FreeBSD supports resource limiting with the rctl(4) framework. It supports various resource types, including I/O resources. It allows to limit resources for users, processes, login classes, and jails. To apply blkiotune limits set limits for the bhyve process. I/O related resources supported by rctl(4) are: readbps filesystem reads, in bytes per second writebps filesystem writes, in bytes per second readiops filesystem reads, in operations per second writeiops filesystem writes, in operations per second Thus, the actual commands look like: rctl -a process:$bhyvepid:writebps:throttle=10000000 rctl -a process:$bhyvepid:readbps:throttle=10000000 rctl -a process:$bhyvepid:writeiops:throttle=20000 rctl -a process:$bhyvepid:readiops:throttle=20000 This is different from the current blkiotune modeling in libvirt as it requires specific device to apply limits to. To adapt this model to per-domain I/O limits, update domain schema to specify "*" as a device name. The rctl(8) may be not available or not enabled, so add a capability check for that. Per process rules get removed when the process disappears, so no special clean up is necessary. Signed-off-by: Roman Bogorodskiy <bogorodskiy@gmail.com> --- Changes since v1: - Documented the "*" device name value in formatdomain.rst - Extended bhyve driver validation to allow only "*" devices and do no allow specifying device weight, added tests for these cases - Updated the RCTL macro to execute the rctl(8) command right away instead of building an array of rules and looping through it once again - Minor formatting fixes docs/formatdomain.rst | 13 ++++-- src/bhyve/bhyve_capabilities.c | 23 ++++++++++ src/bhyve/bhyve_capabilities.h | 1 + src/bhyve/bhyve_domain.c | 20 +++++++++ src/bhyve/bhyve_process.c | 45 +++++++++++++++++++ src/conf/schemas/domaincommon.rng | 5 ++- ...bhyvexml2argv-blkiotune-invalid-device.xml | 32 +++++++++++++ ...yvexml2argv-blkiotune-multiple-devices.xml | 39 ++++++++++++++++ .../x86_64/bhyvexml2argv-blkiotune-weight.xml | 33 ++++++++++++++ .../x86_64/bhyvexml2argv-blkiotune.args | 10 +++++ .../x86_64/bhyvexml2argv-blkiotune.ldargs | 4 ++ .../x86_64/bhyvexml2argv-blkiotune.xml | 32 +++++++++++++ tests/bhyvexml2argvtest.c | 4 ++ .../x86_64/bhyvexml2xmlout-blkiotune.xml | 42 +++++++++++++++++ tests/bhyvexml2xmltest.c | 4 ++ 15 files changed, 302 insertions(+), 5 deletions(-) create mode 100644 tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-invalid-device.xml create mode 100644 tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-multiple-devices.xml create mode 100644 tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-weight.xml create mode 100644 tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.args create mode 100644 tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.ldargs create mode 100644 tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.xml create mode 100644 tests/bhyvexml2xmloutdata/x86_64/bhyvexml2xmlout-blkiotune.xml diff --git a/docs/formatdomain.rst b/docs/formatdomain.rst index 1a4bd4c6e9..6c4e067072 100644 --- a/docs/formatdomain.rst +++ b/docs/formatdomain.rst @@ -1367,10 +1367,15 @@ Block I/O Tuning associated with each guest disk device (contrast this to the <iotune> element of a disk definition (See `Hard drives, floppy disks, CDROMs`_) which can applies to an individual disk). Each ``device`` element has - two mandatory sub-elements, ``path`` describing