varnish-counters¶
Varnish counter field definitions¶
Manual section: | 7 |
---|
MAIN – Main counters¶
summs
– counter - debug
stat summ operations
Number of times per-thread statistics were summed into the global counters.
uptime
– counter - info
Child process uptime
How long the child process has been running.
sess_conn
– counter - info
Sessions accepted
Count of sessions successfully accepted
sess_drop
– counter - info
Sessions dropped
Count of sessions silently dropped due to lack of worker thread.
sess_fail
– counter - info
Session accept failures
Count of failures to accept TCP connection.
This counter is the sum of the sess_fail_* counters, which give more detailed information.
sess_fail_econnaborted
– counter - info
Session accept failures: connection aborted
Detailed reason for sess_fail: Connection aborted by the client, usually harmless.
sess_fail_eintr
– counter - info
Session accept failures: interrupted system call
Detailed reason for sess_fail: The accept() call was interrupted, usually harmless
sess_fail_emfile
– counter - info
Session accept failures: too many open files
Detailed reason for sess_fail: No file descriptor was available. Consider raising RLIMIT_NOFILE (see ulimit -n).
sess_fail_ebadf
– counter - info
Session accept failures: bad file descriptor
Detailed reason for sess_fail: The listen socket file descriptor was invalid. Should never happen.
sess_fail_enomem
– counter - info
Session accept failures: not enough memory
Detailed reason for sess_fail: Most likely insufficient socket buffer memory. Should never happen
sess_fail_other
– counter - info
Session accept failures: other
Detailed reason for sess_fail: neither of the above, see Debug log (varnishlog -g raw -I Debug:^Accept).
client_req_400
– counter - info
Client requests received, subject to 400 errors
400 means we couldn’t make sense of the request, it was malformed in some drastic way.
client_req_417
– counter - info
Client requests received, subject to 417 errors
417 means that something went wrong with an Expect: header.
client_req
– counter - info
Good client requests received
The count of parseable client requests seen.
esi_req
– counter - info
ESI subrequests
Number of ESI subrequests made.
esi_req_abort
– counter - info
Aborted ESI subrequests
Number of ESI subrequests aborted before completing because the delivery of the top request or another ESI subrequest failed.
cache_hit
– counter - info
Cache hits
Count of cache hits. A cache hit indicates that an object has been delivered to a client without fetching it from a backend server.
cache_hit_grace
– counter - info
Cache grace hits
Count of cache hits with grace. A cache hit with grace is a cache hit where the object is expired. Note that such hits are also included in the cache_hit counter.
cache_hitpass
– counter - info
Cache hits for pass.
Count of hits for pass. A cache hit for pass indicates that Varnish is going to pass the request to the backend and this decision has been cached in it self. This counts how many times the cached decision is being used.
cache_hitmiss
– counter - info
Cache hits for miss.
Count of hits for miss. A cache hit for miss indicates that Varnish is going to proceed as for a cache miss without request coalescing, and this decision has been cached. This counts how many times the cached decision is being used.
cache_miss
– counter - info
Cache misses
Count of misses. A cache miss indicates the object was fetched from the backend before delivering it to the client.
backend_conn
– counter - info
Backend conn. success
How many backend connections have successfully been established.
backend_unhealthy
– counter - info
Backend conn. not attempted
backend_busy
– counter - info
Backend conn. too many
backend_fail
– counter - info
Backend conn. failures
backend_reuse
– counter - info
Backend conn. reuses
Count of backend connection reuses. This counter is increased whenever we reuse a recycled connection.
backend_recycle
– counter - info
Backend conn. recycles
Count of backend connection recycles. This counter is increased whenever we have a keep-alive connection that is put back into the pool of connections. It has not yet been used, but it might be, unless the backend closes it.
backend_retry
– counter - info
Backend conn. retry
backend_wait
– counter - info
Backend conn. waited in queue for a connection
Count of backend requests that waited in a backend_wait queue for a connection to become available. The size of a backend wait queue is defined by the backend wait_limit property. The wait queue is only used when max_connections to the backend are in use.
backend_wait_fail
– counter - info
Backend conn. waited in queue and did not get a connection
Count of backend requests that waited in a backend_wait queue for a connection to become available and did not get one (timed out). The maximum time to wait in the queue is defined by the backend wait_timeout property.
fetch_head
– counter - info
Fetch no body (HEAD)
beresp with no body because the request is HEAD.
fetch_length
– counter - info
Fetch with Length
beresp.body with Content-Length.
fetch_chunked
– counter - info
Fetch chunked
beresp.body with Chunked.
fetch_eof
– counter - info
Fetch EOF
beresp.body with EOF.
fetch_bad
– counter - info
Fetch bad T-E
beresp.body length/fetch could not be determined.
fetch_none
– counter - info
Fetch no body
beresp.body empty
fetch_1xx
– counter - info
Fetch no body (1xx)
beresp with no body because of 1XX response.
fetch_204
– counter - info
Fetch no body (204)
beresp with no body because of 204 response.
fetch_304
– counter - info
Fetch no body (304)
beresp with no body because of 304 response.
fetch_fast304
– counter - info
Fast 304 inserts
Fast revalidation of stale object because of 304 reponse
fetch_stale_deliver
– counter - info
Stale deliveries
Stale object deliveries via stale.deliver()
fetch_stale_rearm
– counter - info
Stale object rearmed
Stale object was revived or rearmed
fetch_failed
– counter - info
Fetch failed (all causes)
beresp fetch failed.
bgfetch_no_thread
– counter - info
Background fetch failed (no thread)
A bgfetch triggered by a grace hit failed, no thread available.
pools
– gauge - info
Number of thread pools
Number of thread pools. See also parameter thread_pools. NB: Presently pools cannot be removed once created.
threads
– gauge - info
Total number of threads
Number of threads in all pools. See also parameters thread_pools, thread_pool_min and thread_pool_max.
threads_limited
– counter - info
Threads hit max
Number of times more threads were needed, but limit was reached in a thread pool. See also parameter thread_pool_max.
threads_created
– counter - info
Threads created
Total number of threads created in all pools.
threads_destroyed
– counter - info
Threads destroyed
Total number of threads destroyed in all pools.
threads_failed
– counter - info
Thread creation failed
Number of times creating a thread failed. See VSL::Debug for diagnostics. See also parameter thread_fail_delay.
thread_queue_len
– gauge - info
Length of session queue
Length of session queue waiting for threads. NB: Only updates once per second. See also parameter thread_queue_limit.
task_track_slots
– gauge - info
Available slots to track tasks
The number of slots available to keep track of new tasks or threads not assigned a task yet. See also parameters thread_pool_track and vst_space.
task_track_failed
– counter - info
Failed to track a task
The number of times a worker thread failed to acquire a slot to keep track of a task or itself. See also parameters thread_pool_track and vst_space.
busy_sleep
– counter - info
Number of requests sent to sleep on busy objhdr
Number of requests sent to sleep without a worker thread because they found a busy object.
busy_wakeup
– counter - info
Number of requests woken after sleep on busy objhdr
Number of requests taken off the busy object sleep list and rescheduled.
busy_killed
– counter - info
Number of requests killed after sleep on busy objhdr
Number of requests killed from the busy object sleep list due to the client going away.
sess_queued
– counter - info
Sessions queued for thread
Number of times session was queued waiting for a thread. See also parameter thread_queue_limit.
sess_dropped
– counter - info
Sessions dropped for thread
Number of times an HTTP/1 session was dropped because the queue was too long already. See also parameter thread_queue_limit.
req_dropped
– counter - info
Requests dropped
Number of times an HTTP/2 stream was refused because the queue was too long already. See also parameter thread_queue_limit.
req_reset
– counter - info
Requests reset
Number of times a client left before the VCL processing of its requests completed. For HTTP/2 sessions, either the stream was reset by an RST_STREAM frame from the client, or a stream or connection error occurred.
n_object
– gauge - info
object structs made
Approximate number of HTTP objects (headers + body, if present) in the cache. This count includes hit-for-miss and hit-for-pass objects. See the counters n_object_hitmiss and n_object_hitpass.
n_object_hitmiss
– gauge - info
object structs made that are hit-for-miss
Approximate number of hit-for-miss objects in the cache.
n_object_hitpass
– gauge - info
object structs made that are hit-for-pass
Approximate number of hit-for-pass objects in the cache.
n_vampireobject
– gauge - diag
unresurrected objects
Number of unresurrected objects
n_objectcore
– gauge - info
objectcore structs made
Approximate number of object metadata elements in the cache. Each object needs an objectcore, extra objectcores are for hit-for-miss, hit-for-pass and busy objects.
n_objecthead
– gauge - info
objecthead structs made
Approximate number of different hash entries in the cache.
n_backend
– gauge - info
Number of backends
Number of backends known to us.
n_expired
– counter - info
Number of expired objects
Number of objects that expired from cache because of old age.
n_superseded
– counter - diag
Number of superseded objects
Number of times an object is invalidated because a fresh new copy replaced it.
n_lru_nuked
– counter - info
Number of LRU nuked objects
How many objects have been forcefully evicted from storage to make room for a new object.
n_lru_moved
– counter - diag
Number of LRU moved objects
Number of move operations done on the LRU list.
n_lru_limited
– counter - info
Reached nuke_limit
Number of times more storage space were needed, but limit was reached in a nuke_limit. See also parameter nuke_limit.
losthdr
– counter - info
HTTP header overflows
s_sess
– counter - info
Total sessions seen
s_pipe
– counter - info
Total pipe sessions seen
s_connect
– counter - info
Total CONNECT sessions seen
s_pass
– counter - info
Total pass-ed requests seen
s_fetch
– counter - info
Total backend fetches initiated
s_synth
– counter - info
Total synthetic responses made
s_req_hdrbytes
– counter - info
Request header bytes
Total request header bytes received
s_req_bodybytes
– counter - info
Request body bytes
Total request body bytes received
s_resp_hdrbytes
– counter - info
Response header bytes
Total response header bytes transmitted
s_resp_bodybytes
– counter - info
Response body bytes
Total response body bytes transmitted
s_pipe_hdrbytes
– counter - info
Pipe request header bytes
Total request bytes received for piped sessions
s_pipe_in
– counter - info
Piped bytes from client
Total number of bytes forwarded from clients in pipe sessions
s_pipe_out
– counter - info
Piped bytes to client
Total number of bytes forwarded to clients in pipe sessions
transit_stored
– counter - info
Stored body bytes of uncacheable responses
Total number of uncacheable responses body bytes that were stored.
transit_buffered
– counter - info
Body bytes of uncacheable responses that used the transit buffer.
