Skip to content

Add volume heal entries count metric #21634

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 21, 2025
Merged

Add volume heal entries count metric #21634

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d8904d5
Add volume heal entries count metric
ricmatsui Oct 12, 2025
61fad41
Use case-insensitive check for connected status
ricmatsui Oct 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions glusterfs/changelog.d/21634.added
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Add volume heal entries count metric
20 changes: 19 additions & 1 deletion glusterfs/datadog_checks/glusterfs/check.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
except ImportError:
from datadog_checks.base.stubs import datadog_agent

from .metrics import BRICK_STATS, CLUSTER_STATS, PARSE_METRICS, VOL_SUBVOL_STATS, VOLUME_STATS
from .metrics import BRICK_STATS, CLUSTER_STATS, HEAL_INFO_STATS, PARSE_METRICS, VOL_SUBVOL_STATS, VOLUME_STATS

GLUSTER_VERSION = 'glfs_version'
CLUSTER_STATUS = 'cluster_status'
Expand Down Expand Up @@ -156,6 +156,9 @@ def parse_volume_summary(self, output):
if 'subvols' in volume:
self.parse_subvols_stats(volume.get('subvols', []), volume_tags)

if 'healinfo' in volume:
self.parse_healinfo_stats(volume.get('healinfo', []), volume_tags)

self.submit_service_check(self.VOLUME_SC, volume.get('health'), volume_tags)

def parse_subvols_stats(self, subvols, volume_tags):
Expand All @@ -181,6 +184,21 @@ def parse_subvols_stats(self, subvols, volume_tags):
tags.extend(subvol_tags)
self.submit_metrics(brick, 'brick', BRICK_STATS, tags)

def parse_healinfo_stats(self, healinfo, volume_tags):
for info in healinfo:
if info['status'] != 'Connected':
continue

brick_name = info['name'].split(":")
brick_server = brick_name[0]
brick_export = brick_name[1]
tags = [
'brick_server:{}'.format(brick_server),
'brick_export:{}'.format(brick_export),
]
tags.extend(volume_tags)
self.submit_metrics(info, 'heal_info', HEAL_INFO_STATS, tags)

def submit_metrics(self, payload, prefix, metric_mapping, tags):
"""
Parse a payload with a given metric_mapping and submit metric for valid values.
Expand Down
2 changes: 2 additions & 0 deletions glusterfs/datadog_checks/glusterfs/metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,5 +41,7 @@
BRICK_STATS = {'block_size': 'block_size'}
BRICK_STATS.update(GENERAL_STATS)

