NFS Performance Issue

Hi Listers, We recently found that the Performance of the NFS Client in FreeBSD is worse than that in Linux. Linux [/net/iscsi] -jnlin- sudo ls -al /net/iscsi/mysql/blog-2/var/pixblog_2/blogarticle.ibd -rw-rw 1 3306 3306 734003200 2008-11-27 00:13 /net/iscsi/mysql/blog-2/var/pixblog_2/blogart

Re: NFS Performance Issue

On Thu, Nov 27, 2008 at 2:29 AM, Claus Guttesen <[EMAIL PROTECTED]> wrote: >> We recently found that the Performance of the NFS Client in FreeBSD is >> worse than that in Linux. > > What OS is your nfs-server running? Our NFS server is NetApp. > > You can ommit read- and write-size using tcp-mounts

amd(8) cores dump when load high

Dear listers, We currently found that amd frequently cores dump while loading is high (about 4~5) after we upgrade world & kernel from 7.0-RELEASE to 7.1-PRERELEASE. I have read -stable and svn log of 7-STABLE, but can not found a report or a solution. Did anyone have the same issue? Thank you ve

Re: amd(8) cores dump when load high

Hi, We are running some daily report (php scripts), get data from remote mysql database. And we are running daily backup script, to copy local data to remote NFS Server at the same time. On Tue, Dec 23, 2008 at 12:52 AM, SDH Admin wrote: > > >> #634 0x000e in ?? () > > > > What is ru

Process stuck in STOP state

Dear listers, Our FreeBSD Server uses NFS to access PHP files on NetApp, then serve them with apache 2.2 (worker MPM + php fastcgi mode). At least one time a day the apache process is stuck in the STOP state and is unkillable. gdb won't attach to the process, either. Does anyone have any similar i

Re: Process stuck in STOP state

> Dear listers, > > Our FreeBSD Server uses NFS to access PHP files on NetApp, then serve > them with apache 2.2 (worker MPM + php fastcgi mode). Sorry. we use -STABLE now. event# uname -a FreeBSD event 7.1-PRERELEASE FreeBSD 7.1-PRERELEASE #1: Thu Dec 4 01:45:42 CST 2008 r...@event:/usr/obj/

Re: Process stuck in STOP state

Hi, We have done a textdump, located here: http://aqua.pixnet.tw/~jnlin/textdump/ Thank you! On Wed, Dec 24, 2008 at 11:07 AM, Alfred Perlstein wrote: > * Lin Jui-Nan Eric [081223 09:17] wrote: >> > Dear listers, >> > >> > Our FreeBSD Server uses NFS to access P

Re: Process stuck in STOP state

om all processes, there's > a ddb command to do this. > > -Alfred > >> >> On Wed, Dec 24, 2008 at 11:07 AM, Alfred Perlstein >> wrote: >> > * Lin Jui-Nan Eric [081223 09:17] wrote: >> >> > Dear listers, >> >> > >> >

Re: Process stuck in STOP state

Hi, Full back-trace is located here: http://aqua.pixnet.tw/~jnlin/textdump/event3/1226/ On Fri, Dec 26, 2008 at 11:34 AM, Lin Jui-Nan Eric wrote: > Hi, > > No, NFS is not working (df hangs, and cd /nfs/vol hangs, too). we have > run fstat and see some NFS file is opened. > I will

Re: amd(8) cores dump when load high

Yes, we found that it crashes when swap is used. On Fri, Dec 26, 2008 at 6:02 PM, Rong-en Fan wrote: > On Tue, Dec 23, 2008 at 12:44 AM, Lin Jui-Nan Eric wrote: >> Dear listers, >> >> We currently found that amd frequently cores dump while loading is >> high (about

Re: amd(8) cores dump when load high

>danny > >> >> >> On Fri, Dec 26, 2008 at 6:02 PM, Rong-en Fan wrote: >> > On Tue, Dec 23, 2008 at 12:44 AM, Lin Jui-Nan Eric >> > wrote: >> >> Dear listers, >> >> >> >> We currently found that amd frequently co

Re: amd(8) cores dump when load high

I got "Couldn't lock process pages in memory using mlockall()" too: Dec 27 23:20:38 worker1 amd[90422]: switched to logfile "syslog" Dec 27 23:20:38 worker1 amd[90422]: AM-UTILS VERSION INFORMATION: Dec 27 23:20:38 worker1 amd[90422]: Copyright (c) 1997-2006 Erez Zadok Dec 27 23:20:38 worker1 amd[

Re: amd(8) cores dump when load high

Hi Danny, Can you tell us which patch did you apply? Thank you very much! On Sun, Dec 28, 2008 at 3:52 PM, Danny Braniss wrote: >> I got "Couldn't lock process pages in memory using mlockall()" too: > [...] >> On Sat, Dec 27, 2008 at 9:07 PM, Rong-en Fan wrote: >> > On Sat, Dec 27, 2008 at 7:03

