- 09 Sep, 2010 40 commits
-
-
Zach Brown authored
We're seeing bugs today where IB connection shutdown clears the send ring while the tasklet is processing completed sends. Implementation details cause this to dereference a null pointer. Shutdown needs to wait for send completion to stop before tearing down the connection. We can't simply wait for the ring to empty because it may contain unsignaled sends that will never be processed. This patch tracks the number of signaled sends that we've posted and waits for them to complete. It also makes sure that the tasklet has finished executing. Signed-off-by:Zach Brown <zach.brown@oracle.com>
-
Zach Brown authored
The trivial amount of memory saved isn't worth the cost of dealing with section mismatches. Signed-off-by: -
Andy Grover authored
We are *definitely* counting cycles as closely as DaveM, so ensure hwcache alignment for our recv ring control structs. Signed-off-by:Andy Grover <andy.grover@oracle.com>
-
Zach Brown authored
The recv refill path was leaking fragments because the recv event handler had marked a ring element as free without freeing its frag. This was happening because it wasn't processing receives when the conn wasn't marked up or connecting, as can be the case if it races with rmmod. Two observations support always processing receives in the callback. First, buildup should only post receives, thus triggering recv event handler calls, once it has built up all the state to handle them. Teardown should destroy the CQ and drain the ring before tearing down the state needed to process recvs. Both appear to be true today. Second, this test was fundamentally racy. There is nothing to stop rmmod and connection destruction from swooping in the moment after the conn state was sampled but before real receive procesing starts. Signed-off-by: -
Zach Brown authored
We were seeing very nasty bugs due to fundamental assumption the current code makes about concurrent work struct processing. The code simpy isn't able to handle concurrent connection shutdown work function execution today, for example, which is very much possible once a multi-threaded krdsd was introduced. The problem compounds as additional work structs are added to the mix. krdsd is no longer perforance critical now that send and receive posting and FMR flushing are done elsewhere, so the safest fix is to move back to the single threaded krdsd that the current code was built around. Signed-off-by: -
Zach Brown authored
This patch moves the FMR flushing work in to its own mult-threaded work queue. This is to maintain performance in preparation for returning the main krdsd work queue back to a single threaded work queue to avoid deep-rooted concurrency bugs. This is also good because it further separates FMRs, which might be removed some day, from the rest of the code base. Signed-off-by: -
Zach Brown authored
IB connections were not being destroyed during rmmod. First, recently IB device removal callback was changed to disconnect connections that used the removing device rather than destroying them. So connections with devices during rmmod were not being destroyed. Second, rds_ib_destroy_nodev_conns() was being called before connections are disassociated with devices. It would almost never find connections in the nodev list. We first get rid of rds_ib_destroy_conns(), which is no longer called, and refactor the existing caller into the main body of the function and get rid of the list and lock wrappers. Then we call rds_ib_destroy_nodev_conns() *after* ib_unregister_client() has removed the IB device from all the conns and put the conns on the nodev list. The result is that IB connections are destroyed by rmmod. Signed-off-by: -
Zach Brown authored
The RDS IB client removal callback can queue work to drop the final reference to an IB device. We have to make sure that this function has returned before we complete rmmod or the work threads can try to execute freed code. Signed-off-by: -
Andy Grover authored
Signed-off-by: -
Andy Grover authored
Not used. Signed-off-by: -
Andy Grover authored
-
Chris Mason authored
Using a delayed work queue helps us make sure a healthy number of FMRs have queued up over the limit. It makes for a large improvement in RDMA iops. Signed-off-by:Chris Mason <chris.mason@oracle.com>
-
Chris Mason authored
When we add more FMRs, we flush them less often and so we go faster. Signed-off-by: -
Chris Mason authored
FRM allocation and recycling is performance critical and fairly lock intensive. The current code has a per connection lock that all processes bang on and it becomes a major bottleneck on large systems. This changes things to use a number of cmpxchg based lists instead, allowing us to go through the whole FMR lifecycle without locking inside RDS. Zach Brown pointed out that our usage of cmpxchg for xlist removal is racey if someone manages to remove and add back an FMR struct into the list while another CPU can see the FMR's address at the head of the list. The second CPU might assume the list hasn't changed when in fact any number of operations might have happened in between the deletion and reinsertion. This commit maintains a per cpu count of CPUs that are currently in xlist removal, and establishes a grace period to make sure that nobody can see an entry we have just removed from the list. Signed-off-by: -
Zach Brown authored