HEAL_INFO_STATS = {'nr_entries': 'entries.count'}

# Parse metric values that contain measurements, e.g "2.00 GiB"
PARSE_METRICS = ['v_size_used', 'v_size']
1 change: 1 addition & 0 deletions glusterfs/metadata.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ glusterfs.cluster.nodes.active,gauge,,node,,Current active nodes,0,glusterfs,clu
glusterfs.cluster.nodes.count,gauge,,node,,Total number of nodes in cluster,0,glusterfs,cluster node total,
glusterfs.cluster.volumes.count,gauge,,unit,,Number of volumes in cluster,0,glusterfs,cluster volume count,
glusterfs.cluster.volumes.started,gauge,,unit,,Number of volumes started in cluster,0,glusterfs,cluster volume start,
glusterfs.heal_info.entries.count,gauge,,unit,,Number of entries requiring healing,0,glusterfs,entry count,
glusterfs.subvol.disperse,gauge,,unit,,Disperse count of subvolume,0,glusterfs,subvol disperse,
glusterfs.subvol.disperse_redundancy,gauge,,unit,,Disperse redundancy of subvolume,0,glusterfs,subvol disperse redundancy,
glusterfs.subvol.replica,gauge,,unit,,Replicas in subvolume,0,glusterfs,subvol replica,
Expand Down
1 change: 1 addition & 0 deletions glusterfs/tests/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
"glusterfs.cluster.nodes.count",
"glusterfs.cluster.volumes.count",
"glusterfs.cluster.volumes.started",
"glusterfs.heal_info.entries.count",
"glusterfs.subvol.disperse",
"glusterfs.subvol.disperse_redundancy",
"glusterfs.subvol.replica",
Expand Down
2 changes: 1 addition & 1 deletion glusterfs/tests/fixtures/gstatus.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
Note: Unable to get self-heal status for one or more volumes
{"last_updated": "2024-08-29 20:27:02.124097", "data": {"cluster_status": "Healthy", "glfs_version": "7.1", "node_count": 2, "nodes_active": 2, "volume_count": 1, "volumes_started": 1, "volume_summary": [{"name": "gv0", "uuid": "07d66a0b-a91a-40d6-bf9f-61929d580469", "type": "REPLICATE", "status": "Started", "num_bricks": 2, "distribute": 2, "stripe": 1, "replica": 2, "disperse": 0, "disperse_redundancy": 0, "transport": "TCP", "snapshot_count": 0, "options": [{"name": "transport.address-family", "value": "inet"}, {"name": "storage.fips-mode-rchecksum", "value": "on"}, {"name": "nfs.disable", "value": "on"}, {"name": "performance.client-io-threads", "value": "off"}], "subvols": [{"name": "gv0-replicate-0", "replica": 2, "disperse": 0, "disperse_redundancy": 0, "type": "REPLICATE", "bricks": [{"name": "gluster-node-1:/export-test", "uuid": "8012e8ac-7cf5-4b3d-baa1-267bb3e295cc", "online": false, "pid": "-1", "size_total": 124678225920, "size_free": 68029804544, "inodes_total": 15482880, "inodes_free": 