similar to: nfsmount default timeo=7 causes timeouts on 100 Mbps

In case anyone's interested, I followed up in the linux-nfs mailing list: https://marc.info/?l=linux-nfs&m=156887818618861&w=2 Thanks, Alkis On 9/15/19 10:51 AM, Alkis Georgopoulos wrote: > I think I got it. > > Both nfsmount and `mount -t nfs` now default to rsize/wsize = 1 MB. > By lowering this to 32K, all issues are gone, even with the default > timeo=7. And

I think I got it. Both nfsmount and `mount -t nfs` now default to rsize/wsize = 1 MB. By lowering this to 32K, all issues are gone, even with the default timeo=7. And nfsroot=xxx client responsiveness is a whole lot better. I think when nfsmount was initially written, the default rsize/wsize were much lower, which matched the timeo=7. Now they cause the lags/timeouts that I reported. So

I managed to get to the bottom of this, and filed a bug report for NFS: https://bugzilla.kernel.org/show_bug.cgi?id=204939 Klibc nfsmount still a bug: it needs to NOT hardcode timeo=7. Either the NFS defaults should be used, which result in: timeo=600,rsize=1048576,wsize=1048576, or at least the kernel documented defaults, https://www.kernel.org/doc/Documentation/filesystems/nfs/nfsroot.txt

Commit-ID: 886783e7a10fb7a638bc6034e4cdcb6296cea6a1 Gitweb: http://git.kernel.org/?p=libs/klibc/klibc.git;a=commit;h=886783e7a10fb7a638bc6034e4cdcb6296cea6a1 Author: Ben Hutchings <ben at decadent.org.uk> AuthorDate: Mon, 7 Oct 2019 17:18:41 +0100 Committer: Ben Hutchings <ben at decadent.org.uk> CommitDate: Mon, 7 Oct 2019 17:27:49 +0100 [klibc] nfsmount: Use kernel

Peter, we found that nfs over udp will corrupt data under very extrem load, there is no way to fix it due to the way how UDP works. TCP will not have these problems. I also wonder why the package size is only 1k. Everyone who wishes a slow connection can pass the desired options via the kernel cmdline. Everyone else prefers probably the fast mount. The defaults should look more like that: ---

Hi, In a discussion on the kernel bugzilla (bug 11154) the question of NFS mount options came up. Trond Myklebust seems to consider the default nfsmount options (V3 over TCP, with timeo=7 and retrans=3) to be bad. I don't know yet if that's my problem, but anyway, would you consider changing the defaults to timeo=600 and retrans=2, if only just to match the default util-linux mount

I set up a 3.3 gluster volume for another sysadmin and he has added it to his cluster via automount. It seems to work initially but after some time (days) he is now regularly seeing this warning: "Too many levels of symbolic links" $ df: `/share/gl': Too many levels of symbolic links when he tries to traverse the mounted filesystems. I've been using gluster with static mounts

Hello all, I have observed a problem with a diskless PXE client I am attempting to configure. PXE/NFS/DHCP/TFTPd server is running CentOS5.1 and the Diskless workstation's root and kernel was extracted from a CentOS5.1 (custom kernel due to setting to enable Root File System support). Problem: When the diskless client boots and logs in I notice that my root user is being squashed, even if I

I have been experimenting exporting btrfs subvolumes over nfs. Main subvolume is filesys1 mounted at /filesys1. Below this is subvolume base, user1 is in base and documents is in user1. documents is mounted at /documents. /etc/exports is: /filesys1/base/user1 172.16.0.0/24(rw,no_acl,no_root_squash,fsid=0) /filesys1/user1-snapshot 172.16.0.0/24(rw,no_acl,no_root_squash,fsid=0)

I''ve locked up my dom0 a couple of times this morning copying a 3GB file from local disk to an NFS mount(neither xend nor guests running). I don''t encounter this problem on the stock CentOS 4 kernel. The machine is a PowerEdge 2850 with 2 e1000 cards - the one in use is connected to a PowerConnect 2216 10/100 switch and has negotiated 100Mbit. I''ll check if the stock

