1VARNISH-COUNTERS(7) VARNISH-COUNTERS(7)
2
6 varnish-counters - Varnish counter field definitions
7
9 summs – counter - debug
10 stat summ operations
11 Number of times per-thread statistics were summed into the global
13 counters.
14 uptime – counter - info
16 Child process uptime
17 How long the child process has been running.
19 sess_conn – counter - info
21 Sessions accepted
22 Count of sessions successfully accepted
24 sess_fail – counter - info
26 Session accept failures
27 Count of failures to accept TCP connection.
29 This counter is the sum of the sess_fail_* counters, which give more
31 detailed information.
32 sess_fail_econnaborted – counter - info
34 Session accept failures: connection aborted
35 Detailed reason for sess_fail: Connection aborted by the client,
37 usually harmless.
38 sess_fail_eintr – counter - info
40 Session accept failures: interrupted system call
41 Detailed reason for sess_fail: The accept() call was interrupted,
43 usually harmless
44 sess_fail_emfile – counter - info
46 Session accept failures: too many open files
47 Detailed reason for sess_fail: No file descriptor was available.
49 Consider raising RLIMIT_NOFILE (see ulimit -n).
50 sess_fail_ebadf – counter - info
52 Session accept failures: bad file descriptor
53 Detailed reason for sess_fail: The listen socket file descriptor was
55 invalid. Should never happen.
56 sess_fail_enomem – counter - info
58 Session accept failures: not enough memory
59 Detailed reason for sess_fail: Most likely insufficient socket buf‐
61 fer memory. Should never happen
62 sess_fail_other – counter - info
64 Session accept failures: other
65 Detailed reason for sess_fail: neither of the above, see SessError
67 log (varnishlog -g raw -i SessError).
68 client_req_400 – counter - info
70 Client requests received, subject to 400 errors
71 400 means we couldn't make sense of the request, it was malformed in
73 some drastic way.
74 client_req_417 – counter - info
76 Client requests received, subject to 417 errors
77 417 means that something went wrong with an Expect: header.
79 client_req – counter - info
81 Good client requests received
82 The count of parseable client requests seen.
84 cache_hit – counter - info
86 Cache hits
87 Count of cache hits. A cache hit indicates that an object has been
89 delivered to a client without fetching it from a backend server.
90 cache_hit_grace – counter - info
92 Cache grace hits
93 Count of cache hits with grace. A cache hit with grace is a cache
95 hit where the object is expired. Note that such hits are also
96 included in the cache_hit counter.
97 cache_hitpass – counter - info
99 Cache hits for pass.
100 Count of hits for pass. A cache hit for pass indicates that Varnish
102 is going to pass the request to the backend and this decision has
103 been cached in it self. This counts how many times the cached deci‐
104 sion is being used.
105 cache_hitmiss – counter - info
107 Cache hits for miss.
108 Count of hits for miss. A cache hit for miss indicates that Varnish
110 is going to proceed as for a cache miss without request coalescing,
111 and this decision has been cached. This counts how many times the
112 cached decision is being used.
113 cache_miss – counter - info
115 Cache misses
116 Count of misses. A cache miss indicates the object was fetched from
118 the backend before delivering it to the client.
119 backend_conn – counter - info
121 Backend conn. success
122 How many backend connections have successfully been established.
124 backend_unhealthy – counter - info
126 Backend conn. not attempted
127 backend_busy – counter - info
129 Backend conn. too many
130 backend_fail – counter - info
132 Backend conn. failures
133 backend_reuse – counter - info
135 Backend conn. reuses
136 Count of backend connection reuses. This counter is increased when‐
138 ever we reuse a recycled connection.
139 backend_recycle – counter - info
141 Backend conn. recycles
142 Count of backend connection recycles. This counter is increased
144 whenever we have a keep-alive connection that is put back into the
145 pool of connections. It has not yet been used, but it might be,
146 unless the backend closes it.
147 backend_retry – counter - info
149 Backend conn. retry
150 fetch_head – counter - info
152 Fetch no body (HEAD)
153 beresp with no body because the request is HEAD.
155 fetch_length – counter - info
157 Fetch with Length
158 beresp.body with Content-Length.