14286246, "device": "overlay", "block_size": "4096", "mnt_options": "rw,relatime,lowerdir=/var/lib/docker/overlay2/l/LESL5QOHZYQNDD25KZZHVRX3OB:/var/lib/docker/overlay2/l/PII5LMBVHYV4L4EALWEHCKWPQ3:/var/lib/docker/overlay2/l/OERRABS5DQBFV4INMOMQQ3FX5O:/var/lib/docker/overlay2/l/AYNOUZOPONWWW75WH2RPMP4DOI:/var/lib/docker/overlay2/l/45Q3YDG43GBCMKIJPZDITUUXFX:/var/lib/docker/overlay2/l/G3IKPJOI3F3RIVZEBPTMX5BLPO:/var/lib/docker/overlay2/l/TDLCX2SGGKG7ABDGJDMJC3ONQ6:/var/lib/docker/overlay2/l/Y7CHXYLWEF6HRJBJDI4M5I4GFD:/var/lib/docker/overlay2/l/7TPEWGIZAH3S5U5B72V2K7M3WH:/var/lib/docker/overlay2/l/CKZCWXAMXB6RMLU4A4VFDCOEYK:/var/lib/docker/overlay2/l/NNQ72DJMBC7TUAK277FA5PR4IK:/var/lib/docker/overlay2/l/44LZI42GLK5IHSPPMXPLIEQLHE:/var/lib/docker/overlay2/l/4JUASJHM3RCXVY7LJ77YCXBHWN:/var/lib/docker/overlay2/l/BC4LWP5MFS25IHS7XF2K6LOCZT:/var/lib/docker/overlay2/l/UMY7IRPY4F66A2UYYHWC2XSTZQ:/var/lib/docker/overlay2/l/UQSEQUD36GO7377GNEW5Y5IRR2:/var/lib/docker/overlay2/l/M4WVVFWYC4MNNWA3KUCN2IX64U:/var/lib/docker/overlay2/l/J2RQAAZX2CJNGGPVOVXI253ZVL:/var/lib/docker/overlay2/l/V5VCR6O3VJMTJFBVQ3V2XFBHQ6:/var/lib/docker/overlay2/l/PGLAKHDGTPFYYIXS4ZXF5BCSZZ,upperdir=/var/lib/docker/overlay2/6b5c18e3ea5f4ebbf2d14e6b3d7134177fc8d4a548c83db85d48dc9916a2996e/diff,workdir=/var/lib/docker/overlay2/6b5c18e3ea5f4ebbf2d14e6b3d7134177fc8d4a548c83db85d48dc9916a2996e/work,nouserxattr", "fs_name": "overlay", "size_used": 56648421376, "inodes_used": 1196634, "ports": {"tcp": "N/A", "rdma": "N/A"}, "type": "Brick"}, {"name": "gluster-node-2:/export-test", "uuid": "0e6d296e-eee1-4d9f-9c94-cc8492eb41a6", "online": false, "pid": "-1", "size_total": 124678225920, "size_free": 68029804544, "inodes_total": 15482880, "inodes_free": 14286246, "device": "overlay", "block_size": "4096", "mnt_options": "rw,relatime,lowerdir=/var/lib/docker/overlay2/l/RTX55737OX6K4UJR6OILVMJSEZ:/var/lib/docker/overlay2/l/PII5LMBVHYV4L4EALWEHCKWPQ3:/var/lib/docker/overlay2/l/OERRABS5DQBFV4INMOMQQ3FX5O:/var/lib/docker/overlay2/l/AYNOUZOPONWWW75WH2RPMP4DOI:/var/lib/docker/overlay2/l/45Q3YDG43GBCMKIJPZDITUUXFX:/var/lib/docker/overlay2/l/G3IKPJOI3F3RIVZEBPTMX5BLPO:/var/lib/docker/overlay2/l/TDLCX2SGGKG7ABDGJDMJC3ONQ6:/var/lib/docker/overlay2/l/Y7CHXYLWEF6HRJBJDI4M5I4GFD:/var/lib/docker/overlay2/l/7TPEWGIZAH3S5U5B72V2K7M3WH:/var/lib/docker/overlay2/l/CKZCWXAMXB6RMLU4A4VFDCOEYK:/var/lib/docker/overlay2/l/NNQ72DJMBC7TUAK277FA5PR4IK:/var/lib/docker/overlay2/l/44LZI42GLK5IHSPPMXPLIEQLHE:/var/lib/docker/overlay2/l/4JUASJHM3RCXVY7LJ77YCXBHWN:/var/lib/docker/overlay2/l/BC4LWP5MFS25IHS7XF2K6LOCZT:/var/lib/docker/overlay2/l/UMY7IRPY4F66A2UYYHWC2XSTZQ:/var/lib/docker/overlay2/l/UQSEQUD36GO7377GNEW5Y5IRR2:/var/lib/docker/overlay2/l/M4WVVFWYC4MNNWA3KUCN2IX64U:/var/lib/docker/overlay2/l/J2RQAAZX2CJNGGPVOVXI253ZVL:/var/lib/docker/overlay2/l/V5VCR6O3VJMTJFBVQ3V2XFBHQ6:/var/lib/docker/overlay2/l/PGLAKHDGTPFYYIXS4ZXF5BCSZZ,upperdir=/var/lib/docker/overlay2/c811601994dbcdd9a206a7cff359adb935bbf302e0a74327e1c486067642dc1e/diff,workdir=/var/lib/docker/overlay2/c811601994dbcdd9a206a7cff359adb935bbf302e0a74327e1c486067642dc1e/work,nouserxattr", "fs_name": "overlay", "size_used": 