859-1 client code page = 850 domain admin group = root logon script = %U.bat logon drive = x: domain logons = yes add user script = /var/install/bin/samba-add-workstat...

...Retype*new*UNIX*password:* %n n *passwd:*password*updated*successfully* username map = /etc/user.map username level = 2 unix password sync = yes debug level = 0 max log size = 1000 nameresolveorder = lmhosts host bcast wins time server = yes deadtime = 60 socket options = TCP_NODELAY IPTOS_LOWDELAY SO_KEEPALIVE SO_RCVBUF=16384 SO_S NDBUF=16384 load printers = no mangling method = hash2 character set = iso8859-1 client code page = 850 domain admin group = root logon script = %U.bat logon drive = x: domain logons = yes add user script = /var/install/bin/samba-add-workstation %u os level = 255 prefe...

...--- netcat-1.10/netcat.c 2006-01-04 22:11:40.000000000 +0200 +++ /tmp/dpep.QmuQvQ/netcat-1.10/netcat.c 2006-01-04 22:17:16.000000000 +0200 @@ -71,6 +71,7 @@ #include <sys/time.h> /* timeval, time_t */ #include <setjmp.h> /* jmp_buf et al */ #include <sys/socket.h> /* basics, SO_ and AF_ defs, sockaddr, ... */ +#include <sys/un.h> /* UNIX-domain sockets */ #include <netinet/in.h> /* sockaddr_in, htons, in_addr */ #include <netinet/in_systm.h> /* misc crud that netinet/ip.h references */ #include <netinet/ip.h> /* IPOPT_LSRR, header stuff */ @@...

...here is trouble: the x86-64 Linux ABI says the syscall number goes in eax, then the args go [rdi, rsi, rdx, r10, r8] from left to right. However as noted in line, it clobbers RDX after it has been set up for the call! Checking with strace indeed we see: setsockopt(-1, SOL_SOCKET, 0xffffffff /* SO_??? */, [1], 4) To compare, a version built without using -optimize-regalloc=0 produces x86: 400198: 41 b8 04 00 00 00 mov $0x4,%r8d 40019e: 4c 8d 54 24 fc lea -0x4(%rsp),%r10 4001a3: ba 03 00 00 00 mov $0x3,%edx 4001a8: be 01 00...

On Wed, May 29, 2013 at 08:24:10AM +0200, Paolo Bonzini wrote: > Il 28/05/2013 20:15, Michael S. Tsirkin ha scritto: > > What you write in spec below and what you write above seems to > > contradict. > > > > Look, how about the simpler patch that I sent: > > "[PATCH] virtio-spec: balloon: MUST_TELL_HOST is optional" > > > > does it

...Tweaks.png https://i.ibb.co/mqwZtgR/Debian-10-No-Tweaks.png The latest bloc of 'performance' setting were those: # Settings to enhance performance: strict locking = no read raw = yes write raw = yes oplocks = yes max xmit = 65535 deadtime = 15 getwd cache = yes socket options = TCP_NODELAY SO_SNDBUF=128480 SO_RCVBUF=128480 max protocol = SMB2 # End of performance section I've also tried an empty smb.conf file to fallback to default. Nothing seem to work. Spec of the current machine: CPU: Intel(R) Core(TM)2 CPU 6600 @ 2.40GHz RAM: 2 GB Ethernet controller: Qualcomm Atheros AR8121/...