rds_send_xmit() was changed to hold an interrupt masking spinlock instead of a mutex so that it could be called from the IB receive tasklet path. This broke the TCP transport because its xmit method can block and masks and unmasks interrupts. This patch serializes callers to rds_send_xmit() with a simple bit instead of the current spinlock or previous mutex. This enables rds_send_xmit() to be called from any context and to call functions which block. Getting rid of the c_send_lock exposes the bare c_lock acquisitions which are changed to block interrupts. A waitqueue is added so that rds_conn_shutdown() can wait for callers to leave rds_send_xmit() before tearing down partial send state. This lets us get rid of c_senders. rds_send_xmit() is changed to check the conn state after acquiring the RDS_IN_XMIT bit to resolve races with the shutdown path. Previously both worked with the conn state and then the lock in the same order, allowing them to race and execute the paths concurrently. rds_send_reset() isn't racing with rds_send_xmit() now that rds_conn_shutdown() properly ensures that rds_send_xmit() can't start once the conn state has been changed. We can remove its previous use of the spinlock. Finally, c_send_generation is redundant. Callers can race to test the c_flags bit by simply retrying instead of racing to test the c_send_generation atomic. Signed-off-by: -
Zach Brown authored
conn->c_lock is acquired in interrupt context. rds_conn_message_info() is called from user context and was acquiring c_lock without blocking interrupts, leading to possible deadlocks. Signed-off-by: -
Zach Brown authored
rds_send_acked_before() wasn't blocking interrupts when acquiring c_lock from user context but nothing calls it. Rather than fix its use of c_lock we just remove the function. Signed-off-by: -
Chris Mason authored
When prefilling the rds frags, we end up doing a lot of allocations. We're not in atomic context here, and so there's no reason to dip into atomic reserves. This changes the prefills to use masks that allow waiting. Signed-off-by: -
Chris Mason authored
This patch is based heavily on an initial patch by Chris Mason. Instead of freeing slab memory and pages, it keeps them, and funnels them back to be reused. The lock minimization strategy uses xchg and cmpxchg atomic ops for manipulation of pointers to list heads. We anchor the lists with a pointer to a list_head struct instead of a static list_head struct. We just have to carefully use the existing primitives with the difference between a pointer and a static head struct. For example, 'list_empty()' means that our anchor pointer points to a list with a single item instead of meaning that our static head element doesn't point to any list items. Original patch by Chris, with significant mods and fixes by Andy and Zach. Signed-off-by:
-
Andy Grover authored
All it does is call unmap_sg(), so just call that directly. The comment above unmap_page also may be incorrect, so we shouldn't hold on to it, either. Signed-off-by: -
Andy Grover authored
refill_one() should never be called on a recv struct that doesn't need a new r_frag allocated. Add a WARN and remove conditional around r_frag alloc code. Also, add a comment to explain why r_ibinc may or may not need refilling. Signed-off-by: -
Andy Grover authored
Instead of splitting up a page into RDS_FRAG_SIZE chunks ourselves, ask rds_page_remainder_alloc() to do it. While it is possible PAGE_SIZE > FRAG_SIZE, on x86en it isn't, so having duplicate "carve up a page into buffers" code seems excessive. The other modification this spawns is the use of a single struct scatterlist in rds_page_frag instead of a bare page ptr. This causes verbosity to increase in some places, and decrease in others. Finally, I decided to unify the lifetimes and alloc/free of rds_page_frag and its page. This is a nice simplification in itself, but will be extra-nice once we come to adding cmason's recycling patch. Signed-off-by: -
Zach Brown authored
Currently IB device removal destroys connections which are associated with the device. This prevents connections from being re-established when replacement devices are added. Instead we'll queue shutdown work on the connections as their devices are removed. When we see that devices are added we triger connection attempts on all connections that don't currently have a device. The result is that RDS sockets can resume device-independent work (bcopy, not RDMA) across IB device removal and restoration. Signed-off-by: -
Zach Brown authored
A few paths had the same block of code to queue a connection's connect work if it was in the right state. Let's move this in to a helper function. Signed-off-by: -
Zach Brown authored
