Use 'none' as default io scheduler for virtio-blk devices. Performance
improvements for multi-queue setups and to reduce CPU consumption.
Signed-off-by: Peter Jin <pjin@linux.ibm.com>
Signed-off-by: Jan Höppner <hoeppner@linux.ibm.com>
Performance measurements turned out that in certain situations the
paging/swap logic turns on the rotational feature for block devices. In the
past, this feature has been disabled for DASD devices. FCP and NVMe devices
are considered non-rotational by default (or exposed by the storage server).
Because those are the backing devices on Linux on Z/LinuxONE instances,
ensure that virtio-blk devices are always non-rotational.
Signed-off-by: Peter Jin <pjin@linux.ibm.com>
Signed-off-by: Jan Höppner <hoeppner@linux.ibm.com>
On s390 architecture a newly hotplugged CPU, should only stay offline if
it is on deconfigured state, otherwise it should automatically become
online. Introduce a new udev rule to enforce this behavior. This rule
should always be installed.
Acked-by: Jan Höppner <hoeppner@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Mete Durlu <meted@linux.ibm.com>
Signed-off-by: Steffen Eiden <seiden@linux.ibm.com>
Performance evaluation showed that using the mq-deadline scheduler for DASD
devices leads to a significantly higher CPU consumption compared to using
none scheduler while having the same amount of throughput.
Setting none scheduler as default in the dasd udev rule.
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Signed-off-by: Jan Höppner <hoeppner@linux.ibm.com>
The udev rule for SCSI devices is still using the WAIT_FOR keyword,
which was used to make sure that a file does in fact exist before any
rule is applied. That keyword, however, was removed with systemd-220 and
is therefore no longer valid, which in turn leads to errors on newer
systems.
Use the TEST keyword instead to check the existence of a file before we
apply any rules.
Signed-off-by: Jan Höppner <hoeppner@linux.ibm.com>
Add a new udev rule that is triggered when a KVM VM is started
on the system the very first time. This rule reports over the
sysfs CPI kernel interface that the system is a KVM host.
Currently the cpi.service systemd unit already works with
the CPI sysfs interface. Introduce a new internal utility
script "cpictl" that is used by both the udev rule and
the systemd unit to guarantee coordinated access to the
kernel CPU interface.
Signed-off-by: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Reviewed-by: Viktor Mihajlovski <mihajlov@linux.vnet.ibm.com>
Reviewed-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
This commit is based on the s390-tools-1.39.0 version.
Changes on top of s390-tools-1.39.0:
- Add MIT license to all source files
- Add LICENSE file
- Transform REAMDE to README.md (markdown)
- Add AUTHORS.md file
- Add CONTRIBUTING.md file
- Move changelog from README to CHANGELOG.md file
Reviewed-by: Stefan Haberland <sth@linux.vnet.ibm.com>
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