the absolute path of the - device, and ``weight`` giving the relative weight of that device, in the - range [100, 1000]. After kernel 2.6.39, the value could be in the range [10, - 1000]. :since:`Since 0.9.8` + a mandatory ``path`` sub-element describing the absolute path of the + device. + + A special value ``*`` can be used to throttle all domain + devices. :since:`Since 12.3.0, bhyve` + + An optional ``weight`` sub-element specifies the relative + weight of the device, in the range [100, 1000]. After kernel 2.6.39, + the value could be in the range [10, 1000]. :since:`Since 0.9.8` Additionally, the following optional sub-elements can be used: ``read_bytes_sec`` diff --git a/src/bhyve/bhyve_capabilities.c b/src/bhyve/bhyve_capabilities.c index c3fb88fe9f..1fe0a3ad77 100644 --- a/src/bhyve/bhyve_capabilities.c +++ b/src/bhyve/bhyve_capabilities.c @@ -24,6 +24,7 @@ #include <config.h> #include <sys/utsname.h> #include <dirent.h> +#include <sys/sysctl.h> #include <sys/types.h> #include "viralloc.h" @@ -334,6 +335,27 @@ bhyveProbeCapsVNCPassword(unsigned int *caps, char *binary) } +static void +bhyveProbeCapsRctl(unsigned int *caps) +{ + bool racct_enable; + size_t racct_enable_len; + g_autofree char *rctl = NULL; + + if (!(rctl = virFindFileInPath("rctl"))) + return; + + racct_enable_len = sizeof(racct_enable); + if (sysctlbyname("kern.racct.enable", &racct_enable, + &racct_enable_len, NULL, 0) < 0) + return; + + if (racct_enable) + *caps |= BHYVE_CAP_RCTL; + + return; +} + int virBhyveProbeCaps(unsigned int *caps) { @@ -356,6 +378,7 @@ virBhyveProbeCaps(unsigned int *caps) if ((ret = bhyveProbeCapsVNCPassword(caps, binary))) goto out; + bhyveProbeCapsRctl(caps); out: VIR_FREE(binary); diff --git a/src/bhyve/bhyve_capabilities.h b/src/bhyve/bhyve_capabilities.h index 31fd9ab86a..0302b68e22 100644 --- a/src/bhyve/bhyve_capabilities.h +++ b/src/bhyve/bhyve_capabilities.h @@ -57,6 +57,7 @@ typedef enum { BHYVE_CAP_NVME = 1 << 11, BHYVE_CAP_ACPI = 1 << 12, BHYVE_CAP_NUMA = 1 << 13, + BHYVE_CAP_RCTL = 1 << 14, } virBhyveCapsFlags; int virBhyveProbeGrubCaps(virBhyveGrubCapsFlags *caps); diff --git a/src/bhyve/bhyve_domain.c b/src/bhyve/bhyve_domain.c index 4594d7673f..7bce6a4bc0 100644 --- a/src/bhyve/bhyve_domain.c +++ b/src/bhyve/bhyve_domain.c @@ -464,6 +464,26 @@ bhyveDomainDefValidate(const virDomainDef *def, } } + if (def->blkio.ndevices > 1) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("Per device I/O tuning is not supported")); + return -1; + } else if (def->blkio.ndevices == 1) { + virBlkioDevice *device = &def->blkio.devices[0]; + + if (STRNEQ(device->path, "*")) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("Per device I/O tuning is not supported")); + return -1; + } + + if (device->weight != 0) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("Only \"*\" is supported as a device path for I/O tuning")); + return -1; + } + } + if (!def->os.loader) return 0; diff --git a/src/bhyve/bhyve_process.c b/src/bhyve/bhyve_process.c index 1d436da609..3eb807b9fe 100644 --- a/src/bhyve/bhyve_process.c +++ b/src/bhyve/bhyve_process.c @@ -34,6 +34,7 @@ #include "bhyve_device.h" #include "bhyve_driver.h" +#include "bhyve_capabilities.h" #include "bhyve_command.h" #include "bhyve_firmware.h" #include "bhyve_monitor.h" @@ -132,6 +133,47 @@ bhyveProcessStopHook(struct _bhyveConn *driver, VIR_HOOK_SUBOP_END, NULL, xml, NULL); } +static