[Gluster-users] Parallel process hang on gluster volume
nico at furyweb.fr
nico at furyweb.fr
Fri Jun 21 07:48:47 UTC 2019
I encounterd an issue on production servers using GlusterFS servers 5.1 and clients 4.1.5 when several process write at the same time on a gluster volume.
With more than 48 process writes on the volume at the same time, they are blocked in D state (uninterruptible sleep), I guess some volume settings have to be tuned but can't figure out which.
The client is using op-version 40100 on this volume
Below are volume info, volume settings and ps output on blocked processes.
root at glusterVM1:~# gluster volume info logsscripts
Volume Name: logsscripts
Type: Replicate
Volume ID: cb49af70-d197-43c1-852d-0bcf8dc9f6fa
Status: Started
Snapshot Count: 0
Number of Bricks: 1 x (2 + 1) = 3
Transport-type: tcp
Bricks:
Brick1: glusterVM1:/bricks/logsscripts/brick1/data
Brick2: glusterVM2:/bricks/logsscripts/brick1/data
Brick3: glusterVM3:/bricks/logsscripts/brick1/data (arbiter)
Options Reconfigured:
server.tcp-user-timeout: 42
cluster.data-self-heal-algorithm: full
features.trash: off
diagnostics.client-log-level: ERROR
ssl.cipher-list: HIGH:!SSLv2
server.ssl: on
client.ssl: on
transport.address-family: inet
nfs.disable: on
performance.client-io-threads: off
root at glusterVM1:~# gluster volume get logsscripts all
Option Value
------ -----
cluster.lookup-unhashed on
cluster.lookup-optimize on
cluster.min-free-disk 10%
cluster.min-free-inodes 5%
cluster.rebalance-stats off
cluster.subvols-per-directory (null)
cluster.readdir-optimize off
cluster.rsync-hash-regex (null)
cluster.extra-hash-regex (null)
cluster.dht-xattr-name trusted.glusterfs.dht
cluster.randomize-hash-range-by-gfid off
cluster.rebal-throttle normal
cluster.lock-migration off
cluster.force-migration off
cluster.local-volume-name (null)
cluster.weighted-rebalance on
cluster.switch-pattern (null)
cluster.entry-change-log on
cluster.read-subvolume (null)
cluster.read-subvolume-index -1
cluster.read-hash-mode 1
cluster.background-self-heal-count 8
cluster.metadata-self-heal on
cluster.data-self-heal on
cluster.entry-self-heal on
cluster.self-heal-daemon on
cluster.heal-timeout 600
cluster.self-heal-window-size 1
cluster.data-change-log on
cluster.metadata-change-log on
cluster.data-self-heal-algorithm full
cluster.eager-lock on
disperse.eager-lock on
disperse.other-eager-lock on
disperse.eager-lock-timeout 1
disperse.other-eager-lock-timeout 1
cluster.quorum-type auto
cluster.quorum-count (null)
cluster.choose-local true
cluster.self-heal-readdir-size 1KB
cluster.post-op-delay-secs 1
cluster.ensure-durability on
cluster.consistent-metadata no
cluster.heal-wait-queue-length 128
cluster.favorite-child-policy none
cluster.full-lock yes
cluster.stripe-block-size 128KB
cluster.stripe-coalesce true
diagnostics.latency-measurement off
diagnostics.dump-fd-stats off
diagnostics.count-fop-hits off
diagnostics.brick-log-level INFO
diagnostics.client-log-level ERROR
diagnostics.brick-sys-log-level CRITICAL
diagnostics.client-sys-log-level CRITICAL
diagnostics.brick-logger (null)
diagnostics.client-logger (null)
diagnostics.brick-log-format (null)
diagnostics.client-log-format (null)
diagnostics.brick-log-buf-size 5
diagnostics.client-log-buf-size 5
diagnostics.brick-log-flush-timeout 120
diagnostics.client-log-flush-timeout 120
diagnostics.stats-dump-interval 0
diagnostics.fop-sample-interval 0
diagnostics.stats-dump-format json
diagnostics.fop-sample-buf-size 65535
diagnostics.stats-dnscache-ttl-sec 86400
performance.cache-max-file-size 0
performance.cache-min-file-size 0
performance.cache-refresh-timeout 1
performance.cache-priority
performance.cache-size 32MB
performance.io-thread-count 16
performance.high-prio-threads 16
performance.normal-prio-threads 16
performance.low-prio-threads 16
performance.least-prio-threads 1
performance.enable-least-priority on
performance.iot-watchdog-secs (null)
performance.iot-cleanup-disconnected-reqsoff
performance.iot-pass-through false
performance.io-cache-pass-through false
performance.cache-size 128MB
performance.qr-cache-timeout 1
performance.cache-invalidation false
performance.ctime-invalidation false
performance.flush-behind on
performance.nfs.flush-behind on
performance.write-behind-window-size 1MB
performance.resync-failed-syncs-after-fsyncoff
performance.nfs.write-behind-window-size1MB
performance.strict-o-direct off
performance.nfs.strict-o-direct off
performance.strict-write-ordering off
performance.nfs.strict-write-ordering off
performance.write-behind-trickling-writeson
performance.aggregate-size 128KB
performance.nfs.write-behind-trickling-writeson
performance.lazy-open yes
performance.read-after-open yes
performance.open-behind-pass-through false
performance.read-ahead-page-count 4
performance.read-ahead-pass-through false
performance.readdir-ahead-pass-through false
performance.md-cache-pass-through false
performance.md-cache-timeout 1
performance.cache-swift-metadata true
performance.cache-samba-metadata false
performance.cache-capability-xattrs true
performance.cache-ima-xattrs true
performance.md-cache-statfs off
performance.xattr-cache-list
performance.nl-cache-pass-through false
features.encryption off
encryption.master-key (null)
encryption.data-key-size 256
encryption.block-size 4096
network.frame-timeout 1800
network.ping-timeout 42
network.tcp-window-size (null)
client.ssl on
network.remote-dio disable
client.event-threads 2
client.tcp-user-timeout 0
client.keepalive-time 20
client.keepalive-interval 2
client.keepalive-count 9
network.tcp-window-size (null)
network.inode-lru-limit 16384
auth.allow *
auth.reject (null)
transport.keepalive 1
server.allow-insecure on
server.root-squash off
server.anonuid 65534
server.anongid 65534
server.statedump-path /var/run/gluster
server.outstanding-rpc-limit 64
server.ssl on
auth.ssl-allow *
server.manage-gids off