Re: Process stuck in STOP state

Hi Gavin, I will compile my kernel with WITNESS and try again! On Mon, Dec 29, 2008 at 11:23 PM, Gavin Atkinson wrote: > On Fri, 26 Dec 2008, Lin Jui-Nan Eric wrote: > >> Hi, >> >> Full back-trace is located here: >> http://aqua.pixnet.tw/~jnlin/textdump/event3/

Re: Process stuck in STOP state

Dear All, We have recompiled our kernel with WITNESS and generated another textdump: http://aqua.pixnet.tw/~jnlin/textdump/event3/1230/ On Tue, Dec 30, 2008 at 12:00 AM, Lin Jui-Nan Eric wrote: > Hi Gavin, > > I will compile my kernel with WITNESS and try again! > > On Mon, Dec

TCP packet out-of-order problem

Dear listers, We recently found our new FreeBSD server (located in some foreign region) has poor network performance. After doing some tcpdump and iperf testing, we found that out-of-order TCP packets are not inserted into queue. This is an 100Mbps line, and TSO is disabled. % uname -a FreeBSD b

Re: TCP packet out-of-order problem

Hello, Yes, it's 1 now. On Wed, Dec 31, 2008 at 6:49 PM, Václav Haisman wrote: > Lin Jui-Nan Eric wrote, On 30.12.2008 21:06: >> Dear listers, >> >> We recently found our new FreeBSD server (located in some foreign >> region) has poor network performance. After

Re: amd(8) cores dump when load high

Update: After we add -S flag to "amd_flags" in /etc/rc.conf, amd does not core dump. I think it is a workaround solution. Thank you all guys! ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscr

Re: TCP packet out-of-order problem

Dear All listers, After running "netstat -s -p tcp", we found that lots of packets are discarded due to memory problems. We googled for it, and found that sysctl oid "net.inet.tcp.reass.maxsegments" became 0, therefore packets never reassembled. Then we checked our /boot/loader.conf and /etc/sysc

Re: TCP packet out-of-order problem

Hi Robert, I thought that the system auto-tune improperly in this case. On Mon, Jan 5, 2009 at 9:13 PM, Robert Watson wrote: > On Fri, 2 Jan 2009, Lin Jui-Nan Eric wrote: > >> After running "netstat -s -p tcp", we found that lots of packets are >> discarded due to

Re: TCP packet out-of-order problem

so, could you send me the output of uname -a on the system? > > Thanks, > > Robert N M Watson > Computer Laboratory > University of Cambridge > >> On Mon, Jan 5, 2009 at 9:13 PM, Robert Watson wrote: >>> >>> On Fri, 2 Jan 2009, Lin Jui-Nan Eric wrote: >

Different behavior of make(1) between command line argument and .MAKEFLAGS special target

Hi listers, Recently I found that there's different behavior of specifying -j1 in command line argument and special target ".MAKEFLAGS". According to section "SPECIAL TARGETS" in manpage of make(1): .MAKEFLAGS This target provides a way to specify flags for make when the ma

pf stalls connection when using route-to

Hi listers, We recently found that when the traffic passes pf with route-to, the connection stalls. Turning off TSO solves the problem. Our pf.conf is very simple: table const {10/8, 172.16/12, 192.168/16} pass out quick route-to (em0 10.1.1.1) from to ! no state And we have a tcpdump capture

Re: pf stalls connection when using route-to

On Tue, Apr 13, 2010 at 11:19 PM, Jeremy Chadwick wrote: > > What FreeBSD version?  uname -a output please. > I have tried 7.2-R and 8.0-R. Both version stalls, too. 8.0-RELEASE: # uname -a FreeBSD bsd8 8.0-RELEASE-p2 FreeBSD 8.0-RELEASE-p2 #3: Wed Mar 3 17:15:52 CST 2010 r...@bsd8:/usr/obj/

Lots of FIN_WAIT_1 TCP Connections and deadlock in zoneli state

Hi All, I am running squid as reverse proxy on FreeBSD 7.0-R amd64. After running for a while (~ 8 hours), the throughput degrades to very very low rate. I found the squid is in "zoneli" state and is already a bug report on http://www.freebsd.org/cgi/query-pr.cgi?pr=106317 But after more investig

TMPFS does not support unix socket file?

Hi, I am trying to replace my /tmp to TMPFS. Everything is fine, but I found that MySQL does not run. The error log shows that it cannot bind /tmp/mysql.sock. Does TMPFS support unix socket file? ___ freebsd-stable@freebsd.org mailing list http://lists.f

Re: TMPFS does not support unix socket file?