160 fetch_chunked – counter - info
162 Fetch chunked
163 beresp.body with Chunked.
165 fetch_eof – counter - info
167 Fetch EOF
168 beresp.body with EOF.
170 fetch_bad – counter - info
172 Fetch bad T-E
173 beresp.body length/fetch could not be determined.
175 fetch_none – counter - info
177 Fetch no body
178 beresp.body empty
180 fetch_1xx – counter - info
182 Fetch no body (1xx)
183 beresp with no body because of 1XX response.
185 fetch_204 – counter - info
187 Fetch no body (204)
188 beresp with no body because of 204 response.
190 fetch_304 – counter - info
192 Fetch no body (304)
193 beresp with no body because of 304 response.
195 fetch_failed – counter - info
197 Fetch failed (all causes)
198 beresp fetch failed.
200 fetch_no_thread – counter - info
202 Fetch failed (no thread)
203 beresp fetch failed, no thread available.
205 pools – gauge - info
207 Number of thread pools
208 Number of thread pools. See also parameter thread_pools. NB:
210 Presently pools cannot be removed once created.
211 threads – gauge - info
213 Total number of threads
214 Number of threads in all pools. See also parameters thread_pools,
216 thread_pool_min and thread_pool_max.
217 threads_limited – counter - info
219 Threads hit max
220 Number of times more threads were needed, but limit was reached in a
222 thread pool. See also parameter thread_pool_max.
223 threads_created – counter - info
225 Threads created
226 Total number of threads created in all pools.
228 threads_destroyed – counter - info
230 Threads destroyed
231 Total number of threads destroyed in all pools.
233 threads_failed – counter - info
235 Thread creation failed
236 Number of times creating a thread failed. See VSL::Debug for diag‐
238 nostics. See also parameter thread_fail_delay.
239 thread_queue_len – gauge - info
241 Length of session queue
242 Length of session queue waiting for threads. NB: Only updates once
244 per second. See also parameter thread_queue_limit.
245 busy_sleep – counter - info
247 Number of requests sent to sleep on busy objhdr
248 Number of requests sent to sleep without a worker thread because
250 they found a busy object.
251 busy_wakeup – counter - info
253 Number of requests woken after sleep on busy objhdr
254 Number of requests taken off the busy object sleep list and resched‐
256 uled.
257 busy_killed – counter - info
259 Number of requests killed after sleep on busy objhdr
260 Number of requests killed from the busy object sleep list due to
262 lack of resources.
263 sess_queued – counter - info
265 Sessions queued for thread
266 Number of times session was queued waiting for a thread. See also
268 parameter thread_queue_limit.
269 sess_dropped – counter - info
271 Sessions dropped for thread
272 Number of times an HTTP/1 session was dropped because the queue was
274 too long already. See also parameter thread_queue_limit.
275 req_dropped – counter - info
277 Requests dropped
278 Number of times an HTTP/2 stream was refused because the queue was
280 too long already. See also parameter thread_queue_limit.
281 n_object – gauge - info
283 object structs made
284 Approximate number of HTTP objects (headers + body, if present) in
286 the cache.
287 n_vampireobject – gauge - diag
289 unresurrected objects
290 Number of unresurrected objects
292 n_objectcore – gauge - info
294 objectcore structs made
295 Approximate number of object metadata elements in the cache. Each
297 object needs an objectcore, extra objectcores are for hit-for-miss,
298 hit-for-pass and busy objects.
299 n_objecthead – gauge - info
301 objecthead structs made
302 Approximate number of different hash entries in the cache.
304 n_backend – gauge - info
306 Number of backends
307 Number of backends known to us.
309 n_expired – counter - info
311 Number of expired objects
312 Number of objects that expired from cache because of old age.
314 n_lru_nuked – counter - info
316 Number of LRU nuked objects
317 How many objects have been forcefully evicted from storage to make
319 room for a new object.
320 n_lru_moved – counter - diag
322 Number of LRU moved objects
323 Number of move operations done on the LRU list.
325 n_lru_limited – counter - info
327 Reached nuke_limit
328 Number of times more storage space were needed, but limit was
330 reached in a nuke_limit. See also parameter nuke_limit.
