Data is reported in this form when either --verbose is used OR if there is at least one type of data requested that doesn't have a brief form such as any detail data or ionodes, processes or slabs. Specifying some of the lustre output options with --lustopts such as B, D and M will also force verbose format.
# MEMORY FRAGMENTATION SUMMARY (4K pages) # 1Pg 2Pgs 4Pgs 8Pgs 16Pgs 32Pgs 64Pgs 128Pgs 256Pgs 512Pgs 1024Pgs
# CPU SUMMARY (INTR, CTXSW & PROC /sec) # User Nice Sys Wait IRQ Soft Steal Guest NiceG Idle CPUs Intr Ctxsw Proc RunQ Run Avg1 Avg5 Avg15 RunT BlkT
| User | Time spent in User mode, not including time spend in "nice" mode. |
| Nice | Time spent in Nice mode, that is lower priority as adjusted by the nice command and have the "N" status flag set when examined with "ps". |
| Sys | This is time spent in "pure" system time. |
| Wait | Also known as "iowait", this is the time the CPU was idle during an outstanding disk I/O request. This is not considered to be part of the total or system times reported in brief mode. |
| Irq | Time spent processing interrupts and also considered to be part of the summary system time reported in "brief" mode. |
| Soft | Time spent processing soft interrupts and also considered to be part of the summary system time reported in "brief" mode. |
| Steal | Time spent in other operating systems when running in a virtualized environment |
| Guest | Time spent running a virtual CPU for guest operating systems under the control of the Linux kernel, new since 2.6.24 |
| NiceG | Time spent running a niced guest (virtual CPU for guest operating systems under the control of the Linux kernel), new since 2.6.33 |
This next set of fields apply to processes
| Proc | Process creations/sec. |
| Runq | Number of processes in the run queue. |
| Run | Number of processes in the run state. |
| Avg1, Avg5, Avg15 | Load average over the last 1,5 and 15 minutes. |
| RunT | Total number of process in the run state, not counting collectl itself |
| BlkT | Total number of process blocked, waiting on I/O |
If you specify filtering with --dskfilt, the disks that match the pattern(s) will either be included or excluded from the the summary data. However, the data will still be collected so if recorded to a file can later be viewed.
# DISK SUMMARY (/sec) #KBRead RMerged Reads SizeKB KBWrit WMerged Writes SizeKB
| KBRead | KB read/sec |
| RMerged | Read requests merged per second when being dequeued. |
| Reads | Number of reads/sec |
| SizeKB | Average read size in KB |
| KBWrite | KB written/sec |
| WMerged | Write requests merged per second when being dequeued. |
| Writes | Number of writes/sec |
| SizeKB | Average write size in KB |
# INODE SUMMARY # Dentries File Handles Inodes # Number Unused Alloc MaxPct Number 40585 39442 576 0.17 38348
| DCache | |
| Dentries Number | Number of entries in directory cache |
| Dentried Unused | Number of unused entries in directory cache |
| Handles Alloc | Number of allocated file handles |
| handles % Max | Percentage of maximum available file handles |
| Inodes Number | Number of inodes in use |
NOTE - as of this writing I'm baffled by the dentry unused field. No matter how many files and/or directories I create, this number goes up! Sholdn't it go down?
# INFINIBAND SUMMARY (/sec) # KBIn PktIn SizeIn KBOut PktOut SizeOut Errors
| KBIn | KB received/sec. |
| PktIn | Packets received/sec. |
| SizeIn | Average incoming packet size in KB |
| KBOut | KB transmitted/sec. |
| PktOut | Packets transmitted/sec. |
| SizeOut | Average outgoing packet size in KB |
| Errs | Count of current errors. Since these are typically infrequent, it is felt that reporting them as a rate would result in either not seeing them OR round-off hiding their values. |
Lustre Client, collectl -sl
There are several formats here controlled by the --lustopts switch. There is also detail data for these available as well. Specifying -sL results in data broken out by the file system and --lustopts O further breaks it out by OST. Also note the average read/write sizes are only reported when --lustopts is not specified.
