diff --git a/.github/workflows/experimental.yml b/.github/workflows/experimental.yml
index 61dbf23035..e45b543253 100644
--- a/.github/workflows/experimental.yml
+++ b/.github/workflows/experimental.yml
@@ -334,11 +334,13 @@ jobs:
       # - #1963: util/pytest_shards.py runs pytest once per shard `SHARDS`
       #   names, a directory or a glob of one directory's entries, then once
       #   over the rest, so every run starts its workers afresh and none
-      #   outlives its heap. Each shard is sized by its largest live heap after
-      #   a full GC on GraalPy. The script runs inside the timeout, scope and
-      #   watcher below, so they hold over the whole tier; on the timeout's
-      #   SIGINT no later run starts. Each shard's run writes a JUnit file of
-      #   its own beside junit.xml.
+      #   outlives its heap. #2713: the shards that lost workers are split by
+      #   their tests' JUnit seconds on GraalPy, each to run in under 5
+      #   minutes; the run over the rest is left whole, as it took about 6.7
+      #   minutes in job 125639681253 and lost no worker. The script runs
+      #   inside the timeout, scope and watcher below, so they hold over the
+      #   whole tier; on the timeout's SIGINT no later run starts. Each shard's
+      #   run writes a JUnit file of its own beside junit.xml.
       # - `timeout` sends SIGINT at 110 minutes, under the step's cap, so pytest
       #   still writes the JUnit XML, and exits 124; SIGKILL 3 minutes on.
       #   #2020: GNU's `timeout`, which Ubuntu 26.04 installs as `gnutimeout`:
@@ -394,7 +396,10 @@ jobs:
           SHARDS: >-
             ${{ startsWith(matrix.python-version, 'graalpy') && 'tests/const
             tests/corekit/test_fields_n* tests/corekit/test_[a-h]* tests/corekit/test_i* tests/corekit
-            tests/foundation tests/protocols/internet tests/protocols/[a-m]* tests/protocols
+            tests/foundation/reassembly tests/foundation/test_* tests/foundation
+            tests/protocols/internet/test_ipv4* tests/protocols/internet/test_ipv6* tests/protocols/internet
+            tests/protocols/application tests/protocols/link tests/protocols/misc/test_pcapng* tests/protocols/misc
+            tests/protocols/transport/test_tcp* tests/protocols/transport tests/protocols/test_t* tests/protocols
             tests/toolkit' || '' }}
           GH_TOKEN: ${{ github.token }}
           WATCHER: ${{ steps.watcher.outcome }}
diff --git a/docs/source/contributing/workflows.rst b/docs/source/contributing/workflows.rst
index ca0db328a0..4fb86f0816 100644
--- a/docs/source/contributing/workflows.rst
+++ b/docs/source/contributing/workflows.rst
@@ -1228,15 +1228,27 @@ warnings:
   names -- a directory, or a glob of one directory's entries such as
   ``tests/corekit/test_i*`` -- and once more over the rest, and every run starts its
   own workers. Each run also ignores what every earlier shard took, so a glob may
-  precede its own directory, which then takes the remainder. The shards are sized by
-  each one's largest live heap after a full GC, measured locally on GraalPy 25.4.4 at
-  ``-n 3``: run whole, the tier lost 8 workers, its heap reached the 2 GiB cap, and it
-  took 3559 s; in these shards none went down, no heap passed 1303 MB, and it
-  took 1879 s. The runs share the step's ``timeout``, scope and watcher, so the
-  caps hold over the whole tier; on ``timeout``'s SIGINT the run in progress writes
-  its JUnit file and no later one starts. Each shard's run writes a JUnit file of its
-  own beside ``junit.xml``, such as ``junit-tests-protocols.xml``, and ``Upload test
-  timings`` takes them all. 3.14t's leg runs pytest once.
+  precede its own directory, which then takes the remainder. The shards were first
+  sized by each one's largest live heap after a full GC, measured locally on GraalPy
+  25.4.4 at ``-n 3``: run whole, the tier lost 8 workers, its heap reached the 2 GiB
+  cap, and it took 3559 s; in those shards none went down, no heap passed 1303 MB, and
+  it took 1879 s. The tier outgrew them (:issue:`2713`). On ``57a6c366d``, job
+  125639681253 lost 8 workers, all in its runs of 10-14 minutes -- ``tests/foundation``,
+  ``tests/protocols/internet``, ``tests/protocols/[a-m]*`` and ``tests/protocols`` --
+  and all 9.8-12 minutes into the run. The ``[monitor]`` samples in its ``Run unit
+  tests`` log put each of those runs' largest worker at 2.2 GiB RSS at 5 minutes old,
+  and at 2.65-2.78 GiB at its largest. Its runs of 2-7 minutes lost none, and its
+  tests took 4510 s of the ``timeout``'s 6600. So those shards are split by time,
+  sized from that job's ``junit-experimental-graalpy-25.4`` artifact: a shard's
+  estimate is its tests' JUnit seconds over the 3 workers, plus 50 s for the 46-57 s
+  that each of the job's shards that lost no worker took beyond that, start to start.
+  Every shard split this way comes to under 5 minutes, and the tier to about 4750 s
+  (estimate). The run over the rest is left whole: in that job it took about 6.7
+  minutes and lost no worker. The runs share the step's ``timeout``, scope and
+  watcher, so the caps hold over the whole tier; on ``timeout``'s SIGINT the run in
+  progress writes its JUnit file and no later one starts. Each shard's run writes a
+  JUnit file of its own beside ``junit.xml``, such as ``junit-tests-protocols.xml``,
+  and ``Upload test timings`` takes them all. 3.14t's leg runs pytest once.
 * ``timeout --signal=INT --kill-after=3m 110m`` ends pytest under the step's 120-minute
   cap, so it still writes the junit XML, and exits 124; ``prlimit --fsize=2147483648``
   caps any file at 2 GiB. The ``timeout`` is GNU's, ``gnutimeout`` where it exists
diff --git a/tests/project/test_graalpy_shards_1963.py b/tests/project/test_graalpy_shards_1963.py
index 89745a1c55..4b729089c0 100644
--- a/tests/project/test_graalpy_shards_1963.py
+++ b/tests/project/test_graalpy_shards_1963.py
@@ -34,9 +34,14 @@
 from tests.project.test_resource_monitor_1740 import DEFAULT, EXPERIMENTAL, HEAP, TESTS, by_impl, sh, step
 from util import pytest_shards
 
-#: GraalPy's shards, in the order they run; the rest of the tier runs last.
+#: GraalPy's shards, in the order they run; the rest of the tier runs last. #2713 split the
+#: shards that lost workers in job 125639681253 by their JUnit seconds there.
 SHARDS = ('tests/const tests/corekit/test_fields_n* tests/corekit/test_[a-h]* tests/corekit/test_i* tests/corekit '
-          'tests/foundation tests/protocols/internet tests/protocols/[a-m]* tests/protocols tests/toolkit')
+          'tests/foundation/reassembly tests/foundation/test_* tests/foundation '
+          'tests/protocols/internet/test_ipv4* tests/protocols/internet/test_ipv6* tests/protocols/internet '
+          'tests/protocols/application tests/protocols/link tests/protocols/misc/test_pcapng* tests/protocols/misc '
+          'tests/protocols/transport/test_tcp* tests/protocols/transport tests/protocols/test_t* tests/protocols '
+          'tests/toolkit')
 SCRIPT = ROOT / 'util' / 'pytest_shards.py'
 #: The lines that build the command the step's caps run, in order.
 PYTEST = 'set -- python -m pytest "$@"\n'