Total number of uncacheable responses body bytes that used the transit buffer.
s_connect_hdrbytes_in
– counter - info
CONNECT request header bytes
Total request bytes received for CONNECT tunnels
s_connect_hdrbytes_out
– counter - info
CONNECT response header bytes
s_connect_in
– counter - info
CONNECT bytes tunnelled from client
Total number of bytes forwarded from clients in CONNECT tunnels
s_connect_out
– counter - info
CONNECT bytes tunnelled to client
Total number of bytes forwarded to clients in CONNECT tunnels
sess_closed
– counter - info
Session Closed
sess_closed_err
– counter - info
Session Closed with error
Total number of sessions closed with errors. See sc_* diag counters for detailed breakdown
sess_readahead
– counter - info
Session Read Ahead
sess_herd
– counter - diag
Session herd
Number of times the timeout_linger triggered
sc_rem_close
– counter - diag
Session OK REM_CLOSE
Number of session closes with REM_CLOSE (Client Closed)
sc_req_close
– counter - diag
Session OK REQ_CLOSE
Number of session closes with REQ_CLOSE (Client requested close)
sc_req_http10
– counter - diag
Session Err REQ_HTTP10
Number of session closes with Error REQ_HTTP10 (Proto < HTTP/1.1)
sc_rx_bad
– counter - diag
Session Err RX_BAD
Number of session closes with Error RX_BAD (Received bad req/resp)
sc_rx_body
– counter - diag
Session Err RX_BODY
Number of session closes with Error RX_BODY (Failure receiving req.body)
sc_rx_junk
– counter - diag
Session Err RX_JUNK
Number of session closes with Error RX_JUNK (Received junk data)
sc_rx_overflow
– counter - diag
Session Err RX_OVERFLOW
Number of session closes with Error RX_OVERFLOW (Received buffer overflow)
sc_rx_timeout
– counter - diag
Session Err RX_TIMEOUT
Number of session closes with Error RX_TIMEOUT (Receive timeout)
sc_tx_pipe
– counter - diag
Session OK TX_PIPE
Number of session closes with TX_PIPE (Piped transaction)
sc_tx_error
– counter - diag
Session Err TX_ERROR
Number of session closes with Error TX_ERROR (Error transaction)
sc_tx_eof
– counter - diag
Session OK TX_EOF
Number of session closes with TX_EOF (EOF transmission)
sc_resp_close
– counter - diag
Session OK RESP_CLOSE
Number of session closes with RESP_CLOSE (Backend/VCL requested close)
sc_overload
– counter - diag
Session Err OVERLOAD
Number of session closes with Error OVERLOAD (Out of some resource)
sc_pipe_overflow
– counter - diag
Session Err PIPE_OVERFLOW
Number of session closes with Error PIPE_OVERFLOW (Session pipe overflow)
sc_range_short
– counter - diag
Session Err RANGE_SHORT
Number of session closes with Error RANGE_SHORT (Insufficient data for range)
sc_req_http20
– counter - diag
Session Err REQ_HTTP20
Number of session closes with Error REQ_HTTP20 (HTTP2 not accepted)
sc_vcl_failure
– counter - diag
Session Err VCL_FAILURE
Number of session closes with Error VCL_FAILURE (VCL failure)
sc_vdp_error
– counter - diag
Session Err VDP_FAILURE
Number of times an object delivery failed due to errors reported in the VDP layer
sc_stream_failure
– counter - diag
Session Err VDP_ERROR_FETCH
sc_sock_closed
– counter - diag
Session OK SOCK_CLOSED
Number of times a session was closed because the session’s listen socket was closed. See socket.close in the CLI.
sc_rapid_reset
– counter - diag
Session Err RAPID_RESETNumber of times we failed an http/2 session because it hit its configured limits for the number of permitted rapid stream resets.
sc_bankrupt
– counter - diag
Session Err BANKRUPT
Number of times we failed an http/2 session because all the streams were waiting for their windows to be credited when h2_window_timeout triggered.
client_resp_500
– counter - diag
Delivery failed due to insufficient workspace.
Number of times we failed a response due to running out of workspace memory during delivery.
ws_backend_overflow
– counter - diag
workspace_backend overflows
Number of times we ran out of space in workspace_backend.
ws_client_overflow
– counter - diag
workspace_client overflows
Number of times we ran out of space in workspace_client.
ws_thread_overflow
– counter - diag
workspace_thread overflows
Number of times we ran out of space in workspace_thread.
ws_session_overflow
– counter - diag
workspace_session overflows
Number of times we ran out of space in workspace_session.
shm_records
– counter - diag
SHM records
Number of log records written to the shared memory log.
shm_writes
– counter - diag
SHM writes
Number of individual writes to the shared memory log. A single write may batch multiple records for bufferred tasks.
shm_flushes
– counter - diag
SHM flushes due to overflow
Number of writes performed before the end of a bufferred task because adding a record to a batch would exceed vsl_buffer.
shm_cont
– counter - diag
SHM lock contention
Number of times a write had to wait for the lock.
shm_cycles
– counter - diag
SHM cycles through VSL space
Number of times a write of log records would reach past the end of the shared memory log, cycling back to the beginning.
shm_bytes
– counter - diag
SHM bytes
Number of bytes written to the shared memory log.
backend_req
– counter - info
Backend requests made
n_vcl
– gauge - info
Number of loaded VCLs in total
n_vcl_avail
– gauge - diag
Number of VCLs available
n_vcl_discard
– gauge - diag
Number of discarded VCLs
vcl_fail
– counter - info
VCL failures
Count of failures which prevented VCL from completing.
bans
– gauge - info
Count of bans
Number of all bans in system, including bans superseded by newer bans and bans already checked by the ban-lurker.
bans_completed
– gauge - diag
Number of bans marked ‘completed’
Number of bans which are no longer active, either because they got checked by the ban-lurker or superseded by newer identical bans.
bans_obj
– gauge - diag
Number of bans using obj.*
Number of bans which use obj.* variables. These bans can possibly be washed by the ban-lurker.
bans_req
– gauge - diag
Number of bans using req.*
Number of bans which use req.* variables. These bans can not be washed by the ban-lurker.
bans_added
– counter - diag
Bans added
Counter of bans added to ban list.
bans_deleted
– counter - diag
Bans deleted
Counter of bans deleted from ban list.
bans_tested
– counter - diag
Bans tested against objects (lookup)
Count of how many bans and objects have been tested against each other during hash lookup.
bans_obj_killed
– counter - diag
Objects killed by bans (lookup)
Number of objects killed by bans during object lookup.
bans_lurker_tested
– counter - diag
Bans tested against objects (lurker)
Count of how many bans and objects have been tested against each other by the ban-lurker.
bans_tests_tested
– counter - diag
Ban tests tested against objects (lookup)
Count of how many tests and objects have been tested against each other during lookup. ‘ban req.url == foo && req.http.host == bar’ counts as one in ‘bans_tested’ and as two in ‘bans_tests_tested’
bans_lurker_tests_tested
– counter - diag
Ban tests tested against objects (lurker)
Count of how many tests and objects have been tested against each other by the ban-lurker. ‘ban req.url == foo && req.http.host == bar’ counts as one in ‘bans_tested’ and as two in ‘bans_tests_tested’
bans_lurker_obj_killed
– counter - diag
Objects killed by bans (lurker)
Number of objects killed by the ban-lurker.
bans_lurker_obj_killed_cutoff
– counter - diag
Objects killed by bans for cutoff (lurker)
Number of objects killed by the ban-lurker to keep the number of bans below ban_cutoff.
bans_dups
– counter - diag
Bans superseded by other bans
Count of bans replaced by later identical bans.
bans_lurker_contention
– counter - diag
Lurker gave way for lookup
Number of times the ban-lurker had to wait for lookups.
n_purges
– counter - info
Number of purge operations executed
n_obj_purged
– counter - info
Number of purged objects
exp_mailed
– counter - diag
Number of objects mailed to expiry thread
Number of objects mailed to expiry thread for handling.