server.dynamic-auth on
client.send-gids on
server.gid-timeout 300
server.own-thread (null)
server.event-threads 1
server.tcp-user-timeout 42
server.keepalive-time 20
server.keepalive-interval 2
server.keepalive-count 9
transport.listen-backlog 1024
ssl.own-cert (null)
ssl.private-key (null)
ssl.ca-list (null)
ssl.crl-path (null)
ssl.certificate-depth (null)
ssl.cipher-list HIGH:!SSLv2
ssl.dh-param (null)
ssl.ec-curve (null)
transport.address-family inet
performance.write-behind on
performance.read-ahead on
performance.readdir-ahead on
performance.io-cache on
performance.quick-read on
performance.open-behind on
performance.nl-cache off
performance.stat-prefetch on
performance.client-io-threads off
performance.nfs.write-behind on
performance.nfs.read-ahead off
performance.nfs.io-cache off
performance.nfs.quick-read off
performance.nfs.stat-prefetch off
performance.nfs.io-threads off
performance.force-readdirp true
performance.cache-invalidation false
features.uss off
features.snapshot-directory .snaps
features.show-snapshot-directory off
features.tag-namespaces off
network.compression off
network.compression.window-size -15
network.compression.mem-level 8
network.compression.min-size 0
network.compression.compression-level -1
network.compression.debug false
features.default-soft-limit 80%
features.soft-timeout 60
features.hard-timeout 5
features.alert-time 86400
features.quota-deem-statfs off
geo-replication.indexing off
geo-replication.indexing off
geo-replication.ignore-pid-check off
geo-replication.ignore-pid-check off
features.quota off
features.inode-quota off
features.bitrot disable
debug.trace off
debug.log-history no
debug.log-file no
debug.exclude-ops (null)
debug.include-ops (null)
debug.error-gen off
debug.error-failure (null)
debug.error-number (null)
debug.random-failure off
debug.error-fops (null)
nfs.enable-ino32 no
nfs.mem-factor 15
nfs.export-dirs on
nfs.export-volumes on
nfs.addr-namelookup off
nfs.dynamic-volumes off
nfs.register-with-portmap on
nfs.outstanding-rpc-limit 16
nfs.port 2049
nfs.rpc-auth-unix on
nfs.rpc-auth-null on
nfs.rpc-auth-allow all
nfs.rpc-auth-reject none
nfs.ports-insecure off
nfs.trusted-sync off
nfs.trusted-write off
nfs.volume-access read-write
nfs.export-dir
nfs.disable on
nfs.nlm on
nfs.acl on
nfs.mount-udp off
nfs.mount-rmtab /var/lib/glusterd/nfs/rmtab
nfs.rpc-statd /sbin/rpc.statd
nfs.server-aux-gids off
nfs.drc off
nfs.drc-size 0x20000
nfs.read-size (1 * 1048576ULL)
nfs.write-size (1 * 1048576ULL)
nfs.readdir-size (1 * 1048576ULL)
nfs.rdirplus on
nfs.event-threads 1
nfs.exports-auth-enable (null)
nfs.auth-refresh-interval-sec (null)
nfs.auth-cache-ttl-sec (null)
features.read-only off
features.worm off
features.worm-file-level off
features.worm-files-deletable on
features.default-retention-period 120
features.retention-mode relax
features.auto-commit-period 180
storage.linux-aio off
storage.batch-fsync-mode reverse-fsync
storage.batch-fsync-delay-usec 0
storage.owner-uid -1
storage.owner-gid -1
storage.node-uuid-pathinfo off
storage.health-check-interval 30
storage.build-pgfid off
storage.gfid2path on
storage.gfid2path-separator :
storage.reserve 1
storage.health-check-timeout 10
storage.fips-mode-rchecksum off
storage.force-create-mode 0000
storage.force-directory-mode 0000
storage.create-mask 0777
storage.create-directory-mask 0777
storage.max-hardlinks 100
storage.ctime off
storage.bd-aio off
config.gfproxyd off
cluster.server-quorum-type off
cluster.server-quorum-ratio 0
changelog.changelog off
changelog.changelog-dir {{ brick.path }}/.glusterfs/changelogs
changelog.encoding ascii
changelog.rollover-time 15
changelog.fsync-interval 5
changelog.changelog-barrier-timeout 120
changelog.capture-del-path off
features.barrier disable
features.barrier-timeout 120
features.trash off
features.trash-dir .trashcan
features.trash-eliminate-path (null)
features.trash-max-filesize 5MB
features.trash-internal-op off
cluster.enable-shared-storage disable
cluster.write-freq-threshold 0
cluster.read-freq-threshold 0
cluster.tier-pause off
cluster.tier-promote-frequency 120
cluster.tier-demote-frequency 3600
cluster.watermark-hi 90
cluster.watermark-low 75
cluster.tier-mode cache
cluster.tier-max-promote-file-size 0
cluster.tier-max-mb 4000
cluster.tier-max-files 10000
cluster.tier-query-limit 100
cluster.tier-compact on
cluster.tier-hot-compact-frequency 604800
cluster.tier-cold-compact-frequency 604800
features.ctr-enabled off
features.record-counters off
features.ctr-record-metadata-heat off
features.ctr_link_consistency off
features.ctr_lookupheal_link_timeout 300
features.ctr_lookupheal_inode_timeout 300
features.ctr-sql-db-cachesize 12500
features.ctr-sql-db-wal-autocheckpoint 25000
features.selinux on
locks.trace off
locks.mandatory-locking off
cluster.disperse-self-heal-daemon enable
cluster.quorum-reads no
client.bind-insecure (null)
features.timeout 45
features.failover-hosts (null)
features.shard off
features.shard-block-size 64MB
features.shard-lru-limit 16384
features.shard-deletion-rate 100
features.scrub-throttle lazy
features.scrub-freq biweekly
features.scrub false
features.expiry-time 120
features.cache-invalidation off
features.cache-invalidation-timeout 60
features.leases off
features.lease-lock-recall-timeout 60
disperse.background-heals 8
disperse.heal-wait-qlength 128
cluster.heal-timeout 600
dht.force-readdirp on
disperse.read-policy gfid-hash
cluster.shd-max-threads 1
cluster.shd-wait-qlength 1024
cluster.locking-scheme full
cluster.granular-entry-heal no
features.locks-revocation-secs 0
features.locks-revocation-clear-all false
features.locks-revocation-max-blocked 0
features.locks-monkey-unlocking false
features.locks-notify-contention no
features.locks-notify-contention-delay 5
disperse.shd-max-threads 1
disperse.shd-wait-qlength 1024
disperse.cpu-extensions auto
disperse.self-heal-window-size 1
cluster.use-compound-fops off