int +bhyveSetResourceLimits(struct _bhyveConn *driver, virDomainObj *vm) +{ + virBlkioDevice *device; + + if (vm->def->blkio.ndevices != 1) + return 0; + + if ((bhyveDriverGetBhyveCaps(driver) & BHYVE_CAP_RCTL) == 0) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("Cannot set resource limits: RACCT/RCTL is either not supported or not enabled")); + return -1; + } + + device = &vm->def->blkio.devices[0]; + +#define BHYVE_APPLY_RCTL_RULE(field, type, format) \ + do { \ + if ((field)) { \ + g_auto(virBuffer) buf = VIR_BUFFER_INITIALIZER; \ + g_autofree char *rule = NULL; \ + g_autoptr(virCommand) cmd = virCommandNew("rctl"); \ + virBufferAsprintf(&buf, "process:%d:" type ":throttle=" format, \ + vm->pid, (field)); \ + rule = virBufferContentAndReset(&buf); \ + virCommandAddArgList(cmd, "-a", rule, NULL); \ + if (virCommandRun(cmd, NULL) < 0) \ + return -1; \ + } \ + } while (0) + + BHYVE_APPLY_RCTL_RULE(device->riops, "readiops", "%u"); + BHYVE_APPLY_RCTL_RULE(device->wiops, "writeiops", "%u"); + BHYVE_APPLY_RCTL_RULE(device->rbps, "readbps", "%llu"); + BHYVE_APPLY_RCTL_RULE(device->wbps, "writebps", "%llu"); + +#undef BHYVE_APPLY_RCTL_RULE + + return 0; +} + static int virBhyveProcessStartImpl(struct _bhyveConn *driver, virDomainObj *vm, @@ -258,6 +300,9 @@ virBhyveProcessStartImpl(struct _bhyveConn *driver, BHYVE_STATE_DIR) < 0) goto cleanup; + if (bhyveSetResourceLimits(driver, vm) < 0) + goto cleanup; + if (bhyveProcessStartHook(driver, vm, VIR_HOOK_BHYVE_OP_STARTED) < 0) goto cleanup; diff --git a/src/conf/schemas/domaincommon.rng b/src/conf/schemas/domaincommon.rng index db1dcd3bb7..c7f442a4c1 100644 --- a/src/conf/schemas/domaincommon.rng +++ b/src/conf/schemas/domaincommon.rng @@ -1049,7 +1049,10 @@ <element name="device"> <interleave> <element name="path"> - <ref name="absFilePath"/> + <choice> + <ref name="absFilePath"/> + <value>*</value> + </choice> </element> <optional> <element name="weight"> diff --git a/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-invalid-device.xml b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-invalid-device.xml new file mode 100644 index 0000000000..68d6871e0c --- /dev/null +++ b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-invalid-device.xml @@ -0,0 +1,32 @@ +<domain type='bhyve'> + <name>bhyve</name> + <uuid>df3be7e7-a104-11e3-aeb0-50e5492bd3dc</uuid> + <memory>219136</memory> + <vcpu>1</vcpu> + <os> + <type>hvm</type> + </os> + <blkiotune> + <device> + <path>/dev/sda</path> + <read_bytes_sec>10000</read_bytes_sec> + <write_bytes_sec>10000</write_bytes_sec> + <read_iops_sec>20000</read_iops_sec> + <write_iops_sec>20000</write_iops_sec> + </device> + </blkiotune> + <devices> + <disk type='file'> + <driver name='file' type='raw'/> + <source file='/tmp/freebsd.img'/> + <target dev='hda' bus='sata'/> + <address type='drive' controller='0' bus='0' target='2' unit='0'/> + </disk> + <interface type='bridge'> + <mac address='52:54:00:b9:94:02'/> + <model type='virtio'/> + <source bridge="virbr0"/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x03' function='0x0'/> + </interface> + </devices> +</domain> diff --git a/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-multiple-devices.xml b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-multiple-devices.xml new file mode 100644 index 0000000000..a6b689ad9a --- /dev/null +++ b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-multiple-devices.xml @@ -0,0 +1,39 @@ +<domain type='bhyve'> + <name>bhyve</name> + <uuid>df3be7e7-a104-11e3-aeb0-50e5492bd3dc</uuid> + <memory>219136</memory> + <vcpu>1</vcpu> + <os> + <type>hvm</type> + </os> + <blkiotune> + <device> + <path>*</path> + <read_bytes_sec>10000</read_bytes_sec> + <write_bytes_sec>10000</write_bytes_sec> + <read_iops_sec>20000</read_iops_sec> + <write_iops_sec>20000</write_iops_sec> + </device> + <device> + <path>/dev/hda</path> + <read_bytes_sec>10000</read_bytes_sec> + <write_bytes_sec>10000</write_bytes_sec> + <read_iops_sec>20000</read_iops_sec> + <write_iops_sec>20000</write_iops_sec> + </device> + </blkiotune> + <devices> + <disk type='file'> + <driver name='file' type='raw'/> + <source file='/tmp/freebsd.img'/> + <target dev='hda' bus='sata'/> + <address type='drive' controller='0' bus='0' target='2' unit='0'/> + </disk> + <interface type='bridge'> + <mac address='52:54:00:b9:94:02'/> + <model type='virtio'/> + <source bridge="virbr0"/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x03' function='0x0'/> + </interface> + </devices> +</domain> diff --git a/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-weight.xml b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-weight.xml new file mode 100644 index 0000000000..f7603828e0 --- /dev/null +++ b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune-weight.xml @@ -0,0 +1,33 @@ +<domain type='bhyve'> + <name>bhyve</name> + <uuid>df3be7e7-a104-11e3-aeb0-50e5492bd3dc</uuid> + <memory>219136</memory> + <vcpu>1</vcpu> + <os> + <type>hvm</type> + </os> + <blkiotune> + <device> + <path>*</path> + <weight>100</weight> + <read_bytes_sec>10000</read_bytes_sec> + <write_bytes_sec>10000</write_bytes_sec> + <read_iops_sec>20000</read_iops_sec> + <write_iops_sec>20000</write_iops_sec> + </device> + </blkiotune> + <devices> + <disk type='file'> + <driver name='file' type='raw'/> + <source file='/tmp/freebsd.img'/> + <target dev='hda' bus='sata'/> + <address type='drive' controller='0' bus='0' target='2' unit='0'/> + </disk> + <interface type='bridge'> + <mac address='52:54:00:b9:94:02'/> + <model type='virtio'/> + <source bridge="virbr0"/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x03' function='0x0'/> + </interface> + </devices> +</domain> diff --git a/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.args b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.args new file mode 100644 index 0000000000..507e0be668 --- /dev/null +++ b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.args @@ -0,0 +1,10 @@ +bhyve \ +-c 1 \ +-m 214 \ +-u \ +-H \ +-P \ +-s 0:0,hostbridge \ +-s 2:0,ahci,hd:/tmp/freebsd.img \ +-s 3:0,virtio-net,faketapdev,mac=52:54:00:b9:94:02 \ +bhyve diff --git a/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.ldargs b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.ldargs new file mode 100644 index 0000000000..5905f4b3e6 --- /dev/null +++ b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.ldargs @@ -0,0 +1,4 @@ +bhyveload \ +-m 214 \ +-d /tmp/freebsd.img \ +bhyve diff --git a/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.xml b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.xml new file mode 100644 index 0000000000..956d96cf18 --- /dev/null +++ b/tests/bhyvexml2argvdata/x86_64/bhyvexml2argv-blkiotune.xml @@ -0,0 +1,32 @@ +<domain