exp_received
– counter - diag
Number of objects received by expiry thread
Number of objects received by expiry thread for handling.
goto_dns_cache_hits
– counter - diag
Cache hits within vmod_goto’s DNS
Count the number of cache hits from vmod_goto’s DNS
goto_dns_lookups
– counter - diag
Number of DNS lookups from vmod_goto’s DNS
Count the number DNS lookups from vmod_goto’s DNS. This is also a cache miss.
goto_dns_lookup_fails
– counter - diag
Number of unresolved DNS lookups from vmod_goto’s DNS
Count the number unresolved DNS lookups from vmod_goto’s DNS
hcb_nolock
– counter - debug
HCB Lookups without lock
hcb_lock
– counter - debug
HCB Lookups with lock
hcb_insert
– counter - debug
HCB Inserts
esi_errors
– counter - diag
ESI parse errors (unlock)
esi_warnings
– counter - diag
ESI parse warnings (unlock)
esi_maxdepth
– counter - diag
ESI hit max_esi_depth
ESI subrequest ignored due to hitting max_esi_depth
vmods
– gauge - info
Loaded VMODs
n_gzip
– counter - info
Gzip operations
n_gunzip
– counter - info
Gunzip operations
n_test_gunzip
– counter - info
Test gunzip operations
Those operations occur when Varnish receives a compressed object from a backend. They are done to verify the gzip stream while it’s inserted in storage.
c_ykey_purges
– counter - info
YKey purge operations
Count the number of YKey purge operations, even when no object was actually purged.
c_ykey_purges_slicer
– counter - info
Internal slicer YKey purge operations
Count the number of YKey purge operations initiated internally by the slicer. Slicer-initiated ykey purges are not included in the c_ykey_purges counter.
c_ykey_stats
– counter - info
YKey stats operations
Count the number of YKey stats operations, even when no object was actually found. Does not count cached operations.
g_mem_rss
– gauge - info
Worker process RSS memory usage
The total (Resident Set Size) memory usage of the Varnish cache worker process. This is the sum of g_mem_private and g_mem_file.
g_mem_private
– gauge - info
Worker process private memory usage
The Varnish cache worker process private memory usage. This is the accumulated memory usage of all internal memory allocations, including data structures, workspaces, thread stacks and object payload data.
g_mem_file
– gauge - diag
RSS file usage
The Varnish cache worker process file backed page cache memory usage. This is the memory component of the file system backed run time data files like the loaded VCL programs, varnishstat counters and the shared memory log. When using MSE in persisted mode, it also includes the book data (but not store data).
g_mem_swap
– gauge - diag
Varnish worker process swap usage
The amount of private memory of the Varnish cache worker process currently forced out to system swap.
http1_iovs_flush
– counter - info
Premature iovec flushes
vgs_msg_created
– counter - info
Gravestone message created
Number of messages created for a gravestone.
vgs_msg_nospace
– counter - info
Gravestone message insufficient space
Number of messages not created for a gravestone due to insufficient space. Check ‘-p epitaphs’.
vgs_msg_frozen
– counter - info
Gravestone message frozen
Number of messages frozen for a gravestone. A Frozen message is an incomplete message written by the child. When the remainder of the message is written the message goes from the state frozen to locked.
vgs_msg_locked
– counter - info
Gravestone message locked
Number of messages locked for a gravestone. A locked message is a fully written message by the child awating for the manager process’s rescue.
MGT – Management Process Counters¶
uptime
– counter - info
Management process uptime
Uptime in seconds of the management process
child_start
– counter - diag
Child process started
Number of times the child process has been started
child_exit
– counter - diag
Child process normal exit
Number of times the child process has been cleanly stopped
child_stop
– counter - diag
Child process unexpected exit
Number of times the child process has exited with an unexpected return code
child_died
– counter - diag
Child process died (signal)
Number of times the child process has died due to signals
child_dump
– counter - diag
Child process core dumped
Number of times the child process has produced core dumps
child_panic
– counter - diag
Child process panic
Number of times the management process has caught a child panic
vgs_registered
– counter - diag
Gravestone registered
Number of times the management process has registered a gravestone for child’s birth.
vgs_msg_rescued
– counter - diag
Gravestone messages resuced
Number of times the management process has resuced a message from child’s gravecut.
vgs_msg_frozen
– counter - diag
Gravestone messages frozen
Number of times the management process has resuced an incomplete message from child’s gravecut.
vgs_msg_cleared
– counter - diag
Gravestone messages cleared
Number of times the management process has cleared a message from child’s gravecut.
MEMPOOL – Memory Pool Counters¶
live
– gauge - debug
In use
pool
– gauge - debug
In Pool
sz_wanted
– gauge - debug
Size requested
sz_actual
– gauge - debug
Size allocated
allocs
– counter - debug
Allocations
frees
– counter - debug
Frees
recycle
– counter - debug
Recycled from pool
timeout
– counter - debug
Timed out from pool
toosmall
– counter - debug
Too small to recycle
surplus
– counter - debug
Too many for pool
randry
– counter - debug
Pool ran dry
SMA – Malloc Stevedore Counters¶
c_req
– counter - info
Allocator requests
Number of times the storage has been asked to provide a storage segment.
c_fail
– counter - info
Allocator failures
Number of times the storage has failed to provide a storage segment.
c_bytes
– counter - info
Bytes allocated
Number of total bytes allocated by this storage.
c_freed
– counter - info
Bytes freed
Number of total bytes returned to this storage.
g_alloc
– gauge - info
Allocations outstanding
Number of storage allocations outstanding.
g_bytes
– gauge - info
Bytes outstanding
Number of bytes allocated from the storage.
g_space
– gauge - info
Bytes available
Number of bytes left in the storage.
g_ykey_keys
– gauge - diag
Number of YKeys registered
This is the number of YKeys registered in this storage.
c_ykey_purged
– counter - diag
Number of objects purged with YKey
This is the number of objects purged with YKey in this storage.
c_ykey_purged_slicer
– counter - diag
Number of slicer objects purged with YKey
This is the number of slicer objects purged with YKey in this storage. Slicer object purges are not included in the c_ykey_purged counter.
c_ykey_stats
– counter - diag
Number of objects with YKey stats
This is the number of objects queried for stats with YKey in this storage.
c_ykey_stats_slicer
– counter - diag
Number of slicer objects with YKey stats
This is the number of slicer objects queried for stats with YKey in this storage. Slicer object queried for stats are not included in the c_ykey_stats counter.
SMU – Umem Stevedore Counters¶
c_req
– counter - info
Allocator requests
Number of times the storage has been asked to provide a storage segment.
c_fail
– counter - info
Allocator failures
Number of times the storage has failed to provide a storage segment.
c_bytes
– counter - info
Bytes allocated
Number of total bytes allocated by this storage.
c_freed
– counter - info
Bytes freed
Number of total bytes returned to this storage.
g_alloc
– gauge - info
Allocations outstanding
Number of storage allocations outstanding.
g_bytes
– gauge - info
Bytes outstanding
Number of bytes allocated from the storage.
g_space
– gauge - info
Bytes available
Number of bytes left in the storage.
SMF – File Stevedore Counters¶
c_req
– counter - info
Allocator requests
Number of times the storage has been asked to provide a storage segment.
c_fail
– counter - info
Allocator failures
Number of times the storage has failed to provide a storage segment.
c_bytes
– counter - info
Bytes allocated
Number of total bytes allocated by this storage.
c_freed
– counter - info
Bytes freed
Number of total bytes returned to this storage.
g_alloc
– gauge - info
Allocations outstanding
Number of storage allocations outstanding.
g_bytes
– gauge - info
Bytes outstanding
Number of bytes allocated from the storage.
g_space
– gauge - info
Bytes available
Number of bytes left in the storage.
g_smf
– gauge - info
N struct smf
g_smf_frag
– gauge - info
N small free smf
g_smf_large
– gauge - info
N large free smf
g_ykey_keys
– gauge - diag
Number of YKeys registered
This is the number of YKeys registered in this storage.
c_ykey_purged
– counter - diag
Number of objects purged with YKey
This is the number of objects purged with YKey in this storage.
c_ykey_purged_slicer
– counter - diag
Number of slicer objects purged with YKey
This is the number of slicer objects purged with YKey in this storage. Slicer object purges are not included in the c_ykey_purged counter.
c_ykey_stats
– counter - diag
Number of objects with YKey stats
This is the number of objects queried for stats with YKey in this storage.
c_ykey_stats_slicer
– counter - diag
Number of slicer objects with YKey stats
This is the number of slicer objects queried for stats with YKey in this storage. Slicer object queried for stats are not included in the c_ykey_stats counter.
