http://blog.gmane.org/gmane.linux.file-systems.cachefs.general hourly 1 1901-01-01T00:00+00:00 http://gmane.org/img/gmane-25t.png http://gmane.org http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3100 <pre>Hello, I need help for configuring a NFS version 4 server for caching what clients read from it. That is, the server has to cache locally (not the client) what any NFS client reads from this server. The porpouse of this configuration if to relief the work load of the server HDD. Any suggestion or recommendation will be appreciated. Abraham Aldaco abraham.aldaco&lt; at &gt;gmail.com </pre> Abraham Aldaco 2012-04-26T16:06:02 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3099 <pre>Hi, First of all, I am not sure if this list is appropriate place to ask that question but I think it is the most relevant one. I saw this project proposal[1] on the Fedora Project's GSOC 2012 ideas page few weeks ago. It proposes to add writeback caching support to NFS. I didn't apply to GSOC since I am not a student but I want to spend my time working on that project although this is not accepted by GSOC. I want to learn that is there any ongoing effort on that side? If any, could you point me to that so that i will not duplicate work and I can contribute to current project. [1] - http://fedoraproject.org/wiki/Summer_coding_ideas_for_2012#Linux_kernel_project Thanks </pre> Sertaç Olgunsoylu 2012-04-26T03:10:28 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3097 <pre>Hi: in nfs(RHEL6.x), i do as following. #cat /etc/exports /nfsroot *(rw,no_root_squash,fsid=0,insecure) #mount –t nfs4 –o fsc localhost:/ /nfsmnt #sh create_file.sh wait a while, i find oops. PID: 4196 TASK: ffff88012365b580 CPU: 0 COMMAND: "sh" #0 [ffff880139435750] machine_kexec at ffffffff810310db #1 [ffff8801394357b0] crash_kexec at ffffffff810b63b2 #2 [ffff880139435880] oops_end at ffffffff814dec50 #3 [ffff8801394358b0] die at ffffffff8100f2fb #4 [ffff8801394358e0] do_trap at ffffffff814de544 #5 [ffff880139435940] do_invalid_op at ffffffff8100ceb5 #6 [ffff8801394359e0] invalid_op at ffffffff8100bf5b [exception RIP: __nfs_fscache_invalidate_page+121] #7 [ffff880139435ab0] nfs_invalidate_page at ffffffffa06fff6e [nfs] #8 [ffff880139435ad0] do_invalidatepage at ffffffff811243d5 #9 [ffff880139435ae0] truncate_inode_page at ffffffff811245f2 #10 [ffff880139435b00] truncate_inode_pages_range at ffffffff811248f0 #11 [ffff880139435bf0] truncate_inode_pages at ffffffff81124c05</pre> fanchaoting 2012-03-28T03:48:38 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3095 <pre>Hi: in nfs(RHEL6.x), i do as following. #cat /etc/exports /nfsroot *(rw,no_root_squash,fsid=0,insecure) #mount –t nfs4 –o fsc localhost:/ /nfsmnt #sh create_file.sh wait a while, i find oops. PID: 4196 TASK: ffff88012365b580 CPU: 0 COMMAND: "sh" #0 [ffff880139435750] machine_kexec at ffffffff810310db #1 [ffff8801394357b0] crash_kexec at ffffffff810b63b2 #2 [ffff880139435880] oops_end at ffffffff814dec50 #3 [ffff8801394358b0] die at ffffffff8100f2fb #4 [ffff8801394358e0] do_trap at ffffffff814de544 #5 [ffff880139435940] do_invalid_op at ffffffff8100ceb5 #6 [ffff8801394359e0] invalid_op at ffffffff8100bf5b [exception RIP: __nfs_fscache_invalidate_page+121] #7 [ffff880139435ab0] nfs_invalidate_page at ffffffffa06fff6e [nfs] #8 [ffff880139435ad0] do_invalidatepage at ffffffff811243d5 #9 [ffff880139435ae0] truncate_inode_page at ffffffff811245f2 #10 [ffff880139435b00] truncate_inode_pages_range at ffffffff811248f0 #11 [ffff880139435bf0] truncate_inode_pages at ffffffff81124c05</pre> fanchaoting 2012-03-29T01:53:27 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3092 <pre>Inglés : Many already we have contributed to the first project of free software dedicated to self-management in this campaign of collective financing, it collaborates and it spreads!