# LUSTRE CLIENT SUMMARY # KBRead Reads SizeKB KBWrite Writes SizeKB
| KBRead | KB/sec delivered to the client. |
| Reads | Reads/sec delivered to the client, not necessarily from the lustre storage servers. |
| SizeKB | Average read size in KB |
| KBWrite | KB Writes/sec delievered to the storage servers. |
| Writes | Writes/sec delievered to the storage servers. |
| SizeKB | Average write size in KB |
# LUSTRE CLIENT SUMMARY: METADATA # KBRead Reads KBWrite Writes Open Close GAttr SAttr Seek Fsynk DrtHit DrtMis
| KBRead | KB/sec delivered to the client. |
| Reads | Reads/sec delivered to the client, not necessarily from the lustre storage servers. |
| KBWrite | KB Writes/sec delievered to the storage servers. |
| Writes | Writes/sec delievered to the storage servers. |
| Open | File opens/sec |
| Close | File closes/sec |
| GAttr | getattrs/sec |
| Seek | seeks/sec |
| Fsync | fsyncs/sec |
| DrtHit | dirty hits/sec |
| DrtMis | dirty misses/sec |
# LUSTRE CLIENT SUMMARY: READAHEAD # KBRead Reads KBWrite Writes Pend Hits Misses NotCon MisWin FalGrb LckFal Discrd ZFile ZerWin RA2Eof HitMax Wrong
| KBRead | KB/sec delivered to the client. |
| Reads | Reads/sec delivered to the client, not necessarily from the lustre storage servers. |
| KBWrite | KB Writes/sec delievered to the storage servers. |
| Writes | Writes/sec delievered to the storage servers. |
| Pend | Pending issued pages |
| Hits | prefetch cache hits |
| Misses | prefetch cache misses |
| NotCon | The current pages read that were not consecutive with the previous ones./td> |
| MisWin | Miss inside window. The pages that were expected to be in the prefetch cache but weren't. They were probably reclaimed due to memory pressure |
| LckFal | Failed grab_cache_pages. Tried to prefetch page but it was locked. |
| Discrd | Read but discarded. Prefetched pages (but not read by applicatin) have been discarded either becuase of memory pressure or lock revocation. |
| ZFile | Zero length file. |
| ZerWin | Zero size window. |
| RA2Eof | Read ahead to end of file |
| HitMax | Hit maximum readahead issue. The read-ahead window has grown to the maximum specified by max_read_ahead_mb |
# LUSTRE CLIENT SUMMARY: RPC-BUFFERS (pages) #RdK Rds 1K 2K ... WrtK Wrts 1K 2K ...
| RdK | KBs read/sec |
| Rds | Reads/sec |
| nK | Number of pages of of this size read |
| WrtK | KBs written/sec |
| Wrts | Writes/sec |
| nK | Number of pages of of this size written |
Lustre Meta-Data Server, collectl -sl
As of Lustre 1.6.5, the data reported for the MDS had changed, breaking out the Reint data into 5 individual buckets which are the last 5 fields described below. For earlier versions those 5 fields will be replaced by a single one named Reint.
# LUSTRE MDS SUMMARY #Getattr GttrLck StatFS Sync Gxattr Sxattr Connect Disconn Create Link Setattr Rename Unlink
| Getattr | Number of getattr calls, for example lfs osts. Note that this counter is not incremented as the result of ls - see Gxattr |
| GttrLck | These are getattrs that also return a lock on the file |
| StatFS | Number of stat calls, for example df or lfs df. Note that lustre caches data for up to a second so many calls within a second may only show up as a single statfs |
| Sync | Number of sync calls |
| Gxattr | Extended attribute get operations, for example getfattr, getfacl or even ls. Note that the MDS must have been mounted with -o acl for this counter to be enabled. |
| Sxattr | Extended attribute set operations, for example setfattr or setfacl |
| Connect | Client mount operations |
| Disconn | Client umount operations |
| Create | Count of mknod and mkdir operations, also used by NFS servers internally when creating files |
| Link | Hard and symbolic links, for example ln |
| Setattr | All operations that modify inode attributes including chmod, chown, touch, etc |
| Rename | File and directory renames, for example mv |
| Unlink | File/directory removals, for example rm or rmdir |
The following display is very similar the the RPC buffers in that the sizes of different size I/O requests are reported. In this case there are requests sent to the disk driver. Note that this report is only available for HP's SFS.
# LUSTRE DISK BLOCK LEVEL SUMMARY #Rds RdK 0.5K 1K ... Wrts WrtK 0.5K 1K ...
| Rds | Reads/sec |
| RdK | KBs read/sec |
| nK | Number of blocks of of this size read |
| Wrts | Writes/sec |
| WrtK | KBs written/sec |
| nK | Number of blocks of of this size written |
Lustre Object Storage Server, collectl -sl
# LUSTRE OST SUMMARY # KBRead Reads SizeKB KBWrite Writes SizeKB
| KBRead | KB/sec read |
| Reads | Reads/sec |
| SizeKB | Average read size in KB |
| KBWrite | KB/sec written |
| Writes | Writes/sec |
| SizeKB | Average write size in KB |
Lustre Object Storage Server, collectl -sl --lustopts B
As with client data, when you only get read/write average sizes when --lustopt is not specified.
# LUSTRE OST SUMMARY #<--------reads-----------|----writes----------------- #RdK Rds 1K 2K ... WrtK Wrts 1K 2K ....
| RdK | KBs read/sec |
| Rds | Reads/sec |
| nK | Number of pages of of this size read |
| WrtK | KBs written/sec |
| Wrts | Writes/sec |
| nK | Number of pages of of this size written |
Lustre Object Storage Server, collectl -sl --lustopts D
# LUSTRE DISK BLOCK LEVEL SUMMARY #RdK Rds 0.5K 1K ... WrtK Wrts 0.5K 1K ...
| RdK | KBs read/sec |
| Rds | Reads/sec |
| nK | Number of blocks of of this size read |
| WrtK | KBs written/sec |
| Wrts | Writes/sec |
| nK | Number of blocks of of this size written |
# MEMORY SUMMARY #<-------------------------------Physical Memory-------------------------------------><-----------Swap------------><-------Paging------> # Total Used Free Buff Cached Slab Mapped Anon Commit Locked Inact Total Used Free In Out Fault MajFt In Out
| Total | Total physical memory |
| Used | Used physical memory. This does not include memory used by the kernel itself. |
| Free | Unallocated memory |
| Buff | Memory used for system buffers |
| Cached | Memory used for caching data beween the kernel and disk, noting direct I/O does not use the cache |
| Slab | Memory used for slabs, see collectl -sY |
| Mapped | Memory mapped by processes |
| Anon | Anonymous memory. NOTE - this is included with mapped memory in brief format |
| Commit | According to RedHat: "An estimate of how much RAM you would need to make a 99.99% guarantee that there never is OOM (out of memory) for this workload." |
| Locked | Locked Memory |
| Inactive | Inactive pages. On ealier kernels this number is the sum of the clean, dirty and laundry pages. |
| Swap Total | Total Swap |
| Swap Used | Used Swap |
| Swap Free | Free Swap |
| Swap In | Kb swapped in/sec |
| Swap Out | Kb swapped out/sec |
| Fault | Page faults/sec resolved by not going to disk |
| MajFt | These page faults are resolved by going to disk |
| Paging In | Total number of pages read by block devices |
| Paging Out | Total number of pages written by block devices |
If you include --memopts with P or V, collectl will only display Physical or Virtual memory. The default is PV and will display both.
The p and s options allow you to display data about page and/or steal and scan information. If you want this data combined with the standard physical or virtual data you must explicitly request them as well. The columns show how the memory is allocated for the respective sections.
# MEMORY SUMMARY
#<---Other---|-------Page Alloc------|------Page Refill-----><------Page Steal-------|-------Scan KSwap------|------Scan Direct----->
# Free Activ Dma Dma32 Norm Move Dma Dma32 Norm Move Dma Dma32 Norm Move Dma Dma32 Norm Move Dma Dma32 Norm Move
14M 136K 2 69 13M 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
The entries for error counts in the following are actually the total of several types of errors. To get individual error counts, you must either include --netopts e or report details on individual interfaces in plot format by specifying -P. Transmission errors are categorized by errors, dropped, fifo, collisions and carrier. Receive errors are broken out for errors, dropped, fifo and framing errors.
If you specify filtering with --netfilt, the names that match the pattern(s) will either be included or excluded from the the summary data. However, the data will still be collected so if recorded to a file can later be viewed.
# NETWORK SUMMARY (/sec) # KBIn PktIn SizeIn MultI CmpI ErrsI KBOut PktOut SizeO CmpO ErrsO
| KBIn | Incoming KB/sec |
| PktIn | Incoming packets/sec |
| SizeI | Average incoming packet size in bytes |
| MultI | Incoming multicast packets/sec |
| CmpI | Incoming compressed packets/sec |
| ErrsI | Total incoming errors/sec. This is an aggregation of incoming error counters. To see explicit error counters use --netopts e |
| KBOut | Outgoing KB/sec |
| PktOut | Outgoing packets/sec |
| SizeO | Average outgoing packet size in bytes |
| CmpO | Outgoing compressed packets/sec |
| ErrsO | Total outgoing errors/sec. This is an aggregation of outgoing error counters. To see explicit error counters use --netopts e |
This alternative format, which is displayed when you specify --netopts e enumerates the individual error types. You cannot see both output formats at the same time.
# NETWORK ERRORS SUMMARY (/sec) # ErrIn DropIn FifoIn FrameIn ErrOut DropOut FifoOut CollOut CarrOut
| ErrIn | Receive errors/sec detected by the device driver |
| DropIn | Receive packets dropped/sec |
| FifoIn | Receive packet FIFO buffer errors/sec |
| FrameIn | Receive packet framing errors/sec |
| ErrOut | Transmit errors/sec detected by the device driver |
| DropOut | Transmit packets dropped/sec |
| FifoOut | Transmit packet FIFO buffer errors/sec |
| CollOut | Transmit collisions/sec detected on the interface |
| CarrOut | Transmit packet carrier loss errors detected/sec |
As of version 3.2.1, by default collectl collects and reports on all versions of nfs data, both clients and servers. One can limit the types of data reported with --nfsfilt and if only server or client data has been selected, only that type of data will be reported as shown in the 2 forms below. When both server and client data are being reported they will be displayed side by side. As with brief format, if filters have been selected they will be displayed in the header.
# NFS SUMMARY (/sec) #<---------------------------server---------------------------> # Reads Writes Meta Comm UDP TCP TCPConn BadAuth BadClnt
| Reads | Total reads/sec |
| Writes | Total writes/sec |
| Meta | Total nfs meta data calls/sec, where meta data is considered to be any of: lookup, access, getattr, setattr, readdir and readdirplus, noting that not all types of nfs version report all as V3 clients/servers do. |
| Comm | Total commits/sec |
| UDP | Number of UDP packets/sec |
| TCP | Number of TCP packets/sec |
| TCPConn | Number of TCP connections/sec |
| BadAuth | Number of authentication failures/sec |
| BadClnt | Number of unknown clients/sec |
# NFS SUMMARY (/sec) #<----------------client----------------> # Reads Writes Meta Comm Retrans Authref
| Reads | Total reads/sec |
| Writes | Total writes/sec |
| Meta | Total nfs meta data calls/sec, where meta data is considered to be any of: lookup, access, getattr, setattr, readdir and readdirplus, noting that not all types of nfs version report all as V3 clients/servers do. |
| Comm | Total commits/sec |
| Retrans | Number of retransmissions/sec |
| Authref | Number of authrefreshes/sec |
The data reported for clients is slightly different, specifically the retrans and authref fields.
# NFS CLIENT (/sec) #<----------RPC---------><---NFS V3---> #CALLS RETRANS AUTHREF READ WRITE
| Calls | Number of RPC calls/sec |
| Retrans | Retransmitted calls |
| Authref | Authentication failed |
| Read | Number of reads/sec |
| Write | Number of writes/sec |
As of the 2.6.22 kernel, there is a new slab allocator, called SLUB, and since there is not a 1:1 mapping between what it reports and the older slab allocator, the format of this listing will depend on which allocator is being used. The following format is for the older allocator.
# SLAB SUMMARY #<------------Objects------------><--------Slab Allocation-------><--Caches---> # InUse Bytes Alloc Bytes InUse Bytes Total Bytes InUse Total
| Objects | |
| InUse | Total number of objects that are currently in use. |
| Bytes | Total size of all the objects in use. |
| Alloc | Total number of objects that have been allocated but not necessarily in use. |
| Bytes | Total size of all the allocated objects whether in use or not. |
| Slab Allocation | |
| InUse | Number of slabs that have at least one active object in them. |
| Bytes | Total size of all the slabs. |
| Total | Total number of slabs that have been allocated whether in use or not. |
| Bytes | Total size of all the slabs that have been allocted whether in use or not. |
| Caches | |
| InUse | Not all caches are actully in use. This included only those with non-zero counts. |
| Total | This is the count of all caches, whether currently in use or not. |
This is format for the new slub allocator
# SLAB SUMMARY #<---Objects---><-Slabs-><-----memory-----> # In Use Avail Number Used Total
| Objects | |
| InUse | The total number of objects that have been allocated to processes. |
| Avail | The total number of objects that are available in the currently allocated slabs. This includes those that have already been allocated toprocesses. |
| Slabs | |
| Number | This is the number of individual slabs that have been allocated and taking physical memory. |
| Memory | |
| Used | Used memory corresponds to those objects that have been allocated to processes. |
| Total | Total physical memory allocated to processes. When there is no filtering in effect, this number will be equal to the Slabs field reported by -sm. |
# SOCKET STATISTICS # <-------------Tcp-------------> Udp Raw <---Frag--> #Used Inuse Orphan Tw Alloc Mem Inuse Inuse Inuse Mem
| Used | Total number if socket allocated which can include additional types such as domain. |
| Tcp | |
| Inuse | Number of TCP connections in use |
| Orphan | Number of TCP orphaned connections |
| Tw | Number of connections in TIME_WAIT |
| Alloc | TCP sockets allocated |
| Mem | |
| Udp | |
| Inuse | Number of UCP connections in use |
| Raw | |
| Inuse | Number of RAW connections in use |
| Frag | |
| Inuse | |
| Mem | |
--tcpfilt i
# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) #<----------------------------------IpPkts-----------------------------------> # Receiv Delivr Forwrd DiscdI InvAdd Sent DiscrO ReasRq ReasOK FragOK FragCr
| Receiv | - total packets received/sec | |
| Delivr | - incoming packets delivered/sec | |
| Forwrd | - packets forwarded | |
| DiscdI | - discarded incoming packets | |
| InvAdd | - packets received with invalid addresses | |
| Sent | - requests sent out/sec | |
| DiscrO | - discarded outbound requests | |
| ReasRq | - reassembled requests | |
| ReasOK | - reassembled OK | |
| FragOK | - fragments received OK | |
| FragCr | - fragments created |
--tcpfilt t
# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) #<---------------------------------Tcp---------------------------------> # ActOpn PasOpn Failed ResetR Estab SegIn SegOut SegRtn SegBad SegRes
| ActOpn | - active connections opened/sec |
| PasOpn | - passive connection opened/sec |
| Failed | - failed connection attempts |
| ResetR | - connection resets received |
| Estab | - connections established |
| SegIn | - segments received/sec |
| SegOut | - segments sent out/sec |
| SegRtn | - segments retransmitted |
| SegBad | - bad segments received |
| SegRes | - resets sent |
--tcpfilt u
# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) #<------------Udp-----------> # InDgm OutDgm NoPort Errors
| InDgm | - packets received/sec |
| OutDgm | - packets sent/sec |
| NoPort | - packets received to unknown port |
| Errors | - packet receive errors |
--tcpfilt c
# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) #<----------------------------Icmp---------------------------> # Recvd FailI UnreI EchoI ReplI Trans FailO UnreO EchoO ReplO
| Recvd | - ICMP messages received |
| FailI | - incoming ICMP messages failed |
| UnreI | - input destination unreachable |
| EchoI | - input echo requests |
| ReplI | - input echo reploes |
| Trans | - ICMP messages sent |
| FailO | - outbound ICMP messages failed |
| UnreO | - output destination unreachable |
| EchoO | - output echo requests |
| ReplO | - output echo replies |
--tcpfilt T
# TCP SUMMARY (/sec)# TCP STACK SUMMARY (/sec) #<------------------------------------------TcpExt-----------------------------------------> # FasTim Reject DelAck QikAck PktQue PreQuB HdPdct AkNoPy PreAck DsAcks RUData REClos SackS
| FasTim | - TCP sockets finished time wait in fast timer |
| Reject | - packet rejects in established connections because of timestamp |
| DelAck | - delayed ACKs sent |
| QikAck | - times quick ACK mode activated |
| PktQue | - packets directly queued to recvmsg prequeue |
| PreQuB | - bytes directly received in process context from prequeue |
| HdPdct | - packet headers predicted |
| AkNoPy | - acknowledgements for received packets not containing data |
| PreAck | - predicted acknowledgements |
| DsAcks | - DSACKS sent for old packets |
| RUData | - connections reset to do unexpected data |
| REClos | - connections reset due to early close |
| SackS | - SackShiftFallback |
| updated July 23, 2014 |