VBE – Backend Counters¶
happy
– bitmap - info
Happy health probes
is_healthy
– boolean - info
Backend health status
Wether or not the backend is currently considered healthy.
bereq_hdrbytes
– counter - info
Request header bytes
Total backend request header bytes sent
bereq_bodybytes
– counter - info
Request body bytes
Total backend request body bytes sent
beresp_hdrbytes
– counter - info
Response header bytes
Total backend response header bytes received
beresp_bodybytes
– counter - info
Response body bytes
Total backend response body bytes received
pipe_hdrbytes
– counter - info
Pipe request header bytes
Total request bytes sent for piped sessions
pipe_out
– counter - info
Piped bytes to backend
Total number of bytes forwarded to backend in pipe sessions
pipe_in
– counter - info
Piped bytes from backend
Total number of bytes forwarded from backend in pipe sessions
connect_out
– counter - info
CONNECT bytes tunnelled to backend
Total number of bytes forwarded to backend in CONNECT tunnels
connect_in
– counter - info
CONNECT bytes tunnelled from backend
Total number of bytes forwarded from backend in CONNECT tunnels
conn
– gauge - info
Concurrent connections to backend
req
– counter - info
Backend requests sent
unhealthy
– counter - info
Fetches not attempted due to backend being unhealthy
busy
– counter - info
Fetches not attempted due to backend being busy
Number of times the max_connections limit was reached
fail
– counter - info
Connections failed
Counter of failed opens. Detailed reasons are given in the fail_* counters (DIAG level) and in Debug VSL.
This counter is the sum of all detailed fail_* counters.
All fail_* counters may be slightly inaccurate for efficiency.
fail_eacces
– counter - diag
Connections failed with EACCES or EPERM
fail_eaddrnotavail
– counter - diag
Connections failed with EADDRNOTAVAIL
fail_econnrefused
– counter - diag
Connections failed with ECONNREFUSED
fail_enetunreach
– counter - diag
Connections failed with ENETUNREACH
fail_etimedout
– counter - diag
Connections failed ETIMEDOUT
fail_other
– counter - diag
Connections failed for other reason
helddown
– counter - diag
Connection opens not attempted
Connections not attempted during the backend_local_error_holddown or backend_remote_error_holddown interval after a fundamental connection issue.
LCK – Lock Counters¶
Counters which track the activity in the different classes of mutex-locks.
The counts may be slightly wrong if there are more than one lock instantiated in each class (ie: .creat > 1)
creat
– counter - debug
Created locks
destroy
– counter - debug
Destroyed locks
locks
– counter - debug
Lock Operations
WAITER – Waiter counters¶
conns
– gauge - debug
Number of idle connections
Number of idle connections being waited over.
remclose
– counter - debug
Number of idle connections closed by peer
Number of idle connections that experienced closure by peer while being waited for.
timeout
– counter - debug
Number of idle connections timeout
Number of idle connections that experienced a timeout event while being waited for.
action
– counter - debug
Number of idle connections read events
Number of idle connections that experienced a read event while being waited for.
MSE – MSE¶
c_req
– counter - info
Allocator requestsNumber of times the memory allocator has been invoked.
c_fail
– counter - info
Allocator failuresNumber of times the allocator failed to provide free memory after exhausting the LRU list.
c_fail_malloc
– counter - diag
System allocator failuresNumber of times the system allocator has failed an allocation request.
c_bytes
– counter - info
Bytes allocatedTotal number of bytes the memory allocator has handed out for cache object storage.
c_freed
– counter - info
Bytes freedTotal number of bytes handed back to the memory allocator when freeing objects.
g_alloc
– gauge - info
Allocations outstandingNumber of chunks currently used for cache object storage.
g_bytes
– gauge - info
Bytes outstandingNumber of bytes currently used for cache object storage.
g_space
– gauge - info
Bytes availableNumber of bytes available to be used for cache object storage. When the Varnish memory governor is in use it will show the difference between the configured memory target and the actual memory usage of the Varnish cache worker process (see varnish-mse(7)).
n_lru_nuked
– counter - info
Number of LRU nuked objectsThe number of memory only objects or persisted object chunks that have been forcefully evicted from the memory cache to make room for a new object.
n_lru_moved
– counter - diag
Number of LRU move operationsNumber of move operations done on the LRU list.
n_vary
– counter - info
Number of Vary header keysNumber of Vary header instruction keys stored for the objects in the memory cache. One per unique Vary header seen from the backend responses.
c_memcache_hit
– counter - info
Stored objects cache hitsNumber of bytes of memory cache hits for stored objects.
c_memcache_miss
– counter - info
Stored objects cache missesNumber of bytes of memory cache misses for stored objects.
g_ykey_keys
– gauge - diag
Number of YKeys registeredThis is the number of YKeys registered for memory only objects in this storage.
c_ykey_purged
– counter - diag
Number of objects purged with YKeyThis is the number of memory only objects purged with YKey in this storage.
c_ykey_purged_slicer
– counter - diag
Number of slicer objects purged with YKeyThis is the number of memory only slicer objects purged with YKey in this storage. Slicer object purges are not included in the c_ykey_purged counter.
c_ykey_stats
– counter - diag
Number of objects with YKey statsThis is the number of memory only objects queried for stats with YKey in this storage.
c_ykey_stats_slicer
– counter - diag
Number of slicer objects with YKey statsThis is the number of memory only slicer objects queried for stats with YKey in this storage. Slicer object queried for stats are not included in the c_ykey_stats counter.
c_da_inserts
– counter - diag
Number of degradable object insertedThis is the number of degradable objects inserted to the gravestone to either degrade a book or store.
c_da_removals
– counter - diag
Number of degradable object removalsThis is the number of degradable objects inserted to the gravestone to either revieve a book or store.
g_da_inherited
– gauge - diag
Number of degradable object inherited from MGTThis is the number of degradable objects inherited from the manager. The origin of these could either be from the previous child or come from the persisted state.
MSE_BOOK – MSE_BOOK¶
n_vary
– counter - info
Number of Vary header keysNumber of Vary header instruction keys persisted for the objects in this book. One per unique Vary keader seen from the backend responses.
g_bytes
– gauge - info
Number of bytes used in the book database.Number of bytes used in the book database.
g_space
– gauge - info
Number of bytes available in the book database.Number of bytes available in the book database.
g_waterlevel_queue
– gauge - diag
Number of threads queued waiting for database spaceNumber of threads queued waiting for database space
c_waterlevel_queue
– counter - diag
Number of times a thread has been queued waiting for database spaceNumber of times a thread have been queued waiting for database space
c_waterlevel_runs
– counter - diag
Number of times the waterlevel purge thread was activatedNumber of times the waterlevel purge thread was activated
c_waterlevel_purge
– counter - diag
Number of objects purged to achieve database waterlevelNumber of objects purged to achieve database waterlevel
c_insert_timeout
– counter - diag
Number of times database object insertion timed outNumber of times object database object insertion timed out, falling back to non-persisted objects.
g_banlist_bytes
– gauge - info
Number of bytes used from the banlist journal fileNumber of bytes used from the banlist journal file.
g_banlist_space
– gauge - info
Number of bytes available in the banlist journal fileNumber of bytes available in the banlist journal file.
g_banlist_database
– gauge - info
Number of bytes used in the database for persisted bansNumber of bytes used in the database for persisted bans.
MSE_STORE – MSE_STORE¶
n_lru_moved
– counter - diag
Number of LRU move operationsNumber of move operations done on the LRU list.
g_aio_running
– gauge - info
Number AIO operations currently runningNumber of AIO operations currently being executed by the operating system.
g_aio_running_read
– gauge - diag
Number AIO read operations currently runningNumber of AIO read operations currently being executed by the operating system.
g_aio_running_write
– gauge - diag
Number AIO write operations currently runningNumber of AIO write operations currently being executed by the operating system.
g_aio_running_bytes
– gauge - info
Number AIO bytes currently runningNumber of AIO bytes currently being executed by the operating system.
g_aio_running_bytes_read
– gauge - diag
Number AIO read bytes currently runningNumber of AIO read bytes currently being executed by the operating system.
g_aio_running_bytes_write
– gauge - diag
Number AIO write bytes currently runningNumber of AIO write bytes currently being executed by the operating system.
c_aio_finished
– counter - info
Number AIO operations executedTotal number of AIO operations executed.
c_aio_finished_read
– counter - diag
Number AIO read operations executedTotal number of AIO read operations executed.
c_aio_finished_write
– counter - diag
Number AIO write operations executedTotal number of AIO write operations executed.
c_aio_finished_bytes
– counter - info
Number AIO bytes executedTotal number of AIO operations executed.
c_aio_finished_bytes_read
– counter - diag
Number AIO read bytes executedTotal number of AIO read bytes executed.
c_aio_finished_bytes_write
– counter - diag
Number AIO write bytes executedTotal number of AIO write bytes executed.
g_aio_queue
– gauge - info
Number of threads queued for AIONumber of threads queued waiting for an AIO slot.
g_aio_queue_read
– gauge - diag
Number of threads queued for AIO readNumber of threads queued waiting for an AIO slot to do a read operation.
g_aio_queue_write
– gauge - diag
Number of threads queued for AIO writeNumber of threads queued waiting for an AIO slot to do a write operation.
c_aio_queue
– counter - info
Number of times a thread has been queued for AIONumber of times a thread has been queued waiting for an AIO slot.
c_aio_queue_read
– counter - diag
Number of times a thread has been queued for AIO readNumber of times a thread has been queued waiting for an AIO slot to do a read operation.
c_aio_queue_write
– counter - diag
Number of times a thread has been queued for AIO writeNumber of times a thread has been queued waiting for an AIO slot to do a write operation.
c_aio_write_queue_overflow
– counter - info
Number of times objects have not been stored due to queue length.Number of times objects have bypassed the store (memory only) due to write queue length exceeding maximum.