/ Beginning campaign collective financing http://www.goteo.org/project/rebelaos-publicacion-por-la-autogestion?lang=en Login to enter with user of social networks and for would register in Goteo : http://www.goteo.org/user/login?lang=en Rebelaos! Publication by self-management A massive publication that floods the public transport, the work centers, the parks, the consumption centers, by means of distribution of 500,000 gratuitous units, acting simultaneously in all sides and nowhere. We announce the main tool of a vestibule Web for the management of self-sustaining resources by means of Drupal, in addition in the publication there will be an article dedicated to free software, hardware, It is being prepared in inglès, the machinery You can see more details in the index of the publication https://n-1.cc/pg/file/re</pre> Orquidea Salt mas 2012-03-02T19:22:05 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3090 <pre>Hi, Am trying to figure out why during bootup, at the following point across real and virt boxes. eb 19 11:22:07 frank01 kernel: [ 482.640618] FS-Cache: Loaded Feb 19 11:22:07 frank01 kernel: [ 482.672487] FS-Cache: Netfs 'nfs' registered for caching It sits there for about 10 seconds, with no indication as to what's happening. nfs mount during bootup can be autofs or fstab depending on box. Is this still relevant for debugging FS-Cache: https://www.redhat.com/archives/linux-cachefs/2010-February/msg00022.html " You can also turn on NFS debugging for FS-Cache to see what it's doing: echo $((0x800)) &gt;/proc/sys/sunrpc/nfs_debug " kernels across boxes: 3.2* 3.3* </pre> Frank Murphy 2012-02-21T17:41:39 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3070 <pre>I thought I'd sent this in December, but I didn't see it in the archives, so I thought I'd take another crack at it. The problem seems to be spreading to clients mounting Linux server hosted NFS exports as well. Any help would be appreciated. Thanks, Brian ----- Forwarded message from Brian Kroth &lt;bpkroth&lt; at &gt;gmail.com&gt; ----- Date: Fri, 16 Dec 2011 10:36:45 -0600 From: Brian Kroth &lt;bpkroth&lt; at &gt;gmail.com&gt; To: linux-cachefs&lt; at &gt;redhat.com Subject: hang on __fscache_wait_on_page_write and __nfs_fscache_invalidate_page Reply-To: Brian Kroth &lt;bpkroth&lt; at &gt;gmail.com&gt; User-Agent: Mutt/1.5.20 (2009-06-14) X-Operating-System: Linux 2.6.32-bpo.3-amd64 x86_64 Hello all. I hope this is the right place for this question. If not please let me know where else it should go. I've got some machines that from time to time will hang waiting on an umount.nfs command and eventually spit out a call trace referencing __fscache_wait_on_page_write and __nfs_fscache_invalidate_page. The situation is as follows: Machines are configur</pre> Brian Kroth 2012-01-24T17:06:17 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3069 <pre>Hi, We are getting a number of 'bad page state' and kernel oopses which (I suspect) are related to fscache or cachefilesd. At the time that these occur, the process that was running will go in to an uniterruptable state Sample bad page state: ----------------------------------------------------8&lt;---------------------------------------------------- Jan 22 19:10:30 rb031 kernel: BUG: Bad page state in process nuke pfn:9c509 Jan 22 19:10:30 rb031 kernel: page:ffffea0002714240 count:0 mapcount:0 mapping: (null) index:0x6e63 Jan 22 19:10:30 rb031 kernel: page flags: 0x4000000000001000(private_2) Jan 22 19:10:30 rb031 kernel: Pid: 26646, comm: nuke Tainted: G B D 3.1.7 #2 Jan 22 19:10:30 rb031 kernel: Call Trace: Jan 22 19:10:30 rb031 kernel: [&lt;ffffffff810a99c5&gt;] bad_page+0xe5/0xfb Jan 22 19:10:30 rb031 kernel: [&lt;ffffffff810aaf3c&gt;] get_page_from_freelist+0x2ff/0x433 Jan 22 19:10:30 rb031 kernel: [&lt;ffffffff810ab745&gt;] __alloc_pages_nodemask+0x32a/0x6ac Jan 22 19:10:30 rb031 kernel: [&lt;ffffffffa009caf</pre> Cam Mac 2012-01-24T16:19:58 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3065 <pre>Hello, I have been trying to get local caching to work on a host running SuSE SLES11 SP1 (cachefilesd is still unsupported). I had no problems compiling and inserting a cachefiles module in the kernel or starting the cachefsd daemon (cachefilesd-0.10.1.tar.bz2). I also see files being