similar to: Are there any current, in play plans, to multi-thread rsync?

I am pretty new to Dtrace but use the Dtrace Toolkit when trying to troubleshoot I/O issues On Oracle. I am looking for help on how to do the following: I am trying to answer whether adding more HBA Cards/ports would be effective. To do this, I need to know the i/o''s per second As well as total bandwidth per second. Has anyone done this before? Does anyone have any other ideas on how

Chandler Carruth <chandlerc at google.com> writes: > Having thought a bit about the best strategy to solve this, I think we should > use a tradeoff of memory to reduce contention. I don't really like any of the > other options as much, if we can get that one to work. Here is my specific > suggestion: > > On Thu, Apr 17, 2014 at 5:21 AM, Kostya Serebryany <kcc at

On Apr 17, 2014, at 2:04 PM, Chandler Carruth <chandlerc at google.com> wrote: > On Thu, Apr 17, 2014 at 1:27 PM, Justin Bogner <mail at justinbogner.com> wrote: > Chandler Carruth <chandlerc at google.com> writes: > > if (thread-ID != main's thread-ID && shard_count < std::min(MAX, NUMBER_OF_CORES)) { > > shard_count = std::min(MAX,

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Good day all, I am running CIFS/9000 (which is based on Samba 3.0.22 with, I'm guessing, security and serious bug fixes through 3.0.25 -- it's not all that clear), and running all of this on an HP-UX 11.11 PA-RISC server. The problem I have is when I do a right-click on a mapped printer and ask for the properties, my connected daemon

On Fri, Apr 18, 2014 at 11:13 AM, Dmitry Vyukov <dvyukov at google.com> wrote: > Hi, > > This is long thread, so I will combine several comments into single email. > > > >> - 8-bit per-thread counters, dumping into central counters on overflow. > >The overflow will happen very quickly with 8bit counter. > > Yes, but it reduces contention by 256x (a thread

I have set up samba-1.9.18p10 on Sun Solaris. I have created several shares and whenever a user edits a file it gets set to permission mode 0744, regardless of what it was before. The file permission can than be changed from windows using file properties. To avoid this extra step I added a create mask = 0655 to the share definition. Now the files get created with the correct permission,

We had problem using tagged vlans inside domU. Testing shows that this is caused by changing network interfaces in network-bridge script. Following patch should allow to use vlans in guest. Testing scenario: configure vlan network (e.g. vlan 1 on eth0 => eth0.1) start xend create domU and configure same vlan inside it You can see that vlan is still <interface>.<vlan_id>. You can

Hello All, I'm using OpenSSH 4.3p2 in HP-UX 11.23. On running tusc (a tool to trace system calls and signals) on sshd, I found lot of close calls upto 2047. Those close calls try to close a non-opened file descriptor and results in an error. This behaviour is seen only from OpenSSH 3.9 where closefrom() call is introduced to close the file descriptors before re-exec. The fix is to check

Hello, I have been tracking down a cause for some abnormal CPU utilization with samba. It appears after looking at glance plus that samba is spending the majority of its time (like around 75-80%) doing lstat system calls. When I used tusc I discovered that it appears to be looking for a file /tmp/.winbindd which I am assuming is the unix domain socket for winbind. However this system is not

[This email is either empty or too large to be displayed at this time]

Hi, sorry for the double post, I stupidly composed this as a reply to an earlier mail, which causes it to appear in an older thread. Posting again so it doesn't get lost in the archives: dovecot 1.1.7 reliably crashes every time I try to open a mailbox using IMAP. Error in the logs: dovecot: Dec 02 23:14:15 Error: setmntent(/etc/mtab) failed: No such file or directory dovecot: Dec 02

On Fri, Apr 18, 2014 at 11:44 AM, Dmitry Vyukov <dvyukov at google.com> wrote: > On Fri, Apr 18, 2014 at 11:32 AM, Dmitry Vyukov <dvyukov at google.com>wrote: > >> On Fri, Apr 18, 2014 at 11:13 AM, Dmitry Vyukov <dvyukov at google.com>wrote: >> >>> Hi, >>> >>> This is long thread, so I will combine several comments into single

http://bugzilla.mindrot.org/show_bug.cgi?id=403 Summary: scp generates sparse file when no space left Product: Portable OpenSSH Version: 3.1p1 Platform: HPPA OS/Version: HP-UX Status: NEW Severity: normal Priority: P2 Component: scp AssignedTo: openssh-unix-dev at mindrot.org ReportedBy:

I'm observing a rather strange behaviour when attempting to transfer files from a Linux box (RH 7.3, kernel 2.4.19-rc1) to HP-UX 11.11 box. Both are running rsync 2.5.5. Everything starts off really nice an quick, but the transfer then slows down to a crawl. On 100 Mb/s network I'm getting a few hunder bytes to a few hundred kilobytes per second. Other programs, like RCP and FTP, do not

Trying to do something like this, in Ubuntu 11.10/12.04: Location A (work occurs changing files) rsync --write-batch /media/bkup/foo.rsb /path/to/files/ /path/to/copy/ Location B rsync --read-batch /media/bkup/foo.rsb /path/to/files/ rsync --read-batch /media/bkup/foo.rsb /path/to/copy/ (work occurs changing files) rsync --write-batch /media/bkup/foo.rsb /path/to/files/ /path/to/copy/

Belgardt, Wolfgang wrote: >Hello all, > >can somebody say me if it is supported to locate the secrets.tbd on a NFS share, please? >I have smbd version 2.2.12 based HP CIFS Server A.01.11.04 in HP ServiceGuard Configuration. >If the secrets.tbd is on a local path samba smbd start and run fine, but when secrets.tbd file is locate in >a path which is a NFS share smbd hangs. >I

Hello, We discovered a slight problem with rsync 2.6.8 on HP-UX 11.23 on Itanium2. When trying to get a directory listing via: # oracle@DEV1[]:/~ > rsync dev1::deploy drwxr-xr-x 96 2006/09/06 12:57:36 . drwxrwxrwx 96 2006/09/11 15:35:33 test # ... it works flawlessly, but when trying to get a subdirectory we get the following error: # DEV1:/etc# rsync dev1::deploy/test #

Hi, The current design of -fprofile-instr-generate has the same fundamental flaw as the old gcc's gcov instrumentation: it has contention on counters. A trivial synthetic test case was described here: http://lists.cs.uiuc.edu/pipermail/llvmdev/2013-October/066116.html For the problem to appear we need to have a hot function that is simultaneously executed by multiple threads -- then we will

I've gotten fairly far into compiling and running dovecot on HPUX. The problem I'm currently having is that the index seems to be mmap'ed at twice after login. The 576 byte mmap is the index file: root at hp46t243 # grep mmap64 /tmp/dovecot.tusc [imap ][1707] mmap64(NULL, 576, PROT_READ|PROT_WRITE, MAP_SHARED, 7, 0) = 0xc166c000 [imap ][1707] mmap64(NULL, 18432,

Hi Alexandra, I don't know much, maybe this topic should be bridged with polly-dev (adding it to CC) to bring it more attention. Indeed, polly uses ScopPass, that creates serious limitations in compatibility with other passes. To my understanding, scops are used because ISL loop analysis tool uses scops. In fact, just for handling OpenMP directives scops are not required, unless one need to