331 losthdr – counter - info
333 HTTP header overflows
334 s_sess – counter - info
336 Total sessions seen
337 n_pipe – gauge - info
339 Number of ongoing pipe sessions
340 pipe_limited – counter - info
342 Pipes hit pipe_sess_max
343 Number of times more pipes were needed, but the limit was reached.
345 See also parameter pipe_sess_max.
346 s_pipe – counter - info
348 Total pipe sessions seen
349 s_pass – counter - info
351 Total pass-ed requests seen
352 s_fetch – counter - info
354 Total backend fetches initiated
355 s_synth – counter - info
357 Total synthetic responses made
358 s_req_hdrbytes – counter - info
360 Request header bytes
361 Total request header bytes received
363 s_req_bodybytes – counter - info
365 Request body bytes
366 Total request body bytes received
368 s_resp_hdrbytes – counter - info
370 Response header bytes
371 Total response header bytes transmitted
373 s_resp_bodybytes – counter - info
375 Response body bytes
376 Total response body bytes transmitted
378 s_pipe_hdrbytes – counter - info
380 Pipe request header bytes
381 Total request bytes received for piped sessions
383 s_pipe_in – counter - info
385 Piped bytes from client
386 Total number of bytes forwarded from clients in pipe sessions
388 s_pipe_out – counter - info
390 Piped bytes to client
391 Total number of bytes forwarded to clients in pipe sessions
393 sess_closed – counter - info
395 Session Closed
396 sess_closed_err – counter - info
398 Session Closed with error
399 Total number of sessions closed with errors. See sc_* diag counters
401 for detailed breakdown
402 sess_readahead – counter - info
404 Session Read Ahead
405 sess_herd – counter - diag
407 Session herd
408 Number of times the timeout_linger triggered
410 sc_rem_close – counter - diag
412 Session OK REM_CLOSE
413 Number of session closes with REM_CLOSE (Client Closed)
415 sc_req_close – counter - diag
417 Session OK REQ_CLOSE
418 Number of session closes with REQ_CLOSE (Client requested close)
420 sc_req_http10 – counter - diag
422 Session Err REQ_HTTP10
423 Number of session closes with Error REQ_HTTP10 (Proto < HTTP/1.1)
425 sc_rx_bad – counter - diag
427 Session Err RX_BAD
428 Number of session closes with Error RX_BAD (Received bad req/resp)
430 sc_rx_body – counter - diag
432 Session Err RX_BODY
433 Number of session closes with Error RX_BODY (Failure receiving
435 req.body)
436 sc_rx_junk – counter - diag
438 Session Err RX_JUNK
439 Number of session closes with Error RX_JUNK (Received junk data)
441 sc_rx_overflow – counter - diag
443 Session Err RX_OVERFLOW
444 Number of session closes with Error RX_OVERFLOW (Received buffer
446 overflow)
447 sc_rx_timeout – counter - diag
449 Session Err RX_TIMEOUT
450 Number of session closes with Error RX_TIMEOUT (Receive timeout)
452 sc_rx_close_idle – counter - diag
454 Session Err RX_CLOSE_IDLE
455 Number of session closes with Error RX_CLOSE_IDLE: timeout_idle has
457 been exceeded while waiting for a client request.
458 sc_tx_pipe – counter - diag
460 Session OK TX_PIPE
461 Number of session closes with TX_PIPE (Piped transaction)
463 sc_tx_error – counter - diag
465 Session Err TX_ERROR
466 Number of session closes with Error TX_ERROR (Error transaction)
468 sc_tx_eof – counter - diag
470 Session OK TX_EOF
471 Number of session closes with TX_EOF (EOF transmission)
473 sc_resp_close – counter - diag
475 Session OK RESP_CLOSE
476 Number of session closes with RESP_CLOSE (Backend/VCL requested
478 close)
479 sc_overload – counter - diag
481 Session Err OVERLOAD
482 Number of session closes with Error OVERLOAD (Out of some resource)
484 sc_pipe_overflow – counter - diag
486 Session Err PIPE_OVERFLOW
487 Number of session closes with Error PIPE_OVERFLOW (Session pipe
489 overflow)
490 sc_range_short – counter - diag
492 Session Err RANGE_SHORT
493 Number of session closes with Error RANGE_SHORT (Insufficient data
495 for range)
496 sc_req_http20 – counter - diag
498 Session Err REQ_HTTP20
499 Number of session closes with Error REQ_HTTP20 (HTTP2 not accepted)
501 sc_vcl_failure – counter - diag
503 Session Err VCL_FAILURE
504 Number of session closes with Error VCL_FAILURE (VCL failure)
506 client_resp_500 – counter - diag
508 Delivery failed due to insufficient workspace.
509 Number of times we failed a response due to running out of workspace
511 memory during delivery.
512 ws_backend_overflow – counter - diag
514 workspace_backend overflows
515 Number of times we ran out of space in workspace_backend.
517 ws_client_overflow – counter - diag
519 workspace_client overflows
520 Number of times we ran out of space in workspace_client.
522 ws_thread_overflow – counter - diag
524 workspace_thread overflows
525 Number of times we ran out of space in workspace_thread.
527 ws_session_overflow – counter - diag
529 workspace_session overflows
530 Number of times we ran out of space in workspace_session.
532 shm_records – counter - diag
534 SHM records
535 shm_writes – counter - diag
537 SHM writes
538 shm_flushes – counter - diag
540 SHM flushes due to overflow
541 shm_cont – counter - diag
543 SHM MTX contention
544 shm_cycles – counter - diag
546 SHM cycles through buffer
547 backend_req – counter - info
549 Backend requests made
550 n_vcl – gauge - info
552 Number of loaded VCLs in total
553 n_vcl_avail – gauge - diag
555 Number of VCLs available
556 n_vcl_discard – gauge - diag
558 Number of discarded VCLs
559 vcl_fail – counter - info
561 VCL failures
562 Count of failures which prevented VCL from completing.
564 bans – gauge - info
566 Count of bans
567 Number of all bans in system, including bans superseded by newer
569 bans and bans already checked by the ban-lurker.
570 bans_completed – gauge - diag
572 Number of bans marked 'completed'
573 Number of bans which are no longer active, either because they got
575 checked by the ban-lurker or superseded by newer identical bans.
576 bans_obj – gauge - diag
578 Number of bans using obj.*
579 Number of bans which use obj.* variables. These bans can possibly
581 be washed by the ban-lurker.
582 bans_req – gauge - diag
584 Number of bans using req.*
585 Number of bans which use req.* variables. These bans can not be
587 washed by the ban-lurker.
588 bans_added – counter - diag
590 Bans added
591 Counter of bans added to ban list.
593 bans_deleted – counter - diag
595 Bans deleted
596 Counter of bans deleted from ban list.
598 bans_tested – counter - diag
600 Bans tested against objects (lookup)
601 Count of how many bans and objects have been tested against each
603 other during hash lookup.
604 bans_obj_killed – counter - diag
606 Objects killed by bans (lookup)
607 Number of objects killed by bans during object lookup.
609 bans_lurker_tested – counter - diag
611 Bans tested against objects (lurker)
612 Count of how many bans and objects have been tested against each
614 other by the ban-lurker.
615 bans_tests_tested – counter - diag
617 Ban tests tested against objects (lookup)
618 Count of how many tests and objects have been tested against each
620 other during lookup. 'ban req.url == foo && req.http.host == bar'
621 counts as one in 'bans_tested' and as two in 'bans_tests_tested'
622 bans_lurker_tests_tested – counter - diag
624 Ban tests tested against objects (lurker)
625 Count of how many tests and objects have been tested against each
627 other by the ban-lurker. 'ban req.url == foo && req.http.host ==
628 bar' counts as one in 'bans_tested' and as two in
629 'bans_tests_tested'
630 bans_lurker_obj_killed – counter - diag
632 Objects killed by bans (lurker)
633 Number of objects killed by the ban-lurker.
635 bans_lurker_obj_killed_cutoff – counter - diag
637 Objects killed by bans for cutoff (lurker)
638 Number of objects killed by the ban-lurker to keep the number of
640 bans below ban_cutoff.
641 bans_dups – counter - diag
643 Bans superseded by other bans
644 Count of bans replaced by later identical bans.
646 bans_lurker_contention – counter - diag
648 Lurker gave way for lookup
649 Number of times the ban-lurker had to wait for lookups.
651 bans_persisted_bytes – gauge - diag
653 Bytes used by the persisted ban lists
654 Number of bytes used by the persisted ban lists.
656 bans_persisted_fragmentation – gauge - diag
658 Extra bytes in persisted ban lists due to fragmentation
659 Number of extra bytes accumulated through dropped and completed bans
661 in the persistent ban lists.
662 n_purges – counter - info
664 Number of purge operations executed
665 n_obj_purged – counter - info
667 Number of purged objects
668 exp_mailed – counter - diag
670 Number of objects mailed to expiry thread
671 Number of objects mailed to expiry thread for handling.
673 exp_received – counter - diag
675 Number of objects received by expiry thread
676 Number of objects received by expiry thread for handling.
678 hcb_nolock – counter - debug
680 HCB Lookups without lock
681 hcb_lock – counter - debug
683 HCB Lookups with lock
684 hcb_insert – counter - debug
686 HCB Inserts
687 esi_errors – counter - diag
689 ESI parse errors (unlock)
690 esi_warnings – counter - diag
692 ESI parse warnings (unlock)
693 vmods – gauge - info
695 Loaded VMODs
696 n_gzip – counter - info
698 Gzip operations
699 n_gunzip – counter - info
701 Gunzip operations
702 n_test_gunzip – counter - info
704 Test gunzip operations
705 Those operations occur when Varnish receives a compressed object
707 from a backend. They are done to verify the gzip stream while it's
708 inserted in storage.
709
711 uptime – counter - info
712 Management process uptime
713 Uptime in seconds of the management process
715 child_start – counter - diag
717 Child process started
718 Number of times the child process has been started
720 child_exit – counter - diag
722 Child process normal exit
723 Number of times the child process has been cleanly stopped
725 child_stop – counter - diag
727 Child process unexpected exit
728 Number of times the child process has exited with an unexpected
730 return code
731 child_died – counter - diag
733 Child process died (signal)
734 Number of times the child process has died due to signals
736 child_dump – counter - diag
738 Child process core dumped
739 Number of times the child process has produced core dumps
741 child_panic – counter - diag
743 Child process panic
744 Number of times the management process has caught a child panic
746
748 live – gauge - debug
749 In use
750 pool – gauge - debug
752 In Pool
753 sz_wanted – gauge - debug
755 Size requested
756 sz_actual – gauge - debug
758 Size allocated
759 allocs – counter - debug
761 Allocations
762 frees – counter - debug
764 Frees
765 recycle – counter - debug
767 Recycled from pool
768 timeout – counter - debug
770 Timed out from pool
771 toosmall – counter - debug
773 Too small to recycle
774 surplus – counter - debug
776 Too many for pool
777 randry – counter - debug
779 Pool ran dry
780
782 c_req – counter - info
783 Allocator requests
784 Number of times the storage has been asked to provide a storage seg‐
786 ment.
787 c_fail – counter - info
789 Allocator failures
790 Number of times the storage has failed to provide a storage segment.
792 c_bytes – counter - info
794 Bytes allocated
795 Number of total bytes allocated by this storage.
797 c_freed – counter - info
799 Bytes freed
800 Number of total bytes returned to this storage.
802 g_alloc – gauge - info
804 Allocations outstanding
805 Number of storage allocations outstanding.
807 g_bytes – gauge - info
809 Bytes outstanding
810 Number of bytes allocated from the storage.
812 g_space – gauge - info
814 Bytes available
815 Number of bytes left in the storage.
817
819 c_req – counter - info
820 Allocator requests
821 Number of times the storage has been asked to provide a storage seg‐
823 ment.
824 c_fail – counter - info
826 Allocator failures
827 Number of times the storage has failed to provide a storage segment.
829 c_bytes – counter - info
831 Bytes allocated
832 Number of total bytes allocated by this storage.
834 c_freed – counter - info
836 Bytes freed
837 Number of total bytes returned to this storage.
839 g_alloc – gauge - info
841 Allocations outstanding
842 Number of storage allocations outstanding.
844 g_bytes – gauge - info
846 Bytes outstanding
847 Number of bytes allocated from the storage.
849 g_space – gauge - info
851 Bytes available
852 Number of bytes left in the storage.
854
856 c_req – counter - info
857 Allocator requests
858 Number of times the storage has been asked to provide a storage seg‐
860 ment.