performance.parallel-readdir off
performance.rda-request-size 131072
performance.rda-low-wmark 4096
performance.rda-high-wmark 128KB
performance.rda-cache-limit 10MB
performance.nl-cache-positive-entry false
performance.nl-cache-limit 10MB
performance.nl-cache-timeout 60
cluster.brick-multiplex off
cluster.max-bricks-per-process 0
disperse.optimistic-change-log on
disperse.stripe-cache 4
cluster.halo-enabled False
cluster.halo-shd-max-latency 99999
cluster.halo-nfsd-max-latency 5
cluster.halo-max-latency 5
cluster.halo-max-replicas 99999
cluster.halo-min-replicas 2
cluster.daemon-log-level INFO
debug.delay-gen off
delay-gen.delay-percentage 10%
delay-gen.delay-duration 100000
delay-gen.enable
disperse.parallel-writes on
features.sdfs on
features.cloudsync off
features.utime off
ctime.noatime on
traitVM2:~# ps fax | grep '[_]save'
7305 ? D 2:57 [remote_save]
7801 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7802 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7803 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7804 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7805 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7806 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7807 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7808 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7809 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7810 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7811 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7812 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7813 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7814 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7815 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7816 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7817 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7818 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7819 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7820 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7821 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7822 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7823 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7824 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7825 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7826 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7827 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7828 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7829 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7830 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7831 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7832 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7833 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7834 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7835 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7836 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7837 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7838 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7839 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7840 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7841 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7842 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7843 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7844 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7845 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7846 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7847 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7848 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7849 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7850 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7851 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7852 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7853 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7854 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7855 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7856 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7857 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7858 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7859 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7860 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7861 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7862 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7863 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7864 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7865 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7866 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7867 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7868 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7869 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7870 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7871 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7872 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7873 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7874 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7875 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7876 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7877 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7878 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7879 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7880 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7881 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7882 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7883 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7884 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
7885 ? D 0:00 \_ /usr/bin/perl /home/prod/current/app/scripts/remote_save.pl 30000
More information about the Gluster-users
mailing list