type='bhyve'> + <name>bhyve</name> + <uuid>df3be7e7-a104-11e3-aeb0-50e5492bd3dc</uuid> + <memory>219136</memory> + <vcpu>1</vcpu> + <os> + <type>hvm</type> + </os> + <blkiotune> + <device> + <path>*</path> + <read_bytes_sec>10000</read_bytes_sec> + <write_bytes_sec>10000</write_bytes_sec> + <read_iops_sec>20000</read_iops_sec> + <write_iops_sec>20000</write_iops_sec> + </device> + </blkiotune> + <devices> + <disk type='file'> + <driver name='file' type='raw'/> + <source file='/tmp/freebsd.img'/> + <target dev='hda' bus='sata'/> + <address type='drive' controller='0' bus='0' target='2' unit='0'/> + </disk> + <interface type='bridge'> + <mac address='52:54:00:b9:94:02'/> + <model type='virtio'/> + <source bridge="virbr0"/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x03' function='0x0'/> + </interface> + </devices> +</domain> diff --git a/tests/bhyvexml2argvtest.c b/tests/bhyvexml2argvtest.c index b7749fec6f..71c67ba2a2 100644 --- a/tests/bhyvexml2argvtest.c +++ b/tests/bhyvexml2argvtest.c @@ -289,6 +289,10 @@ mymain(void) DO_TEST_FAILURE("slirp-ip"); DO_TEST("virtio-scsi"); DO_TEST("vcpupin"); + DO_TEST("blkiotune"); + DO_TEST_FAILURE("blkiotune-invalid-device"); + DO_TEST_FAILURE("blkiotune-multiple-devices"); + DO_TEST_FAILURE("blkiotune-weight"); /* Address allocation tests */ DO_TEST("addr-single-sata-disk"); diff --git a/tests/bhyvexml2xmloutdata/x86_64/bhyvexml2xmlout-blkiotune.xml b/tests/bhyvexml2xmloutdata/x86_64/bhyvexml2xmlout-blkiotune.xml new file mode 100644 index 0000000000..4170303a6e --- /dev/null +++ b/tests/bhyvexml2xmloutdata/x86_64/bhyvexml2xmlout-blkiotune.xml @@ -0,0 +1,42 @@ +<domain type='bhyve'> + <name>bhyve</name> + <uuid>df3be7e7-a104-11e3-aeb0-50e5492bd3dc</uuid> + <memory unit='KiB'>219136</memory> + <currentMemory unit='KiB'>219136</currentMemory> + <blkiotune> + <device> + <path>*</path> + <read_iops_sec>20000</read_iops_sec> + <write_iops_sec>20000</write_iops_sec> + <read_bytes_sec>10000</read_bytes_sec> + <write_bytes_sec>10000</write_bytes_sec> + </device> + </blkiotune> + <vcpu placement='static'>1</vcpu> + <os> + <type arch='x86_64'>hvm</type> + <boot dev='hd'/> + </os> + <clock offset='utc'/> + <on_poweroff>destroy</on_poweroff> + <on_reboot>restart</on_reboot> + <on_crash>destroy</on_crash> + <devices> + <disk type='file' device='disk'> + <driver name='file' type='raw'/> + <source file='/tmp/freebsd.img'/> + <target dev='hda' bus='sata'/> + <address type='drive' controller='0' bus='0' target='2' unit='0'/> + </disk> + <controller type='pci' index='0' model='pci-root'/> + <controller type='sata' index='0'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x02' function='0x0'/> + </controller> + <interface type='bridge'> + <mac address='52:54:00:b9:94:02'/> + <source bridge='virbr0'/> + <model type='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x03' function='0x0'/> + </interface> + </devices> +</domain> diff --git a/tests/bhyvexml2xmltest.c b/tests/bhyvexml2xmltest.c index 950aaea672..9fa8a9765d 100644 --- a/tests/bhyvexml2xmltest.c +++ b/tests/bhyvexml2xmltest.c @@ -133,6 +133,10 @@ mymain(void) DO_TEST_DIFFERENT("slirp"); DO_TEST_DIFFERENT("virtio-scsi"); DO_TEST_DIFFERENT("numa"); + DO_TEST_DIFFERENT("blkiotune"); + DO_TEST_FAILURE("blkiotune-invalid-device"); + DO_TEST_FAILURE("blkiotune-weight"); + DO_TEST_FAILURE("blkiotune-multiple-devices"); /* Address allocation tests */ DO_TEST_DIFFERENT("addr-single-sata-disk"); -- 2.52.0