861 c_fail – counter - info
863 Allocator failures
864 Number of times the storage has failed to provide a storage segment.
866 c_bytes – counter - info
868 Bytes allocated
869 Number of total bytes allocated by this storage.
871 c_freed – counter - info
873 Bytes freed
874 Number of total bytes returned to this storage.
876 g_alloc – gauge - info
878 Allocations outstanding
879 Number of storage allocations outstanding.
881 g_bytes – gauge - info
883 Bytes outstanding
884 Number of bytes allocated from the storage.
886 g_space – gauge - info
888 Bytes available
889 Number of bytes left in the storage.
891 g_smf – gauge - info
893 N struct smf
894 g_smf_frag – gauge - info
896 N small free smf
897 g_smf_large – gauge - info
899 N large free smf
900
902 happy – bitmap - info
903 Happy health probes
904 bereq_hdrbytes – counter - info
906 Request header bytes
907 Total backend request header bytes sent
909 bereq_bodybytes – counter - info
911 Request body bytes
912 Total backend request body bytes sent
914 beresp_hdrbytes – counter - info
916 Response header bytes
917 Total backend response header bytes received
919 beresp_bodybytes – counter - info
921 Response body bytes
922 Total backend response body bytes received
924 pipe_hdrbytes – counter - info
926 Pipe request header bytes
927 Total request bytes sent for piped sessions
929 pipe_out – counter - info
931 Piped bytes to backend
932 Total number of bytes forwarded to backend in pipe sessions
934 pipe_in – counter - info
936 Piped bytes from backend
937 Total number of bytes forwarded from backend in pipe sessions
939 conn – gauge - info
941 Concurrent connections to backend
942 req – counter - info
944 Backend requests sent
945 unhealthy – counter - info
947 Fetches not attempted due to backend being unhealthy
948 busy – counter - info
950 Fetches not attempted due to backend being busy
951 Number of times the max_connections limit was reached
953 fail – counter - info
955 Connections failed
956 Counter of failed opens. Detailed reasons are given in the fail_*
958 counters (DIAG level) and in the log under the FetchError tag.
959 This counter is the sum of all detailed fail_* counters.
961 All fail_* counters may be slightly inaccurate for efficiency.
963 fail_eacces – counter - diag
965 Connections failed with EACCES or EPERM
966 fail_eaddrnotavail – counter - diag
968 Connections failed with EADDRNOTAVAIL
969 fail_econnrefused – counter - diag
971 Connections failed with ECONNREFUSED
972 fail_enetunreach – counter - diag
974 Connections failed with ENETUNREACH
975 fail_etimedout – counter - diag
977 Connections failed ETIMEDOUT
978 fail_other – counter - diag
980 Connections failed for other reason
981 helddown – counter - diag
983 Connection opens not attempted
984 Connections not attempted during the backend_local_error_holddown or
986 backend_remote_error_holddown interval after a fundamental connec‐
987 tion issue.
988
990 Counters which track the activity in the different classes of
991 mutex-locks.
992 The counts may be slightly wrong if there are more than one lock
994 instantiated in each class (ie: .creat > 1)
995 creat – counter - debug
997 Created locks
998 destroy – counter - debug
1000 Destroyed locks
1001 locks – counter - debug
1003 Lock Operations
1004 dbg_busy – counter - debug
1006 Contended lock operations
1007 If the lck debug bit is set: Lock operations which returned EBUSY on
1009 the first locking attempt.
1010 If the lck debug bit is unset, this counter will never be incre‐
1012 mented even if lock operations are contended.
1013 dbg_try_fail – counter - debug
1015 Contended trylock operations
1016 If the lck debug bit is set: Trylock operations which returned
1018 EBUSY.
1019 If the lck debug bit is unset, this counter will never be incre‐
1021 mented even if lock operations are contended.
1022
1024 This man page was written by Lasse Karstensen, using content from
1025 vsc2rst written by Tollef Fog Heen.
1026 VARNISH-COUNTERS(7)