This seems like another basic question because I always assumed that if I threw something in my /etc/fstab then it will be automatically mounted at boot time (unless I put in the 'noauto' option). But my NFS partition isn't getting mounted, here's the excerpt from my /etc/fstab file, split on the whitespace so it's easier to read: nfs_server:/exports/var/www /var/www nfs

Yes, multiple imap servers using one shared nfs storage. With the same config on 2.2.13 the public interface traffic was similar to the storage interface, around 100 mbps. After we switch to 2.2.27 the storage interface traffic jumped 10 times while the public interface stayed the same. This make us thinking that something is wrong and each time a user logs in the whole Inbox content is read

Hi I use rsync for daily backups from a mailserver. Every day the mailserver pushes backup to the backupserver. Cron runs the command: rsync -q -zrlpt --specials --chmod=Du+rwx \ --rsh 'ssh -F /root/ssh/config -i /root/ssh/private.key -o UserKnownHostsFile=/root/ssh/known_hosts' \ --files-from=/root/include \ --exclude-from=/root/exclude \ --link-dest=../previous \ /

Commit-ID: c4b811a1e4647224ddc717fac59900d16d0e9d4d Gitweb: http://git.kernel.org/?p=libs/klibc/klibc.git;a=commit;h=c4b811a1e4647224ddc717fac59900d16d0e9d4d Author: Baptiste Jonglez <baptiste.jonglez at imag.fr> AuthorDate: Thu, 14 Sep 2017 09:22:21 -0700 Committer: Ben Hutchings <ben at decadent.org.uk> CommitDate: Wed, 2 Jan 2019 03:08:04 +0000 [klibc] nfsmount: support

The standard mount option nowadays to specify NFS version is "nfsvers", as documented in nfs(5) on modern Linux systems. Up to now, nfsmount only supported the old "v2" or "v3" boolean options. Extend option parsing to support both "nfsvers=X" and "vers=X", with X being equal to either 2 or 3 (nfsmount does not support NFSv4 at present). If both

Hello. We have a number of Xen 3.4.2. boxes which have constant iowaits at around 10% with spikes up to 100% when accessing data over NFS. We have been unable to nail down the issue. Any advice? System info: release : 2.6.18-194.3.1.el5xen version : #1 SMP Thu May 13 13:49:53 EDT 2010 machine : x86_64 nr_cpus : 16 nr_nodes

Hello I have a problem with Invalid data System debian10 dovecot-2.2.36.4 # 2.2.36.4 (baf9232c1): /etc/dovecot/dovecot.conf # Pigeonhole version 0.4.24.rc1 (debaa297) # OS: Linux 4.19.0-12-amd64 x86_64 Debian 10 Oct 23 15:57:52 dovecot6 dovecot: lmtp(33973,media4_js,2KEXD2Dhkl+1hAAAe3x6RQ): Error: Broken file /vmail/me/media4_js/Maildir/dovecot-uidlist line 6875: Invalid data: In debian9 -

Hi, I hit a bizare problem with dovecot 2.2.7 on debian 9 with LMTP enabled and auth/penalty disabled as documented here : https://wiki.dovecot.org/Authentication/Penalty Use case : I run a swaks command to send an email to an exim4 that tries to make a callout to dovecot-lmtp. At RCPT TO: swaks hangs 5.0<something-small> seconds then process normally (exim is waiting for callout

Our large and complex build system is having very sporadic failurs as we try to update to CentOS 4.5. This takes the form of files that exist - and have existed for some time - not being found: file.whatever: No such file: No such file or directory This happens both with source files, .o's - meaning that the errors come from both the compiler and linker. The build storage is on NFS and the

We have a 2-node Oracle RAC that keeps getting the following error: kernel: nfs: RPC call returned error 88 The storage being mounted is netapp. We don't see any errors/issues on the storage itself or the switches this client is connecting thru. The NFS network is a 2-interface ( 2 x 1Gb UTP) bond which shows no errors of any kind. We are mounting with the following mount options: