Merge pull request #942 from prometheus/superq/0.16-doc

Document upgrade options for v0.16.0

3 files changed, 202 insertions, 1 deletions

diff --git a/CHANGELOG.md b/CHANGELOG.md
index bd2e29a..549fd46 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,7 +16,7 @@ This release contains major breaking changes to metric names.  Many metrics have
 * Many counter metrics have been renamed to include `_total`.
 * Many metrics have been renamed/modified to include base units, for example `node_cpu` is now `node_cpu_seconds_total`.
 
-In order to help with backwards compatibility, a `metric_relabel_config` is being worked on to allow for easier transition of metric names.  See: https://github.com/prometheus/node_exporter/issues/830
+In order to help with the transition we have an [upgrade guide](docs/V0_16_UPGRADE_GUIDE.md).
 
 Other breaking changes:
 * The megacli collector has been removed, is now replaced by the storcli.py textfile helper.
diff --git a/docs/V0_16_UPGRADE_GUIDE.md b/docs/V0_16_UPGRADE_GUIDE.md
new file mode 100644
index 0000000..d987683
--- /dev/null
+++ b/docs/V0_16_UPGRADE_GUIDE.md
@@ -0,0 +1,20 @@
+# Version 0.16.0 Upgrade Guide
+
+The `node_exporter` 0.16.0 and newer renamed many metrics in order to conform with Prometheus [naming best practices].
+
+In order to allow easy upgrades, there are several options.
+
+## Update dashboards
+
+Grafana users can add multiple queries in order to display both the old and new data simultaneously.
+
+## Use recording rules
+
+We have provides a [sample recording rule set] to create duplicate metrics.  This has a minor disadvantage that it creates a lot of extra data, and re-aligns the timestamps of the data.
+
+## Run both old and new versions simultaneously.
+
+It's possible to run both the old and new exporter on different ports, and include an additional scrape job in Prometheus.  It's recommended to enable only the collectors that have name changes that you care about.
+
+[naming best practices]: https://prometheus.io/docs/practices/naming/
+[sample recording rule set]: example-16-compatibility-rules.yml
diff --git a/docs/example-16-compatibility-rules.yml b/docs/example-16-compatibility-rules.yml
new file mode 100644
index 0000000..0a471f5
--- /dev/null
+++ b/docs/example-16-compatibility-rules.yml
@@ -0,0 +1,181 @@
+groups:
+- name: node_exporter-16-bcache
+  rules:
+  - record: node_bcache_cache_read_races
+    expr: node_bcache_cache_read_races_total
+- name: node_exporter-16-buddyinfo
+  rules:
+  - record: node_buddyinfo_blocks
+    expr: node_buddyinfo_count
+- name: node_exporter-16-stat
+  rules:
+  - record: node_boot_time_seconds
+    expr: node_boot_time
+  - record: node_context_switches_total
+    expr: node_context_switches
+  - record: node_forks_total
+    expr: node_forks
+  - record: node_intr_total
+    expr: node_intr
+- name: node_exporter-16-cpu
+  rules:
+  - record: node_cpu_seconds_total
+    expr: label_replace(node_cpu, "cpu", "$1", "cpu", "cpu(.+)")
+- name: node_exporter-16-diskstats
+  rules:
+  - record: node_disk_read_bytes_total
+    expr: node_disk_bytes_read
+  - record: node_disk_written_bytes_total
+    expr: node_disk_bytes_written
+  - record: node_disk_io_time_seconds_total
+    expr: node_disk_io_time_ms
+  - record: node_disk_io_time_weighted_seconds_total
+    expr: node_disk_io_time_weighted
+  - record: node_disk_reads_completed_total
+    expr: node_disk_reads_completed
+  - record: node_disk_reads_merged_total
+    expr: node_disk_reads_merged
+  - record: node_disk_read_time_seconds_total
+    expr: node_disk_read_time_ms
+  - record: node_disk_writes_completed_total
+    expr: node_disk_writes_completed
+  - record: node_disk_writes_merged_total
+    expr: node_disk_writes_merged
+  - record: node_disk_write_time_seconds_total
+    expr: node_disk_write_time_ms
+- name: node_exporter-16-infiniband
+  rules:
+  - record: node_infiniband_port_data_received_bytes_total
+    expr: node_infiniband_port_data_received_bytes
+  - record: node_infiniband_port_data_transmitted_bytes_total
+    expr: node_infiniband_port_data_transmitted_bytes
+- name: node_exporter-16-interrupts
+  rules:
+  - record: node_interrupts_total
+    expr: node_interrupts
+- name: node_exporter-16-memory
+  rules:
+  - record: node_memory_Active_bytes
+    expr: node_memory_Active
+  - record: node_memory_Active_anon_bytes
+    expr: node_memory_Active_anon
+  - record: node_memory_Active_file_bytes
+    expr: node_memory_Active_file
+  - record: node_memory_AnonHugePages_bytes
+    expr: node_memory_AnonHugePages
+  - record: node_memory_AnonPages_bytes
+    expr: node_memory_AnonPages
+  - record: node_memory_Bounce_bytes
+    expr: node_memory_Bounce
+  - record: node_memory_Buffers_bytes
+    expr: node_memory_Buffers
+  - record: node_memory_Cached_bytes
+    expr: node_memory_Cached
+  - record: node_memory_CommitLimit_bytes
+    expr: node_memory_CommitLimit
+  - record: node_memory_Committed_AS_bytes
+    expr: node_memory_Committed_AS
+  - record: node_memory_DirectMap2M_bytes
+    expr: node_memory_DirectMap2M
+  - record: node_memory_DirectMap4k_bytes
+    expr: node_memory_DirectMap4k
+  - record: node_memory_Dirty_bytes
+    expr: node_memory_Dirty
+  - record: node_memory_HardwareCorrupted_bytes
+    expr: node_memory_HardwareCorrupted
+  - record: node_memory_Hugepagesize_bytes
+    expr: node_memory_Hugepagesize
+  - record: node_memory_Inactive_bytes
+    expr: node_memory_Inactive
+  - record: node_memory_Inactive_anon_bytes
+    expr: node_memory_Inactive_anon
+  - record: node_memory_Inactive_file_bytes
+    expr: node_memory_Inactive_file
+  - record: node_memory_KernelStack_bytes
+    expr: node_memory_KernelStack
+  - record: node_memory_Mapped_bytes
+    expr: node_memory_Mapped
+  - record: node_memory_MemFree_bytes
+    expr: node_memory_MemFree
+  - record: node_memory_MemTotal_bytes
+    expr: node_memory_MemTotal
+  - record: node_memory_Mlocked_bytes
+    expr: node_memory_Mlocked
+  - record: node_memory_NFS_Unstable_bytes
+    expr: node_memory_NFS_Unstable
+  - record: node_memory_PageTables_bytes
+    expr: node_memory_PageTables
+  - record: node_memory_Shmem_bytes
+    expr: node_memory_Shmem
+  - record: node_memory_Slab_bytes
+    expr: node_memory_Slab
+  - record: node_memory_SReclaimable_bytes
+    expr: node_memory_SReclaimable
+  - record: node_memory_SUnreclaim_bytes
+    expr: node_memory_SUnreclaim
+  - record: node_memory_SwapCached_bytes
+    expr: node_memory_SwapCached
+  - record: node_memory_SwapFree_bytes
+    expr: node_memory_SwapFree
+  - record: node_memory_SwapTotal_bytes
+    expr: node_memory_SwapTotal
+  - record: node_memory_Unevictable_bytes
+    expr: node_memory_Unevictable
+  - record: node_memory_VmallocChunk_bytes
+    expr: node_memory_VmallocChunk
+  - record: node_memory_VmallocTotal_bytes
+    expr: node_memory_VmallocTotal
+  - record: node_memory_VmallocUsed_bytes
+    expr: node_memory_VmallocUsed
+  - record: node_memory_Writeback_bytes
+    expr: node_memory_Writeback
+  - record: node_memory_WritebackTmp_bytes
+    expr: node_memory_WritebackTmp
+- name: node_exporter-16-network
+  rules:
+  - record: node_network_receive_bytes_total
+    expr: node_network_receive_bytes
+  - record: node_network_receive_compressed_total
+    expr: node_network_receive_compressed
+  - record: node_network_receive_drop_total
+    expr: node_network_receive_drop
+  - record: node_network_receive_errs_total
+    expr: node_network_receive_errs
+  - record: node_network_receive_fifo_total
+    expr: node_network_receive_fifo
+  - record: node_network_receive_frame_total
+    expr: node_network_receive_frame
+  - record: node_network_receive_multicast_total
+    expr: node_network_receive_multicast
+  - record: node_network_receive_packets_total
+    expr: node_network_receive_packets
+  - record: node_network_transmit_bytes_total
+    expr: node_network_transmit_bytes
+  - record: node_network_transmit_compressed_total
+    expr: node_network_transmit_compressed
+  - record: node_network_transmit_drop_total
+    expr: node_network_transmit_drop
+  - record: node_network_transmit_errs_total
+    expr: node_network_transmit_errs
+  - record: node_network_transmit_fifo_total
+    expr: node_network_transmit_fifo
+  - record: node_network_transmit_frame_total
+    expr: node_network_transmit_frame
+  - record: node_network_transmit_multicast_total
+    expr: node_network_transmit_multicast
+  - record: node_network_transmit_packets_total
+    expr: node_network_transmit_packets
+- name: node_exporter-16-nfs
+  rules:
+  - record: node_nfs_connections_total
+    expr: node_nfs_net_connections
+  - record: node_nfs_packets_total
+    expr: node_nfs_net_reads
+  - record: node_nfs_requests_total
+    expr: label_replace(label_replace(node_nfs_procedures, "proto", "$1", "version", "(.+)"), "method", "$1", "procedure", "(.+)")
+  - record: node_nfs_rpc_authentication_refreshes_total
+    expr: node_nfs_rpc_authentication_refreshes
+  - record: node_nfs_rpcs_total
+    expr: node_nfs_rpc_operations
+  - record: node_nfs_rpc_retransmissions_total
+    expr: node_nfs_rpc_retransmissions