g_database_queue
– gauge - diag
Number of threads queued for database handle.Number of threads queued waiting for a read-only database handle.
g_waterlevel_queue
– gauge - diag
Number of threads queued waiting for store spaceNumber of threads queued waiting for store space
c_waterlevel_queue
– counter - diag
Number of times a thread has been queued waiting for store spaceNumber of times a thread have been queued waiting for store space
c_waterlevel_purge
– counter - diag
Number of objects purged to achieve store waterlevelNumber of objects purged to achieve store waterlevel
g_objects
– gauge - info
Number of objects in the storeNumber of objects in the store
g_ykey_keys
– gauge - diag
Number of YKeys registeredThis is the number of YKeys registered for objects in this store.
c_ykey_purged
– counter - diag
Number of objects purged with YKeyThis is the number of objects purged with YKey in this store.
c_ykey_purged_slicer
– counter - diag
Number of slicer objects purged with YKey
- This is the number of slicer objects purged with YKey in this
- store. Slicer object purges are not included in the c_ykey_purged counter.
c_ykey_stats
– counter - diag
Number of objects with YKey statsThis is the number of objects queried for stats with YKey in this store.
c_ykey_stats_slicer
– counter - diag
Number of slicer objects with YKey statsThis is the number of slicer objects queried for stats with YKey in this storage. Slicer object queried for stats are not included in the c_ykey_stats counter.
g_alloc_extents
– gauge - info
Total number of allocation extentsTotal number of extents making up the allocated space in this store
g_alloc_bytes
– gauge - info
Total number of bytes in allocation extentsTotal number of bytes allocated from this store
g_free_extents
– gauge - info
Total number of free extentsTotal number of extents making up the free space in this store
g_free_bytes
– gauge - info
Total number of bytes in free extentsTotal number of bytes of free space in this store
g_alloc_small_extents
– gauge - diag
Number of allocation extents smaller than 16k
g_alloc_small_bytes
– gauge - diag
Number of bytes in allocation extents smaller than 16k
g_alloc_16k_extents
– gauge - diag
Number of allocation extents between 16k and 32k
g_alloc_16k_bytes
– gauge - diag
Number of bytes in allocation extents between 16k and 32k
g_alloc_32k_extents
– gauge - diag
Number of allocation extents between 32k and 64k
g_alloc_32k_bytes
– gauge - diag
Number of bytes in allocation extents between 32k and 64k
g_alloc_64k_extents
– gauge - diag
Number of allocation extents between 64k and 128k
g_alloc_64k_bytes
– gauge - diag
Number of bytes in allocation extents between 64k and 128k
g_alloc_128k_extents
– gauge - diag
Number of allocation extents between 128k and 256k
g_alloc_128k_bytes
– gauge - diag
Number of bytes in allocation extents between 128k and 256k
g_alloc_256k_extents
– gauge - diag
Number of allocation extents between 256k and 512k
g_alloc_256k_bytes
– gauge - diag
Number of bytes in allocation extents between 256k and 512k
g_alloc_512k_extents
– gauge - diag
Number of allocation extents between 512k and 1m
g_alloc_512k_bytes
– gauge - diag
Number of bytes in allocation extents between 512k and 1m
g_alloc_1m_extents
– gauge - diag
Number of allocation extents between 1m and 2m
g_alloc_1m_bytes
– gauge - diag
Number of bytes in allocation extents between 1m and 2m
g_alloc_2m_extents
– gauge - diag
Number of allocation extents between 2m and 4m
g_alloc_2m_bytes
– gauge - diag
Number of bytes in allocation extents between 2m and 4m
g_alloc_4m_extents
– gauge - diag
Number of allocation extents between 4m and 8m
g_alloc_4m_bytes
– gauge - diag
Number of bytes in allocation extents between 4m and 8m
g_alloc_large_extents
– gauge - diag
Number of allocation extents larger than 8m
g_alloc_large_bytes
– gauge - diag
Number of bytes in allocation extents larger than 8m
g_free_small_extents
– gauge - diag
Number of free extents smaller than 16k
g_free_small_bytes
– gauge - diag
Number of bytes in free extents smaller than 16k
g_free_16k_extents
– gauge - diag
Number of free extents between 16k and 32k
g_free_16k_bytes
– gauge - diag
Number of bytes in free extents between 16k and 32k
g_free_32k_extents
– gauge - diag
Number of free extents between 32k and 64k
g_free_32k_bytes
– gauge - diag
Number of bytes in free extents between 32k and 64k
g_free_64k_extents
– gauge - diag
Number of free extents between 64k and 128k
g_free_64k_bytes
– gauge - diag
Number of bytes in free extents between 64k and 128k
g_free_128k_extents
– gauge - diag
Number of free extents between 128k and 256k
g_free_128k_bytes
– gauge - diag
Number of bytes in free extents between 128k and 256k
g_free_256k_extents
– gauge - diag
Number of free extents between 256k and 512k
g_free_256k_bytes
– gauge - diag
Number of bytes in free extents between 256k and 512k
g_free_512k_extents
– gauge - diag
Number of free extents between 512k and 1m
g_free_512k_bytes
– gauge - diag
Number of bytes in free extents between 512k and 1m
g_free_1m_extents
– gauge - diag
Number of free extents between 1m and 2m
g_free_1m_bytes
– gauge - diag
Number of bytes in free extents between 1m and 2m
g_free_2m_extents
– gauge - diag
Number of free extents between 2m and 4m
g_free_2m_bytes
– gauge - diag
Number of bytes in free extents between 2m and 4m
g_free_4m_extents
– gauge - diag
Number of free extents between 4m and 8m
g_free_4m_bytes
– gauge - diag
Number of bytes in free extents between 4m and 8m
g_free_large_extents
– gauge - diag
Number of free extents larger than 8m
g_free_large_bytes
– gauge - diag
Number of bytes in free extents larger than 8m
MSE4 – MSE4¶
g_varyspec
– counter - info
Number of Vary header keysNumber of Vary header instruction keys stored for the objects in the memory cache. One per unique Vary header seen from the backend responses.
g_ykey_keys
– gauge - info
Number of YKeys registeredThis is the number of YKeys registered for memory only objects in this storage.
c_ykey_purged
– counter - diag
Number of objects purged with YKeyThis is the number of memory only objects purged with YKey in this storage.
c_ykey_purged_slicer
– counter - diag
Number of slicer objects purged with YKeyThis is the number of memory only slicer objects purged with YKey in this storage. Slicer object purges are not included in the c_ykey_purged counter.
c_ykey_stats
– counter - diag
Number of objects queried using YKey statsThis is the number of memory only objects queried for stats with YKey in this storage.
c_ykey_stats_slicer
– counter - diag
Number of slicer objects queried using YKey statsThis is the number of memory only slicer objects queried for stats with YKey in this storage. Slicer object queried for stats are not included in the c_ykey_stats counter.
MSE4_MEM – MSE4_MEM¶
g_bytes
– gauge - info
Bytes in useNumber of bytes currently in use for cache payload storage.This is the sum of the other
g_bytes_*
counters.
g_bytes_ephemeral
– gauge - info
Bytes in use for ephemeral object chunksNumber of bytes in use for chunks belonging to ephemeral (not persisted) objects.
g_bytes_persisted
– gauge - info
Bytes in use for in memory chunks of persisted objectsNumber of bytes in use for persisted objects chunks that are currently in memory.
g_bytes_pass
– gauge - info
Bytes allocated for passed objectsNumber of bytes in use for private objects held by pass transactions.
g_bytes_synthetic
– gauge - diag
Bytes in use for client response synthetic objectsNumber of bytes in use for client response synthetic temporary objects.
g_bytes_reqbody
– gauge - diag
Bytes in use for request body objectsNumber of bytes in use for temporary objects holding request bodies.
g_bytes_buffer
– gauge - diag
Bytes in use for misc buffer spaceNumber of bytes in use for miscellaneous buffer space managed by the stevedore.
g_objects
– gauge - info
Number of objects in memory.Number of objects in memory. This is the sum of the
g_objects_*
counters.
g_objects_ephemeral
– gauge - info
Number of cached ephemeral objectsNumber of cached ephemeral (not persisted) objects.
g_objects_persisted
– gauge - info
Number of persisted objects with at least one chunk in memoryNumber of persisted objects with at least one chunk in memory.
g_objects_pass
– gauge - info
Number of pass objects allocatedNumber of objects allocated for private objects used by pass transactions.
g_objects_reqbody
– gauge - info
Number of request body objectsNumber of temporary objects allocated to hold request bodies.
g_objects_synthetic
– gauge - diag
Number of client response synthetic objectsNumber of client response synthetic response temporary objects currently allocated.
g_buffers
– gauge - diag
Number of stevedore managed buffers allocatedNumber of stevedore managed miscellaneous buffers allocated.
g_space
– gauge - info
Bytes availableNumber of bytes available to be used for cache object storage. It shows the difference between the configured memory target and the actual memory usage of the Varnish cache worker process.
g_allocations
– gauge - diag
Allocations in useNumber of memory chunks currently in use for cache payload storage.
c_allocation
– counter - diag
Memory allocationsNumber of times the memory allocator has been invoked.
