search for: thrash

...thing changed on the server. > > Recently (Jan 27th) some of the Archlinux clients updated from a 4.8.x > kernel to a 4.9.x kernel. Again, things ran fine. Then on Jan 30th > around 2am the Archlinux clients using 4.9.x kernels and utilizing > mount.cifs to access samba shares began thrashing on TCP port 445, > causing high CPU load on the server. These machines now cause > thrashing after 15-20 minutes whenever a share is mounted using > mount.cifs. > > When it's thrashing, I see thousands of opened ports from a single > client: # sockstat -4 | grep 10.0.1.87...

...g fine for a while and nothing changed on the server. Recently (Jan 27th) some of the Archlinux clients updated from a 4.8.x kernel to a 4.9.x kernel. Again, things ran fine. Then on Jan 30th around 2am the Archlinux clients using 4.9.x kernels and utilizing mount.cifs to access samba shares began thrashing on TCP port 445, causing high CPU load on the server. These machines now cause thrashing after 15-20 minutes whenever a share is mounted using mount.cifs. When it's thrashing, I see thousands of opened ports from a single client: # sockstat -4 | grep 10.0.1.87 | wc 10013 70091 740962...

...20:15:05 -0600 Paul Klapperich via samba <samba at lists.samba.org> wrote: > Well that was easier than I thought. Here's the default config > provided by archlinux's samba package, but with "deadtime = 1" > included. With this config, shares mounted via mount.cifs thrash on > port 445 after a few minutes. I think the reconnect logic in the > kernel's CIFS client is broken. Should I report this on the kernel > mailing list? > It doesn't seem to be a Samba bug, it seems to be a mixture of Freenas adding the wrong lines in smb.conf and possibly a...

Rsync thrashes my buffer cache when transfering large files. I see that some people worked on this problem about a year ago. Did they find a workable solution? I'm getting tired of everything slowing to zero while rsync grinds away. Josh Snyder -------------- next part -------------- HTML attachment scr...

At some stage (possibly commit r17268) oggpack_writecopy started to fail with some strings longer than 256 bytes and all strings longer than 512 bytes. Also it thrashes the stack with very long strings. Lithopsian

Sent 12 hours ago and it never showed up (slightly reworded here). Sorry if this is a duplicate: --------------------------------------------- Scenario: a person selects an Auto Attendant option that fires off the Directory application (CVS circa 3/22). Three questions: 1) How do they escape if they didn't mean to go there in the first place (without having to hang up...)? Config of

...been more of a challenge then I expected. Anyway, from a Windows ME box, printing from applications happens quickly and transparently without a hitch. But, I have another client machine that is a Windows 2000 box. When printing a document from Word (or excel...), the Win 2000 box absolutely thrashes our network. The box itself becomes sluggish and Word becomes unuseable for 7 to 10 minutes. After that period of time, the document will print. But as you can imagine, that doesn't go over too well with the user of the Win 2000 box. During that time the utilization of our 100Mb netwo...

...ver. > > > > Recently (Jan 27th) some of the Archlinux clients updated from a 4.8.x > > kernel to a 4.9.x kernel. Again, things ran fine. Then on Jan 30th > > around 2am the Archlinux clients using 4.9.x kernels and utilizing > > mount.cifs to access samba shares began thrashing on TCP port 445, > > causing high CPU load on the server. These machines now cause > > thrashing after 15-20 minutes whenever a share is mounted using > > mount.cifs. > > > > When it's thrashing, I see thousands of opened ports from a single > > client: #...

On 25/11/2014, isdtor <isdtor at gmail.com> wrote: > We recently started upgrading users' workstations to CentOS6. Now > we've come across an interesting issue: > ~user/.local/share/gvfs-metadata is filling up with tons of files. > Once there are around 69270 of them, no more are being created, and > the NetApp filer the user's home is on logs: > > Directory

Does R do its own swapping out to disk? I disabled Linux swapping and the system still gets stuck in Purgatory where there's little CPU activity but the disk goes like crazy. That's with R having almost the whole machine to itself and running a memory hungry compute only function. I've seen this behavior with other version numbers but I'm running R 2.0.0 under Fedora Core 3.