cached to /var/cache/fscache (ext3 partition mounted with user_xattr) Nov 14 19:38:17 cachefilesd[6586]: About to bind cache Nov 14 19:38:17 cachefilesd[6586]: Bound cache Nov 14 19:38:17 cachefilesd[6589]: Daemon Started Nov 14 19:38:17 kernel: [ 9667.331384] FS-Cache: Cache "mycache" added (type cachefiles) Nov 14 19:38:17 kernel: [ 9667.331394] CacheFiles: File cache on cciss/c0d0p11 registered Nov 14 19:38:17 cachefilesd[6589]: Scan complete Nov 14 19:38:17 cachefilesd[6589]: Decant (all 213) However when i try to cat a previously cached file ( after flushing the kernel page cache using echo 3 &gt;/proc/sys/vm/drop_caches) the process hangs indefinitely. . It shows up with a status sync_p in process listing and a t</pre> Raghuram Bondalapati 2011-11-16T04:00:47 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3064 <pre>Hi, I have encountered an issue when using fscache where the Linux page cache consumes memory on the system that then cannot be cleared. This eventually leaves the system in a crippled swapping state. To outline what I am doing: [With a data set of ~35GB in ~2000 files] 1. Start four processes that each read the entire contents of a file then move to the next etc. 2. After the first read from NFS we are constantly reading ~250MB/s from the cache. 3. Very high system CPU utilisation is observed on (kswapd0 &amp; flush-0). 4. After ~30min we find that part of the page cache can't be cleared (by echo 3 &gt; /proc/sys/vm/drop_caches) 5. Eventually all RAM becomes consumed and the system starts swapping heavily. 6. The four reading processes are terminated. 7. The page cache still will not clear, even after unmounting the NFS filesystem and restarting cachefilesd. Many messages of this form are seen in /var/log/messages, but not sure if this is connected: FS-Cache: Assertion failed 1 == 0 is false FS-Cache</pre> Stefan Blanke 2011-11-04T16:10:59 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3063 <pre>We have had a very heavily loaded web server which delivers mp3 files through apache with the files residing on an NFS file system. The server receives around 4-10 requests a second, and the files are each around 600KB in size. The server delivers a throughput of between 20Mb/s - 60Mb/s depending on the time of day. The NFS file system being used is read only. The load on this server was increasing to over 100 at busy times during the day, I thought, due to high wait times from the NFS server As the load was so high, the server was becoming unresponsive so we have implemented fscache with local ssd drives to alleviate this on a new server. The fs cache implementation has been somewhat successful, load figures on the new server are now down in the rang of 0-30 which is much better, and looking at throughput on the network and the fscache stats, I can see that around 75% of requests are now satisfied by fscache. See fscache stats below, which I hope I am interpreting correctly. Despite this, f</pre> Ben Yarwood 2011-10-31T12:02:47 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3034 <pre>Every two seconds, cachefilesd logs a Can complete message. Oct 7 06:23:15 node010 cachefilesd[6297]: Scan complete Oct 7 06:23:17 node010 cachefilesd[6297]: Scan complete Oct 7 06:23:19 node010 cachefilesd[6297]: Scan complete Oct 7 06:23:21 node010 cachefilesd[6297]: Scan complete Oct 7 06:23:23 node010 cachefilesd[6297]: Scan complete Oct 7 06:23:25 node010 cachefilesd[6297]: Scan complete Oct 7 06:23:27 node010 cachefilesd[6297]: Scan complete Oct 7 06:23:29 node010 cachefilesd[6297]: Scan complete Why is it looping so fast? /etc/cachefilesd.conf: dir /tmp/fscache tag mycache brun 50% bcull 40% bstop 30% frun 50% fcull 40% fstop 30% # mount /dev/sda1 on / type ext4 (rw,noatime) tmpfs on /lib/init/rw type tmpfs (rw,nosuid,mode=0755) proc on /proc type proc (rw,noexec,nosuid,nodev) sysfs on /sys type sysfs (rw,noexec,nosuid,nodev) udev on /dev type tmpfs (rw,mode=0755) tmpfs on /dev/shm type tmpfs (rw,nosuid,nodev) devpts on /dev/pts type devpts (rw,noexec,nosuid,gid=5,mode=620) /dev/sda2 