c_allocation_ephemeral
– counter - diag
Memory allocations for ephemeral objectsNumber of times the memory allocator has been invoked to allocate chunks for ephemeral (not persisted) objects.
c_allocation_persisted
– counter - diag
Memory allocations for persisted objectsNumber of times the memory allocator has been invoked to allocate chunks for persisted objects.
c_allocation_pass
– counter - diag
Memory allocations for private pass objectsNumber of times the memory allocator has been invoked to allocate chunks for pass objects.
c_allocation_synthetic
– counter - diag
Memory allocations for synthetic client objectsNumber of times the memory allocater has been invoked to allocate chunks for synthetic client objects.
c_allocation_reqbody
– counter - diag
Memory allocations for temporary request objectsNumber of times the memory allocator has been invoked to allocate chunks for request body objects.
c_allocation_buffer
– counter - diag
Stevedore managed buffer allocationsNumber of times the memory allocator has been invoked to acquire stevedore managed buffers.
c_free
– counter - diag
Number of memory chunk releasesNumber of times memory chunks has been released.
c_free_ephemeral
– counter - diag
Number of memory chunk releases for ephemeral objectsNumber of times memory chunks for ephemeral (not persisted) objects has been released.
c_free_persisted
– counter - diag
Number of memory chunk releases for persisted objectsNumber of times memory chunks for persisted objects has been released.
c_free_pass
– counter - diag
Number of memory chunk releases for pass objectsNumber of times memory chunks for pass objects has been released.
c_free_synthetic
– counter - diag
Number of memory chunk releases for synthetic client objectsNumber of times memory chunks for synthetic client objects has been released.
c_free_reqbody
– counter - diag
Number of memory chunk releases for request body objectsNumber of times memory chunks for request body objects has been released.
c_free_buffer
– counter - diag
Number of memory chunk releases for stevedore managed buffersNumber of times memory chunks for stevedore managed buffers has been released.
c_eviction
– counter - info
Number of evicted objects or persisted chunksHow many objects or persisted memory chunks have been evicted to make room for new content. This does not imply eviction from any on-disk storage.
c_eviction_failure
– counter - diag
Number of times object or chunk eviction failedHow many times the memory eviction routine failed to produce an object or persisted memory chunk to evict. This can happen when all the objects or chunks are being perused by active transactions.
c_eviction_reorder
– counter - diag
Number of eviction list reorder operationsNumber of reorder operations done on the memory eviction list.
c_allocation_failure
– counter - diag
Allocator failuresNumber of times the system memory allocator failed to allocate memory for cache payload storage.
c_memcache_hit
– counter - info
Stored objects memory cache hitsNumber of bytes of memory cache hits for stored (persisted) objects.
c_memcache_miss
– counter - info
Stored objects memory cache missesNumber of bytes of memory cache misses for stored (persisted) objects.
MSE4_CAT – MSE4_CAT¶
g_bytes
– gauge - info
Bytes in useNumber of bytes currently in use for cache payload storage in this category. This is the sum of the other
g_bytes_*
counters.
g_bytes_ephemeral
– gauge - info
Bytes in use for ephemeral object chunksNumber of bytes in use for chunks belonging to ephemeral (not persisted) objects in this category.
g_bytes_persisted
– gauge - info
Bytes in use for in memory chunks of persisted objectsNumber of bytes in use for persisted objects chunks that are currently in memory in this category.
g_bytes_pass
– gauge - info
Bytes allocated for passed objectsNumber of bytes in use for private objects held by pass transactions.
g_objects
– gauge - info
Number of objects in memory.Number of objects in memory in this category. This is the sum of the
g_objects_*
counters.
g_objects_ephemeral
– gauge - info
Number of cached ephemeral objectsNumber of cached ephemeral (not persisted) objects in this category.
g_objects_persisted
– gauge - info
Number of persisted objects with at least one chunk in memoryNumber of persisted objects with at least one chunk in memory in this category.
g_objects_pass
– gauge - info
Number of pass objects allocatedNumber of objects allocated for private objects used by pass transactions in this category.
g_allocations
– gauge - diag
Allocations in useNumber of memory chunks currently in use for cache payload storage in this category.
c_allocation
– counter - diag
Memory allocationsNumber of times the memory allocator has been invoked for this category.
c_allocation_ephemeral
– counter - diag
Memory allocations for ephemeral objectsNumber of times the memory allocator has been invoked to allocate chunks for ephemeral (not persisted) objects in this category.
c_allocation_persisted
– counter - diag
Memory allocations for persisted objectsNumber of times the memory allocator has been invoked to allocate chunks for persisted objects in this category.
c_allocation_pass
– counter - diag
Memory allocations for private pass objectsNumber of times the memory allocator has been invoked to allocate chunks for pass objects in this category.
c_free
– counter - diag
Number of memory chunk releasesNumber of times memory chunks in this category has been released.
c_free_ephemeral
– counter - diag
Number of memory chunk releases for ephemeral objectsNumber of times memory chunks for ephemeral (not persisted) objects has been released in this category.
c_free_persisted
– counter - diag
Number of memory chunk releases for persisted objectsNumber of times memory chunks for persisted objects has been released in this category.
c_free_pass
– counter - diag
Number of memory chunk releases for pass objectsNumber of times memory chunks for pass objects has been released in this category.
c_eviction
– counter - info
Number of evicted objects or persisted chunksHow many objects or persisted memory chunks have been evicted from memory in this category to make room for new content. This does not imply eviction from any on-disk storage.
c_eviction_failure
– counter - diag
Number of times object or chunk eviction failedHow many times the memory eviction routine failed to produce an object or persisted memory chunk to evict for this category. This can happen when all the objects or chunks are being perused by active transactions.
c_eviction_reorder
– counter - diag
Number of eviction list reorder operationsNumber of reorder operations done on the memory eviction list for this category.
c_memcache_hit
– counter - info
Stored objects memory cache hitsNumber of bytes of memory cache hits for stored (persisted) objects for this category.
c_memcache_miss
– counter - info
Stored objects memory cache missesNumber of bytes of memory cache misses for stored (persisted) objects for this category.
MSE4_BOOK – MSE4_BOOK¶
online
– gauge - info
Non-zero if the book is onlineNon-zero if the book is in state ONLINE. Zero when in state FAILING or OFFLINE.
g_slots_used
– gauge - info
Number of slots in useNumber of slots currently in use in the book.
g_slots_unused
– gauge - info
Number of slots freeNumber of slots currently in use in the book.
g_objects
– gauge - info
Number of objects defined in the bookNumber of objects defined in the book.
g_unreachable_objects
– gauge - diag
Number of objects from unreachable stores in the bookNumber of objects held in the book that belong to stores that are unreachable, typically because the store was previously marked failed. These objects will be evicted first whenever the number of free slots in the book gets low.
g_varyspec
– counter - info
Number of Vary header instruction keysNumber of Vary header instruction keys persisted for the objects in this book. One per unique Vary header seen from the backend responses.
c_freeslot_queued
– counter - info
Number of times a thread has been queued waiting for a free slotNumber of times a thread has been queued waiting for a free slot.
g_freeslot_queue
– gauge - info
Length of queue of threads waiting for a free slotLength of queue of threads waiting for a free slot.
c_submitslot_queued
– counter - info
Number of times a thread has been queued waiting to commit a slotNumber of times a thread has been queued waiting to commit a slot by submitting it to the slot journal.
g_submitslot_queue
– gauge - info
Length of queue of threads waiting to submit a slotLength of queue of threads waiting to submit a slot to the slot journal.
c_io_read_bytes
– counter - diag
Number of bytes read from the bookNumber of bytes read from the book.
c_io_write_bytes
– counter - info
Number of bytes written to the bookNumber of bytes written to the book.
c_io_write_journal_slots
– counter - info
Number of slots written to the to the slot journalNumber of slots written to the to the slot journal.
c_io_write_journal_slots_padding
– counter - debug
Number of padding slots written to the to the slot journalNumber of padding slots written to the to the slot journal to create aligned writes. Note that this is included in c_io_write_journal_slots.
c_io_write_journal_bytes
– counter - diag
Number of bytes written to the slot journalNumber of bytes written to the slot journal.
c_io_write_slot_table_bytes
– counter - diag
Number of bytes written to the slot tableNumber of bytes written to the slot table.
g_io_write_slot_table
– gauge - diag
Number of in-progress IO writes to the book slot tableNumber of in-progress IO write calls to the book slot table.
g_io_write_slot_table_bytes
– gauge - diag
Number of bytes of in-progress IO writes to the book slot tableNumber of bytes of in-progress IO writes to the book slot table.
c_checkpoint
– counter - diag
Number of times the slot table has been checkpointedNumber of times the slot table has been checkpointed.
g_dirty_blocks
– gauge - diag
Number of dirty blocks to write out during next checkpointNumber of dirty blocks to write out during next checkpoint.
c_objects_liberated
– counter - info
Number of objects evicted to gain free book slotsNumber of persisted objects evicted from the cache to gain free slots in this book.
c_slot_liberation_failure
– counter - diag
Slot liberation failedSlot liberation failed
g_ykey_keys
– gauge - info
Number of YKeys registered in bookThis is the number of YKeys registered for objects in this book.
c_ykey_purged
– counter - diag
Number of objects purged with YKeyThis is the number of persisted objects purged using YKey in this book.