On Wed, 8 Feb 2017 16:43:53 -0600 Paul Klapperich via samba <samba at lists.samba.org> wrote: > Very well. Here is the affected smb.conf. > ------ > [global] > server min protocol = NT1 > server max protocol = SMB3 > interfaces = 127.0.0.1 10.0.0.8 > bind interfaces only = yes > encrypt passwords = yes > dns proxy = no > strict

...some reason, so I'll have to talk to them on that one and it seems they have no option for me to modify the server role. Thankfully I can edit smb.conf directly on the archlinux box where I was able to duplicate the issue. Setting sever role = auto, domain logons = yes doesn't fix the TCP thrashing and works with the SIDs already populated in LDAP. It looks like removing "deadtime = 15" from the smb.conf prevents the TCP thrashing. If I set "deadtime = 1" then the thrashing happens after 3 minutes or so. I'll see if I can put together a conf file that isn't a...

okey doke. I have read the faq, I have browsed the samba web sites, and I did go through diagnose.txt and the other documentation but still... none of the win95 boxes on my network can see my samba server in the network neighborhood. usage of "net use x: \\server\share" seem to work fine on the client machines though as well as everything else in the diagnose.txt document. Could

...I want a fair comparison between LLVM performance >> and the native x86 codegen. If I don't give LLVM the same information >> the x86 codegen has, it's an unfair comparison. > >Even if this puts LLVM at an unfair disadvantage, I think you will find >that >LLVM will thrash MLton's current x86 backend anyway. > >I did some benchmarking on HLVM and found that it was often several times >faster than OCaml when the GC is not the bottleneck: > >http://flyingfrogblog.blogspot.com/2009/03/performance-ocaml-vs-hlvm-beta-04.html For numerical tasks and Arr...

We recently started upgrading users' workstations to CentOS6. Now we've come across an interesting issue: ~user/.local/share/gvfs-metadata is filling up with tons of files. Once there are around 69270 of them, no more are being created, and the NetApp filer the user's home is on logs: Directory ..../user/.local/share/gvfs-metadata/ reached the maxdirsize limit. Reduce the number of

Le 09/09/2017 ? 15:14, Robert Nichols a ?crit : > Every system that runs continuously for more that a few days will have > some pages that were used once when some long-running process started > and were never referenced again. Those pages will eventually migrate out > to swap, and that's the best place for them. Right now, I see that this > system has been up for 16 days and

...it's very dumb, and is pure mechanism. It's told how much memory to target, and it either allocates or frees memory until the target is reached. Unfortunately, that means if it's asked to shrink to an unreasonably small size, it will do so without question, killing the domain in a thrash-storm in the process. There are several problems: 1. it doesn't know what a reasonable lower limit is, and 2. it doesn't moderate the rate of shrinkage to give the rest of the VM time to adjust to having less memory (by paging out, dropping inactive, etc) And possibly t...

...it's very dumb, and is pure mechanism. It's told how much memory to target, and it either allocates or frees memory until the target is reached. Unfortunately, that means if it's asked to shrink to an unreasonably small size, it will do so without question, killing the domain in a thrash-storm in the process. There are several problems: 1. it doesn't know what a reasonable lower limit is, and 2. it doesn't moderate the rate of shrinkage to give the rest of the VM time to adjust to having less memory (by paging out, dropping inactive, etc) And possibly t...

...LVMContext, and then put the work of uniquing by accessing the context off of the type. There are obviously some pros and to both approaches. Going back to the old-style increases compatibility with 2.5, and breaks up the massive LLVMContext class. On the downside, it would cause massive thrashing on TOT, because I will have to revert about two weeks worth of commits in widely dispersed parts of the tree, and because a number of clients have already switched to the new TOT API. Any comments and/or opinions on this decision are welcome. --Owen -------------- next part --------------...

Well that was easier than I thought. Here's the default config provided by archlinux's samba package, but with "deadtime = 1" included. With this config, shares mounted via mount.cifs thrash on port 445 after a few minutes. I think the reconnect logic in the kernel's CIFS client is broken. Should I report this on the kernel mailing list? ----- # This is the main Samba configuration file. You should read the # smb.conf(5) manual page in order to understand the options listed # here...