On Mon, May 12, 2008 at 1:18 AM, pluknet <[EMAIL PROTECTED]> wrote: > 2008/5/11 Lin Jui-Nan Eric <[EMAIL PROTECTED]>: >> Hi, >> >> I am trying to replace my /tmp to TMPFS. >> Everything is fine, but I found that MySQL does not run. The error log >&g

TMPFS: File System is Full

Hi, I found when we exhaust memory, tmpfs will not be able to write anything into it and cannot mount it. I use ZFS and TMPFS at the same time. Florence# cd /usr/src && make buildworld > /dev/null & Florence# uname -a FreeBSD Florence.tamama.org 7.0-RELEASE-p1 FreeBSD 7.0-RELEASE-p1 #5: Mon May

TMPFS: File System is Full

Hi, I found when we exhaust memory, tmpfs will not be able to write anything into it and cannot mount it. I use ZFS and TMPFS at the same time. Florence# cd /usr/src && make buildworld > /dev/null & Florence# uname -a FreeBSD Florence.tamama.org 7.0-RELEASE-p1 FreeBSD 7.0-RELEASE-p1 #5: Mon May

Max size of one swap slice

Hi All, Recently we found that we can only allocate 32GB for one swap slice. Does there is any sysctl oid or any kernel option to increase it? Why we have this restriction? ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/lis

Re: Max size of one swap slice

On Wed, Aug 6, 2008 at 12:46 AM, Chuck Swiger <[EMAIL PROTECTED]> wrote: > It's hard to conceive of why you'd want to add so much swap space, anyway-- > if you've got programs which actually need to deal with 10s of gigabytes > worth of data, then they ought to maintain a smaller/reasonable-sized >

mountd changed?

Hi, I have a freebsd box (6-stable) which export its root slice to NFS. The exports file is: / -alldirs -maproot=root -network 10.0.0 -mask 255.255.255.0 After making world & kernel today, the nfs client said that permission denied. But another freebsd box (making world & kernel today, to

Re: mountd changed?

Hi, If I revert to revision 1.81.2.4, it worked correctly. On 10/15/06, Rink Springer <[EMAIL PROTECTED]> wrote: Hi, Hmm, I recently changed something which might trigger this. Could you back out revision 1.81.2.5 of src/usr.sbin/mountd/mountd.c and let me know whether this fixed the problem?

Re: mountd changed?

On 10/15/06, Lin Jui-Nan Eric <[EMAIL PROTECTED]> wrote: Hi, But another freebsd box (making world & kernel today, too) exports its /home slice, and the nfs client did complain about it. Sorry, should be "did not complain". __

Re: mountd changed?

Hi, On 10/15/06, Rink Springer <[EMAIL PROTECTED]> wrote: Hi, OK, could you try the attached patch (untested) and let me know whether it works? (it patches the 1.81.2.5 revision of mountd.c) No, it does not work. ___ freebsd-stable@freebsd.org mailin

Re: mountd changed?

Hi, The filesystem isn't shown in a 'showmount -e'. Nothing relevant in my /var/log/messages. On 10/16/06, Rink Springer <[EMAIL PROTECTED]> wrote: On Sun, Oct 15, 2006 at 11:45:23PM +0800, Lin Jui-Nan Eric wrote: > No, it does not work. Hmm, I am assuming that the fil

Re: mountd changed?

Hi, On 10/16/06, Erik Trulsson <[EMAIL PROTECTED]> wrote: I had the same problems, but only when trying to export directories from the root filesystem. Your patch below would not help. The following patch (very much inspired by the comment on line 1038 in mountd.c) makes things work for me: I

Installing 6.1-R on Dell Powervault 745N

Dear All, We have a Dell Powervault 745N and want to install FreeBSD 6.1-R. But the installer complains that it can not find out any hard disk. Since the dmesg contains ata2~5, I think the controller is recognized by FreeBSD, but it cannot get the SATA drive. The dmesg and result of running pc

Re: Installing 6.1-R on Dell Powervault 745N

Hi, On 10/19/06, Søren Schmidt <[EMAIL PROTECTED]> wrote: Nothing else that that it should work. I dont own any HW that uses this chip so I cannot test it out. The current support was done for the ARM port IIRC so things might be different on other systems. At any rate you definitly should try o

Re: Installing 6.1-R on Dell Powervault 745N

Hi, On 10/20/06, Søren Schmidt <[EMAIL PROTECTED]> wrote: OK, I need the output from a verbose boot. That will tell if the disks are seen at all and just the attach phase is failing. I might have a few ideas depending on the outcome of that... There is no message about ad0 shown in the boot pr

Re: Installing 6.1-R on Dell Powervault 745N

Dear, On 10/20/06, Søren Schmidt <[EMAIL PROTECTED]> wrote: Boot verbose and grap the output like you did earlier in this thread will do nicely. What I need are the lines from where the channels on the controller are probed for raw devices, that should reveal if we can se any HW at all.. The v