The RDS IB client .remove callback used to free the rds_ibdev for the given device unconditionally. This could race other users of the struct. This patch adds refcounting so that we only free the rds_ibdev once all of its users are done. Many rds_ibdev users are tied to connections. We give the connection a reference and change these users to reference the device in the connection instead of looking it up in the IB client data. The only user of the IB client data remaining is the first lookup of the device as connections are built up. Incrementing the reference count of a device found in the IB client data could race with final freeing so we use an RCU grace period to make sure that freeing won't happen until those lookups are done. MRs need the rds_ibdev to get at the pool that they're freed in to. They exist outside a connection and many MRs can reference different devices from one socket, so it was natural to have each MR hold a reference. MR refs can be dropped from interrupt handlers and final device teardown can block so we push it off to a work struct. Pool teardown had to be fixed to cancel its pending work instead of deadlocking waiting for all queued work, including itself, to finish. MRs get their reference from the global device list, which gets a reference. It is left unprotected by locks and remains racy. A simple global lock would be a significant bottleneck. More scalable (complicated) locking should be done carefully in a later patch. Signed-off-by: -
Zach Brown authored
rds_ib_xmit_rdma() was calling ib_get_client_data() to get at the rds_ibdevice just to get the max_sge for the transmit. This patch instead has it get it directly off the rds_ibdev which is stored on the connection. The current code won't free the rds_ibdev until all the IB connections that use it are freed. So it's safe to reference the rds_ibdev this way. In the future it also makes it easier to support proper reference counting of the rds_ibdev struct. As an additional bonus, this gets rid of the performance hit of calling in to the IB stack to look up the rds_ibdev. The current implementation in the IB stack acquires an interrupt blocking spinlock to protect the registration of client callback data. Signed-off-by: -
Zach Brown authored
rds_ib_cm_handle_connect() could return without unlocking the c_conn_lock if rds_setup_qp() failed. Rather than adding another imbalanced mutex_unlock() to this error path we only unlock the mutex once as we exit the function, reducing the likelyhood of making this same mistake in the future. We remove the previous mulitple return sites, leaving one unambigious return path. Signed-off-by: -
Chris Mason authored
This makes sure we have the proper number of references in rds_ib_xmit_atomic and rds_ib_xmit_rdma. We also consistently drop references the same way for all message types as the IOs end. Signed-off-by: -
Chris Mason authored
The connection hash was almost entirely RCU ready, this just makes the final couple of changes to use RCU instead of spinlocks for everything. Signed-off-by: -
Chris Mason authored
rds_conn_destroy really needs locking while it changes the connection hash. Signed-off-by: -
Chris Mason authored
The RDS send_xmit code was trying to get fancy with message counting and was dropping the final reference on the RDMA messages too early. This resulted in memory corruption and oopsen. The fix here is to always add a ref as the parts of the message passes through rds_send_xmit, and always drop a ref as the parts of the message go through completion handling. Signed-off-by: -
Chris Mason authored
This is the first in a long line of patches that tries to fix races between RDS connection shutdown and RDS traffic. Here we are maintaining a count of active senders to make sure the connection doesn't go away while they are using it. Signed-off-by: -
Chris Mason authored
The RDS bind lookups are somewhat expensive in terms of CPU time and locking overhead. This commit changes them into a faster RCU based hash tree instead of the rbtrees they were using before. On large NUMA systems it is a significant improvement. Signed-off-by: -
Andy Grover authored
Allocate send/recv rings in memory that is node-local to the HCA. This significantly helps performance. Signed-off-by: -
Andy Grover authored
Signed-off-by: -
Chris Mason authored
rds_ib_get_device is called very often as we turn an ip address into a corresponding device structure. It currently take a global spinlock as it walks different lists to find active devices. This commit changes the lists over to RCU, which isn't very complex because they are not updated very often at all. Signed-off-by: -
Chris Mason authored
This removes a global waitqueue used to wait for rds messages and replaces it with a waitqueue inside the rds_message struct. The global waitqueue turns into a global lock and significantly bottlenecks operations on large machines. Signed-off-by: -
Chris Mason authored
The bind_lock is almost entirely readonly, but it gets hammered during normal operations and is a major bottleneck. This commit changes it to an rwlock, which takes it from 80% of the system time on a big numa machine down to much lower numbers. A better fix would involve RCU, which is done in a later commit Signed-off-by: -
Andy Grover authored
Update comments to reflect changes in previous commit. Keeping as separate commits due to different authorship. Signed-off-by: -
Chris Mason authored
rds_send_xmit is required to loop around after it releases the lock because someone else could done a trylock, found someone working on the list and backed off. But, once we drop our lock, it is possible that someone else does come in and make progress on the list. We should detect this and not loop around if another process is actually working on the list. This patch adds a generation counter that is bumped every time we get the lock and do some send work. If the retry notices someone else has bumped the generation counter, it does not need to loop around and continue working. Signed-off-by:
-
