https://github.com/torvalds/linux
Revision a516440542afcb9647f88d12c35640baf02d07ea authored by Jens Axboe on 10 September 2014, 15:02:03 UTC, committed by Jens Axboe on 10 September 2014, 15:02:03 UTC
If we are running in a kdump environment, resources are scarce.
For some SCSI setups with a huge set of shared tags, we run out
of memory allocating what the drivers is asking for. So implement
a scale back logic to reduce the tag depth for those cases, allowing
the driver to successfully load.

We should extend this to detect low memory situations, and implement
a sane fallback for those (1 queue, 64 tags, or something like that).

Tested-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
1 parent df35c7c
History
Tip revision: a516440542afcb9647f88d12c35640baf02d07ea authored by Jens Axboe on 10 September 2014, 15:02:03 UTC
blk-mq: scale depth and rq map appropriate if low on memory
Tip revision: a516440
File Mode Size
Kconfig -rw-r--r-- 803 bytes
Makefile -rw-r--r-- 263 bytes
crypto.c -rw-r--r-- 63.6 KB
debug.c -rw-r--r-- 3.8 KB
dentry.c -rw-r--r-- 2.6 KB
ecryptfs_kernel.h -rw-r--r-- 24.9 KB
file.c -rw-r--r-- 10.2 KB
inode.c -rw-r--r-- 32.7 KB
keystore.c -rw-r--r-- 79.1 KB
kthread.c -rw-r--r-- 4.9 KB
main.c -rw-r--r-- 25.0 KB
messaging.c -rw-r--r-- 13.9 KB
miscdev.c -rw-r--r-- 14.7 KB
mmap.c -rw-r--r-- 16.0 KB
read_write.c -rw-r--r-- 8.5 KB
super.c -rw-r--r-- 6.0 KB

back to top