c_ykey_purged_slicer
– counter - diag
Number of slicer objects purged with YKeyThis is the number of persisted slicer objects purged with YKey in this book. Slicer object purges are not included in the c_ykey_purged counter.
c_ykey_stats
– counter - diag
Number of objects with YKey statsThis is the number of persisted objects queried for stats with YKey in this book.
c_ykey_stats_slicer
– counter - diag
Number of slicer objects with YKey statsThis is the number of persisted slicer objects queried for stats with YKey in this book. Slicer object queried for stats are not included in the c_ykey_stats counter.
g_ykey_bytes
– gauge - diag
Number of bytes spent on Ykey search treesThe number of bytes spent on the Ykey search trees for objects from this book. Note that this memory is reused as objects come and go during runtime, but never freed. The value is thus a high level watermark.
g_ykey_nodes
– gauge - debug
Number of Ykey search tree nodes in useThe number of Ykey search tree nodes currently in use for objects from this book.
c_ykey_iter_10ms
– counter - diag
Number of ykey iterations taking 0.01s or lessNumber of ykey iterations executed that took 0.01s or less to complete.
c_ykey_iter_100ms
– counter - diag
Number of ykey iterations taking between 0.01s and 0.1sNumber of ykey iterations executed that took between 0.01s and 0.1s to complete.
c_ykey_iter_1000ms
– counter - diag
Number of ykey iterations taking between 0.1s and 1sNumber of ykey iterations executed that took between 0.1s and 1s to complete.
c_ykey_iter_1000ms_up
– counter - diag
Number of ykey iterations taking more than 1sNumber of ykey iterations executed that took more 1s to complete.
MSE4_STORE – MSE4_STORE¶
online
– gauge - info
Non-zero if the store is onlineNon-zero if the store is in state ONLINE. Zero when in state FAILING or OFFLINE.
g_objects
– gauge - info
Number of objects in the storeNumber of objects in the store
g_allocations
– gauge - diag
Number of data allocations in the storeNumber of data allocations in the store.
g_bytes_used
– gauge - info
Number of bytes in useNumber of bytes in use for cache content in this store
g_bytes_unused
– gauge - info
Number of bytes not in useNumber of bytes unused in this store
c_allocation_success
– counter - info
Number of successful allocation requestsNumber of times an allocation request has been fullfilled.
c_allocation_success_truncated
– counter - diag
Number of times an allocation request was truncatedNumber of times an allocation request was truncated. Note that this count is included in c_allocation_successes.
c_allocation_failure
– counter - info
Number of times an allocation request failedNumber of times an allocation request failed.
c_allocation_failure_timeout
– counter - diag
Number of times an allocation request failed due to a timeoutNumber of times an allocation request failed due to a timeout. Note that this count is included in c_alloc_failed.
c_allocation_failure_noslot
– counter - diag
Number of times an allocation request failed due to no slot availableNumber of times an allocation request failed due to no slot being available. Note that this count is included in c_alloc_failed.
g_allocation_queue
– gauge - info
Length of allocation queueLength of the allocation request queue.
c_allocation_queued
– counter - info
Number of times an allocation request was queuedNumber of times an allocation request was queued.
c_eviction_reorder
– counter - diag
Number of eviction list reorder operationsNumber of reorder operations done on the store eviction list.
g_slist_usage
– gauge - diag
Number of bytes of memory used for the object slot slistsNumber of bytes of memory used for the object slot slists.
c_segment_remap
– counter - diag
Number of times a segment has been remapped for free chunksNumber of times a segment has been remapped for free chunks.
c_segment_remap_fail
– counter - diag
Number of times segment remap failed to produce towards the reserveNumber of times segment mapping failed to produce towards the reserve.
c_segment_prune
– counter - diag
Number of times a segment has been prunedNumber of times a segment has been pruned to produce more free space.
c_segment_prune_fail
– counter - diag
Number of times segment pruning failed to produce towards the reserveNumber of times segment pruning failed to produce towards the reserve.
c_segment_pruned_objects
– counter - info
Number of objects evicted during segment pruningNumber of objects evicted during segment pruning in order to produce more free space.
g_io_running
– gauge - info
Number of IO operations currently runningNumber of IO operations currently being executed on the store.
g_io_running_read
– gauge - diag
Number of read IO operations currently runningNumber of read IO operations currently being executed on the store.
g_io_running_write
– gauge - diag
Number of write IO operations currently runningNumber of write IO operations currently being executed on the store.
g_io_running_bytes
– gauge - diag
Number of bytes in IO operations currently runningNumber of bytes in IO operations currently being executed on the store.
g_io_running_bytes_read
– gauge - info
Number of bytes in read IO operations currently runningNumber of bytes in read IO operations currently being executed on the store.
g_io_running_bytes_write
– gauge - info
Number of bytes in write IO operations currently runningNumber of bytes in write IO operations currently being executed on the store.
c_io_finished
– counter - info
Number of IO operations executedTotal number of IO operations executed on the store.
c_io_finished_read
– counter - diag
Numer of read IO operations executedTotal number of read IO operations executed on the store.
c_io_finished_write
– counter - diag
Numer of write IO operations executedTotal number of write IO operations executed on the store.
c_io_finished_bytes
– counter - diag
Number of bytes in IO operations executedTotal number of bytes in IO operations executed on the store.
c_io_finished_bytes_read
– counter - info
Number of bytes in read IO operations executedTotal number of bytes in read IO operations executed on the store.
c_io_finished_bytes_write
– counter - info
Number of bytes in write IO operations executedTotal number of bytes in write IO operations executed on the store.
c_io_limited
– counter - diag
Number of times the IO engine has been request limitedNumber of times the IO engine queue has been limited by exceeding the configured maximum number of simultaneous asynchronous IO requests.
g_io_queued
– gauge - info
Number of IO operations queued for schedulingNumber of IO operations currently queued for scheduling.
g_io_queued_read
– gauge - diag
Number of read IO operations queued for schedulingNumber of read IO operations currently queued for scheduling.
g_io_queued_write
– gauge - diag
Number of write IO operations queued for schedulingNumber of read IO operations currently queued for scheduling.
g_io_blocked
– gauge - info
Number of IO operations currently blockedNumber of IO operations currently blocked due to exceeding queue length.
g_io_blocked_read
– gauge - diag
Number of read IO operations currently blockedNumber of read IO operations currently blocked due to exceeding queue length.
g_io_blocked_write
– gauge - diag
Number of write IO operations currently blockedNumber of write IO operations currently blocked due to exceeding queue length.
g_mapped_segments
– gauge - diag
Number of segments currently mapped for free spaceNumber of segments currently mapped for free space.
g_reserve_bytes
– gauge - info
Number of bytes of mapped free space to use for allocationsNumber of bytes of mapped free space to use for allocations.
g_reserve_map_usage
– gauge - diag
Number of bytes of memory used for holding free chunk dataNumber of bytes of memory used for holding free chunk data.
g_reserve_class_0
– gauge - debug
Class 0 free chunks currently mapped
Class 0 free chunks currently mapped.
g_reserve_class_1
– gauge - debug
Class 1 free chunks currently mapped
Class 1 free chunks currently mapped.
g_reserve_class_2
– gauge - debug
Class 2 free chunks currently mapped
Class 2 free chunks currently mapped.
g_reserve_class_3
– gauge - debug
Class 3 free chunks currently mapped
Class 3 free chunks currently mapped.
g_reserve_class_4
– gauge - debug
Class 4 free chunks currently mapped
Class 4 free chunks currently mapped.
g_reserve_class_5
– gauge - debug
Class 5 free chunks currently mapped
Class 5 free chunks currently mapped.
g_reserve_class_6
– gauge - debug
Class 6 free chunks currently mapped
Class 6 free chunks currently mapped.
g_reserve_class_7
– gauge - debug
Class 7 free chunks currently mapped
Class 7 free chunks currently mapped.
g_reserve_class_8
– gauge - debug
Class 8 free chunks currently mapped
Class 8 free chunks currently mapped.
g_reserve_class_9
– gauge - debug
Class 9 free chunks currently mapped
Class 9 free chunks currently mapped.
g_reserve_class_10
– gauge - debug
Class 10 free chunks currently mapped
Class 10 free chunks currently mapped.
g_reserve_class_11
– gauge - debug
Class 11 free chunks currently mapped
Class 11 free chunks currently mapped.
MSE4_BANJRN – MSE4_BANJRN¶
g_space
– gauge - info
Number of bytes available in the banlist journalNumber of bytes available in the banlist journal
g_bans
– gauge - info
Number of bans persisted in the banlist journalNumber of bans persisted in the banlist journal
g_bytes
– gauge - diag
Number of bytes of ban data currently stored in the banlist journalNumber of bytes of ban data currently stored in the banlist journal
g_overflow_bans
– gauge - info
Number of bans not recorded in the banlist journalNumber of active bans that have been purged from the banlist journal due space consideration. A non-zero value means that there may be persisted objects in the cache that can not be revived on a restart due to lost ban information.
g_overflow_bytes
– gauge - diag
Number of bytes of ban data not recorded in the banlist journalThe byte count of all of the overflowed bans.