56648421376, "inodes_used": 1196634, "ports": {"tcp": "N/A", "rdma": "N/A"}, "type": "Brick"}], "health": "down"}], "size_total": 124678225920, "size_free": 68029804544, "size_used": 56648421376, "inodes_total": 15482880, "inodes_free": 14286246, "inodes_used": 1196634, "health": "down", "v_size": "116.12 GiB", "v_size_used": "52.76 GiB", "v_used_percent": "45.44", "online": 0, "voltype": "", "quota": ""}]}}
{"last_updated": "2024-08-29 20:27:02.124097", "data": {"cluster_status": "Healthy", "glfs_version": "7.1", "node_count": 2, "nodes_active": 2, "volume_count": 1, "volumes_started": 1, "volume_summary": [{"name": "gv0", "uuid": "07d66a0b-a91a-40d6-bf9f-61929d580469", "type": "REPLICATE", "status": "Started", "num_bricks": 2, "distribute": 2, "stripe": 1, "replica": 2, "disperse": 0, "disperse_redundancy": 0, "transport": "TCP", "snapshot_count": 0, "options": [{"name": "transport.address-family", "value": "inet"}, {"name": "storage.fips-mode-rchecksum", "value": "on"}, {"name": "nfs.disable", "value": "on"}, {"name": "performance.client-io-threads", "value": "off"}], "subvols": [{"name": "gv0-replicate-0", "replica": 2, "disperse": 0, "disperse_redundancy": 0, "type": "REPLICATE", "bricks": [{"name": "gluster-node-1:/export-test", "uuid": "8012e8ac-7cf5-4b3d-baa1-267bb3e295cc", "online": false, "pid": "-1", "size_total": 124678225920, "size_free": 68029804544, "inodes_total": 15482880, "inodes_free": 14286246, "device": "overlay", "block_size": "4096", "mnt_options": "rw,relatime,lowerdir=/var/lib/docker/overlay2/l/LESL5QOHZYQNDD25KZZHVRX3OB:/var/lib/docker/overlay2/l/PII5LMBVHYV4L4EALWEHCKWPQ3:/var/lib/docker/overlay2/l/OERRABS5DQBFV4INMOMQQ3FX5O:/var/lib/docker/overlay2/l/AYNOUZOPONWWW75WH2RPMP4DOI:/var/lib/docker/overlay2/l/45Q3YDG43GBCMKIJPZDITUUXFX:/var/lib/docker/overlay2/l/G3IKPJOI3F3RIVZEBPTMX5BLPO:/var/lib/docker/overlay2/l/TDLCX2SGGKG7ABDGJDMJC3ONQ6:/var/lib/docker/overlay2/l/Y7CHXYLWEF6HRJBJDI4M5I4GFD:/var/lib/docker/overlay2/l/7TPEWGIZAH3S5U5B72V2K7M3WH:/var/lib/docker/overlay2/l/CKZCWXAMXB6RMLU4A4VFDCOEYK:/var/lib/docker/overlay2/l/NNQ72DJMBC7TUAK277FA5PR4IK:/var/lib/docker/overlay2/l/44LZI42GLK5IHSPPMXPLIEQLHE:/var/lib/docker/overlay2/l/4JUASJHM3RCXVY7LJ77YCXBHWN:/var/lib/docker/overlay2/l/BC4LWP5MFS25IHS7XF2K6LOCZT:/var/lib/docker/overlay2/l/UMY7IRPY4F66A2UYYHWC2XSTZQ:/var/lib/docker/overlay2/l/UQSEQUD36GO7377GNEW5Y5IRR2:/var/lib/docker/overlay2/l/M4WVVFWYC4MNNWA3KUCN2IX64U:/var/lib/docker/overlay2/l/J2RQAAZX2CJNGGPVOVXI253ZVL:/var/lib/docker/overlay2/l/V5VCR6O3VJMTJFBVQ3V2XFBHQ6:/var/lib/docker/overlay2/l/PGLAKHDGTPFYYIXS4ZXF5BCSZZ,upperdir=/var/lib/docker/overlay2/6b5c18e3ea5f4ebbf2d14e6b3d7134177fc8d4a548c83db85d48dc9916a2996e/diff,workdir=/var/lib/docker/overlay2/6b5c18e3ea5f4ebbf2d14e6b3d7134177fc8d4a548c83db85d48dc9916a2996e/work,nouserxattr", "fs_name": "overlay", "size_used": 