on /v</pre> Frederik Himpe 2011-10-07T10:00:34 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3028 <pre>Hi David, I tested your recent patches, with much better results. Many thanks for these. I didn't do formal testing, but I've not yet seen the "Overlong wait" message in an hour or so of use, which is excellent. But now that I can reasonably use fscache with NFS, I noticed that the page cache doesn't seem to be used? * When cachefilesd is running, reads do not come from the page cache * The page cache fills up with something, but the local cache filesystem continues to be read * If the page cache was populated before cachefilesd was launched (ie. with NFS pages), then these are successfully used I tested using a set of large image files which fit in RAM. In the first cases, I'm not sure if the page cache memory contains NFS pages, or local disk pages. Is there an easy way to check? This test is on v2.6.39.4, with the recent patches applied. I didn't need to modify any code, as long as I included one other fscache patch since that version. It seems that v3.0 onward does not boot on my hardw</pre> Mark Hills 2011-10-03T14:53:01 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/3003 <pre> Here are some patches to debug and fix FS-Cache problems. (1) A debugging patch to add a predictable pattern generator with a filesystem interface. Can be used to generate regular apparent changes on the NFS server. This was very useful in breaking FS-Cache. (2) A patch to correctly mark cached netfs pages. (3) A debugging patch to validate page-&gt;mapping on a page for which retrieval was requested. (4) A patch to downgrade memory allocation levels in the cache to not try so hard and to be more willing to abort with ENOMEM. It's a cache - it doesn't matter if we can't store something. (5) A debugging patch to check that there are no read operations outstanding on a cookie when it is relinquished. (6) A debugging patch to check that the object cookie pointer doesn't get cleared whilst we're trying to read for it. (7) A patch to make conditional some debugging prints. (8) A patch to make cookie relinquishment log a warning and wait for any outstanding</pre> David Howells 2011-09-29T14:45:36 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/2988 <pre>Hello to all, I am looking for a possibility to cache reads and writes from and to a nfs mount. Read requests will be cached, that works fine, but I also want to cache writes. The situation is the following: I've got some people working in office A and some in office B. The offices are combined by glusterfs. Write-back or write-behind caching doesn't work in glusterfs, so I am looking for a workaround. The method of storing cached files locally on hard disk is what I'm looking for. So the client applications gets an "finished" and the cachefs / glusterfs is syncing the content in background. Is there a way to use cachefs as a write-back / write-behind cache? thanks a lot, Christian </pre> Christian 2011-08-30T13:19:58 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/2984 <pre>Hello. I have same problem as Mark Hills http://www.spinics.net/lists/linux-cachefs/msg02369.html [416779.040059] CacheFiles: Error: Overlong wait for old active object to go away [416779.040104] object: OBJ43981 [416779.040127] objstate=OBJECT_LOOKING_UP fl=0 wbusy=2 ev=0[7b] [416779.040154] ops=0 inp=0 exc=0 [416779.040174] parent=ffff8800cca3c3c0 [416779.040197] cookie=ffff880100029870 [pr=ffff8801131520f0 nd=ffff88000662b180 fl=7] [416779.040241] key=[36] '010007010100a00800000000e6c715cb23cd4aa38338eea581f3d1045c2e680a1b56d03d' [416779.040325] xobject: OBJ431fe [416779.040348] xobjstate=OBJECT_RECYCLING fl=0 wbusy=2 ev=20[3] [416779.040373] xops=0 inp=0 exc=0 [416779.040394] xparent=ffff8800cca3c3c0 [416779.040416] xcookie=NULL kernel: 2.6.38-8-server from natty Sometimes processes hang, sometimes even kernel panic. Googling gave no answer. Could you give at least some clues how to debug it? </pre> Дмитрий Ильин 2011-08-23T07:30:38 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/2983 <pre>I find CacheFiles gives a valuable performance benefit, but unfortunately is not usable due to hangs. In dmesg "Overlong wait for old active object to go away" (see full message below), and an application will hang or lock, eg. blocking on read(). Sometimes it unblocks, sometimes it seems to hang indefinitely. Is there a higher level explanation for what is going on here? It seems logical that the message is a symptom, rather than the cause itself. What could hold the lock in such a way? The timeout in question appears to be "60 * HZ" in fs/cachefiles/namei.c. I am using the default configuration of cachefilesd, from Git, and kernel 2.6.39.4. Many thanks, </pre> Mark Hills 2011-08-16T15:33:12 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/2982 <pre>Short version: What happens with FS-Cache/cachefilesd as the cache grows to the size of the NFS filesystem it's caching? Where I work we've used a network filesystem to achieve Single System Image for years (actually decades) now. It's been nice, but in the past few years it seems that network speeds haven't kept up. Add to this the fact that disk space is pretty darned cheap, and it makes me wonder about a slightly different operating regime for a network filesystem. We're not using NFS/FS-Cache at work, but I do for my home cluster, prompting this question. I suspect it's a generally applicable question, as well. I'd like to just have enough disk space on my user-facing system(s) to hold all of their data. In this situation, the network filesystem becomes a real-time backup, a way to propagate data to different systems, a way to keep those systems in sync, and since I mentioned backup, a central point to run some sort of "time-machine"-like backup of old files. Are you aware of limita</pre> Dale Pontius 2011-08-16T15:24:18 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/2981 <pre>Hi, I am trying out CacheFS over NFS in RHEL 6.1. If you have any experiences in RHEL6.1 please do share. </pre> Janardhan Molumuri 2011-08-02T01:16:32 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/2980 <pre>From: Jan Beulich &lt;JBeulich&lt; at &gt;novell.com&gt; The compiler, at least for ix86 and m68k, validly warns that the comparison: next &lt;= (loff_t)-1 is always true (and it's always true also for x86-64 and probably all other arches - as long as pgoff_t isn't wider than loff_t). The intention appears to be to avoid wrapping of "next", so rather than eliminating the pointless comparison, fix the loop to indeed get exited when "next" would otherwise wrap. On m68k the following warning is observed: fs/fscache/page.c: In function '__fscache_uncache_all_inode_pages': fs/fscache/page.c:979: warning: comparison is always false due to limited range of data type Reported-by: Geert Uytterhoeven &lt;geert&lt; at &gt;linux-m68k.org&gt; Reported-by: Jan Beulich &lt;jbeulich&lt; at &gt;novell.com&gt; Signed-off-by: Jan Beulich &lt;jbeulich&lt; at &gt;novell.com&gt; Signed-off-by: David Howells &lt;dhowells&lt; at &gt;redhat.com&gt; Cc: Suresh Jayaraman &lt;sjayaraman&lt; at &gt;suse.de&gt; Cc: Geert Uytterhoeven &lt;geert&lt; at &gt;linux-m68k.org&gt; Cc: stable&lt; at &gt;kernel.org --- fs/fscache/page.c | 14 +++++--------- 1 files </pre> David Howells 2011-07-21T14:02:43 http://comments.gmane.org/gmane.linux.file-systems.cachefs.general/2979 <pre>Hello, I am working on a Linux-Media Center. Here, I have some large (video) files, and some small descriptive files. I need a lot of storage, which is either on USB or Network (NFS, Samba). The files are in many sub-directories. Thus, the listing of the recordings, which needs a) Folder Names b) Some info Files with the descriptions is slow and wakes the HDDs from suspend. Thus, I'd like to cache the directory structure and the info-files. Is cachefs the right thing for me? If not, what's an alternative? Regards, Hendrik </pre> Hendrik Friedel 2011-07-09T17:13:09 Search the mailing list at Gmane query http://search.gmane.org/?group=$group=gmane.linux.file-systems.cachefs.general