Commit Graph

11 Commits

Author SHA1 Message Date
Aliaksandr Valialkin
19d61737c1
app/{vminsert,vmselect}: follow-up after 2b7b3293c1
- Document the change at docs/CHANGELOG.md
- Set the default value for -vmstorageUserTimeout to 3 seconds. This is much better
  than the 0 value, which means that TCP connection to unreachable vmstorage could block
  for up to 16 minutes.
- Document -vmstorageUserTimeout at docs/Cluster-VictoriaMetrics.md
2023-08-29 12:17:39 +02:00
Will Jordan
2b7b3293c1
Add vmstorageUserTimeout flags to configure TCP user timeout (Linux) ()
`TCP_USER_TIMEOUT` (since Linux 2.6.37) specifies the maximum amount of
time that transmitted data may remain unacknowledged before TCP will
forcibly close the connection and return `ETIMEDOUT` to the application.

Setting a low TCP user timeout allows RPC connections quickly reroute
around unavailable storage nodes during network interruptions.
2023-08-29 11:46:39 +02:00
Aliaksandr Valialkin
4f53147ed4
app/{vminsert,vmselect}/netstorage: allow calling Init()+MustStop() in a loop
Previously netstorage.MustStop() call didn't free up all the resources,
so the subsequent call to nestorage.Init() would panic.

This allows writing tests, which call nestorage.Init() + nestorage.MustStop() in a loop.
2022-10-25 14:43:05 +03:00
Aliaksandr Valialkin
288d13af8d
lib/netutil: parallelize background pings for remote addresses
This should improve the time needed for determining unavailale remote addresses
across big numer of ConnPool's.

This is a follow-up for a1629bd3be

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/711
2022-06-21 13:32:27 +03:00
Aliaksandr Valialkin
a1629bd3be
lib/netutil.ConnPool: skip dialing remote address if the previous dial attempt was unsuccessful
If the previous dial attempt was unsuccessful, then all the new dial attempts are skipped
until the background goroutine determines that the given address can be successfully dialed.

This reduces query latency when some of vmstorage nodes are unavailable and dialing them is slow.

This should help with https://github.com/VictoriaMetrics/VictoriaMetrics/issues/711

This commit is based on ideas from the https://github.com/VictoriaMetrics/VictoriaMetrics/pull/2756

The main differences are:

- The check for healthy/unhealthy storage nodes is moved one level lower from app/vmselect/netstorage to lib/netutil.ConnPool.
  This makes possible re-using this feature everywhere lib/netutil.ConnPool is used.
- The check doesn't take into account handshake errors for already established connections.
  Handshake errors usually mean improperly configured VictoriaMetrics cluster, so they shouldn't be ignored.
2022-06-20 17:33:54 +03:00
Aliaksandr Valialkin
b28c6febf9
app/{vminsert,vmselect}: add -vmstorageDialTimeout command-line flag for tuning the maximum time needed for establishing connections to vmstorage
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/711
2022-06-20 15:17:34 +03:00
Aliaksandr Valialkin
d8a276fbe4
lib/netutil: limit the number of concurrently established connections when calling ConnPool.Get()
This should reduce potential spikes in the number of established connections in the following cases:
- when the connection establishing procedure becomes temporarily slow
- after a temporary spike in the rate of ConnPool.Get() calls

See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2552
2022-05-11 14:11:06 +03:00
Aliaksandr Valialkin
190c8b463c
lib/netutil: close connections in ConnPool if they are idle for more than 30 seconds
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2508
2022-05-02 15:01:52 +03:00
mxlxm
42e07cfaea
reset deadline, fix . ()
* reset deadline, fix .
reset deadline before we put it back to pool.

* make errcheck happy
2021-09-07 20:54:17 +03:00
Aliaksandr Valialkin
d962568e93 all: use %w instead of %s for wrapping errors in fmt.Errorf
This will simplify examining the returned errors such as httpserver.ErrorWithStatusCode .
See https://blog.golang.org/go1.13-errors for details.
2020-06-30 23:33:46 +03:00
Aliaksandr Valialkin
24578b4bb1 all: open-sourcing cluster version 2019-05-23 00:25:38 +03:00