56648421376, "inodes_used": 1196634, "ports": {"tcp": "N/A", "rdma": "N/A"}, "type": "Brick"}, {"name": "gluster-node-2:/export-test", "uuid": "0e6d296e-eee1-4d9f-9c94-cc8492eb41a6", "online": false, "pid": "-1", "size_total": 124678225920, "size_free": 68029804544, "inodes_total": 15482880, "inodes_free": 14286246, "device": "overlay", "block_size": "4096", "mnt_options": "rw,relatime,lowerdir=/var/lib/docker/overlay2/l/RTX55737OX6K4UJR6OILVMJSEZ:/var/lib/docker/overlay2/l/PII5LMBVHYV4L4EALWEHCKWPQ3:/var/lib/docker/overlay2/l/OERRABS5DQBFV4INMOMQQ3FX5O:/var/lib/docker/overlay2/l/AYNOUZOPONWWW75WH2RPMP4DOI:/var/lib/docker/overlay2/l/45Q3YDG43GBCMKIJPZDITUUXFX:/var/lib/docker/overlay2/l/G3IKPJOI3F3RIVZEBPTMX5BLPO:/var/lib/docker/overlay2/l/TDLCX2SGGKG7ABDGJDMJC3ONQ6:/var/lib/docker/overlay2/l/Y7CHXYLWEF6HRJBJDI4M5I4GFD:/var/lib/docker/overlay2/l/7TPEWGIZAH3S5U5B72V2K7M3WH:/var/lib/docker/overlay2/l/CKZCWXAMXB6RMLU4A4VFDCOEYK:/var/lib/docker/overlay2/l/NNQ72DJMBC7TUAK277FA5PR4IK:/var/lib/docker/overlay2/l/44LZI42GLK5IHSPPMXPLIEQLHE:/var/lib/docker/overlay2/l/4JUASJHM3RCXVY7LJ77YCXBHWN:/var/lib/docker/overlay2/l/BC4LWP5MFS25IHS7XF2K6LOCZT:/var/lib/docker/overlay2/l/UMY7IRPY4F66A2UYYHWC2XSTZQ:/var/lib/docker/overlay2/l/UQSEQUD36GO7377GNEW5Y5IRR2:/var/lib/docker/overlay2/l/M4WVVFWYC4MNNWA3KUCN2IX64U:/var/lib/docker/overlay2/l/J2RQAAZX2CJNGGPVOVXI253ZVL:/var/lib/docker/overlay2/l/V5VCR6O3VJMTJFBVQ3V2XFBHQ6:/var/lib/docker/overlay2/l/PGLAKHDGTPFYYIXS4ZXF5BCSZZ,upperdir=/var/lib/docker/overlay2/c811601994dbcdd9a206a7cff359adb935bbf302e0a74327e1c486067642dc1e/diff,workdir=/var/lib/docker/overlay2/c811601994dbcdd9a206a7cff359adb935bbf302e0a74327e1c486067642dc1e/work,nouserxattr", "fs_name": "overlay", "size_used": 56648421376, "inodes_used": 1196634, "ports": {"tcp": "N/A", "rdma": "N/A"}, "type": "Brick"}], "health": "down"}], "size_total": 124678225920, "size_free": 68029804544, "size_used": 56648421376, "inodes_total": 15482880, "inodes_free": 14286246, "inodes_used": 1196634, "health": "down", "v_size": "116.12 GiB", "v_size_used": "52.76 GiB", "v_used_percent": "45.44", "online": 0, "voltype": "", "quota": "", "healinfo": [{ "name": "gluster-node-1:/export-test", "status": "Connected", "host_uuid": "8012e8ac-7cf5-4b3d-baa1-267bb3e295cc", "nr_entries": "0" }, { "name": "gluster-node-2:/export-test", "status": "Unknown error", "host_uuid": "0e6d296e-eee1-4d9f-9c94-cc8492eb41a6", "nr_entries": "-" }]}]}}
Loading