Revision c4f675cd40d955d539180506c09515c90169b15b authored by Sergei Trofimovich on 20 May 2011, 20:20:30 UTC, committed by Chris Mason on 23 May 2011, 17:24:14 UTC
Observed as a large delay when --mixed filesystem is filled up.
Test example:
1. create tiny --mixed FS:
$ dd if=/dev/zero of=2G.img seek=$((2048 * 1024 * 1024 - 1)) count=1 bs=1
$ mkfs.btrfs --mixed 2G.img
$ mount -oloop 2G.img /mnt/ut/
2. Try to fill it up:
$ dd if=/dev/urandom of=10M.file bs=10240 count=1024
$ seq 1 256 | while read file_no; do echo $file_no; time cp 10M.file ${file_no}.copy; done
Up to '200.copy' it goes fast, but when disk fills-up each -ENOSPC
message takes 3 seconds to pop-up _every_ ENOSPC (and in usermode linux
it's even more: 30-60 seconds!). (Maybe, time depends on kernel's timer resolution).
No IO, no CPU load, just rescheduling. Some debugging revealed busy spinning
in shrink_delalloc.
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Reviewed-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
1 parent 0f3b708
| File | Mode | Size |
|---|---|---|
| ircomm | ||
| irlan | ||
| irnet | ||
| Kconfig | -rw-r--r-- | 3.3 KB |
| Makefile | -rw-r--r-- | 503 bytes |
| af_irda.c | -rw-r--r-- | 67.5 KB |
| discovery.c | -rw-r--r-- | 12.5 KB |
| irda_device.c | -rw-r--r-- | 8.0 KB |
| iriap.c | -rw-r--r-- | 26.3 KB |
| iriap_event.c | -rw-r--r-- | 12.5 KB |
| irias_object.c | -rw-r--r-- | 13.4 KB |
| irlap.c | -rw-r--r-- | 33.7 KB |
| irlap_event.c | -rw-r--r-- | 65.0 KB |
| irlap_frame.c | -rw-r--r-- | 35.9 KB |
| irlmp.c | -rw-r--r-- | 54.3 KB |
| irlmp_event.c | -rw-r--r-- | 26.0 KB |
| irlmp_frame.c | -rw-r--r-- | 14.0 KB |
| irmod.c | -rw-r--r-- | 5.4 KB |
| irnetlink.c | -rw-r--r-- | 3.2 KB |
| irproc.c | -rw-r--r-- | 2.5 KB |
| irqueue.c | -rw-r--r-- | 22.8 KB |
| irsysctl.c | -rw-r--r-- | 7.1 KB |
| irttp.c | -rw-r--r-- | 50.8 KB |
| parameters.c | -rw-r--r-- | 15.4 KB |
| qos.c | -rw-r--r-- | 22.4 KB |
| timer.c | -rw-r--r-- | 6.3 KB |
| wrapper.c | -rw-r--r-- | 13.0 KB |
Computing file changes ...