ACCG – ACCG¶
client_req_count
– counter - info
Total number of client requests processedTotal number of client requests processed.
client_req_hdrbytes
– counter - info
Client request header bytes totalClient request header bytes total.
client_req_bodybytes
– counter - info
Client request body bytes totalClient request body bytes total.
client_resp_hdrbytes
– counter - info
Client response header bytes totalClient response header bytes total.
client_resp_bodybytes
– counter - info
Client response body bytes totalClient response body bytes total.
client_hit_count
– counter - info
Number of client request hitsNumber of client request hits.
client_hit_req_hdrbytes
– counter - info
Client request header bytes for hitsClient request header bytes for hits.
client_hit_req_bodybytes
– counter - info
Client request body bytes for hitsClient request body bytes for hits.
client_hit_resp_hdrbytes
– counter - info
Client response header bytes for hitsClient response header bytes for hits.
client_hit_resp_bodybytes
– counter - info
Client response body bytes for hitsClient response body bytes for hits.
client_miss_count
– counter - info
Number of client request missesNumber of client request misses.
client_miss_req_hdrbytes
– counter - info
Client request header for missesClient request header bytes for misses.
client_miss_req_bodybytes
– counter - info
Client request body bytes for missesClient request body bytes for misses.
client_miss_resp_hdrbytes
– counter - info
Client response header for missesClient response header bytes for misses.
client_miss_resp_bodybytes
– counter - info
Client response body bytes for missesClient response body bytes for misses.
client_pass_count
– counter - info
Number of client request passesNumber of client request passes.
client_pass_req_hdrbytes
– counter - info
Client request header for passesClient request header bytes for passes.
client_pass_req_bodybytes
– counter - info
Client request body bytes for passesClient request body bytes for passes.
client_pass_resp_hdrbytes
– counter - info
Client response header bytes for passesClient response header bytes for passes.
client_pass_resp_bodybytes
– counter - info
Client response body bytes for passesClient response body bytes for passes.
client_synth_count
– counter - info
Number of client request synthsNumber of client request synths.
client_synth_req_hdrbytes
– counter - info
Client request header bytes for synthsClient request header bytes for synths.
client_synth_req_bodybytes
– counter - info
Client request body bytes for synthsClient request body bytes for synths.
client_synth_resp_hdrbytes
– counter - info
Client response header bytes for synthsClient response header bytes for synths.
client_synth_resp_bodybytes
– counter - info
Client response body bytes for synthsClient response body bytes for synths.
client_pipe_count
– counter - info
Number of client request pipesNumber of client request pipes.
client_pipe_req_hdrbytes
– counter - info
Client request header bytes for pipesClient request header bytes for pipes.
client_pipe_req_bodybytes
– counter - info
Client request body bytes for pipesClient request body bytes for pipes.
client_pipe_resp_hdrbytes
– counter - info
Client response header bytes for pipesClient response header bytes for pipes.
client_pipe_resp_bodybytes
– counter - info
Client response body bytes for pipesClient response body bytes for pipes.
client_200_count
– counter - info
Number of 200 responses for client requestsNumber of 200 responses for client requests.
client_304_count
– counter - info
Number of 304 responses for client requestsNumber of 304 responses for client requests.
client_404_count
– counter - info
Number of 404 responses for client requestsNumber of 404 responses for client requests.
client_503_count
– counter - info
Number of 503 responses for client requestsNumber of 503 responses for client requests.
client_2xx_count
– counter - info
Number of 2xx responses for client requestsNumber of 2xx responses for client requests (including 200). (Response codes below 200 does not have a specific counter.)
client_3xx_count
– counter - info
Number of 3xx responses for client requestsNumber of 3xx responses for client requests (including 304).
client_4xx_count
– counter - info
Number of 4xx responses for client requestsNumber of 4xx responses for client requests (including 404).
client_5xx_count
– counter - info
Number of 5xx responses for client requestsNumber of 5xx responses for client requests (including 503). (Response codes above 599 does not have a specific counter.)
client_grace_hit_count
– counter - info
Number of cache hits with graceNumber of cache hits with grace. A cache hit with grace is a cache hit where the object is expired. Note that these hits are also included in the client_hit_count counter.
backend_req_count
– counter - info
Total number of backend requests processedTotal number of backend requests of any kind processed.
backend_req_hdrbytes
– counter - info
Backend request header bytes totalBackend request header bytes total.
backend_req_bodybytes
– counter - info
Backend request body bytes totalBackend request body bytes total.
backend_resp_hdrbytes
– counter - info
Backend response header bytes totalBackend response header bytes total.
backend_resp_bodybytes
– counter - info
Backend response body bytes totalBackend response body bytes total. Note: This will only include bytes actually processed by Varnish. This means that any request towards the backend that ends early due to ‘restart’, ‘abandon’ or ‘fail’ will not add to bodybytes, reardless of what the backend may have sent.
backend_200_count
– counter - info
Number of backend responses of type 200Number of backend responses of type 200.
backend_304_count
– counter - info
Number of backend responses of type 304Number of backend responses of type 304.
backend_404_count
– counter - info
Number of backend responses of type 404Number of backend responses of type 404.
backend_503_count
– counter - info
Number of backend responses of type 503Number of backend responses of type .
backend_2xx_count
– counter - info
Number of backend responses of type 2xxNumber of backend responses of type 2xx (including 200). (Response codes below 200 does not have a specific counter.)
backend_3xx_count
– counter - info
Number of backend responses of type 3xxNumber of backend responses of type 3xx (including 304).
backend_4xx_count
– counter - info
Number of backend responses of type 4xxNumber of backend responses of type 4xx (including 404).
backend_5xx_count
– counter - info
Number of backend responses of type 5xxNumber of backend responses of type 5xx (including 503). (Response codes above 599 does not have a specific counter.)
ACCG_DIAG – ACCG diagnostic stats¶
set_key_failure
– counter - diag
Failed attempts to set key any reasonTotal number of failed attempts to set a key, due to any reason. If setting many keys, this stat will be incremented with the number of keys that failed.
out_of_key_slots
– counter - diag
Failed to set key due to no key slotsFailed attempts to set key due to no unused key slots in namespace. If setting many keys, this stat will be incremented with the number of keys that failed.
key_without_namespace
– counter - diag
Failed to set key due to no namespaceFailed attempts to set key due to no namespace set for request. If setting many keys, this stat will be incremented with the number of keys that failed.
namespace_already_set
– counter - diag
Attempt to escape namespaceFailed attempts to set namespace, due to namespace already set.
namespace_undefined
– counter - diag
Failed to set namespace due to not createdFailed attempts to set namespace, due to not created.
create_namespace_failure
– counter - diag
Failed attempts to create namespace any reasonTotal number of failed attempts to create a namespace, due to any reason.
req_dropped
– counter - diag
Number of times a request was not accounted forTotal number of client requests not accounted for because vmod_accounting was no longer loaded by the time they completed. This includes sub-requests.
bereq_dropped
– counter - diag
Number of times a backend request was not accounted forTotal number of backend requests not accounted for because vmod_accounting was no longer loaded by the time they completed.
SLICER – SLICER¶
slice_req
– counter - info
Count of slicer subrequestsThe total number of slicer subrequests seen.
slice_cache_hit
– counter - info
Count of slicer subrequest cache hitsThe total number of cache hits for slicer subrequests.
slice_cache_miss
– counter - info
Count of slicer subrequest cache missesThe total number of cache misses for slicer subrequests.
meta_req
– counter - info
Count of slicer top-level requestsThe total number of slicer top-level meta requests seen.
meta_cache_hit
– counter - info
Count of cache hits for slicer top-level requestsThe total number of cache hits for slicer top-level meta requests.
meta_cache_miss
– counter - info
Count of cache misses for slicer top-level requestsThe total number of cache misses for slicer top-level meta requests.
slice_beresp_200
– counter - info
Count of slicer subrequests fetched with a 200 response codeThe total number of slicer subrequests where a fetch resulted in a 200 response code. For a 200 response, slicer will accept the response and discard all the bytes that were not part of the requested range.
slice_beresp_206
– counter - info
Count of slicer subrequests fetched with a 206 response codeThe total number of slicer subrequests where a fetch resulted in a 206 response code.
BROTLI – Counters for Brotli¶
Information counters for Brotli.
c_br
– counter - info
Brotli compressions
Total number of Brotli compression operations.
c_br_bytes_in
– counter - info
Bytes into compressor
Total number of bytes passed to Brotli compressor.
c_br_bytes_out
– counter - info
Bytes out of compressor
Total number of bytes outputted from Brotli compressor.
c_br_fail
– counter - info
Brotli compressions failures
Total number of times Brotli compression failed.
c_unbr
– counter - info
Brotli decompressions
Total number of Brotli decompression operations.
c_unbr_bytes_in
– counter - info
Bytes into decompressor
Total number of bytes passed to Brotli decompressor.
c_unbr_bytes_out
– counter - info
Bytes out of decompressor
Total number of bytes outputted from Brotli decompressor.
c_unbr_fail
– counter - info
Brotli decompression Failures
Total number of times Brotli decompression failed.
c_testunbr
– counter - info
Brotli test decompressions
Total number of test Brotli decompression operations.
c_testunbr_fail
– counter - info
Brotli test decompressions failures
Total number of times test Brotli decompression failed.
AUTHORS¶
This man page was written by Lasse Karstensen, using content from vsc2rst written by Tollef Fog Heen.